- Face and Expression Recognition
- Emotion and Mood Recognition
- Gaze Tracking and Assistive Technology
- Face recognition and analysis
- Anomaly Detection Techniques and Applications
- Hand Gesture Recognition Systems
- Advanced Statistical Methods and Models
- Brain Tumor Detection and Classification
- Video Surveillance and Tracking Methods
- Non-Invasive Vital Sign Monitoring
- Retinal Imaging and Analysis
- Sleep and Work-Related Fatigue
- Biometric Identification and Security
- Water Quality Monitoring Technologies
- Sports Analytics and Performance
- COVID-19 diagnosis using AI
- EEG and Brain-Computer Interfaces
- IoT-based Smart Home Systems
- Cutaneous Melanoma Detection and Management
- Financial Distress and Bankruptcy Prediction
- AI in cancer detection
- ECG Monitoring and Analysis
- Imbalanced Data Classification Techniques
- Smart Parking Systems Research
- Heart Rate Variability and Autonomic Control
Guru Teg Bahadur Hospital
2023-2024
University of Delhi
2023-2024
Sir Padampat Singhania University
2023
Bharati Vidyapeeth Deemed University
2018-2021
Guru Gobind Singh Indraprastha University
2018-2021
Every week, millions of dollars are pumped into the sport football (Association Football). The transfer value players proliferates each year and records get shattered every other window. Players signed with a certain fee which is determined during that player. However, it noteworthy to have metric or economic valuation signifying price tag on player throughout season rather than only transfer. This paper introduces contribution consistency, popularity, crowd estimation performance parameters...
Image caption generation is a stimulating multimodal task. Substantial advancements have been made in thefield of deep learning notably computer vision and natural language processing. Yet, human-generated captions are still considered better, which makes it challenging application for interactive machine learning. In this paper, we aim to compare different transfer techniques develop novel architecture improve image captioning accuracy. We compute feature vectors using state-of-the-art...
AbstractAbstractIn this paper, a model for facial expression recognition (FER) fusing local and global features is proposed. Local are extracted by dividing the face into multiple regions carefully selecting of interest which assists in reducing redundancy. Global from entire subject recognition. The major drawback with previously available techniques literature that they do not take finer details account along geometric features. In our work, using concatenation fusion, FER performed an...
In today’s world different data sets are available on which regression or classification algorithms of machine learning applied. One the is k-nearest neighbor (kNN) computes distance amongst various rows in a dataset. The performance kNN evaluated based K-value and metric used where K total count neighboring elements. Many metrics have been by researchers literature, one them Canberra metric. this paper measured datasets, further proposed metric, namely, Modified Euclidean-Canberra Blend...
In everyday life, there are situations where the only way to communicate emotions. EMOTICONS epitome of same. This aspect communication can also be used in emergency (terrorist attacks, hijacks) is by performing some extraordinary actions or through Incorporating technology above mentioned circumstances paper proposes a novel framework detecting an situation retrieving information from emotions and eye blinks using sensor nodes. The proposed deployed places (hotels, banks, airports etc.)...
In diurnal life, there are circumstances in which communication without words is required, emoticons or facial expressions used to exchange virtual dialogues. This genre of completely injects into situation(emergency), where the sole way interconnect by performing some unusual activities, eye blinks through emotions. The paper proposes a Sagacious Information Recuperation Technique (SIRT) for sensing an emergency capturing intelligent information from behavioral (emotions) and biological...
Heart Rate (HR) analysis has always been an area of interest not only for medical field investigators but also researchers from variety other fields. In the last decade, research focus shifted towards non-contact based systems. Variability (HRV) can be used to estimate physical characteristics emotional aspect a subject. this paper, HR is calculated face subject extracting photoplethysmography signal using Fast Fourier Transform (FFT) and filters (band-pass). A comparison presented between...
Fatigue leads to tiredness, exhaustion, and sleepiness. Driving in fatigue conditions is considered dangerous can cause serious road accidents. According reports about 25% of accidents are due driver drowsiness. The main reason behind drowsiness fatigue. While driving continuously on long trips, drivers feel sleepy. In this paper, we proposed a novel approach that efficient enough detect accurately. An intelligent system, quickly precisely determine whether the feeling or not during also...
Eye blink is a semi-autonomic rapid closing of eyelid. controlled by the autonomic nervous system human brain. This normal and most important function eye can be embedded with some created (abnormal) sequences to indicate any unusual message. In this paper, real time nove l algorithm reckon number blinks (RTREB) in video sequence using facet correlation (EFC) proposed. The proposed RTREB approximates landmark positions EFC- an extricate variable value eyelids clearly differentiating between...
Micro-expression comes under nonverbal communication, and for a matter of fact, it appears minute fractions second. One cannot control micro-expression as tells about our actual state emotionally, even if we try to hide or conceal genuine emotions. As know that micro-expressions are very rapid due which becomes challenging any human being detect with bare eyes. This subtle-expression is spontaneous, involuntary gives the emotional response. It happens when person wants specific emotion, but...
Water quality assessment is essential for safeguarding public health and protecting water resources. This study focused on predicting quality, specifically the presence of total coliforms, using various machine-learning techniques. The present utilises a publicly available dataset encompassing geographical area India consisting physical parameters. Various regression techniques were applied to after appropriate pre-processing including feature selection normalisation. findings demonstrate...
Every single day, thousands of crimes are perpetrated, and hundreds may be probably taking place right now throughout the world. Without a doubt, crime is viewed as social blight. Nothing can truly stop it, no matter what done. Surveillance cameras, on other hand, dramatically minimize it. Using public surveillance camera systems to prevent, document, cost-effective solution. Installing enough cameras detect in progress integrating technology automate monitoring live stream from these will...
In today’s world different data sets are available on which regression or classification algorithms of machine learning applied. One the is k-nearest neighbor (kNN) computes distance amongst various rows in a dataset. The performance kNN evaluated based K-value and metric used, where K total count neighboring elements. Many metrics have been used by researchers literature, one them Canberra metric. this paper measured datasets, further proposed metric, namely, Modified Euclidean-Canberra...
Skin cancer is a common and possibly fatal condition. Effective therapy depends on early discovery precise diagnosis. This study proposes two-step, segmentation-and classification-based method for skin lesion analysis. The U-Net architecture, semantic segmentation model based deep learning, used in the initial stage to segment lesions. On test set, suggested achieves promising accuracy of 94.88%. Precise helps separate lesions from surrounding environment facilitates further classification....
Facial emotion recognition (FER) is a necessary in order to bridge the communication gap between people and computers since, complete range of face-to-face contact, facial expressions are sort that convey majority person's emotional mental state. This field's innovations also enhance how successfully interact with or assist people. The vast body research this field focused on Deep Learning. FER has drawn interest from community due its possible applications. main objective relate different...
The expansion of online transactions, particularly credit card has revolutionized the field e-commerce and streamlined electronic payment systems. However, this growth also given rise to a significant challenge in form fraud. To combat issue, banks financial organizations have recognized need for robust fraud detection applications. Machine learning (ML) approaches emerged as valuable tool regard, they offer potential accurately detect prevent fraudulent transactions. Long Short-Term Memory...