With its vast applications in the industry, computing influential nodes is becoming a popular research field in recent days. The Department of Computer Science and Engineering is delighted to inform you that the paper, Computing Influential Nodes Using Nearest Neighborhood Trust Value and Pagerank in Complex Networks have been published by Dr Murali Krishna Enduri, Assistant Professor, Dr Satish Anamalamudi, Associate Professor, and the PhD students; Koduru Hazarathaiah, Ms Srilatha Tokala in the Entropy Journal (Q2 Journal), with an impact factor 2.587.

Abstract

Computing influential nodes attract many researchers’ attention for spreading information in complex networks. It has vast applications such as viral marketing, social leaders, rumour control, and opinion monitoring. The information spreading ability of influential nodes is more compared with other nodes in the network. Several researchers proposed centrality measures to compute the influential nodes in the complex network, such as degree, betweenness, closeness, semi-local centralities, PageRank, etc. These centrality methods are defined based on the local and/or global information of nodes in the network. However, due to the high time complexity, centrality measures based on the global information of nodes have become unsuitable for large-scale networks. Very few centrality measures exist that are based on the attributes between nodes and the structure of the network. We propose the Nearest Neighbourhood Trust PageRank (NTPR) based on the structural attributes of neighbours and nearest neighbours of nodes. We define the measure based on the degree ratio, the similarity between nodes, the trust value of neighbours, and the nearest neighbours.

Explanation of the research

The research computes the influential nodes on the various real-world networks by using the proposed centrality method NTPR. The researchers find the maximum influence by using influential nodes with SIR and independent cascade methods. They also compare the maximum influence of our centrality measure with the existing basic centrality measures.

Social implications

Viral Marketing is a business strategy that uses existing social networks to promote products. The influential nodes in complex networks can be found using the centrality measure and can be used as the seed nodes for promoting products in the social networks. A rumour is a statement being said without knowing if it is true or not. The rumours can be easily controlled by discovering influential nodes. The researchers look forward to finding a centrality measure to detect the influential nodes efficiently.

Q1 journal publications of our faculty members always bring honour to SRM University-AP. Dr Priyanka Singh, Assistant Professor from the Department of Computer Science and Engineering has published a paper titled “Ameliorated Follow the Leader: Algorithm and Application to Truss Design Problem” in the journal Structures (Q1 journal) having an impact factor of 2.983.

Abstract

In the real world, resources, time, and money are always limited, necessitating the need for well-balanced algorithms. According to the “No-free-lunch” theorem, no single algorithm exists that works well in all applications. Hence, an optimisation algorithm with improved performance is always needed. The paper presents an improved follow the leader (iFTL) algorithm that imitates the behavioural movement of a sheep within the flock. The algorithm has been utilised to solve eight complex 10, 37, 52, 72, 120, 200, 224, and 942 bar truss design problems.

Practical implications

The algorithm can be utilised to solve several structural and mechanical design problems such as bride design, antenna design, welded beam design, speed reducer, and many more. The algorithm is well suited for all types of real-life engineering problems where optimisation is required, from travel cost optimisation to optimisation of resources in the organisation under the given constraints and objective function.

Collaborators

1. Rahul Kottath (Computer Vision Engineer, Digital Tower, Bentley Systems India Private Limited, Pune, India)
2. Ghanshyam G. Tejani (Assistant Professor, Department of Mechanical Engineering, School of Technology, GSFC University, Vadodara, Gujarat, India)

Future Research Plan

Currently, Dr Priyanka is exploring new engineering applications where optimisation techniques can be used. She is working on optimisation methods that can be utilised to classify microarray data, energy optimisation, and mechanical and structural design problems. In future, she plans to propose her work to the industrial level for the greater good and better solutions.

In recent years, human activity recognition has gained significant attention inside the scientific community. The enhanced spotlight is on the ground of its direct application in multiple domains. The latest research at the Department of Computer Science validates this assumption. Assistant Professor Dr V M Manikandan, and the 4th year B Tech Student Chaitanya Krishna Pasula have published a chapter titled An analysis of human activity recognition systems and their importance in the current era in the book Computational Intelligence Based Solutions for Vision Systems. The book is published by IOP Publishing Ltd.

Explanation of the chapter

Human activity recognition is one of the most interesting and active research areas in computer vision. More research efforts are being put towards automatically identifying and analysing human activities due to their emerging importance in everyday applications. It serves applications in various areas like security video surveillance, smart homes, healthcare, human-computer interaction, virtual reality, robotics, and digital entertainment. Numerous papers have been published in the domain of human activity recognition. This book chapter discusses the various applications of human activity recognition, different methods available for automatic activity detection from videos, and the advantages of the human activity recognition system. It also describes the challenges in designing and implementing human activity detection schemes. Researchers further explain the publicly available datasets used for training and evaluating the systems for human activity recognition. The efficiency parameters used to evaluate the human activity recognition systems are also briefed in this chapter. The chapter is concluded by comparing the methodologies and speculating the possibilities of future research in this field.

In the future, the researchers are planning to design and implement an activity recognition system to identify abnormal activities in public places for safety purposes. This book chapter will be a helpful reference for UG/PG/Ph.D students who aspire to research in the domain of activity detection from video.

Wireless Sensor Networks (WSNs) and their derivatives such as Internet of Things (IoT) and the Internet of Industrial Things (IIOT) are no longer confined to traditional applications such as smart homes and transportation. It has already marked its presence in Industrial applications and extended even to wildlife conservation. The impending concerns associated with such wireless networks are their privacy and security. One such menace afflicting wildlife is cyber poaching. Taking this into consideration, Dr Manjula R, Assistant Professor, and her student Mr Tejodbhav Koduru, from the Department of Computer Science and Engineering, have published a paper, “Position-independent and Section-based Source Location Privacy Protection in WSN” in the journal, ‘IEEE Transactions on Industrial Informatics’ having an Impact Factor of 10.215. The article is published in collaboration with Ms Florence Mukamanzi from the University of Rwanda, Rwanda, Africa and Prof Raja Datta from IIT Kharagpur, West Bengal, India.

The sensors collect data about these endangered animals and report it to the central controller which is connected to the Internet. Over the period, the hunters have also evolved and are equipped with smart devices that help them to easily locate the animal with minimal effort. In the simplest form, the attacker or the hunter just eavesdrops on the communication links to know the message’s origin and backtrack to the source of information. Once the source of information i.e., the location is identified then the endangered animal is captured. To overcome such backtracking issues, their work aims at delaying the information disclosure to the attacker through traffic obfuscation.

Although it may not act as an ultimate solution, the research work focuses on contextual privacy, unlike traditional content privacy. The attacker collects only contextual information such as packet rate, traffic intensities, routing paths, time correlations etc., to determine the source of information. The work focuses on mitigating traffic correlation i.e., hop-by-hop backtrack attacks and protecting the assets that are monitored using WSNs. The performance metrics include safety period and network lifetime amongst other metrics. The proposed random-walk-based routing solution achieves an improved safety period and network lifetime compared to the existing schemes. The work was simulated using a custom-designed simulation tool and was validated with the numerical results obtained using mathematical models.

The proposed solutions could be seamlessly used in monitoring endangered animals such as rhinoceros or in military applications to track soldiers. In addition, the routing algorithm could also be used in delaying tolerant networks to improve the efficiency and lifetime of the network, in designing the random trajectories of bio-nano bots for intrabody monitoring etc. Their future research plan includes developing improved source location privacy preservation techniques for terrestrial and underwater wireless sensor networks using the benefits of Artificial Intelligence and Machine Learning. In addition, they also aims at the development of data collection and routing protocols for intrabody nanonetwork operating at tera hertz frequencies— next-generation networks, envisioned networks.

The power of merging art with science is beyond our imagination. This amalgamation can pull off things that may seem insurmountable without the assistance of the other. Professor Hiren Deva Sarma, Guest faculty of the Department of Computer Science and Engineering, has developed a computational technique to find the similarity between the given songs in a pool. His paper titled An Approach to Discover Similar Musical Patterns has been published in IEEE ACCESS, a Q1 journal with an impact factor of 3.36.

Abstract

An algorithm has been developed to find the similarity between given songs. The song pattern similarity has been determined by knowing the note structures and the fundamental frequencies of each note of the two songs under consideration. The statistical concept, Correlation of Coefficient, is used in this work. The correlation of Coefficient is determined by applying the 16 Note-Measure Method. If the Correlation of Coefficient is near 1, it indicates that the patterns of the two songs under consideration are similar. Otherwise, there exists a certain percentage of similarity only. This basic principle is used in a set of Indian Classical Music (ICM) based songs. The proposed algorithm can determine the similarity between songs, so alternative songs in place of some well-known songs can be identified in terms of the embedded raga patterns. A digital music library has been constructed as a part of this work. The library consists of different songs, their raga name, and their corresponding healing capabilities in terms of music therapy. The proposed work may find application in the area of music therapy. Music therapy is an area of research that has been explored significantly in recent times. This work can also be exploited for developing an intelligent multimedia tool applicable in the healthcare domain. A multimedia-based mobile app has been developed encapsulating the abovementioned idea that can recommend alternative or similar songs to the existing ICM-based songs. This mobile app-based music recommendation system may be used for different purposes, including entertainment and healthcare. As a result of the applications of the proposed algorithm, similar songs in terms of raga patterns can be discovered from within the pool of a set of songs. A Music Recommendation System built on this algorithm can retrieve an alternative song from within the pool of songs as a replacement to a well-known song, which otherwise may be used for particular music therapy. Results are reported and analysed thoroughly. The future scope of the work is outlined.

Explanation of the research

A computational technique has been developed to identify a particular song similar to another in terms of its embedded raga pattern. Indian Classical Music (ICM) based songs are considered in this work. As a result of the application of the proposed technique, it is possible to identify similar songs in terms of their raga patterns from within a pool of songs. Subsequently, a similar alternative song can be recommended for different applications, including music therapy. If we consider music therapy, an alternative medicine (note: here, medicine is the song) is possible to recommend due to the proposed technique. This algorithm will find many applications in the domain of music information retrieval (MIR) and music recommendation systems (MRS).

Practical implementation of the research

This algorithm may be applied in recommending music in music recommendation systems. Moreover, music information retrieval based on raga patterns can be an important domain where the proposed algorithm may be exploited. Considering the social implications, music therapy has been the intended area of the research; therefore, this algorithm has been developed considering numerous applications of music therapy based on Indian Classical Music. The music therapy community will be benefited from the proposed algorithm.

In this research project, Professor Hiren Deva Sarma has collaborated with; Assistant Professor Sudipta Chakrabarty, Techno India, Salt Lake at the Department of Master of Computer Application; Mr Ruhul Islam, IT Consultant, Cloud Shine Global LLP; and Emil Pricop, Associate Professor in the Department of Automatic Control, Computers and Electronics, Petroleum-Gas University of Ploiesti, Romania.

In the future, the researchers look forward to exploring the music therapy capabilities of Indian Folk Music (IFM) like Kamrupia Lokgeet, Goalparia Lokgeet, and Baul Geet. Understanding the similarity and dissimilarity of the above-mentioned folk songs with Indian Classical Music (ICM) from computational musicology perspectives is another objective of the proposed research work. The researchers also aim to develop Music Recommendation Systems (i.e., applications) considering the songs mentioned above (ICM + IFM) and the different requirements of the users.

Computational and artificial intelligence is enjoying an unparalleled relevance in the modern world. They improve people’s lives and are highly anticipated in the healthcare industry. Research in this domain is hugely appreciated by the contemporary world, considering its potential to create revolutionary changes in the health care system. The Department of Computer Science and Engineering is delighted to inform you that the paper Robust, Reversible Medical Image Watermarking for Transmission of Medical Images over Cloud in Smart IoT Healthcare has been accepted for publishing as a chapter in the book Predictive Analysis in Cloud, Fog and Edge Computing and Practice of Blockchain, IoT and 5G.

The paper was submitted by Assistant Professor Dr Priyanka S, her PhD student Ms Jyothsna Devi, and MTech student Mr Jayant Krishna. The book chapter for the edited book is entitled Predictive Data Security using Ai – Insights and Issues of Blockchain, IoT, and DevOps and is published by Springer Nature. It is a part of the book series, Studies in Computational Intelligence, indexed by SCOPUS.

The book Studies in Computational Intelligence targets to bring together researchers and practitioners in computational intelligence and AI technology, especially those related to the areas of Machine learning, blockchain, multimedia using AI, smart IoT environment and email spam and online surveys, and many more recent emerging fields. The research work mainly provides highly secure, robust medical image transmission over the cloud in a smart IoT healthcare environment to ensure high embedding capacity and integrity.

This book’s target audience comprises professionals and researchers working in the field of computational intelligence and AI for health services in a smart environment. The book will attract Engineers (computer, industrial, software, and others), health care scholars, and information scientists since it caters to their interests.

Two research papers from the Department of Computer Science and Engineering were presented at the 4th International Conference on Energy, Power, and Environment held from April 29 to May 1, 2022. Assistance professor V M Manikandan and three BTech students participated in the conference organised by NIT Meghalaya, India. The papers will be published in IEEE Xplore Digital Library (Scopus Indexed).

Third-year BTech CSE student Harshad Dhane presented the paper A Novel High Capacity Reversible Data Hiding through Encryption Scheme by Permuting Encryption Key and Entropy Analysis, co-authored by Palak Agarwal, third-year BTech student, and Dr V M Manikandan. The reversible data hiding scheme proposed by the research can be used in the healthcare sector to transmit electronic patient reports along with medical images. Improving the embedding rate of the reversible data hiding is the further plan of the researchers.

Explanation of the research

A Reversible Data Hiding Through Encryption (RDTE) scheme will consider an original image and a sequence of bits as the input and generate an encrypted image as the output. This encrypted image will be able to transmit through the network securely, and the authorized receiver can take out the hidden details along with the restoration of the actual image. This paper proposes a new RDTE scheme with a good rate of embedding without any issues during the restoration of the original image. The researchers used the well-known RC4 pseudo-random generator for the image encryption and performed data hiding during block-wise image encryption. In the proposed scheme, the original image is considered non-overlapping blocks of size BXB pixels, and these blocks will be encrypted using a sequence of pseudo-random integers. During the RDTE process, all the possible unique permutations of the encryption key, K, will be generated, say (K0, K1,…, KN). Further, the sender will be capable of embedding one integer value from the set {0, 1, …,N} in a selected image block. A selected block will be encrypted using the pseudo-random sequence of integers using the key K_Q to embed the integer Q in the selected block. The proposed scheme prefers to select keys with unique characters with sufficient length to ensure the maximum embedding capacity. The message extraction and image restoration are performed by analysing the entropy measure from each block after attempting the decryption.

The paper presented by second year BTech CSE student Sri Satya Maram is titled A Novel System for Automated Coloring of Neat Sketches and was co-authored by Dr V M Manikandan. The research introduces a new algorithm to colour a given neat sketch. The proposed algorithm can be used to colour drawings to create animated movies or to colour the designs developed by the designers. The researchers plan to develop artistic features on the coloured image for better visual appearance.

Explanation of the research

The process of colouring neat sketches is a significant activity when making animated movies or for better visualization in computer modelling. The colour filling tools are widely available in almost all the image/video editing software, which will help us pick a colour from a colour palette and can be filled in a selected region. This process is known as flat colouring. The flat colouring process has several challenges. One of the significant challenges is that the colour may leak from the selected regions to neighbouring regions if there are some small openings on the contours. The second concern while using flat colouring is that the designated areas will be filled entirely with the same colour, so the drawing will not have an artistic look. The research proposes a new software application that will take a neat sketch as the input, and the system will generate a coloured drawing as the output. In the proposed scheme, the researchers have converted the given sketch to a grayscale or binary image and applied image dilation operation to fill the small open spaces in the contours (if any). Further, the closed regions are identified and coloured with a predefined set of colours or random colour combinations. While colouring the regions, the proposed system will ensure that the adjacent regions will not be coloured with the same colours. A number of sketches have been considered during the experimental study, and the results are validated manually.