@amity.edu
Associate Professor, CSE
Amity University Madhya Pradesh
PhD in Computer Science and Engineering
PhD, M.E, MCA, MBA
Cyber Security, WSN, IOT
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Anangsha Halder, Subhrendu Guha Neogi, Shibdas Dutta, Koustov Khamaru, Arghya Bhattacharya, and Shovan Roy
IEEE
The world population relies on agricultural plants for food, and illnesses reduce yield, but proper plant disease monitoring can help to resolve such issues. Computer vision and machine learning methods can detect plant illnesses early, reducing their negative consequences and overcoming the drawbacks of continual human monitoring. After pre-processing of input images, the target region needs to be isolated. The proposed models analyzes images for detection and classification to identify edges, colors, and textures. This research has agricultural applications for early disease identification. This study examined ResNet, MobileNet, DenseNet, InceptionV3 and modified CNN model on the PlantVillage dataset to classify tomato illnesses. The F1 score, accuracy, sensitivity, and specificity can evaluate models. This paper evaluates these models using a diverse collection of tomato leaf pictures, contributing to automated disease detection systems and may be helpful for improving farm management and sustainability.
Joy Chatterjee, Subhrendu Guha Neogi, and Sanjeev Saraswat
Springer Nature Singapore
Pralov Biswas, Subhrendu Guha Neogi, Daniel Arockiam, and Anirban Mitra
IEEE
Multilingual sentiment analysis has become essential for brands targeting international customers across multiple cultures and languages as a result of the corporate world's growing globalization. To accurately comprehend client opinions and expectations, it is becoming increasingly important to analyze feelings expressed in local languages. In contrast to translating literature to English, it emphasizes how linguistic subtleties, contextual allusions, and cultural connotations collected through native language analysis offer greater insights. Key issues are listed in this research, including linguistic diversity, a dearth of training data, and challenges related to cultural context interpretation across geographic boundaries. To assist businesses in deriving useful insights from multilingual data, it highlights the necessity for advanced Artificial intelligence and deep neural network solutions that incorporate cross-channel, cross-lingual analytics frameworks. Brands can gain a major competitive advantage in optimizing global marketing strategies, increasing customer engagement, and fostering enduring loyalty by tracking attitudes in local languages. This paper proposed a novel approach to deal with Multi-lingual Sentiment Analysis in Digital Marketing.
Pulkit Ohri, A. Daniel, Subhrendu Guha Neogi, and Sunil Kumar Muttoo
Springer Science and Business Media LLC
Joy Chatterjee, Subhrendu Guha Neogi, Rajiv Kumar Dwivedi, and Anil Vashisht
IEEE
In recent years, online business models have been developed due to the availability of low-cost, high-speed internet. Online pharmacies using e-commerce sites now can reach to their customers easily and sell medications online. It is easy for customers to evaluate prices and product reviews before purchasing medicines. To understand the factors that affect consumers' behavioral and purchase intention from online pharmacies, a modified UTAUT model was used to investigate five determinants related to adoption intention namely perceived trust, perceived risk, perceived ease of use, performance expectancy, and social influence. This research delves into the viewpoints of online pharmacy customers, specifically examining the effects of deep learning algorithms. With their unparalleled accessibility and ease of use, internet pharmacies have revolutionized the healthcare industry. If these digital platforms are to be optimized for user happiness and optimal operation, it is crucial to understand how people perceive and interact with them. Customers now have more alternatives than ever before for getting their medications, Most prediction models' inputs were determined to be criteria pertaining to online activities and behaviors. Various deep learning techniques are used in purchase intention prediction because of their superior capacity to manage complex and massive datasets with little to no human oversight. The predictions using CNN and LSTM models achieve a high level of accuracy and are studied in our model with a modified framework for purchase prediction using these algorithms.
Pulkit Ohri, Subhrendu Guha Neogi, Somenath Sengupta, Daniel Arockiam, and Sunil Kumar Muttoo
IEEE
In the realm of network management, the integration of Software-Defined Networking (SDN) with blockchain-based smart contracts is an emerging frontier with significant potential to enhance inter-domain communications. This paper presents an in-depth analysis of the application of smart contracts within SDN, particularly focusing on the automation and security of inter-domain interactions. Smart contracts, characterized by their immutable and autonomous nature, offer a novel approach to enforcing network policies and agreements across different SDN domains seamlessly. We explore the inherent benefits of this integration, including enhanced security through the tamper-proof nature of blockchain, and the efficiency gains achieved by automating network policy enforcement. The paper also addresses critical challenges such as scalability, interoperability, and the complexity of smart contract development within the SDN context. Through a combination of theoretical analysis and practical case studies, this research illuminates the transformative potential of smart contracts in SDN, paving the way for more secure, efficient, and self-regulating network environments. The findings and discussions in this paper aim to contribute to the ongoing evolution of SDN, particularly in scenarios where multiple administrative domains necessitate robust, automated, and secure communication frameworks.
Pulkit Ohri, Daniel Arockiam, Subhrendu Guha Neogi, and Sunil Kumar Muttoo
IEEE
Software Defined Networking (SDN) introduced the third layer, known as the control layer, due to which management and updating of devices became easy. The control layer in SDN provides an additional remote controlling feature of devices, which offers better management over traditional hardware networks. Traditional networking uses a hardwired mechanism for controlling the apparatus, a slow and complicated management approach. Unlike conventional networks, where every device needs to be updated separately, the SDN Control layer handles all the devices simultaneously. Only one command from the control layer can change, update, and manage hundreds of devices simultaneously. ONOS is the most popular and widely used Open Source SDN controller. So far, efforts have been made to improve the performance and availability of the ONOS controller. ONOS provides better performance and fault tolerance than any other controller available. However, no security module in the ONOS Controller can protect itself from DDoS attacks. This paper used the popular Suricata Intrusion Prevention System (IPS) to mitigate these web-based attacks. Wireshark statistics showed that our experimental study removed malicious DDoS traffic sent toward the control layer. This is the first study where Suricata actively detects and mitigates DDoS traffic sent toward the ONOS Controller.
Ram Kumar Yadav, Subhrendu Guha Neogi, and Vijay Bhaskar Semwal
Springer Science and Business Media LLC
Shiv Kumar Tiwari and Subhrendu Guha Neogi
Springer Science and Business Media LLC
Pulkit Ohri, Subhrendu Guha Neogi, and Sunil Kumar Muttoo
IEEE
Software-Defined Networking (SDN) is becoming an increasingly relevant networking approach day by day, due to its myriad benefits over Traditional hardwired-based Networks. Still, SDN Controllers are popular for their weak security mechanism. This paper discusses the vulnerability issues in the security of SDN Controllers. The Control layer is the most vulnerable to network attacks in the three-layered SDN architecture. DDoS attacks on the Control layer can cause a Single Point of Failure for the entire SDN network. OpenDaylight (ODL) and Open Networking Operating System (ONOS) are the top two leading open-source SDN Controllers. We found out that ODL and ONOS Controller fail to provide any protection from DDoS attacks. SDN developers have compromised the security aspects of the Controller to improve its performance. In this research article, an attempt is being made to address such security vulnerabilities of SDN with ODL and ONOS Controllers for DDoS attacks.
Shiv Kumar Tiwari, Subhrendu G. Neogi, and Ashish Mishra
Springer Nature Singapore
Ram Kumar Yadav, Subhrendu Guha Neogi, and Vijay Bhaskar Semwal
Springer Nature Singapore
Ram Kumar Yadav, Subhrendu Guha Neogi, and Vijay Bhaskar Semwal
Springer Nature Switzerland
Sachin Saxena and Subhrendu Guha Neogi
IEEE
The basic design principle of insight finder includes Arduino as a microcontroller device, Pixy2 CMUCam5 for object detection and other different sensors used for finding paths. As a result, insight finder (IFBot) rover had been produced to find a suitable path between different types and colors of objects. This device can remember different color object signatures and objects at the same time, also have capabilities of handling 60 frames per second at super-fast processing and can process synchronous serial data for communication within short distance. Pixy2 has been used in IFBot Rover system as a color object sensor for object detection. The other hardware devices used to design IFBot are ultrasonic sensors, IR Sensors, Motor Drivers, gear motors. By adopting a simple wall following, line following and barcode reading algorithm, the device can detect object and path. Pixy Mon application software can produce high accuracy data with relatively high speed. The discussion in the result shows that the design of IFBot model can be further upgraded to perform better in terms of speed and accuracy.