- Topic Modeling
- Speech and dialogue systems
- AI in Service Interactions
- Digital Mental Health Interventions
- Mental Health via Writing
- Intelligent Tutoring Systems and Adaptive Learning
- Natural Language Processing Techniques
- Automotive and Human Injury Biomechanics
- Elasticity and Material Modeling
- Automated Road and Building Extraction
- Medical Imaging and Analysis
- Multi-Agent Systems and Negotiation
- Digital Marketing and Social Media
- EEG and Brain-Computer Interfaces
- Edible Oils Quality and Analysis
- Gaze Tracking and Assistive Technology
- Tea Polyphenols and Effects
- Urban and Freight Transport Logistics
- Neural Networks and Applications
- Essential Oils and Antimicrobial Activity
- Autism Spectrum Disorder Research
- Assistive Technology in Communication and Mobility
- Environmental Sustainability in Business
- Media Influence and Health
- Mechanical Engineering and Vibrations Research
Indian Institute of Technology Patna
2022-2024
Himalayan University
2024
International Institute of Information Technology, Hyderabad
2022
National Institute of Technology Arunachal Pradesh
2019-2021
International Institute of Information Technology
2015
Indian Institute of Technology Hyderabad
2014
Extraction of water bodies from satellite imagery has been widely explored in the recent past. Several approaches have developed to delineate different varying spatial, spectral, and temporal characteristics. The current study puts forward an automatic approach extract body a Landsat using perceptron model. Perceptron involves classification based on linear predictor function that merges few characteristic properties object commonly known as feature vectors. vectors, combined with weights,...
Individuals living with disabilities often face challenges in their daily lives, from managing physical tasks to coping emotional needs. It is imperative provide them personalized, courteous, and empathetic support that can address unique To bridge this gap, we propose an Empathetic Disability Support System (EDiSS), designed offer personalized tailored correct politeness strategies as per individual users’ OCEAN traits, gender, age. train EDiSS, first, a specialized disability dialogue...
Persuasion is an intricate process involving empathetic connection between two individuals. Plain persuasive responses may make a conversation non-engaging. Even the most well-intended and reasoned conversations can fall through in absence of speaker listener. In this paper, we propose novel task incorporating empathy when generating responses. We develop dialogue system by fine-tuning maximum likelihood Estimation (MLE)-based language model reinforcement learning (RL) framework. To design...
The potential for conversational agents offering mental health and legal counseling in an autonomous, interactive, vitally accessible environment is getting highlighted due to the increased access information through internet mobile devices. A agent should be able offer higher engagement mimicking real-time sessions. ability empathize or comprehend feel another person’s emotions experiences a crucial quality that promotes effective therapeutic bonding rapport-building. Further, use of polite...
Politeness is an expression in language that eases the conversation toward a positive undertone. If there display of rudeness, even finest communication can fall through. In addition, if lathered with politeness, most angst-prone scenario be expressed far less hurt. this article, we address task identifying politeness goal-oriented dialog systems. regard, create politeness-annotated conversational data (PACD) utilizing Microsoft Dialogue Challenge and DSTC1 datasets. For correctly employ...
Even though, a lot of research has already been done on Machine Translation, translating complex sentences stumbling block in the process.To improve performance machine translation sentences, simplifying becomes imperative.In this paper, we present rule based approach to address problem by Hindi into multiple simple sentences.The sentence is split using clause boundaries and dependency parsing which identifies different arguments verbs, thus changing grammatical structure way that semantic...
In a task-oriented dialogue setting, user’s mood and demands can change in an ongoing dialogue, which may lead to non-informative conversation or result drop-off. To rectify such scenarios, conversational agent should be able learn the behaviour online, form informative, empathetic interactive responses. incorporate these three aspects, we propose novel end-to-end system GenPADS . First, build train two models, viz. politeness classifier extract polite information present agent’s utterances...
The World Health Organization has underlined the significance of expediting preventive measures for crime against women and children to attain United Nations Sustainable Development Goals 2030 (promoting well-being, gender equality, equal access justice). victims typically need mental health legal counselling support their ultimate well-being sometimes they be persuaded seek desired support. Further, interactions should adopt correct politeness empathy strategies so that a warm, amicable,...
Electroencephalogram signal is the used for detection of a neurological disorder as epilepsy disorder, sleep and many more. The types EEG gives hidden information regarding distribution data that may consist large volume poor noisy signal. In order to reduce outlier effects noise, incorporation prior knowledge in model, universum help enhance better generalization ability model. This paper proposes regularized twin support vector machine (RUTWSVM) classification healthy seizure signals....
The World Health Organization (WHO) has significantly emphasized the need for mental health care. social stigma associated with illness prevents individuals from addressing their issues and getting assistance. In such a scenario, relevance of online counseling increased dramatically. feelings attitudes that client counselor express towards each other result in higher or lower experience. A should be friendly gain clients' trust to make them share problems comfortably. Thus, it is essential...
This comprehensive systematic analysis examines the complicated interplay between technology, governance, and consumer behavior. Technological advancement shifting governance systems affect behavior; therefore, understanding how they do so is vital. review meticulously analyzes a variety of literature to elucidate complex relationships government, behavior in many fields. The study highlights technological advances customer preferences, attitudes, decision-making. Governance can also...
In a persuasive conversation for <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">social good</i> , even the most compelling and argument may fail to persuade persuadee resisting persuasion. Whereas use of polite tone, apologetic expressions, or deferential modes reference such as, 'thank you', 'Please' etc. can make more interesting, engaging, persuading persuadee. We propose resistance handling dialogue system ( <bold...
In the realm of multi-arm bandit problems, Gittins index policy is known to be optimal in maximizing expected total discounted reward obtained from pulling Markovian arms. most realistic scenarios however, state transition probabilities are unknown and therefore indices cannot computed. One can then resort reinforcement learning (RL) algorithms that explore space learn these while exploiting maximize collected. this work, we propose tabular (QGI) Deep RL (DGN) for based on retirement...
In Medical question-answering (QA) tasks, the need for effective systems is pivotal in delivering accurate responses to intricate medical queries. However, existing approaches often struggle grasp logical structures and relationships inherent contexts, thus limiting their capacity furnish precise nuanced answers. this work, we address gap by proposing a novel Abstractive QA system MedLogic-AQA that harnesses First Order Logic (FOL) based rules extracted from both context questions generate...
Although there has been a plethora of work on open-domain conversational systems, most the systems lack mechanism controlling concept transitions in dialogue. For activities like switching from casual chit-chat to task-oriented conversation, an agent with ability manage flow concepts conversation might be helpful. The user would find dialogue more engaging and receptive such if these were made while taking into account user’s persona. Focusing persona-aware transitions, we propose Reinforced...
The shortage of therapists for mental health patients emphasizes the importance globally accessible dialogue systems alleviating their issues. To have effective interpersonal psychotherapy, these must exhibit politeness and empathy when needed. However, factors may vary as per user’s gender, age, persona, sentiment. Hence, in order to establish trust provide a personalized cordial experience, it is essential that generated responses should be tailored individual profiles attributes. Focusing...
Deployment of Accident Relief Medical Vans (ARMV) used for accident relief and rescue operations is generally done heuristically. ARMV an ambulance-train equipped with various tools like jacks, heavy cutting tools, generators, operation theatre, artificial breathing equipment etc. to ease the process. Taking North Eastern Railway (NER) as a case study, Location Set Covering Problem (LSCP) model will be find minimum number ARMVs required given network their locations so that all demand points...