Assistant Professor, Department of Computer Science and Engineering (Artificial Intelligence & Machine Learning), Vishwakarma Institute of Technology, Pune, India
Thursday August 27, 2026 12:28pm - 12:30pm IST Virtual Room CGOA, India
Authors - Prranjali Jadhav, Varsha H Patil Abstract - Recommendation systems play a crucial role in personalized content delivery across various domains such as e-commerce, streaming platforms, and healthcare. This survey presents a comprehensive analysis of recommendation frameworks, emphasizing their architectures, methodologies, challenges, and future directions. The provided framework integrates hybrid models, deep learning, collaborative filtering, and content-based filtering, processed through a multi-layered architecture. The data processing layer handles preprocessing, feature extraction, and data collection, while the model selection layer chooses an appropriate recommendation technique. The recommendation engine ranks and scores predictions before delivering final recommendations. A critical component is the user feedback & continuous learning module, incorporating explicit and implicit feedback to dynamically update the model. Challenges such as scalability, data sparsity, and real-time adaptation are explored, along with emerging advancements like knowledge graphs and reinforcement learning. The paper highlights future research opportunities to enhance recommendation accuracy and user experience.
Authors - Amit Budhodkar, Rupali Umbare, Nihar Ranjan, Shubham Udgirkar, Sakshi Suryawanshi, Pradnya Aher Abstract - As mock interviews are essential for job interview preparation, the resources available cannot evaluate both technical and non-technical skills. This paper outlines the AI Mock Interview Platform which interfaces with learners and simulates truthful interviews by assessing non-technical competencies such as body language, confidence, emotional expression, and technical knowledge. The platform is capable of dynamically generating interview questions relevant to a candidate's particular role using AI technologies. In addition, AI technologies enable real-time feedback provision. With regard to feedback generation, the system utilizes AI technologies to consider specific features unique to the candidates’ voices, movement, and gaze direction. It utilizes Dlib’s human body posture detection library and video sentiment analysis for facial expression recognition with AffectNet dataset for Convolutional Neural Network faces as well as videos. With the Courses feature, learners can focus on varied topics and the platform automatically selects suitable instructional content consistent with the candidates’ preferred method of learning
Authors - SHALINI S, C NANDINI, LAKSHMI MR, KOUSTAV BISWAS, L DIVYASHREE, MITAYI AJAY KUMAR, MONIKA V Abstract - This research work uses Artificial Intelligence for early detection and targeted intervention in the case of Autism Spectrum Disorder (ASD). Through sophisticated language analysis and pattern identification of interactions, the platform detects signs of autism to facilitate early intervention. Relying on these findings, the platform tailors developmental programs in pivotal areas of communication, daily living, and adaptive learning through fun, interactive modules. An integrated chatbot powered by AI improves user experience through conversational assistance, responding to questions, and assisting individuals with autism, as well as their caregivers. Ongoing interaction develops a greater familiarity with the resources available on the platform and encourages active involvement in skill development exercises. Structured with users from every age group, the platform places strong emphasis on ethical use of AI and protecting data, offering a secure and reliable environment. Through its fit to the singular developmental path of each user, it fosters autonomy, skills development, and social integration. The platform is an integrated system of care and empowerment for the autism community. It seeks to respond to the broad range of individual needs on a universal, adaptable, and empathetic level, facilitating personal development and increased autonomy for individuals on the spectrum.
Authors - Abhay Pratap Singh, Aanya Mittal, Ashmit Tyagi, Kanan Agrawal, Avdhesh Gupta Abstract - Communication is one of the major attributes of human life[1]. The system discussed in this research paper focuses on developing a novel and efficient way of communicating between a deaf-mute person and any other person who is normal (does not have deaf or dumb handicaps). Advanced technologies used in the design will support the conversion from voice to Indian Sign Language using Natural Language Processing Machine learning algorithms and computer vision techniques and vice versa. It translates audio messages into sign language images with text in real-time, trying to basically eliminate the conventional dependency on interpreters as a means of communication for every person. The main idea of the research is the solution of urgent problems connected with communication of the deaf-mute people and, at the same time, to be able to solve this task with the use of modern technologies, keeping in mind the principles of inclusiveness and independence. The design, implementation, and potential of the system to improve the living standards of deaf-mute people by bringing them closer to society are discussed. The aim is to plead for inclusion by raising the awareness of educators, policymakers, and the public at large regarding the demand for communication resources addressed specifically to the deaf and mute community. The consciousness of the demand for ISL interpreters and the promotion of video datasets will be helpful in bridging the gap in communication, as seen in the research on the lack of certified ISL interpreters and the demand for automated sign recognition systems.
Thursday August 27, 2026 12:30pm - 2:30pm IST Virtual Room CGOA, India
Authors - Debabala Swain, Monalisa Swain, Sharmistha Roy, Debabrata Swain, Jayanta Mondal, Prachee Dewangan Abstract - The information stored or transmitted digitally is vulnerable to unauthorized access. The authentication of digital images is a critical issue in the era of digital advancements, given the ease with which any image can be altered. Consequently, methods for verifying the credibility of images are gaining widespread recognition due to their relevance in various societal domains, such as government, military, forensics, and electronic commerce. The significance of protecting images from manipulation has escalated, recognizing that even a minor tampering incident could lead to severe consequences. Hence, safeguarding images from alterations has become increasingly essential. Literature has seen the development of numerous approaches to ensure the genuineness and integrity of digital images. This study offers a comprehensive overview of both domain-based and AI-based watermark techniques for authenticating images, providing the capability to detect tampering and pinpoint the specific manipulated areas within an image.
Authors - Pooja Singh Chaudhary, Nirav Bhatt, Purvi Prajapati Abstract - Object Detection and the Object Pursuit are the fundamental and the emerging tasks in the Machine learning and in the computer vision to detect the object and then too track the object in all the real and the dynamic environments. The latest trends which are emerged in this area, highlighting the embedding of deep learning techniques has transformed the field of object detection and tracking. Methods like Convolutional Neural Networks, Deep SORT, You Only Look Once and Region-Based Convolutional Neural Networks have significantly improved accuracy and efficiency. We examine the shift towards more robust and measurable and the scalable solutions, with particular focus on multi-object tracking, real-time processing, and handling challenging Challenges like occlusion, variations in scale, and varying in illumination. The survey also addresses key challenges that remain, including computational efficiency, accuracy in complex scenarios, and the development of algorithms. Furthermore, we discuss the applications of object detection and pursuit across industries like autonomous driving, robotics, surveillance, and augmented reality, while offering insights into future research directions that may overcome existing limitations and drive the field forward. These recent advancements, combined with the evolution of tracking algorithms, have made it possible to detect and track objects in real-time with high precision.
Authors - Akhil K J, Saurabh Shrivastava, Harish R Abstract - The increasing concerns over online privacy and the growing prevalence of internet censorship have driven many users to seek greater anonymity through tools like proxies and virtual private networks (VPNs). While peer-to-peer (P2P) networks provide a decentralized way for users to communicate securely across multiple nodes, they are not immune to security threats. One of the major vulnerabilities in P2P networks is the risk of man-in-the-middle (MITM) attacks, where malicious actors intercept communication between nodes. In these attacks, attackers can manipulate, inject, or even remove data being transmitted, compromising the integrity of the information. Another rising threat within these networks is cryptojacking—a tactic where attackers surreptitiously use a website’s resources to mine cryptocurrency, often without the knowledge or consent of the website visitors. This malicious practice has gained attention due to its increasing prevalence on popular sites. In the context of P2P networks, the exploitation of exit nodes poses a significant risk, as attackers can inject mining scripts into the HTTP responses sent from these nodes. These risks highlight the need for robust security protocols to safeguard decentralized networks and prevent malicious interference, ensuring the security, privacy, and integrity of online communication systems. Effective measures are vital to protecting users and maintaining trust in these technologies.
Thursday August 27, 2026 12:30pm - 2:30pm IST Virtual Room CGOA, India
Authors - Kamini Solanki, Nilay Vaidya, Jaimin Undavia, Krishna Kant, Jay Panchal, Anjali Mahavar Abstract - The rapid growth of internet-based applications, such as social media platforms and blogs, has led to an increase in comments and reviews about everyday activities. Sentiment analysis involves collecting and analysing people's opinions, thoughts, and perceptions on various topics, products, services, and subjects. These opinions can provide valuable insights for businesses, governments, and individuals in making informed decisions. However, the process of sentiment analysis faces several challenges that make it difficult to accurately interpret sentiments and determine the correct sentiment polarity. Sentiment analysis extracts subjective information from text using natural language processing (NLP) and text mining techniques. This article provides an in-depth overview of the methods used to perform sentiment analysis, along with its applications. It also evaluates and compares different approaches, discussing their advantages and limitations. Finally, the article examines the challenges in sentiment analysis and proposes future directions for the field. Sentiment analysis, also referred to as opinion mining, is a vital area of research in natural language processing (NLP) that focuses on identifying the sentiment expressed in text. This paper reviews various sentiment analysis techniques, explores its broad range of applications, and discusses the challenges within the field. The goal is to provide a thorough understanding of the current state of sentiment analysis and its potential future developments.
Authors - Botcha Divya, Yelavarti Kalyan Chakravarti, V. Esther Jyothi, A. Satya Kranthi Abstract - Software-Defined Networking (SDN) has transformed contemporary network topology by separating the control plane from the data plane, allowing the network to be centrally and dynamically managed. Its central design, however, also presents enormous security threats that must be mitigated using efficient Intrusion Detection Systems (IDS). This paper proposes an intelligent IDS framework for SDN networks utilizing machine learning algorithms. The proposed method employs the UNSW-NB15 dataset, preprocessing with advanced methods, SMOTE-Tomek resampling, and multi-class classification by XGBoost for attack detection and classification of different attacks. Interactive Streamlit-based dashboards and packet simulation allow real-time observation, filtering of attacks, and visualization of anomalies in detail. Experimental results demonstrate enhanced detection accuracy of 84% using the top 20 features selected that outperform conventional classifiers in precision and responsiveness. The addition of real-time prediction counters, attack distribution graphs, and downloading capability allows for tremendous flexibility when used in live SDN contexts. The project tries to minimize the theoretical/practical implementation gap found among existing IDS models and live deployments with its suggested scalable, interpretable, and effective intrusion detection solution.
Authors - Deepesh Sudhan Arunachalam, Dennis Andrew, K. S. Gayathri, A. Shahina, V. Durgadevi, A. Saravanan Abstract - This work introduces a deep learning-based framework for 3D pressure mapping to assess sleep quality and body strain. 2D pressure maps suffer from loss of depth information, poor spatial context, posture misclassification errors, and limited accuracy in capturing regional pressure variations. To overcome these limitations, the framework constructs 3D pressure maps that enable precise region-wise pressure estimation with anatomical landmarks to analyze body strain. Sleep quality is monitored by tracking frequent posture changes with converting pressure maps to point clouds achieved 99.26% accuracy with PointNet and 99.49% with PointCNN.
Assistant Professor, Department of Computer Science and Engineering (Artificial Intelligence & Machine Learning), Vishwakarma Institute of Technology, Pune, India
Thursday August 27, 2026 2:30pm - 2:32pm IST Virtual Room CGOA, India
