Abhishek Majumder
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Abhishek Majumder has a total of 42 co-authors. Here are the top co-authors by number of shared publications:
Sudipta Roy
Assam University
7 shared publicationsSukanta Chakraborty
Tripura University
7 shared publications- Sukanta Chakraborty
Tripura University, India
6 shared publications - Joy Lal Sarkar
Department of CSE, ICFAI University Tripura, Agartala, India
5 shared publications - Bibudhendu Pati
Rama Devi Women’s University
3 shared publications - Chhabi Rani Panigrahi
Department of Computer Science, Rama Devi Women’s University, Bhubaneswar, India
3 shared publications
Latest Publications
- 27 August 2026
- Published by IGI Global Scientific Publishing
- p. 231-256
Convolutional Neural Network-Based Music Genre Prediction
In this work, deep learning is utilized to develop a scalable and robust convolutional neural network-based music genre predication. Here, the audio data are divided into overlapping chunks. Then it is converted into Mel spectrograms and log-scaled representations which capture visually relevant frequency content. These spectrograms are resized and fed into a deep CNN architecture. The model has been trained for real-time prediction to guarantee practical usability. It has been designed to provide genre classification of unseen audio files, even though those are in different formats like MP3 and WAV. It is achieved through dynamic generation of Mel-spectrogram and aggregation of chunk-wise prediction. Overlapping temporal chunking, high-resolution Mel-spectrogram processing, and a deep CNN process built for short audio clip classification boost model generalization and prediction robustness. For performance analysis the GTZAN dataset has been used. Performance comparison highlights that proposed model outperforms baselines considering recall, precision, F1-score and accuracy.
- 27 August 2026
- Published by IGI Global Scientific Publishing
- p. 231-256
Convolutional Neural Network-Based Music Genre Prediction
In this work, deep learning is utilized to develop a scalable and robust convolutional neural network-based music genre predication. Here, the audio data are divided into overlapping chunks. Then it is converted into Mel spectrograms and log-scaled representations which capture visually relevant frequency content. These spectrograms are resized and fed into a deep CNN architecture. The model has been trained for real-time prediction to guarantee practical usability. It has been designed to provide genre classification of unseen audio files, even though those are in different formats like MP3 and WAV. It is achieved through dynamic generation of Mel-spectrogram and aggregation of chunk-wise prediction. Overlapping temporal chunking, high-resolution Mel-spectrogram processing, and a deep CNN process built for short audio clip classification boost model generalization and prediction robustness. For performance analysis the GTZAN dataset has been used. Performance comparison highlights that proposed model outperforms baselines considering recall, precision, F1-score and accuracy.
- 31 July 2026
- Published by IGI Global Scientific Publishing
- p. 141-164
Blockchain-Based Forest Plant Record Storage System Using Hyperledger Fabric
In today's era, securing data related to environmental and forest department has become a crucial aspect. Integrating blockchain based technologies with the forest data management is an effective solution. Blockchain technology such as Hyperledger Fabric is a permissioned blockchain. It can be helpful in storing the forest data in a more accurate, secure and tamper-proof manner. In this work a Hyperledger Fabric based framework has been developed to store the forest data in a secure and cost effective manner. The developed system can be used in the forest department to improve security and to monitor forest activities like illegal logging. In the developed system all the records are stored in an immutable manner. Its decentralized and permissioned nature helps to prevent any unauthorized participants, which means it only allows the participants that are authorized or permitted to perform within the network. The proposed technique has been implemented on Fabric 2.5 Test-Network. Performance analysis revels that the proposed system can be implemented in real time.
- 31 July 2026
- Published by IGI Global Scientific Publishing
- p. 141-164
Blockchain-Based Forest Plant Record Storage System Using Hyperledger Fabric
In today's era, securing data related to environmental and forest department has become a crucial aspect. Integrating blockchain based technologies with the forest data management is an effective solution. Blockchain technology such as Hyperledger Fabric is a permissioned blockchain. It can be helpful in storing the forest data in a more accurate, secure and tamper-proof manner. In this work a Hyperledger Fabric based framework has been developed to store the forest data in a secure and cost effective manner. The developed system can be used in the forest department to improve security and to monitor forest activities like illegal logging. In the developed system all the records are stored in an immutable manner. Its decentralized and permissioned nature helps to prevent any unauthorized participants, which means it only allows the participants that are authorized or permitted to perform within the network. The proposed technique has been implemented on Fabric 2.5 Test-Network. Performance analysis revels that the proposed system can be implemented in real time.
- Open Access
CID: A Compact Deep Learning Framework for Intrusion Detection Based on Binary Greylag Goose Optimization
The application of Internet of Things-based ecosystems is growing rapidly. Cyber attacks are also increasing at a similar pace. Intrusion detection using deep learning is getting harder as these devices lack enough resources for a large Intrusion Detection System. A compact deep learning-based Intrusion Detection System for IoT, called CID, has been proposed to reduce computational complexity. The proposed CID framework uses MobileNet v1 as the main classification model, and the Binary Greylag Goose Optimization technique is used for feature selection to improve detection while minimizing processing time. On comparing the experimental results, it has been found that the proposed method works better than the baseline methods.
Open AccessCID: A Compact Deep Learning Framework for Intrusion Detection Based on Binary Greylag Goose Optimization
The application of Internet of Things-based ecosystems is growing rapidly. Cyber attacks are also increasing at a similar pace. Intrusion detection using deep learning is getting harder as these devices lack enough resources for a large Intrusion Detection System. A compact deep learning-based Intrusion Detection System for IoT, called CID, has been proposed to reduce computational complexity. The proposed CID framework uses MobileNet v1 as the main classification model, and the Binary Greylag Goose Optimization technique is used for feature selection to improve detection while minimizing processing time. On comparing the experimental results, it has been found that the proposed method works better than the baseline methods.
- 3 June 2026
- Published by Springer Nature
- p. 118-130
SaFesTrip: Safe Festive Season Based Trip Recommendation System
- 3 June 2026
- Published by Springer Nature
- p. 118-130
SaFesTrip: Safe Festive Season Based Trip Recommendation System
- 1 May 2026
- Published by Springer Nature
- p. 391-401
MultiCrowd: Crowd Management for Smart City for Concurrent Requests
- 1 May 2026
- Published by Springer Nature
- p. 391-401
MultiCrowd: Crowd Management for Smart City for Concurrent Requests
- Open Access
- 1 January 2026
- Published by Institution of Engineering and Technology (IET) in IET Blockchain
- Vol. 6 (1)
C3Crowd$C^3Crowd$: Crowd Contributor and Consumer Framework for Secure Crowd Management Using Blockchain
Over the years, numerous efforts have been undertaken to accurately forecast traffic conditions and thereby preventing additional congestion. However, existing crowd management techniques focus on recognizing and counting the crowd while leaving the security of crowd information. A typical crowd management system is centralized and faces challenges, such as contributor selection reliability, fair payment evaluation, privacy concerns and high deployment costs. This study investigates security concerns in crowd management and evaluates the potential of blockchain technology to improve crowd management security. Combining the power of blockchain (decentralization and security) and smart contracts, this work proposes a secure crowd management architecture named . The framework operates on blockchain, utilizes cryptographic algorithms, and incorporates reputation management along with credit distribution through smart contracts. effectively safeguards crowd data while its revenue structure entices users to actively contribute to the system. has been simulated on GoQuorum's Ethereum private blockchain, using elliptic curve signatures for secure and efficient processing. Its performance was tested with RAFT, PoA and IBFT consensus mechanisms where RAFT led in throughput, IBFT lagged and PoA offered a middle ground. PoA stands out for balancing scalability and security, supporting network growth while preserving identity‐based validation and data integrity.
- 1 January 2026
- Published by Institution of Engineering and Technology (IET) in IET Blockchain
- Vol. 6 (1)
Open AccessC3Crowd$C^3Crowd$: Crowd Contributor and Consumer Framework for Secure Crowd Management Using Blockchain
Over the years, numerous efforts have been undertaken to accurately forecast traffic conditions and thereby preventing additional congestion. However, existing crowd management techniques focus on recognizing and counting the crowd while leaving the security of crowd information. A typical crowd management system is centralized and faces challenges, such as contributor selection reliability, fair payment evaluation, privacy concerns and high deployment costs. This study investigates security concerns in crowd management and evaluates the potential of blockchain technology to improve crowd management security. Combining the power of blockchain (decentralization and security) and smart contracts, this work proposes a secure crowd management architecture named . The framework operates on blockchain, utilizes cryptographic algorithms, and incorporates reputation management along with credit distribution through smart contracts. effectively safeguards crowd data while its revenue structure entices users to actively contribute to the system. has been simulated on GoQuorum's Ethereum private blockchain, using elliptic curve signatures for secure and efficient processing. Its performance was tested with RAFT, PoA and IBFT consensus mechanisms where RAFT led in throughput, IBFT lagged and PoA offered a middle ground. PoA stands out for balancing scalability and security, supporting network growth while preserving identity‐based validation and data integrity.
- 28 November 2025
- Published by IGI Global Scientific Publishing
- p. 293-318
Group Recommendation System Using Sentimental Analysis for User Satisfaction
Studies have shown that the existing recommendation systems provide misleading recommendations that actually do not meet the expectations of the tourists. Despite the fact that there have been efforts to build group recommendation system, they are primarily focused on offline settings. Moreover, combining individual suggestions into group recommendations or combining individual preferences into group preferences is a crucial element of group recommendation. Tourist recommendation system using sentimental analysis has given a better opportunity to the developer to know the user opinions for travelling. By extracting sentiment from group members, this work proposes an improved technique for group recommendation that boosts both the effectiveness and satisfaction of the users. The proposed technique uses clustering and similarity scores for recommending points of interests to the tourist groups. For performance analysis the proposed technique has been implemented using Python. Performance comparison shows that the proposed scheme outperforms the baselines with respect to accuracy.
- 28 November 2025
- Published by IGI Global Scientific Publishing
- p. 293-318
Group Recommendation System Using Sentimental Analysis for User Satisfaction
Studies have shown that the existing recommendation systems provide misleading recommendations that actually do not meet the expectations of the tourists. Despite the fact that there have been efforts to build group recommendation system, they are primarily focused on offline settings. Moreover, combining individual suggestions into group recommendations or combining individual preferences into group preferences is a crucial element of group recommendation. Tourist recommendation system using sentimental analysis has given a better opportunity to the developer to know the user opinions for travelling. By extracting sentiment from group members, this work proposes an improved technique for group recommendation that boosts both the effectiveness and satisfaction of the users. The proposed technique uses clustering and similarity scores for recommending points of interests to the tourist groups. For performance analysis the proposed technique has been implemented using Python. Performance comparison shows that the proposed scheme outperforms the baselines with respect to accuracy.
- 1 November 2025
- Published by Springer Nature
- p. 210-221
FOSTOUR: Festive Oriented Seasonal Tour Recommendation
- 1 November 2025
- Published by Springer Nature
- p. 210-221
FOSTOUR: Festive Oriented Seasonal Tour Recommendation
- 17 October 2025
- Published by Springer Nature
- p. 275-285
VIM: Vehicle Information Management Using Blockchain Technology
- 17 October 2025
- Published by Springer Nature
- p. 275-285
VIM: Vehicle Information Management Using Blockchain Technology
- 1 October 2025
- Published by Springer Nature
- p. 515-526
A Hyperledger-Based Chaincode for Registration and Authentication in Secure Parking Systems
- 1 October 2025
- Published by Springer Nature
- p. 515-526
A Hyperledger-Based Chaincode for Registration and Authentication in Secure Parking Systems