Real Time Deep Learning Model for Food Item Identification and Recipe Data Generation Sanshruth Ralhan, Ronit Kumar Das, Sweta Srivastava Bio Web of Conferences, 2025 Accurate and fast identification of various food items can be very useful, in terms of preventing harm caused by allergies and other problems. In this work, an attempt is made to classify food items from real-world images with great accuracy and in real time. The proposed model is designed in a dual-phase classification method incorporating unsupervised clustering followed by a classification model to improve the initial prediction results. The dataset, selected primarily for its various food classes, consists of real-world images of food, captured outside controlled conditions. During the first stage, clustering is used to group class predictions into clusters. In the next stage, the model for the cluster with the highest prediction value is loaded to make the final prediction. Each cluster model is trained on a small subset of classes, reducing time and cost thereby improving performance. The accuracy metrics of the general model and some of the sub-models are compared to see if using smaller label subsets provides improved performance without a large increase in training time. Finally, for the generation of detailed information about food items and suggested recipes, an LLM will be integrated into the proposed model. Custom prompts will be used to generate contextually relevant data more effectively
Image Steganography Using CNN Divyanshi, Sparsh Sundriyal, Sweta Srivastava Lecture Notes in Networks and Systems, 2025
Deep Learning Based Hybrid Framework for Food Classification and Recipe Generation Sanshruth Ralhan, Ronit Kumar Das, Sweta Srivastava Icoicc 2025 3rd International Conference on Intelligent and Cloud Computing, 2025 In this paper, an attempt is made to improve the classification of food items from real-world images in addition to images sourced from controlled conditions. The dataset, which was selected for its large number of food classes, consists of 101,000 real-world food images divided equally between 101 class labels. The proposed model is designed in a two-stage methodology using a general model trained on all classes to obtain a heuristic value followed by use of a specialized sub-model for fine-tuned classification. In the first stage, a general model groups and adds up the predictions by cluster, providing a confidence value for each cluster. In the second stage, the model for the cluster with the highest confidence value is used for the final classification. Each cluster model is trained on a small subset of classes, reducing time and cost along with improving the performance. The study evaluates whether using smaller label subsets in sub-models leads to better classification performance in comparison to the general model while keeping training time manageable. The sub-models reach over 95 percent accuracy after training for 30 epochs, while the general model achieves 82 percent after 50 epochs. Therefore, the sub-models outperform the general model on the specific label subsets they were trained on, and take converge faster.
Machine Learning Techniques for Twitter Spam Detection: Comparative Insights and Real-Time Application Yashvardhan Asthana, Rahul Chhabra, Sweta Srivastava Proceedings of the 14th International Conference on Cloud Computing Data Science and Engineering Confluence 2024, 2024 In today's world of digital communication, platforms like Twitter are essential for connecting people globally. But there's a problem – spam on Twitter can be a big issue for users. Our main goal is to make a system that can spot and stop spam using fancy computer techniques. We looked at many tweets on Twitter, trying to understand how spam and regular tweets are spread out. We found a problem with our data – there were way more regular tweets than spam ones. To fix it, we used something called Synthetic Minority Over-sampling Technique (SMOTE) to make the number of tweets more equal. After that, we made and tested 13 computer models, looking at how good they were using important measures like accuracy and recall. The result is a strong system that can tell the difference between spam and real tweets on Twitter. This helps make online talks better, keeps users safe, and makes sure Twitter stays a good place to be. Since spam tactics keep changing, our work is an important step in making social media safer. This means everyone can enjoy a safer and better time online.
Mobile app review analysis for crowdsourcing of software requirements: a mapping study of automated and semi-automated tools Rhodes Massenon, Ishaya Gambo, Roseline Oluwaseun Ogundokun, Ezekiel Adebayo Ogundepo, Sweta Srivastava, Saurabh Agarwal, Wooguil Pak Peerj Computer Science, 2024 Mobile app reviews are valuable for gaining user feedback on features, usability, and areas for improvement. Analyzing these reviews manually is difficult due to volume and structure, leading to the need for automated techniques. This mapping study categorizes existing approaches for automated and semi-automated tools by analyzing 180 primary studies. Techniques include topic modeling, collocation finding, association rule-based, aspect-based sentiment analysis, frequency-based, word vector-based, and hybrid approaches. The study compares various tools for analyzing mobile app reviews based on performance, scalability, and user-friendliness. Tools like KEFE, MERIT, DIVER, SAFER, SIRA, T-FEX, RE-BERT, and AOBTM outperformed baseline tools like IDEA and SAFE in identifying emerging issues and extracting relevant information. The study also discusses limitations such as manual intervention, linguistic complexities, scalability issues, and interpretability challenges in incorporating user feedback. Overall, this mapping study outlines the current state of feature extraction from app reviews, suggesting future research and innovation opportunities for extracting software requirements from mobile app reviews, thereby improving mobile app development.
An Innovative Hybrid Biologically Inspired Method for Traffic Optimization Problem Sweta Srivastava, Thompson Stephan, Sudip Kumar Sahana International Journal on Artificial Intelligence Tools, 2022 The transport network and road services are the foundation for the development of human civilization. It is immensely essential to manage network congestion as well as to minimize the travel time of the growing traffic load on the road network. Traffic signals may play an important role in managing the mounting traffic. This work relies on reducing the total time lag at the traffic signals, thus reducing the overall travel period. The model is designed on a bi-level framework. The overall wait time is optimized at the traffic signals by the upper level while the User Equilibrium (UE) is estimated by the lower level. Biologically inspired metaheuristic methods like Bat Algorithm (BA), Genetic algorithms (GA), Ant Colony Optimization (ACO), and many others demonstrated optimized outcomes for bi-level problems. To improve the desirability of the metaheuristic techniques an innovative method encapsulating the desirability of both BA and GA is proposed to evaluate the traffic optimization problem (TOP). While BA helps in faster convergence GA diversifies the search space. A comparative analysis has been carried out with the parent algorithms as well as an existing ACO-GA-based model. It was observed that the proposed BA-GA method performs better than the rest of the techniques.
Hybrid microscopic discrete evolutionary model for traffic signal optimization Journal of Next Generation Information Technology, 2015
RECENT SCHOLAR PUBLICATIONS
AgesAI: An Intelligent Cybersecurity Framework for Advanced Threat Detection and Mitigation I Singh, M Singh, V Kamra, S Srivastava, I Singh 2026 3rd International Conference on Research Methodologies in Knowledge … , 2026 2026
Evaluating Machine Learning Models for Detecting Credit Card Fraud A Jain, R Lathwal, S Srivastava Doctoral Symposium on Computational Intelligence, 335-346 , 2025 2025
Real Time Deep Learning Model for Food Item Identification and Recipe Data Generation S Ralhan, RK Das, S Srivastava 8th AMIFOST 2025, BIO Web of Conferences 178 , 2025 2025 Citations: 1
Deep Learning Based Hybrid Framework for Food Classification and Recipe Generation S Ralhan, RK Das, S Srivastava 2025 International Conference on Intelligent and Cloud Computing (ICoICC), 1-6 , 2025 2025
Image Steganography Using CNN Divyanshi, S Sundriyal, S Srivastava International Conference on Mathematical Modeling, Computational … , 2025 2025
Mobile app review analysis for crowdsourcing of software requirements: a mapping study of automated and semi-automated tools R Massenon, I Gambo, RO Ogundokun, EA Ogundepo, S Srivastava, ... PeerJ Computer Science , 2024 2024 Citations: 10
Optimizing Real-Time Performance in ML-Based Application Layer Firewalls. N Vinayak, M Tushar, AB Khan, S Srivastava Proceedings of Fifth International Conference on Computing, Communications … , 2024 2024 Citations: 1
Extraction of Handwritten Text from Doctors’ Prescriptions M Mitra, S Goyal, T Agrawal, S Srivastava International Conference on Information and Communication Technology for … , 2024 2024 Citations: 1
Machine Learning Techniques for Twitter Spam Detection: Comparative Insights and Real-Time Application Y Asthana, R Chhabra, S Srivastava 14th International Conference on Cloud Computing, Data Science & Engineering … , 2024 2024 Citations: 9
Twitter Sentiment Analysis on Oxygen Supply During Covid 19 Outbreak. A Kashyap, K Yadav, S Srivastava. Lecture Notes in Electrical Engineering 925, 655-665. , 2022 2022 Citations: 2
An innovative hybrid biologically inspired method for traffic optimization problem S Srivastava, T Stephan, SK Sahana International Journal on Artificial Intelligence Tools 31 (02), 2240004 , 2022 2022 Citations: 1
Artificial intelligence inspired energy and spectrum aware cluster based routing protocol for cognitive radio sensor networks T Stephan, F Al-Turjman, KS Joseph, B Balusamy, S Srivastava Journal of Parallel and Distributed Computing 142, 90-105 , 2020 2020 Citations: 65
A survey on traffic optimization problem using biologically inspired techniques S Srivastava, SK Sahana Natural Computing, 1-15 , 2019 2019 Citations: 22
Application of bat algorithm for transport network design problem S Srivastava, SK Sahana Applied Computational Intelligence and soft computing 2019 (1), 9864090 , 2019 2019 Citations: 57
Bat algorithm-based traffic signal optimization problem S Srivastava, SK Sahana Soft Computing for Problem Solving: SocProS 2017, Volume 1, 927-936 , 2018 2018 Citations: 4
Nested hybrid evolutionary model for traffic signal optimization S Srivastava, SK Sahana Applied intelligence 46 (1), 113-123 , 2017 2017 Citations: 51
The Insects of Nature-Inspired Computational Intelligence S Srivastava, SK Sahana Handbook of Research on Soft Computing and Nature-Inspired Algorithms, 398-428 , 2017 2017
The Insects of Innovative Computational Intelligence S Srivastava, SK Sahana International Conference on Computational Intelligence, 177-186 , 2015 2015 Citations: 1
ACONN—A Multicast Routing Implementation S Srivastava, SK Sahana Computational Intelligence in Data Mining—Volume 2: Proceedings of the … , 2015 2015 Citations: 1
Hbrid Microscopic Discrete Evolutionary Model for Traffic Signal Optimization S Srivastava, SK Sahana, D Pant, P Mahanti Journal of Next Generation Information Technology 6 (2), 1 , 2015 2015 Citations: 7
MOST CITED SCHOLAR PUBLICATIONS
Artificial intelligence inspired energy and spectrum aware cluster based routing protocol for cognitive radio sensor networks T Stephan, F Al-Turjman, KS Joseph, B Balusamy, S Srivastava Journal of Parallel and Distributed Computing 142, 90-105 , 2020 2020 Citations: 65
Application of bat algorithm for transport network design problem S Srivastava, SK Sahana Applied Computational Intelligence and soft computing 2019 (1), 9864090 , 2019 2019 Citations: 57
Nested hybrid evolutionary model for traffic signal optimization S Srivastava, SK Sahana Applied intelligence 46 (1), 113-123 , 2017 2017 Citations: 51
A survey on traffic optimization problem using biologically inspired techniques S Srivastava, SK Sahana Natural Computing, 1-15 , 2019 2019 Citations: 22
Mobile app review analysis for crowdsourcing of software requirements: a mapping study of automated and semi-automated tools R Massenon, I Gambo, RO Ogundokun, EA Ogundepo, S Srivastava, ... PeerJ Computer Science , 2024 2024 Citations: 10
Machine Learning Techniques for Twitter Spam Detection: Comparative Insights and Real-Time Application Y Asthana, R Chhabra, S Srivastava 14th International Conference on Cloud Computing, Data Science & Engineering … , 2024 2024 Citations: 9
Hbrid Microscopic Discrete Evolutionary Model for Traffic Signal Optimization S Srivastava, SK Sahana, D Pant, P Mahanti Journal of Next Generation Information Technology 6 (2), 1 , 2015 2015 Citations: 7
Bat algorithm-based traffic signal optimization problem S Srivastava, SK Sahana Soft Computing for Problem Solving: SocProS 2017, Volume 1, 927-936 , 2018 2018 Citations: 4
Twitter Sentiment Analysis on Oxygen Supply During Covid 19 Outbreak. A Kashyap, K Yadav, S Srivastava. Lecture Notes in Electrical Engineering 925, 655-665. , 2022 2022 Citations: 2
Real Time Deep Learning Model for Food Item Identification and Recipe Data Generation S Ralhan, RK Das, S Srivastava 8th AMIFOST 2025, BIO Web of Conferences 178 , 2025 2025 Citations: 1
Optimizing Real-Time Performance in ML-Based Application Layer Firewalls. N Vinayak, M Tushar, AB Khan, S Srivastava Proceedings of Fifth International Conference on Computing, Communications … , 2024 2024 Citations: 1
Extraction of Handwritten Text from Doctors’ Prescriptions M Mitra, S Goyal, T Agrawal, S Srivastava International Conference on Information and Communication Technology for … , 2024 2024 Citations: 1
An innovative hybrid biologically inspired method for traffic optimization problem S Srivastava, T Stephan, SK Sahana International Journal on Artificial Intelligence Tools 31 (02), 2240004 , 2022 2022 Citations: 1
The Insects of Innovative Computational Intelligence S Srivastava, SK Sahana International Conference on Computational Intelligence, 177-186 , 2015 2015 Citations: 1
ACONN—A Multicast Routing Implementation S Srivastava, SK Sahana Computational Intelligence in Data Mining—Volume 2: Proceedings of the … , 2015 2015 Citations: 1
AgesAI: An Intelligent Cybersecurity Framework for Advanced Threat Detection and Mitigation I Singh, M Singh, V Kamra, S Srivastava, I Singh 2026 3rd International Conference on Research Methodologies in Knowledge … , 2026 2026
Evaluating Machine Learning Models for Detecting Credit Card Fraud A Jain, R Lathwal, S Srivastava Doctoral Symposium on Computational Intelligence, 335-346 , 2025 2025
Deep Learning Based Hybrid Framework for Food Classification and Recipe Generation S Ralhan, RK Das, S Srivastava 2025 International Conference on Intelligent and Cloud Computing (ICoICC), 1-6 , 2025 2025
Image Steganography Using CNN Divyanshi, S Sundriyal, S Srivastava International Conference on Mathematical Modeling, Computational … , 2025 2025
The Insects of Nature-Inspired Computational Intelligence S Srivastava, SK Sahana Handbook of Research on Soft Computing and Nature-Inspired Algorithms, 398-428 , 2017 2017
