RETRACTED: Improving Efficiency of Large RFID Networks Using a Clustered Method: A Comparative Analysis (Electronics, (2022), 11, 18, (2968), 10.3390/electronics11182968)
Pandian M.T., Chouhan K., Kumar B.M., Dash J.K., Jhanjhi N.Z., Ibrahim A.O., Abulfaraj A.W.
Electronics (Switzerland), 2025, DOI Link
View abstract ⏷
The journal retracts the article “Improving Efficiency of Large RFID Networks Using a Clustered Method: A Comparative Analysis” [1], as cited above. Following publication, concerns were brought to the attention of the Editorial Office regarding the reliability of this study [1]. Adhering to our standard procedure, an investigation was conducted by the Editorial Office and the Editorial Board and concluded that a range of flaws were present in the study, including incoherent phrasing suggestive of non-expert or automated text generation, the reporting of invalid and implausible metrics, and contradictory results across multiple sections. As a result, the Editorial Board has lost confidence in the validity of the overall findings and have decided to retract this article [1] as per MDPI’s retraction policy (https://www.mdpi.com/ethics#_bookmark30, accessed on 9 October 2025). This retraction was approved by the Editor-in-Chief of the journal Electronics. The author did not provide a comment on this decision.
Merged Spatial Temporal Deep Learning Based Content Based Video Retrieval
6th IEEE International Conference on Recent Advances in Information Technology, RAIT 2025, 2025, DOI Link
View abstract ⏷
Imagine searching for a specific scene in a movie, not by remembering its title or actors, but by describing the action itself. This is the essence of content-based video retrieval (CBVR), a technique that searches for a video based on what's inside it, rather than relying solely on manually assigned labels. Unlike traditional methods, which can be time-consuming, error-prone, and struggle with vast datasets, CBVR offers a more efficient and accurate approach.Our proposed system leverages the strong capability of deep learning, a subset of artificial intelligence, to analyze videos and extract their key characteristics. This process occurs in two stages: offline and online. Through the first stage, important features are extracted from all videos in the dataset and stored for future use. When a user submits a query video, its features are extracted in real-time (online) and compared to the stored features of all videos. The videos with features most similar to the query, essentially those with the 'closest match,' are then presented to the user.To capture the full essence of a video, our system employs a two-stream neural network architecture. This innovative approach allows us to extract both temporal features, which capture the changes and motion patterns within the video (think: someone running or jumping), and spatial features, which pivot about the static visual content of each individual frame (think: the objects and scene depicted).By utilizing a pre-trained neural network called ResNet-60, our system benefits from existing knowledge and can efficiently extract meaningful features from videos. To evaluate its effectiveness, we tested our system on the UCF101 dataset, a widely used benchmark consisting of 101 categorized videos. Our approach obtained accuracy 93,7% for top 5 retrieval and 95.95% for top 10 retrieval. The outcomes illustrate that our approach obtains superior accuracy compared to other state-of-the-art video retrieval methods.
Leveraging Spatio-temporal Deep Learning and Fuzzy Class Membership for Robust Content-Based Video Retrieval
SN Computer Science, 2025, DOI Link
View abstract ⏷
The exponential growth of information and communication technologies has led to an unprecedented surge in digital data, with a significant portion comprising unstructured visual media, such as images and videos that often lack metadata. This absence of structured metadata presents a major challenge in efficiently managing and extracting value from these vast repositories, rendering traditional search and retrieval methods ineffective. Content-based video retrieval (CBVR) has emerged as a crucial solution, transforming fields such as traffic analysis, video surveillance, medicine, and sports. Unlike static images, videos consist of objects that continuously move and undergo appearance changes over time, making it challenging to effectively capture both spatial details and temporal dynamics. This paper proposes a method that leverages the strengths of DenseNet-151, a densely connected convolutional neural network designed for extracting rich spatial features, and Long Short-Term Memory (LSTM), a recurrent neural network specialized in capturing temporal dependencies. Additionally, a modified distance function incorporating fuzzy class membership is employed to enhance the retrieval of similar videos from the database, leading to improved retrieval performance. The effectiveness of the proposed method is evaluated on the UCF101 Human Action Recognition dataset, demonstrating a 6% improvement in Precision, a 5% increase in Recall, a 5% enhancement in F1-Score, and an 8% boost in AUC compared to the most competitive approaches in the literature.
Leveraging 3DCNN and Weighted Similarity Metrics for Enhanced Content-Based Video Retrieval
Signal, Image and Video Processing, 2025, DOI Link
View abstract ⏷
With the widespread adoption of high-speed networks such as 4G and 5G, along with the explosive growth of social media platforms, video content is now frequently captured and shared online without accompanying metadata such as tags or descriptions. This absence of textual annotations presents a significant challenge for indexing and retrieving relevant video content. Content-Based Video Retrieval systems address this issue by analyzing the visual content of videos rather than relying on external metadata. However, only limited efforts in the literature have jointly explored both the spatial and temporal context of video data for retrieval. To address this gap, we propose a Content-Based Video Retrieval framework that leverages a 3D Convolutional Neural Network, specifically the R(2+1)D architecture enhanced with transfer learning. This model decomposes spatiotemporal convolutions to more effectively capture both spatial and temporal video features. In addition, we introduce a novel classification-similarity-based weighted distance approach, which overcomes the limitations of traditional distance-based and classifier-based retrieval methods. Experimental evaluation on the UCF101 dataset demonstrates that the proposed system achieves a significant improvement in retrieval performance, with over a 20% increase in AUC compared to baseline techniques.
Message from Convener and Co-Conveners ICEC-2024
Intelligent Computing and Emerging Communication Technologies, ICEC 2024, 2024, DOI Link
ML Applications in Healthcare
How Machine Learning is Innovating Today’s World: A Concise Technical Guide, 2024, DOI Link
View abstract ⏷
The era of intelligent algorithms has arrived, and machine learning is one of the most promising technologies to revolutionize healthcare. Until recently, manufacturing, transportation, and administration were the primary industries where machine learning algorithms had a significant impact. However, even formerly impervious industries like healthcare are suddenly being affected by these algorithms. While machine learning has been around for quite some time, its use in healthcare is continuously increasing alongside the availability of data. It is a statistical method that allows computers to learn from past data. They are able to identify patterns and come to conclusions or judgments depending on the information that they are presented with. Machine learning (ML) has numerous prospective applications within the healthcare industry. They extend from drug discovery to clinical decision-making and diagnosis. There are petabytes of healthcare-related data that require analysis. For instance, the human genome is an example of this, which is approximately 100 gigabytes per person. Furthermore, carry-and-wear devices generate a large quantity of data, including heart rate, blood pressure, and walking pattern. Therefore, on the basis of these data, ML techniques can be used to predict diseases and develop personalized treatments. Moreover, X-ray and MRI image classification techniques can be used to construct an ML algorithm for potential disease diagnosing, thereby reducing the burden on clinicians. Likewise, in drug discovery and development, ML algorithms have been utilized to help identify novel therapeutic targets, design new drug candidates, and predict drug toxicity. ML techniques can be used to create predictive models for patient outcomes like mortality, readmission, and disease progression. ML algorithms can be put to use to analyze electronic health record (EHR) data to facilitate clinical decision-making, such as predicting patient readmission rates or identifying patients who may benefit from a specific treatment. Therefore, ML has the potential to revolutionize the healthcare industry by providing methods to cluster, classify, predict, and assist clinicians in making informed decisions. Consequently, this chapter will investigate the current state of machine learning (ML) in the healthcare industry, as well as the challenges it faces and its future development potential.
Content Based Video Retrieval with Handcrafted Features
Intelligent Computing and Emerging Communication Technologies, ICEC 2024, 2024, DOI Link
View abstract ⏷
With rapid growth of social media platforms and widespread use of handheld devices such as mobile phones and video cameras, the number of videos being captured and shared over the internet has increased significantly. However, due to the lack of organization, most of these videos lack semantic context. Traditional methods of video retrieval involve searching for relevant videos using attached semantics. which has led to the need for content-based video retrieval, where video contents are utilized for searching, whether by video or text queries.The primary goal of our system is to provide relevant videos from a database. Our proposed approach in this paper employs Pearson's coefficient of correlation (PCC) for key frame extraction from videos, subsequently building a feature vector that represents the video's content. We have also experimented with linear binary pattern (LBP) and Colour moments (CM). We have used precision metric for evaluating performance. For conducting experiments, we utilized the UCF101 dataset, comprising 13,320 videos across 101 categories.
Content based texture image retrieval using Linear Discriminant Analysis and weighted distance metric
Intelligent Computing and Emerging Communication Technologies, ICEC 2024, 2024, DOI Link
View abstract ⏷
In the digital era, low-cost hardware like sensors and cameras has led to the creation of numerous image databases for various applications. This has led to the need for retrieval systems that rely on visual content, and these types of systems are called content-based image retrieval (CBIR) systems. It's a method utilized to locate and extract digital images from extensive databases by considering their visual attributes, as opposed to relying exclusively on metadata or written descriptions. In order to obtain appropriate images from the database, features including colour histograms, texture patterns, and shape descriptors are being used to determine similarities between the images. Over the course of the last twenty years, efforts have been directed towards creating hand-crafted features tailored for CBIR systems. However, depending solely on distance-based retrieval methods is a formidable task. Hence, this study strives to leverage the capabilities of classifiers as well for the purpose of retrieval. So, the proposed CBIR paradigm uses not only the hand-crafted features but also the strength of the classifier with weighted distance metricTherefore, the proposed CBIR paradigm is designed in a way that it uses the strength of the NaiveBayes classifier to compute weighted distance using hand-crafted wavelet features to get similar images from the database. The performance of the proposed method is evaluated on three most popular texture datasets and found to be better among all the methods reported in this work.
Fundamentals of machine learning in healthcare
Prediction in Medicine: The Impact of Machine Learning on Healthcare, 2024, DOI Link
View abstract ⏷
Machine learning (ML), a subset of artificial intelligence (AI), is revolutionizing industries by leveraging statistical algorithms that learn from data and experiences. Unlike traditional programs following predetermined sequences, ML algorithms discern patterns and predict outcomes through extensive datasets. This transformative technology has profoundly impacted diverse sectors, including manufacturing, finance, retail, transportation, entertainment, and healthcare. The influence of ML is amplified by the accessibility of extensive datasets and the escalating computational prowess of modern systems. As ML algorithms progress, they are fundamentally reshaping business operations, streamlining processes, enhancing decision-making, and fuelling innovation across sectors. The impact of machine learning algorithms on healthcare applications and the usage of diverse data sources, such as electronic health records, medical imaging, wearable devices, and genomic data, is discussed in this chapter.
Deep CNN in Healthcare
Deep Learning in Biomedical Signal and Medical Imaging, 2024, DOI Link
Image watermarking based on remainder value differencing and extended Hamming code
Gottimukkala A.R., Kumar N., Dash J.K., Swain G.
Journal of Electronic Imaging, 2024, DOI Link
View abstract ⏷
Due to the availability of various photo editing tools, intruders can tamper with an image very easily. So, various watermarking and tamper detection approaches have been proposed by researchers. Basically, tamper detection techniques focus on embedding the watermark, extracting the water mark, and identifying the tampered regions. But it is very important that the tampered pixels should also be corrected. We bring forward an image watermarking technique for tamper detection and correction using remainder value differencing (RVD) and extended Hamming code (EHC). It operates on a pixel group of size 2 × 2. Watermark bits (WBs) are generated from four most significant bits of the pixels in a pixel group by EHC and concealed in four lower bit planes by the principle of RVD. The WBs are extracted at the receiver along with the identification of tampered pixels. The tampered pixels are corrected by the developed correction logic. As the principle of RVD is used, precautions are taken to avoid the fall-off boundary problem. The efficacy of this technique is accessed through various quality metrics. It is noted that it performs better than the existing techniques. The recorded peak signal-to-noise ratio value is 45.49 dB with structural similarity value 0.9889. The tampered pixels are identified and corrected.
Deep Learning Models in Finance: Past, Present, and Future
Vishnumolakala S.K., Gopu S.R., Dash J.K., Tripathy S., Singh S.
Intelligent Systems Reference Library, 2024, DOI Link
View abstract ⏷
Over the past few decades, the financial industry has shown a keen interest in using computational intelligence to improve various financial processes. As a result, a range of models have been developed and published in numerous studies. However, in recent years, deep learning (DL) has gained significant attention within the field of machine learning (ML) due to its superior performance compared to traditional models. There are now several different DL implementations being used in finance, particularly in the rapidly growing field of Fintech. DL is being widely utilized to develop advanced banking services and investment strategies. This chapter provides a comprehensive overview of the current state-of-the-art in DL models for financial applications. The chapter is divided into categories based on the specific sub-fields of finance, and examines the use of DL models in each area. These include algorithmic trading, price forecasting, credit assessment, and fraud detection. The chapter aims to provide a concise overview of the various DL models being used in these fields and their potential impact on the future of finance.
Deep Semantic Feature Reduction for Efficient Remote Sensing Image Retrieval
Yelchuri R., Khadidos A.O., Khadidos A.O., Alshareef A.M., Swain G., Dash J.K.
IEEE Access, 2023, DOI Link
View abstract ⏷
Content-Based Remote Sensing Image Retrieval (CBRSIR) is used to find relevant images from large collections of remote sensing images. CBRSIR works by indexing each image in the database with a feature vector. Deep semantic features generated using convolutional neural networks (CNNs) are more powerful than low-level features for CBRSIR tasks because they can comprehend the context and content within an image. However, the major problem with the deep features is its large vector size which in turn can impact the performance of the retrieval system and are more susceptible to noise and outlier data. Therefore, in this work, a modified ResNet50 architecture is proposed that serves as a powerful feature extractor, benefiting from its deep learning capabilities. Specific modifications are introduced to enhance its discriminative power and generalization ability, enabling it to extract more robust deep features for image indexing. The proposed method achieves a mean average precision (mAP) of 0.899 surpassing the popular competing methods ResNet50 and GoogleNet by a substantial margin of 22.02%, 26.79% respectively. Moreover, to address the curse of dimensionality, this study also proposes a novel approach that combines a modified ResNet50 architecture with Linear Discriminant Analysis (LDA) and Maximum Relevance and Minimum Redundancy (MRMR) technique. The proposed approach achieves 85.45% reduction in size of the feature vector using MRMR and 98.19% using LDA, thereby improving retrieval efficiency without impacting the performance.
GLS-NET: An ensemble framework for classification of images
2023 IEEE 20th India Council International Conference, INDICON 2023, 2023, DOI Link
View abstract ⏷
Image classification stands as a fundamental task in computer vision, and Convolutional Neural Networks (CNNs) have emerged as highly proficient tools, demonstrating remarkable accuracy and performance. However, with the increasing complexity and diversity of image datasets, there is a growing need to improve the robustness and generalization of CNN-based classifiers. One promising approach to address this challenge is the ensembling of CNNs. Ensembling involves combining the outputs of multiple CNNs to enhance classification performance. This technique leverages the strength and diversity of individual models to achieve superior results compared to using a single model alone. Therefore, GLS-NET, an ensemble framework is proposed which uses three parallel ResNet50 CNNs and takes different features as input so as to induce the diversity in data which in turn can learn discriminative features to produce high accuracy. The proposed framework is evaluated on the most popular dataset, EMNIST, and achieved good performance improvement in accuracy. EMNIST is the most popular dataset used extensively in evaluating the performance of many deep learning techniques.
Study and development of hybrid and ensemble forecasting models for air quality index forecasting
Pradhan S.S., Panigrahi S., Purohit S.K., Dash J.K.
Expert Systems, 2023, DOI Link
View abstract ⏷
In this paper, a viable, robust, and highly accurate additive hybrid model employing autoregressive fractionally integrated moving average (ARFIMA) and support vector machine (SVM) with functionally expanded inputs (Additive-ARFIMA-SVM) is presented for forecasting the air quality index (AQI). Additionally, thirteen additive and multiplicative hybrid models are introduced. Several alternatives in feature engineering employing functional expansion of inputs are incorporated to boost the performance of hybrid models. Furthermore, a gradient whale optimization algorithm with group best leader strategy (GWOA-GBL) based meta-heuristic algorithm is proposed. The missing values are imputed and a variable weight ensemble forecasting model is developed using the proposed GWOA-GBL algorithm. To evaluate the effectiveness of the proposed Additive-ARFIMA-SVM forecasting model with functionally expanded inputs, comparisons are made with sixteen machine learning models, including long short-term memory (LSTM), five statistical models, seventeen hybrid models, and ten variable weight ensemble models. Extensive statistical analyses are carried out on the obtained results considering four accuracy measures that show the statistical supremacy of the proposed Additive-ARFIMA-SVM model and GWOA-GBL algorithm in predicting the AQI time series. The proposed Additive-ARFIMA-SVM model with functionally expanded inputs improves the AQI forecasting performance by 16.34% than autoregressive integrated moving average, 14.47% than ARFIMA, 33.96% than XGBoost, 43.47% than SVM, 49.39% than LSTM, 8.64% than Multiplicative-ARIMA-SVM model considering symmetric mean absolute percentage error. The proposed Additive-ARFIMA-SVM model is so efficient and reliable that it can be applied to forecast other time series like stock price, electricity load, crude oil price, sunspot number, stream flow, flood, drought etc.
A Novel Model to Predict the Effects of Enhanced Students’ Computer Interaction on Their Health in COVID-19 Pandemics
Agarwal N., Mohanty S.N., Sankhwar S., Dash J.K.
New Generation Computing, 2023, DOI Link
View abstract ⏷
During the COVID-19 pandemic time, educational institutions have really played a good role in imparting online education to students. Their career and academic tenure were not affected as contrary to the past pandemics throughout world history. All this has been possible through long sessions of classes, quizzes, assignments, discussions, chat interactions, and examinations through online video-based learning using computer interactive measures. The students were privileged to utilize digital technologies for longer durations for learning purposes. However, these long stretches have adversely affected their body postures, and physical and mental health as they majorly remain confined to chairs with restricted levels of physical activities. Thus, there is a need to have a model which can act as an insight for parents, doctors (pediatricians), and academic policymakers to decide on maximum hours for online teaching and related activities during future pandemics. The novel model proposed in this work helps to predict the impact of enhanced students’ computer interactions on their physical and mental health. The method proposed uses a novel model which is advanced and computationally strong. The model follows a two-step methodology, where at the first level, a variant of already existing machine learning algorithm is proposed and at the next level, it is optimized further using a hybrid bio-inspired optimization algorithm. The model consists of proposing a variant of XGBoost model (step1 optimization) followed by a hybrid bio-inspired algorithm (step2 optimization). The work considers a humongous dataset with varied age groups of students with more than 10 attributes. The proposed model is highly efficient in making predictions with 98.07% accuracy level and 98.43% F1-score. The time complexity of the model obtained is also of order of “n” where “n” depicts the number of input variables. Strong empirical results for other parameters also like specificity (95.63%) and sensitivity (96.74%) ascertain the enhanced predictive power generated using the proposed model. An extensive comparative study with other machine learning models ascertains the elevated accuracy and predictive power using the proposed model. Till now none of the researchers have proposed any such pioneering tool for parents, doctors, and academicians using advanced machine learning algorithms.
Secure transmission of medical images in multi-cloud e-healthcare applications using data hiding scheme
Devi K.J., Singh P., Dash J.K., Thakkar H.K., Tanwar S., Alabdulatif A.
Journal of Information Security and Applications, 2023, DOI Link
View abstract ⏷
In recent years, medical image transmission using a multi-cloud system has played a significant role in e-Healthcare infrastructure. It allows medical practitioners to easily store, retrieve, and share patients’ medical information across multiple stakeholders. However, multi-cloud image transmission may be vulnerable to multiple security breaches, such as authentication, confidentiality, and security issues. Motivated by these issues, this paper proposes a data-hiding scheme for secure medical image transmission in a multi-cloud environment. The proposed scheme ensures imperceptible robustness and watermark security at a low computational cost. Here, the medical image is divided into a number of shares using Neighbor Mean Interpolation (NMI). To achieve confidentiality, Electronic Patient Healthcare Record (EPHR) is encrypted using Double Scan Pixel Position Shuffling (DSPPS) approach. Then, the encrypted EPHR is divided into shares and embedded in the cover medical image shares. Finally, a minimum of 50% of watermarked image shares are utilized to retrieve the original medical image and encrypted EPHR, consequently reducing multi-cloud latency and computational burden. Experimental results show that the proposed scheme shows high imperceptibility, robustness, and watermark security at a low computational cost. Comparative analysis with some of the recent popular data hiding schemes shows that the proposed scheme has improved imperceptibility and robustness by 10%–15% (approximately) with higher watermark security at a low computational cost.
Exploiting deep and hand-crafted features for texture image retrieval using class membership
Pattern Recognition Letters, 2022, DOI Link
View abstract ⏷
In the modern digital era, with the availability of low-cost hardware like sensors and cameras, a huge amount of image databases are being created for diverse applications. These databases give rise to the need of developing efficient content-based image retrieval (CBIR) systems. Major efforts have been put over the past two decades to develop different global and low-level texture features to build efficient CBIR systems. However, designing texture features that are suitable for distance-based retrieval is always a challenging task. Recently, Convolution Neural Networks have shown promising results for object detection and classification. CNNs are also applied to build classifier-based retrieval systems. However, the classifier-based retrieval methods can retrieve images only from the predicted class. Therefore, the performance of such system greatly depends on classification performance of the classifier. This paper proposes a method that exploits the strength of the Convolutional Neural Networks for predicting the class membership of the query image for all output classes and retrieve images using a modified distance function in the wavelet feature space. The performance of the proposed method is evaluated using three popular texture datasets of varying complexity and found to be superior to all competing methods considered.
Efficient image retrieval system for textural images using fuzzy class membership
Kale M., Dash J., Mukhopadhyay S.
Multimedia Tools and Applications, 2022, DOI Link
View abstract ⏷
The article describes enhancements in retrieval performance of content-based image retrieval (CBIR) system using the fuzzy class membership-based retrieval (CMR) framework. The CMR approach explores the CBIR as a classifier-based retrieval problem using a neural network classifier, accompanied by a simple distance-based retrieval method. The fuzzy class membership-based approach is known to enhance the retrieval performance along with slight variation without any constraint on the feature set to be used. Despite that, its efficacy is not known for color and multi-band textures. We have proposed several advancements in a fuzzy class membership-based retrieval framework for improved retrieval. The main contributions are the simplification of vital threshold selection process and effective use of membership values to encourage the use of appropriate classifiers, investigation of the role of the cost function in neural network and distance weighting functions for improved retrieval, a way to adapt a new classifier in fuzzy class membership-based retrieval framework in place of neural network. Experimental analysis of all proposed advancements are evaluated using benchmark gray-scale texture databases viz. three versions of Broadtz and Outex database. The p-value analysis is carried out to check if the improvements are statistically significant. The proposed method is further tested with the Describable texture database (DTD) and Multi-band texture (MBT) database to check its applicability on color textures. The comparison with recent methods using gray-scale image databases viz. AT&T face database, MIT VisTex database, Broadatz texture database, and natural-color image databases viz. Corel-1K and Corel-10K showcase the efficacy of the proposed method.
Motion Recognition in Bharatanatyam Dance
Bhuyan H., Killi J., Dash J.K., Das P.P., Paul S.
IEEE Access, 2022, DOI Link
View abstract ⏷
This paper provides a method to understand the underlying semantics of Bharatnatyam dance motion and classifies it. Each dance performance is audio-driven and spans over space and time. The dance is captured and analyzed, which is helpful in cultural heritage preservation, and tutoring systems to assist the naive learner. This paper attempts to solve the fundamental problem; recognizing the motions during a dance performance based on motion-pattern. The used dataset is the video recordings of an Indian Classical Dance form known as Bharatanatyam. The different Adavu s (The basic unit of Bharatanatyam) of Bharatanatyam dance are captured using Kinect. We choose RGB from various forms of captured data (RGB, Depth, and Skeleton). Motion History Image (MHI) and Histogram of Gradient of MHI (HoGMHI) are computed for each motion and used as an input for the Machine Learning (ML) algorithms to recognize motion. The paper explores two ML techniques; Support Vector Machine (SVM) and Convolutional Neural Network (CNN). The overall accuracy of both the classifiers is more than 90%. The novelties of the work are (a) analysing all possible involved motions based on the motion-patterns rather than the joint velocities or pose, (b)exploring the impact of training data and the different features on the classifiers' accuracy, (c) not restricting the number of frames in a motion during recognition and formulate a method to deal with the variable number of frames in the motions.
A New Robust and Secure 3-Level Digital Image Watermarking Method Based on G-BAT Hybrid Optimization
Devi K.J., Singh P., Dash J.K., Thakkar H.K., Santamaria J., Krishna M.V.J., Romero-Manchado A.
Mathematics, 2022, DOI Link
View abstract ⏷
This contribution applies tools from the information theory and soft computing (SC) paradigms to the embedding and extraction of watermarks in aerial remote sensing (RS) images to protect copyright. By the time 5G came along, Internet usage had already grown exponentially. Regarding copyright protection, the most important responsibility of the digital image watermarking (DIW) approach is to provide authentication and security for digital content. In this paper, our main goal is to provide authentication and security to aerial RS images transmitted over the Internet by the proposal of a hybrid approach using both the redundant discrete wavelet transform (RDWT) and the singular value decomposition (SVD) schemes for DIW. Specifically, SC is adopted in this work for the numerical optimization of critical parameters. Moreover, 1-level RDWT and SVD are applied on digital cover image and singular matrices of LH and HL sub-bands are selected for watermark embedding. Further selected singular matrices (Formula presented.) and (Formula presented.) are split into (Formula presented.) non-overlapping blocks, and diagonal positions are used for watermark embedding. Three-level symmetric encryption with low computational cost is used to ensure higher watermark security. A hybrid grasshopper–BAT (G-BAT) SC-based optimization algorithm is also proposed in order to achieve high quality DIW outcomes, and a broad comparison against other methods in the state-of-the-art is provided. The experimental results have demonstrated that our proposal provides high levels of imperceptibility, robustness, embedding capacity and security when dealing with DIW of aerial RS images, even higher than the state-of-the-art methods.
A modified ranking function of linear programming problem directly approach to fuzzy environment
Prasad R., Das S.K., Mandal T., Dash J.K.
International Journal of Mathematics in Operational Research, 2021, DOI Link
View abstract ⏷
This work introduced a modified ranking function which produced crisp linear programming (CLP) problems. A fully fuzzy linear programming (FFLP) problem in its balanced form having all the parameters and variables are triangular fuzzy numbers is taken into account during this study. Within the literature of the sector, the prevailing proposed approaches have many shortcomings, i.e., incorporate the rule of surplus variable and does not satisfy the constraints. Here, we bearing in mind of the prevailing shortcomings, a constructive solution is approached to beat the restrictions. For better exactness of the answer which is proposed by us, we use fuzzy number. Two numerical examples are illustrated and compared with the pre-existing methods.
Efficient plastic recycling and remolding circular economy using the technology of trust–blockchain
Khadke S., Gupta P., Rachakunta S., Mahata C., Dawn S., Sharma M., Verma D., Pradhan A., Krishna A.M.S., Ramakrishna S., Chakrabortty S., Saianand G., Sonar P., Biring S., Dash J.K., Dalapati G.K.
Sustainability (Switzerland), 2021, DOI Link
View abstract ⏷
Global plastic waste is increasing rapidly. In general, densely populated regions generate tons of plastic waste daily, which is sometimes disposed of on land or diverged to sea. Most of the plastics created in the form of waste have complex degradation behavior and are non-biodegradable by nature. These remain intact in the environment for a long time span and potentially originate complications within terrestrial and marine life ecosystems. The strategic management of plastic waste and recycling can preserve environmental species and associated costs. The key contribution in this work focuses on ongoing efforts to utilize plastic waste by introducing blockchain during plastic waste recycling. It is proposed that the efficiency of plastic recycling can be improved enormously by using the blockchain phenomenon. Automation for the segregation and collection of plastic waste can effectively establish a globally recognizable tool using blockchain-based applications. Collection and sorting of plastic recycling are feasible by keeping track of plastic with unique codes or digital badges throughout the supply chain. This approach can support a collaborative digital consortium for efficient plastic waste management, which can bring together multiple stakeholders, plastic manufacturers, government entities, retailers, suppliers, waste collectors, and recyclers.
Content-based image retrieval system for HRCT lung images: assisting radiologists in self-learning and diagnosis of Interstitial Lung Diseases
Dash J.K., Mukhopadhyay S., Gupta R.D., Khandelwal N.
Multimedia Tools and Applications, 2021, DOI Link
View abstract ⏷
Content-based Image Retrieval (CBIR) is a technique that can exploit the wealth of the data stored in a repository and help radiologists in decision making by providing references to the image in hand. A CBIR system for High-Resolution Computed Tomography (HRCT) lung images depicting signs of Interstitial Lung Diseases (ILDs) can be built and used as a self-learning tool for budding radiologists. The study of a few lung image retrieval systems available in the literature identifies some important issues that need to be taken care of. In most of the works, the creation of the reference database involves painstaking manual activity, which is time-consuming and needs skilled labor. A lot of human interventions are required, particularly for the proper delineation of the region of interest (ROI) that represents pathology in each of the images in a database. In most cases, the size of the ROIs representing different disease findings are fixed (i.e., either a fixed size square or circle), which at times may not be a proper representation of the disease pattern and as a consequence, it might limit the system’s performance. Until date, a few learning-based approaches have been developed for content-based image retrieval of HRCT lung images, which either learn the similarity using a classifier or get trained through relevance feedback. For medical image analysis, the availability of labelled data for learning makes these learning-based retrieval systems meaningful as it enhances their performance in contrast to their simple distance-based counterpart. The objective of this paper is to develop a CBIR system for ILDs that is reliable and needs minimal human intervention. The paper evaluates the performance of three popular segmentation algorithms. It identifies the best for the effective and automated delineation of an arbitrary region of interest (AROI) depicting the sign of ILDs on HRCT images of the thorax in contrast to the manual delineation of fixed size ROI. This minimizes the manual effort for the creation and maintenance of the reference database, as well as the manual delineation of AROI during query formation. Moreover, AROI created through the automated clustering is found to have a better representation of disease patterns. Three recently proposed general-purpose learning based CBIR techniques are implemented and tested for retrieval of HRCT lung images depicting the sign of ILDs. The best method is suggested after careful evaluation of all the competing techniques.
A novel lexicographical-based method for trapezoidal neutrosophic linear programming problem
Das S.K., Edalatpanah S.A., Dash J.K.
Neutrosophic Sets and Systems, 2021,
View abstract ⏷
The aim of this paper is to introduce a simplified presentation of a new computing procedure for solving trapezoidal neutrosophic linear programming (TrNLP) problem under uncertainties. Therefore, we firstly define the concept of single valued neutrosophic (SVN) numbers and ranking functions. A new strategy is planned for solving the NLP problem without any ranking function. The planned strategy is depends on multi-objective LP (MOLP) issue and lexicographic order (LO). By following the means of planned strategy, the problem is changed into crisp LP (CLP) problem. In addition to this, a theoretical analysis is provided. Numerical examples are illustrated the proposed method and the consequences are in contrast with the distinct choice methods. The outcome shows that the proposed technique defeats the deficiencies and constraints of the existing method.
An Automated Method for Identification of Key frames in Bharatanatyam Dance Videos
Bhuyan H., Das P.P., Dash J.K., Killi J.
IEEE Access, 2021, DOI Link
View abstract ⏷
Identifying k ey frames is the first and necessary step before solving the variety of other B haratanatyam problems. The paper aims to partition the momentarily stationary frames (key frame s) from this dance video's motion frames. The proposed key frame s (KFs) localization is novel, simple, and effective compared to the existing dance video analysis methods. It is distinctive from standard KFs detection algorithms as used in other human motion videos. In the dance's basic structure, the occurrence of KFs during performances is often not completely stationary and varies with the dance form and the performer. Hence, it is not easy to decide a global threshold (on the quantum of motion) to work across dancers and performances. The earlier approaches try to compute the threshold iteratively. However, the novelty of the paper is: (a) formulating an adaptive threshold, (b) adopting Machine Learning (ML) approach and, (c) generating the effective feature by combining three frame differencing and bit-plane technique for the KF detection. In ML, we use Support Vector Machine (SVM) and Convolutional Neural Network (CNN) as the classifiers. The proposed approaches are also compared and analyzed with the earlier approaches. Finally, the proposed ML techniques emerge as a winner with around 90% accuracy.
Introduction to Unsupervised Learning in Bioinformatics
Parasa N.A., Namgiri J.V., Mohanty S.N., Dash J.K.
Data Analytics in Bioinformatics: A Machine Learning Perspective, 2021, DOI Link
View abstract ⏷
Unsupervised learning algorithmic techniques are applied in grouping the data depending upon similar attributes, most similar patterns, or relationships amongst the dataset points or values. These Machine learning models are also referred to as self-organizing models which operate on clustering technique. Distinct approaches are employed on every other algorithm in splitting up data into clusters. Unsupervised machine learning uncovers previously unknown patterns in data. Unsupervised machine learning algorithms are applied in case of data insufficiency. Few applications of unsupervised machine learning techniques include: Clustering, anomaly detection. Clustering algorithms in bioinformatics are mostly used to decrypt the salient data in gene expression which is used to acknowledge biological processes in an organism. These models aid in drug design through gene expression profiling. Self organising maps are used in data reduction which provides a better understanding of genomics. Various clustering algorithms are deployed in microarray analysis which is useful in clinical research in keeping track of gene expression data. To define in simpler terms unsupervised learning is a technique which works on the input data to produce the output which is hidden or undetermined. This chapter presents various unsupervised algorithms used for knowledge exploration in the field of bioinformatics and highlights several novel works reported in the recent literature.
A genetic algorithm for energy efficient fog layer resource management in context-aware smart cities
Reddy K.H.K., Luhach A.K., Pradhan B., Dash J.K., Roy D.S.
Sustainable Cities and Society, 2020, DOI Link
View abstract ⏷
The development of novel Information and Communication Technology (ICT) based solutions becomes essential to meet the ever increasing rate of global urbanization in order to satiate the constraint in resources. The popular ‘smart city paradigm is characterized by ubiquitous cyber provisions for the monitoring and control of such city's critical infrastructures, encompassing healthcare, environment, transportation and utilities among others. In order to manage the numerous services keeping their Quality of Service (QoS) demands upright, it is imperative to employ context aware computing as well as fog computing simultaneously. This paper investigates the feasibility of energy minimization at the fog layer through intelligent sleep and wake-up cycles of the fog nodes which are context-aware. It proposes a virtual machine management approach for effectively allocating service requests with a minimal number of active fog nodes using a genetic algorithm (GA); and thereafter, a reinforcement learning (RL) approach is incorporated to optimize the period of fog nodes’ duty cycle. Simulations are carried out using MATLAB and the results demonstrate that the proposed scheme improves energy consumption of the fog layer by approximately 11–21% when compared to existing context sharing based algorithms.
An AI-based Real-Time Roadway-Environment Perception for Autonomous Driving
Shubham, Reza M., Choudhury S., Dash J.K., Roy D.S.
2020 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2020, 2020, DOI Link
View abstract ⏷
Real-time roadway-environment perception is one of the primary applications of IoT based autonomous driving to improve road safety. Roadway-environment insights include on-road detection of any type of moving vehicles, non-vehicle (persons, animals, etc.), curves and lanes. There have been various studies that provided Artificial Intelligence (AI)-based detection approaches, however, most of the methods are atomistic which are not well suited for such real-time autonomous driving owing to high detection latency and low accuracy. Therefore, in this paper, we propose a holistic AI-based roadway-environment learning system for simultaneous real-time detection of various on-road objects with high accuracy (more than 90%) at reduced computation complexity.
Teaching learning based optimized support vector regression model for prediction of Indian stock market
Singh A., Kumar Dash J., Behura B., Chakravarty S.
International Journal of Advanced Science and Technology, 2020,
View abstract ⏷
The accurate prediction of financial market prices is highly important for making crucial investments with the least amount of risk. With regard to complex financial data resulting due to several factors that may be political or economic, machine learning and evolutionary computation techniques have been implemented by various authors for financial time series forecasting. Particle Swarm Optimization (PSO) and Teaching Learning Based Optimization (TLBO) algorithms have been implemented independently to optimize the parameters of many forecasting models. This paper presents the comparison between two hybrid Support Vector Regression (SVR) models to predict future Indian stock market price. In particular a PSO-optimized SVR model along with a TLBO-optimized SVR model was developed and the results yielded by both were studied. The proposed PSO-SVR model is based on the natural flocking behavior shown by birds and fish to get to the food source. The proposed TLBO-SVR model, inspired from the knowledge transfer occurring between a teacher and students in a classroom, is a parameter-less optimization algorithm that avoids any algorithm-specific parameter that is to be provided by the user during optimization. Regression metric – Root Mean Squared Error (RMSE) is used as Fitness function for both optimization algorithms. The efficiency of both the hybrid models was calculated by predicting the daily closing prices of S&P BSE SENSEX index traded in the Bombay Stock Exchange of India. Metrics such as Normalized Mean Squared Error (NMSE), Root Mean Squared Error (RMSE), Directional Symmetry (DS) and Mean Absolute Error (MAE) were used to find the performance of both models. The comparison of the experimental results shows that both hybrid models are effective and perform far better than the standard SVR model. It is noticed that even though TLBO algorithm yields slightly better results, PSO is better compared to others with respect to time taken for optimization and delivering optimized parameters fast enough.
An Intelligent Dual Simplex Method to Solve Triangular Neutrosophic Linear Fractional Programming Problem
Das S.K., Edalatpanah S.A., Dash J.K.
Neutrosophic Sets and Systems, 2020, DOI Link
View abstract ⏷
This paper develops a general form of neutrosophic linear fractional programming (NLFP) problem and proposed a novel model to solve it. In this method the NLFP problem is decomposed into two neutrosophic linear programming (NLP) problem. Furthermore, the problem has been solved by combination of dual simplex method and a special ranking function. In addition, the model is compared with an existing method. An illustrative example is shown for better understanding of the proposed method. The results show that the method is computationally very simple and comprehensible.
Machine learning approach for materials technologies
Dash J.K., Sharma M., Dalapati G.K.
Energy Saving Coating Materials: Design, Process, Implementation and Recent Developments, 2020, DOI Link
View abstract ⏷
A substantial amount of the energy produced globally is utilized for household utilities, for example to maintain air-conditioning in buildings for personal comfort and essential weathering necessities, in tropical or cold climate geographic regions. The development of innovative functional materials in combination with cutting edge technology is vital for sustainable urban solutions. The progress and scaling-up of new technology for urban solution is necessary to addresses key concerns like improved energy efficacies, zero energy building (ZEB), recyclability, waste management, reduce carbon footprints, de-carbonization, etc. The building energy consumption can be controlled by adopting specialized cloaking technologies using materials or nanoadditives to create high reflective coatings/surfaces. However, large number of possible configurations and physical experiments that includes complexity of nanoadditives to achieve optimized materials performance and optical properties are time consuming as well as very expensive. In remedies, physical experiments and computational modeling methods have been utilized to develop optimized functional properties of the materials. Progression in materials research and innovation is critical for the requirement of futuristic sustainable solution, for example, green electricity and energy saving needs. Experimental techniques and computational modeling are time consuming; hence, it is much desirable to develop new methods to accelerate the materials development technologies, design optimization and implementation. This chapter aims to introduce the basics of machine learning for material technologies and list out major work carried out in this domain recently.
Local Texture Features for Content-Based Image Retrieval of Interstitial Lung Disease Patterns on HRCT Lung Images
Dash J.K., Patro M., Majhi S., Girish G., Nancy Anurag P.
Advances in Intelligent Systems and Computing, 2020, DOI Link
View abstract ⏷
Content-based image retrieval (CBIR) is a technique that may help radiologists in their daily clinical practice by providing reference images against a given subject in hand for diagnosis. Several special purpose medical CBIR systems are built for the diagnosis of interstitial lung diseases (ILDs). Texture is used as a primitive feature to build such systems due to the texture-like appearance of ILD patterns. Therefore, it is necessary to evaluate the efficacy of promising texture feature descriptors proposed recently for building the CBIR system for ILDs. This paper presents an effective and exhaustive evaluation of five such recently proposed texture feature descriptors (viz. local binary pattern (LBP), orthogonal combination of local binary pattern (OC-LBP), center-symmetric local binary pattern (CS-LBP), local neighborhood difference pattern (LNDP), and combination of LNDP and LBP) for the design and development of CBIR system for ILDs. The performance of each method is compared using the most used performance metrics such as precision, recall, and F-score. The LNDP descriptor is found to be the best performer and therefore can be considered as a descriptor for ILD patterns for the design and development of CBIR system.
Adaptive fuzzy local binary pattern for texture classification
Proceedings - 2017 2nd International Conference on Man and Machine Interfacing, MAMI 2017, 2018, DOI Link
View abstract ⏷
Many local texture features are proposed for texture classification and retrieval. Fuzzy Local Binary Pattern (FLBP) is one of such promising texture descriptor found in the literature. However, the fuzzification parameter (T) used in FLBP is computed empirically and not adaptive to local content. In addition, one need to perform several experiments over a large range of T to find its optimal value. In this paper a novel technique is proposed to compute fuzzification parameter and the resulting descriptor is named as Adaptive Fuzzy Local Binary Pattern (AFLBP). In the proposed technique, the computation of fuzzification parameter is adaptive in nature and thereby capture most representative feature for each pixel in the image. The earlier paper makes use of Support Vector Machine (that uses a non-linear kernel) to test the discriminating ability of the FLBP descriptor. Here, in this paper, the K-Nearest Neighbors (kNN) classifier is used as a classifier to investigate the discriminating strength of the proposed feature descriptor. The discriminating ability of the proposed texture descriptor is compared with that of local binary pattern (LBP) and fuzzy local binary pattern (FLBP) using Brodatz texture database. The result shows that the proposed descriptor outperforms other competing descriptors used in the experiment irrespective of the distance measure used for classification. It is also observed that the k-NN classifier using Manhattan distance outperforms all other combinations.
Similarity learning for texture image retrieval using multiple classifier system
Multimedia Tools and Applications, 2018, DOI Link
View abstract ⏷
Multiple Classifier System has found its applications in many areas such as handwriting recognition, speaker recognition, medical diagnosis, fingerprint recognition, personal identification and others. However, there have been rare attempts to develop content-based image retrieval (CBIR) system that uses multiple classifiers to learn visual similarity. Texture as a primitive visual content is often used in many important applications (viz. Medical image analysis and medical CBIR system). In this paper, a texture image retrieval system is developed that learns the visual similarity in terms of class membership using multiple classifiers. The way proposed approach combines the decisions of multiple classifiers to obtain final class memberships of query for each of the output classes is also a novel concept. A modified distance that is weighted with the membership values obtained through similarity learning is used for ranking. Three different algorithms are proposed for the retrieval of images against a query image displaying the strength of multiple classifier approach, class membership score and their interplay to achieve the objective defined in terms of simplicity, retrieval effectiveness and speed. The proposed methods based on multiple classifiers achieve higher retrieval accuracy with lower standard deviation compared to all the competing methods irrespective of the texture database and feature set used. The multiple classifier retrieval schemes proposed here is tested for texture image retrieval. However, these can be used for any other challenging retrieval problems.
Multiple classifier system using classification confidence for texture classification
Dash J.K., Mukhopadhyay S., Gupta R.D.
Multimedia Tools and Applications, 2017, DOI Link
View abstract ⏷
This paper proposes a simple yet effective novel classifier fusion strategy for multi-class texture classification. The resulting classification framework is named as Classification Confidence-based Multiple Classifier Approach (CCMCA). The proposed training based scheme fuses the decisions of two base classifiers (those constitute the classifier ensemble) using their classification confidence to enhance the final classification accuracy. 4-fold cross validation approach is followed to perform experiments on four different texture databases those vary in terms of orientation, number of texture classes and complexity. Apart from its simplicity, the proposed CCMCA method shows better and consistent performance with lowest standard deviation as compared to fixed rule and simple trainable fusion techniques irrespective of the feature set used across all the databases used in the experiment. The performance gain of the proposed CCMCA method over other competing methods is found to be statistically significant.
Content based retrieval of interstitial lung disease patterns using spatial distribution of intensity, gradient magnitude and gradient direction
Gupta R.D., Dash J.K., Mukhopadhyay S.
2016 International Conference on Systems in Medicine and Biology, ICSMB 2016, 2017, DOI Link
View abstract ⏷
Today the enormous growth of medical images and scarcity of experienced pulmonologists and radiologists has led to the necessity of an efficient content-based image retrieval system capable of retrieve lung images similar to a given query image. This paper presents a promising texture-based image retrieval technique for interstitial lung disease categorisation by analysing the spatial distribution of intensity, along with its gradient magnitude and direction. The strengths of textural features derived from all different combinations of intensity, gradient magnitude and gradient direction are analysed. It is observed that both the magnitude and direction of intensity gradient contains significant textural information. Texture features can be substantially enriched by combining the features extracted from intensity, magnitude and direction of the intensity gradient as compared to that obtained from intensity alone. This approach is invariant to orientation of the texture and shape of the region of interest (ROI). The technique is simple, and is applicable to several other pattern recognition problems.
An experimental study of interstitial lung tissue classification in HRCT images using ANN and role of cost functions
Dash J.K., Kale M., Mukhopadhyay S., Khandelwal N., Prabhakar N., Garg M., Kalra N.
Progress in Biomedical Optics and Imaging - Proceedings of SPIE, 2017, DOI Link
View abstract ⏷
In this paper, we investigate the effect of the error criteria used during a training phase of the artificial neural network (ANN) on the accuracy of the classifier for classification of lung tissues affected with Interstitial Lung Diseases (ILD). Mean square error (MSE) and the cross-entropy (CE) criteria are chosen being most popular choice in state-of-the-art implementations. The classification experiment performed on the six interstitial lung disease (ILD) patterns viz. Consolidation, Emphysema, Ground Glass Opacity, Micronodules, Fibrosis and Healthy from MedGIFT database. The texture features from an arbitrary region of interest (AROI) are extracted using Gabor filter. Two different neural networks are trained with the scaled conjugate gradient back propagation algorithm with MSE and CE error criteria function respectively for weight updation. Performance is evaluated in terms of average accuracy of these classifiers using 4 fold cross-validation. Each network is trained for five times for each fold with randomly initialized weight vectors and accuracies are computed. Significant improvement in classification accuracy is observed when ANN is trained by using CE (67.27%) as error function compared to MSE (63.60%). Moreover, standard deviation of the classification accuracy for the network trained with CE (6.69) error criteria is found less as compared to network trained with MSE (10.32) criteria.
Differentiation of several interstitial lung disease patterns in HRCT images using support vector machine: Role of databases on performance
Kale M., Mukhopadhyay S., Dash J.K., Garg M., Khandelwal N.
Progress in Biomedical Optics and Imaging - Proceedings of SPIE, 2016, DOI Link
View abstract ⏷
Interstitial lung disease (ILD) is complicated group of pulmonary disorders. High Resolution Computed Tomography (HRCT) considered to be best imaging technique for analysis of different pulmonary disorders. HRCT findings can be categorised in several patterns viz. Consolidation, Emphysema, Ground Glass Opacity, Nodular, Normal etc. based on their texture like appearance. Clinician often find it difficult to diagnosis these pattern because of their complex nature. In such scenario computer-aided diagnosis system could help clinician to identify patterns. Several approaches had been proposed for classification of ILD patterns. This includes computation of textural feature and training /testing of classifier such as artificial neural network (ANN), support vector machine (SVM) etc. In this paper, wavelet features are calculated from two different ILD database, publically available MedGIFT ILD database and private ILD database, followed by performance evaluation of ANN and SVM classifiers in terms of average accuracy. It is found that average classification accuracy by SVM is greater than ANN where trained and tested on same database. Investigation continued further to test variation in accuracy of classifier when training and testing is performed with alternate database and training and testing of classifier with database formed by merging samples from same class from two individual databases. The average classification accuracy drops when two independent databases used for training and testing respectively. There is significant improvement in average accuracy when classifiers are trained and tested with merged database. It infers dependency of classification accuracy on training data. It is observed that SVM outperforms ANN when same database is used for training and testing.
Content-based image retrieval using fuzzy class membership and rules based on classifier confidence
Dash J.K., Mukhopadhyay S., Das Gupta R.
IET Image Processing, 2015, DOI Link
View abstract ⏷
Content representation for images with well-defined inter-class boundaries in the feature space remains to be a difficult task. Simple distance-based retrieval (SDR) approaches those operate on the feature space for content-based image retrieval (CBIR) are, therefore claimed to be inefficient by many researchers. Different CBIR approaches have been proposed to surmount the drawbacks of SDR scheme. This study proposes a novel image retrieval scheme. In this scheme, effort is taken to reduce the overall search time of the recently proposed approach called 'class membership-based retrieval' (CMR). The proposed method identifies the confidence in the classification and limits the search to single output class and therefore, reduces the overall search time by 21.76% as compared to CMR. Quantitative methods are proposed to select various parameters used in the algorithm which were computed empirically in the case of earlier approach CMR. The computed parameters are validated using experimental results. The consistent behaviours of the proposed method and earlier methods used in the experiment are demonstrated using different feature sets and distance metrics. While the method can be used as a general purpose image retrieval system, experiment is performed on four texture databases wit different complexities in terms of size, number of texture classes and orientation.
Segmentation of interstitial lung disease patterns in HRCT images
Dash J.K., Madhavi V., Mukhopadhyay S., Khandelwal N., Kumar P.
Progress in Biomedical Optics and Imaging - Proceedings of SPIE, 2015, DOI Link
View abstract ⏷
Automated segmentation of pathological bearing region is the first step towards the development of lung CAD. Most of the work reported in the literature related to automated analysis of lung tissue aims towards classification of fixed sized block into one of the classes. This block level classification of lung tissues in the image never results in accurate or smooth boundaries between different regions. In this work, effort is taken to investigate the performance of three automated image segmentation algorithms those results in smooth boundaries among lung tissue patterns commonly encountered in HRCT images of the thorax. A public database that consists of HRCT images taken from patients affected with Interstitial Lung Diseases (ILDs) is used for the evaluation. The algorithms considered are Markov Random Field (MRF), Gaussian Mixture Model (GMM) and Mean Shift (MS). 2-fold cross validation approach is followed for the selection of the best parameter value for individual algorithm as well as to evaluate the performance of all the algorithms. Mean shift algorithm is observed as the best performer in terms of Jaccard Index, Modified Hausdorff Distance, accuracy, Dice Similarity Coefficient and execution speed.
Wavelet based rotation invariant texture feature for lung tissue classification and retrieval
Dash J.K., Mukhopadhyay S., Das Gupta R., Garg M.K., Prabhakar N., Khandelwal N.
Progress in Biomedical Optics and Imaging - Proceedings of SPIE, 2014, DOI Link
View abstract ⏷
This paper evaluates the performance of recently proposed rotation invariant texture feature extraction method for the classīcation and retrieval of lung tissues a®ected with Interstitial Lung Diseases (ILDs). The method makes use of principle texture direction as the reference direction and extracts texture features using Discrete Wavelet Transform (DWT). A private database containing high resolution computed tomography (HRCT) images belonging to ̄ve category of lung tissue is used for the experiment. The experimental result shows that the texture appearances of lung tissues are anisotropic in nature and hence rotation invariant features achieve better retrieval as well as classīcation accuracy. © 2014 SPIE.
Multi-classifier framework for lung tissue classification
Dash J.K., Mukhopadhyay S., Garg M.K., Prabhakar N., Khandelwal N.
IEEE TechSym 2014 - 2014 IEEE Students' Technology Symposium, 2014, DOI Link
View abstract ⏷
Many systems have been developed for computer analysis of the lungs in high resolution computed tomography (HRCT) scans for detection and analysis of Interstitial Lung Diseases (ILDs). This paper presents a novel approach for classification of lung tissue patterns affected with Interstitial Lung Diseases (ILDs) in high resolution computed tomography (HRCT) scans. The proposed scheme makes use of texture features obtained using Discrete Wavelet Transform (DWT) and multiple classifiers to obtain the initial decisions on the input image. The decisions obtained from all the classifiers are fused to obtain the final decision on the input pattern. The method is tested on a private database containing HRCT images belongs to four ILDs patterns (viz. consolidation, emphysema, ground glass, nodular) and normal lung tissue. The performance of the method is compared with its single classifier based counterpart and found to be superior. © 2014 IEEE.
Complementary cumulative precision distribution: A new graphical metric for medical image retrieval system
Dash J.K., Mukhopadhyay S., Khandelwal N.
Progress in Biomedical Optics and Imaging - Proceedings of SPIE, 2014, DOI Link
View abstract ⏷
Several single valued measures have been proposed by researchers for the quantitative performance evaluation of medical image retrieval systems. Precision and recall are the most common evaluation measures used by researchers. Amongst graphical measures proposed, precision vs. recall graph is the most common evaluation measure. Precision vs. recall graph evaluates di®erent systems by varying the operating points (number of top retrieval considered). However, in real life the operating point for di®erent applications are known. Therefore, it is essential to evaluate di®erent retrieval systems at a particular operating point set by the user. None of the graphical metric provides the variation of performance of query images over the entire database at a particular operating point. This paper proposes a graphical metric called Complementary Cumulative Precision Distribution (CCPD) that evaluates di®erent systems at a particular operating point considering each images in the database for query. The strength of the metric is its ability to represent all these measures pictorially. The proposed metric (CCPD) pictorially represents the di®erent possible values of precision and the fraction of query images at those precision values considering number of top retrievals constant. Di®erent scalar measures are derived from the proposed graphical metric (CCPD) for e®ective evaluation of retrieval systems. It is also observed that the proposed metric can be used as a tie breaker when the performance of di®erent methods are very close to each other in terms of average precision. © 2014 SPIE.
Content-based texture image retrieval using fuzzy class membership
Mukhopadhyay S., Dash J.K., Das Gupta R.
Pattern Recognition Letters, 2013, DOI Link
View abstract ⏷
There is no single best representation of images that can separate different classes with well defined boundaries in the feature space. Therefore, content-based image retrieval (CBIR) using conventional distance metric is not efficient in the low level image feature space viz. texture. Classifier based retrieval approaches (classification followed by retrieval) classify the query image and retrieve images only from the identified class. The performance of such approaches greatly relies on the performance of classifier. For each correct classification of query image, these systems yield high retrieval accuracy and for each misclassification the systems result in complete failure. It results huge variance in performance. This paper proposes a novel approach to content-based image retrieval called "Class Membership-based Retrieval" that addresses the limitations of both conventional distance based and conventional classifier based retrieval approaches. The proposed method consists of two steps. First, the class label and fuzzy class membership of query image is computed using neural network. In the second step, the retrieval is performed using a combination of simple and weighted (class membership based) distance metric in complete search space unlike the conventional classifier based retrieval techniques. The proposed technique also provides flexibility in reducing the search space in steps increasing the speed of retrieval at the cost of gradual reduction in accuracy. The performance of the method is evaluated using three texture data sets varying in orientations, complexity and number of classes. Experimental results support the proposed technique favorably when compared with other promising texture retrieval schemes. © 2013 Elsevier B.V. All rights reserved.
Content-based image retrieval for interstitial lung diseases using classification confidence
Dash J.K., Mukhopadhyay S., Prabhakar N., Garg M., Khandelwal N.
Proceedings of SPIE - The International Society for Optical Engineering, 2013, DOI Link
View abstract ⏷
Content Based Image Retrieval (CBIR) system could exploit the wealth of High-Resolution Computed Tomog- raphy (HRCT) data stored in the archive by finding similar images to assist radiologists for self learning and differential diagnosis of Interstitial Lung Diseases (ILDs). HRCT findings of ILDs are classified into several categories (e.g. consolidation, emphysema, ground glass, nodular etc.) based on their texture like appearances. Therefore, analysis of ILDs is considered as a texture analysis problem. Many approaches have been proposed for CBIR of lung images using texture as primitive visual content. This paper presents a new approach to CBIR for ILDs. The proposed approach makes use of a trained neural network (NN) to find the output class label of query image. The degree of confidence of the NN classifier is analyzed using Naive Bayes classifier that dynamically takes a decision on the size of the search space to be used for retrieval. The proposed approach is compared with three simple distance based and one classifier based texture retrieval approaches. Experimental results show that the proposed technique achieved highest average percentage precision of 92.60% with lowest standard deviation of 20.82%. © 2013 SPIE.
Rotation invariant textural feature extraction for image retrieval using eigen value analysis of intensity gradients and multi-resolution analysis
Das Gupta R., Dash J.K., Sudipta M.
Pattern Recognition, 2013, DOI Link
View abstract ⏷
In this paper a novel rotation invariant multi-resolution based texture retrieval technique is proposed. The rotation invariance is achieved by aligning the direction of maximum variation of intensity gradient (defined as principal texture direction) along the reference axis. The principal direction is determined using eigen value analysis of gradient image. Wavelet transform based techniques are applied on the rotated image. The independent representation of textural energies along various directions enhances the retrieval performance over the existing rotation invariant wavelet based techniques which achieve rotation invariance by averaging the direction sensitive components. Extensive experiments on Brodatz database support this postulate. © 2013 Elsevier Ltd.
Wavelet based features of circular scan lines for mammographic mass classification
2012 1st International Conference on Recent Advances in Information Technology, RAIT-2012, 2012, DOI Link
View abstract ⏷
Breast cancer is reported as the second most deadly cancer in the world on which public awareness has been increasing during the last few decades. Early detection can play an effective role in prevention and the most reliable detection technology is mammography. At the early stages of breast cancer, the clinical signs are very mild and vary in appearance, making diagnosis difficult even for specialists. Therefore, automatic reading of medical images becomes highly desirable. This paper aims to develop an automated system for mass classification in digital mammograms. Mini - MIAS database is used to obtain mammogram images. A novel approach for feature extraction is proposed which exploits the wavelet features of radial and circular scan lines drawn over the region of interest (ROI). The discriminating ability of these features are evaluated using three classifiers such as Neural Network (Scaled conjugate back propagation), Bayesian and Support Vector Machine (SVM). The experimental results show that SVM outperforms with an accuracy of 85.96%. © 2012 IEEE.
Content-based image retrieval for interstitial lung diseases
Dash J.K., Khandelwal N., Das Gupta R., Bhattacharya P., Mukhopadhyay S., Garg M.
2012 IEEE International Conference on Signal Processing, Computing and Control, ISPCC 2012, 2012, DOI Link
View abstract ⏷
Finding similar images or reference is one way to assist radiologist during daily clinical practice for differential diagnosis of Interstitial Lung Diseases (ILDs). Content Based Image Retrieval (CBIR) system could exploit the wealth of HRCT data stored in the archive by finding similar images or reference to assist radiologists during daily clinical practice. We have designed a special purpose CBIR system (Med-IR) for Interstitial Lung Diseases (ILDs), where the user can provide one interstitial disease pattern as input and the system will retrieve few most similar patterns available in the database. Three different feature extraction techniques are implemented. A graphical interface has been developed to give a query image and to display the retrieved images. The retrieval performances of three rotation invariant texture feature sets derived using Discrete Wavelet Transform (DWT), Dual Tree Complex Wavelet Transform (DT-CWT) and DT-CWT combined with Dual Tree Rotated Complex Wavelet Frame (DT-RCWF) are compared in terms of average precision and recall for ILDs pattern. The dataset used for evaluation contains 64 images representing four ILDs pattern such as consolidation, nodular, emphysema, ground glass and normal. It is observed that feature obtained using DT-CWT and DT-CWT combined with DT-RCWT out performs the features obtained using DWT techniques. © 2012 IEEE.
