Rajarshi Roy Chowdhury
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Rajarshi Roy Chowdhury has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
Pg Emeroylariffion Abas
Faculty of Integrated Technologies, Universiti Brunei Darussalam, Gadong, Brunei Darussalam
5 shared publicationsAzam Che Idris
Faculty of Integrated Technologies, Universiti Brunei Darussalam, Gadong, Brunei Darussalam
3 shared publications- Debashish Roy
Toronto Metropolitan University
2 shared publications - Abu Jafar Md Jakaria
Dept. of Computer Science and Engineering, Metropolitan University, Sylhet, Bangladesh
1 shared publication - Ajoy Roy
American International University-Bangladesh
1 shared publication - Arjun Kumar Bose Arnob
Department of Computer Science, American International University-Bangladesh, Dhaka, Bangladesh
1 shared publication
Latest Publications
- Open Access
- 15 June 2025
- Published by FOREX Publication in International Journal of Electrical and Electronics Research
- Vol. 13 (2) , 353-363
IntelligentGuard: Smart Doorbell with Deep Learning for Secure User Recognition and Instant Notifications
In the modern world, daily activities are heavily reliant on the Internet. This study aims to provide users with a simple, personalized technology that effectively manages visitor interactions. The primary objectives are to operate the doorbell intelligently and notify users about visitors by sending a notification with an image of an unknown visitor. This system introduces a low-cost Internet of Things (IoT) smart doorbell designed to enhance home security, utilizing a Raspberry Pi and a camera sensor. Camera sensor is used to capture images in front of the doorbell, which are then processed by the Raspberry Pi and sent to the server. The pre-trained deep learning model kept on a remote server checks the captured image whether it is known or unknown; if it is unknown, a new photo is taken. The proposed hybrid CNN-LSTM model achieves 98% accuracy on the collected dataset and 96.1% accuracy on the Human Faces dataset from Kaggle. This device is utilized to remotely monitor activities outside the door and receive notifications when visitors approach the doorbell using a user-friendly mobile application. This modern security doorbell requires minimal installation tools and lacks interior wiring. In the proposed system, the ESP32-CAM sensor detects visitors and announces their names if they are recognized as known individuals; otherwise, they are labeled as strangers. All relevant details, including timestamps, are promptly sent to the user's mobile application for real-time monitoring.
- 15 June 2025
- Published by FOREX Publication in International Journal of Electrical and Electronics Research
- Vol. 13 (2) , 353-363
Open AccessIntelligentGuard: Smart Doorbell with Deep Learning for Secure User Recognition and Instant Notifications
In the modern world, daily activities are heavily reliant on the Internet. This study aims to provide users with a simple, personalized technology that effectively manages visitor interactions. The primary objectives are to operate the doorbell intelligently and notify users about visitors by sending a notification with an image of an unknown visitor. This system introduces a low-cost Internet of Things (IoT) smart doorbell designed to enhance home security, utilizing a Raspberry Pi and a camera sensor. Camera sensor is used to capture images in front of the doorbell, which are then processed by the Raspberry Pi and sent to the server. The pre-trained deep learning model kept on a remote server checks the captured image whether it is known or unknown; if it is unknown, a new photo is taken. The proposed hybrid CNN-LSTM model achieves 98% accuracy on the collected dataset and 96.1% accuracy on the Human Faces dataset from Kaggle. This device is utilized to remotely monitor activities outside the door and receive notifications when visitors approach the doorbell using a user-friendly mobile application. This modern security doorbell requires minimal installation tools and lacks interior wiring. In the proposed system, the ESP32-CAM sensor detects visitors and announces their names if they are recognized as known individuals; otherwise, they are labeled as strangers. All relevant details, including timestamps, are promptly sent to the user's mobile application for real-time monitoring.
- Open Access
- 21 May 2025
- Published by Academy of Cognitive and Natural Sciences in Journal of Edge Computing
- Vol. 4 (1) , 73-104
A comprehensive systematic review of intrusion detection systems: emerging techniques, challenges, and future research directions
The role of Intrusion Detection Systems (IDS) in the protection against the increasing variety of cybersecurity threats in complex environments, including the Internet of Things (IoT), cloud computing, and industrial networks. This study evaluates the existing state-of-the-art IDS methodologies using Deep Learning (DL) approaches, and advanced feature engineering techniques. This research also highlights the success of models such as Genetic Algorithms (GA), Particle Swarm Optimization (PSO), and Explainable AI (XAI) in improving detection accuracy as well as computational efficiency and interoperability. Blockchain and quantum computing technologies are explored to improve data privacy, resilience, and scalability in decentralized and resource-constrained environments. This work primarily identifies key challenges, including real-time anomaly detection, adversarial robustness, and imbalance datasets, to assist researchers in investigating further research opportunities. Focusing on future research in filling these gaps, proceeds toward developing lightweight, adaptive, and ethical IDS frameworks that can operate in real-time across dynamic and heterogeneous environments. In this paper, existing IDS approaches, research opportunities, and advanced cybersecurity strategies are critically synthesized to create a useful resource for academics, researchers, and industry practitioners.
- 21 May 2025
- Published by Academy of Cognitive and Natural Sciences in Journal of Edge Computing
- Vol. 4 (1) , 73-104
Open AccessA comprehensive systematic review of intrusion detection systems: emerging techniques, challenges, and future research directions
The role of Intrusion Detection Systems (IDS) in the protection against the increasing variety of cybersecurity threats in complex environments, including the Internet of Things (IoT), cloud computing, and industrial networks. This study evaluates the existing state-of-the-art IDS methodologies using Deep Learning (DL) approaches, and advanced feature engineering techniques. This research also highlights the success of models such as Genetic Algorithms (GA), Particle Swarm Optimization (PSO), and Explainable AI (XAI) in improving detection accuracy as well as computational efficiency and interoperability. Blockchain and quantum computing technologies are explored to improve data privacy, resilience, and scalability in decentralized and resource-constrained environments. This work primarily identifies key challenges, including real-time anomaly detection, adversarial robustness, and imbalance datasets, to assist researchers in investigating further research opportunities. Focusing on future research in filling these gaps, proceeds toward developing lightweight, adaptive, and ethical IDS frameworks that can operate in real-time across dynamic and heterogeneous environments. In this paper, existing IDS approaches, research opportunities, and advanced cybersecurity strategies are critically synthesized to create a useful resource for academics, researchers, and industry practitioners.
- Open Access
- 17 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 423-428
Deep Learning Based IoT Device Categorization Using Network Traffic Analysis
- 17 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 423-428
Open AccessDeep Learning Based IoT Device Categorization Using Network Traffic Analysis
- Open Access
A Hypergraph-Based Approach to Recommend Online Resources in a Library
When users in a digital library read or browse online resources, it generates an immense amount of data. If the underlying system can recommend items, such as books and journals, to the users, it will help them to find the related items. This research analyzes a digital library's usage data to recommend items to its users, and it uses different clustering algorithms to design the recommender system. We have used content-based clustering, including hierarchical, expectation maximization (EM), K-mean, FarthestFirst, and density-based clustering algorithms, and user access pattern-based clustering, which uses a hypergraph-based approach to generate the clusters. This research shows that the recommender system designed using the hypergraph algorithm generates the most accurate recommendation model compared to those designed using the content-based clustering approaches.
Open AccessA Hypergraph-Based Approach to Recommend Online Resources in a Library
When users in a digital library read or browse online resources, it generates an immense amount of data. If the underlying system can recommend items, such as books and journals, to the users, it will help them to find the related items. This research analyzes a digital library's usage data to recommend items to its users, and it uses different clustering algorithms to design the recommender system. We have used content-based clustering, including hierarchical, expectation maximization (EM), K-mean, FarthestFirst, and density-based clustering algorithms, and user access pattern-based clustering, which uses a hypergraph-based approach to generate the clusters. This research shows that the recommender system designed using the hypergraph algorithm generates the most accurate recommendation model compared to those designed using the content-based clustering approaches.
- 31 August 2023
- Published by Springer Nature in Wireless Networks
- Vol. 30 (1) , 405-419
Identifying SH-IoT devices from network traffic characteristics using random forest classifier
- 31 August 2023
- Published by Springer Nature in Wireless Networks
- Vol. 30 (1) , 405-419
Identifying SH-IoT devices from network traffic characteristics using random forest classifier
- Open Access
- 14 July 2023
- Published by Centre for Research on Islamic Banking and Finance and Business in American International Journal of Multidisciplinary Scientific Research
- Vol. 14 (2) , 1-9
SOCIAL, ECONOMIC, AND ENVIRONMENTAL IMPACTS OF THE ONE BELT ONE ROAD INITIATIVES
The One Belt One Road Initiative (OBOR) by China presents a grand vision to the world that aims to foster cooperation among different countries in various fields such as global trade, international relations, infrastructure development, education, and technology. Also known as the Belt and Road Initiative (BRI), it comprises a network of roads, railways, and sea routes, all geared toward the development of humanity. The purpose of this research is to analyze some of the significant impacts of this massive project in terms of social, economic, and environmental aspects. Through the exchange of culture, sports, education, and international relations on six economic corridors, the BRI has the potential to create substantial economic benefits. The project also prioritizes environmental sustainability through a green BRI approach. All the quantitative and qualitative data are extracted from different research papers/reports, published books, and some online based data portals. It has been shown that the OBOR/BRI seeks to connect the world and foster peace, whilst its implementation may face significant challenges. Nonetheless, it presents new opportunities for people and may usher in a new era of globalization. JEL Classification Codes: D86, F18, F35, F63, K3.
- 14 July 2023
- Published by Centre for Research on Islamic Banking and Finance and Business in American International Journal of Multidisciplinary Scientific Research
- Vol. 14 (2) , 1-9
Open AccessSOCIAL, ECONOMIC, AND ENVIRONMENTAL IMPACTS OF THE ONE BELT ONE ROAD INITIATIVES
The One Belt One Road Initiative (OBOR) by China presents a grand vision to the world that aims to foster cooperation among different countries in various fields such as global trade, international relations, infrastructure development, education, and technology. Also known as the Belt and Road Initiative (BRI), it comprises a network of roads, railways, and sea routes, all geared toward the development of humanity. The purpose of this research is to analyze some of the significant impacts of this massive project in terms of social, economic, and environmental aspects. Through the exchange of culture, sports, education, and international relations on six economic corridors, the BRI has the potential to create substantial economic benefits. The project also prioritizes environmental sustainability through a green BRI approach. All the quantitative and qualitative data are extracted from different research papers/reports, published books, and some online based data portals. It has been shown that the OBOR/BRI seeks to connect the world and foster peace, whilst its implementation may face significant challenges. Nonetheless, it presents new opportunities for people and may usher in a new era of globalization. JEL Classification Codes: D86, F18, F35, F63, K3.
- Open Access
- 1 March 2023
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 12 (1) , 232-240
Device identification using optimized digital footprints
The rapidly increasing number of internet of things (IoT) and non-IoT devices has imposed new security challenges to network administrators. Accurate device identification in the increasingly complex network structures is necessary. In this paper, a device fingerprinting (DFP) method has been proposed for device identification, based on digital footprints, which devices use for communication over a network. A subset of nine features have been selected from the network and transport layers of a single transmission control protocol/internet protocol packet based on attribute evaluators in Weka, to generate device-specific signatures. The method has been evaluated on two online datasets, and an experimental dataset, using different supervised machine learning (ML) algorithms. Results have shown that the method is able to distinguish device type with up to 100% precision using the random forest (RF) classifier, and classify individual devices with up to 95.7% precision. These results demonstrate the applicability of the proposed DFP method for device identification, in order to provide a more secure and robust network.
- 1 March 2023
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 12 (1) , 232-240
Open AccessDevice identification using optimized digital footprints
The rapidly increasing number of internet of things (IoT) and non-IoT devices has imposed new security challenges to network administrators. Accurate device identification in the increasingly complex network structures is necessary. In this paper, a device fingerprinting (DFP) method has been proposed for device identification, based on digital footprints, which devices use for communication over a network. A subset of nine features have been selected from the network and transport layers of a single transmission control protocol/internet protocol packet based on attribute evaluators in Weka, to generate device-specific signatures. The method has been evaluated on two online datasets, and an experimental dataset, using different supervised machine learning (ML) algorithms. Results have shown that the method is able to distinguish device type with up to 100% precision using the random forest (RF) classifier, and classify individual devices with up to 95.7% precision. These results demonstrate the applicability of the proposed DFP method for device identification, in order to provide a more secure and robust network.
- 12 January 2023
- Published by Springer Nature in Journal of Network and Systems Management
- Vol. 31 (1) , 1-21
A Deep Learning Approach for Classifying Network Connected IoT Devices Using Communication Traffic Characteristics
- 12 January 2023
- Published by Springer Nature in Journal of Network and Systems Management
- Vol. 31 (1) , 1-21
A Deep Learning Approach for Classifying Network Connected IoT Devices Using Communication Traffic Characteristics
- Open Access
Internet of Things: Digital Footprints Carry A Device Identity
The usage of technologically advanced devices has seen a boom in many domains, including education, automation, and healthcare; with most of the services requiring Internet connectivity. To secure a network, device identification plays key role. In this paper, a device fingerprinting (DFP) model, which is able to distinguish between Internet of Things (IoT) and non-IoT devices, as well as uniquely identify individual devices, has been proposed. Four statistical features have been extracted from the consecutive five device-originated packets, to generate individual device fingerprints. The method has been evaluated using the Random Forest (RF) classifier and different datasets. Experimental results have shown that the proposed method achieves up to 99.8% accuracy in distinguishing between IoT and non-IoT devices and over 97.6% in classifying individual devices. These signify that the proposed method is useful in assisting operators in making their networks more secure and robust to security breaches and unauthorized access.
Open AccessInternet of Things: Digital Footprints Carry A Device Identity
The usage of technologically advanced devices has seen a boom in many domains, including education, automation, and healthcare; with most of the services requiring Internet connectivity. To secure a network, device identification plays key role. In this paper, a device fingerprinting (DFP) model, which is able to distinguish between Internet of Things (IoT) and non-IoT devices, as well as uniquely identify individual devices, has been proposed. Four statistical features have been extracted from the consecutive five device-originated packets, to generate individual device fingerprints. The method has been evaluated using the Random Forest (RF) classifier and different datasets. Experimental results have shown that the proposed method achieves up to 99.8% accuracy in distinguishing between IoT and non-IoT devices and over 97.6% in classifying individual devices. These signify that the proposed method is useful in assisting operators in making their networks more secure and robust to security breaches and unauthorized access.
- 22 October 2022
- Published by Elsevier in Internet of Things
- Vol. 20
A survey on device fingerprinting approach for resource-constraint IoT devices: Comparative study and research challenges
- 22 October 2022
- Published by Elsevier in Internet of Things
- Vol. 20
A survey on device fingerprinting approach for resource-constraint IoT devices: Comparative study and research challenges