A5016123311- Topic Modeling
- Text and Document Classification Technologies
- Natural Language Processing Techniques
- Privacy-Preserving Technologies in Data
- Data Stream Mining Techniques
- Network Security and Intrusion Detection
- COVID-19 diagnosis using AI
- Advanced Malware Detection Techniques
- Blockchain Technology Applications and Security
- Sentiment Analysis and Opinion Mining
- Machine Learning and Data Classification
- Software Testing and Debugging Techniques
- Spam and Phishing Detection
- Model Reduction and Neural Networks
- Complex Network Analysis Techniques
- Anomaly Detection Techniques and Applications
- Bayesian Methods and Mixture Models
- AI in cancer detection
- Advanced Neural Network Applications
- Genomic variations and chromosomal abnormalities
- Genetics and Neurodevelopmental Disorders
- IoT and Edge/Fog Computing
- Advanced Adaptive Filtering Techniques
- Evolutionary Algorithms and Applications
- Brain Tumor Detection and Classification
Dalhousie University
2022-2024
University of Electronic Science and Technology of China
2019-2023
Huzhou University
2021-2023
Lovely Professional University
2023
Chandigarh University
2023
University of California, Davis
2019-2022
Rajasthan Technical University
2019-2022
Quaid-i-Azam University
2018
University of Kota
2015
Dr. Bhim Rao Ambedkar University
2010
With the increase of COVID-19 cases worldwide, an effective way is required to diagnose patients. The primary problem in diagnosing patients shortage and reliability testing kits, due quick spread virus, medical practitioners are facing difficulty identifying positive cases. second real-world share data among hospitals globally while keeping view privacy concerns organizations. Building a collaborative model preserving major for training global deep learning model. This paper proposes...
Traditional target detection algorithms have difficulty to adapt complex environmental changes and limited applicable scenarios. However, the deep-learning-based model can automatically learn with strong generalization capability. In this article, we choose a single-stage for research based on model's real-time processing requirements improve accuracy robustness of in remote sensing images. addition, YOLOv4 network present new approach. First, propose classification setting nonmaximum...
Internet of things (IoT) is revolutionizing this world with its evolving applications in various aspects life such as sensing, healthcare, remote monitoring, and so on. Android devices are working hand to realize dreams the IoT. Recently, there a rapid increase threats malware attacks on Android-based devices. Moreover, due extensive exploitation platform IoT creates task challenging securing kind activities. This paper presents novel framework that combines advantages both machine learning...
In this study, we have used the Image Similarity technique to detect unknown or new type of malware using CNN ap- proach. was investigated and tested with three types datasets i.e. one from Vision Research Lab, which contains 9458 gray-scale images that been extracted same number samples come 25 differ- ent families, second benign dataset contained 3000 different kinds software. Benign vision research lab were initially exe- cutable files converted in binary code then image files. We...
Know your client or essentially KYC is the prepare of approving and confirming personality its clients analyzing potential dangers illicit eagerly for commerce relationship. A few issues with existing manual are that it less secure, time devouring expensive. With appearance Blockchain innovation, properties such as unchanging nature, security, decentralization make them a great arrangement to issues. Whereas commercial arrangements like “kyc-chain.com”, “KYC.legal” right empower blockchain-...
Clustering short text streams is a challenging task due to its unique properties: infinite length, sparse data representation and cluster evolution. Existing approaches often exploit in batch way. However, determine the optimal size usually difficult since we have no priori knowledge when topics evolve. In addition, traditional independent word graphical model tends cause “term ambiguity” problem clustering. Therefore, this paper, propose an Online Semantic-enhanced Dirichlet Model for sext...
The fragile X mental retardation (FMR1) gene contains an expansion-prone CGG repeat within its 5' UTR. Alleles with 55-200 repeats are known as premutation (PM) alleles and confer risk for one or more of the FMR1 disorders that include Fragile X-associated Tremor/Ataxia Syndrome (FXTAS), Primary Ovarian Insufficiency (FXPOI), X-Associated Neuropsychiatric Disorders (FXAND). PM expand on intergenerational transmission, children mothers being at inheriting > 200 (full mutation FM) alleles)...
Anomaly in Online Social Network can be referred as abnormal or unexpected behavior which deviates from majority of users. Due to popularity social networking sites such Facebook, Twitter etc., malicious activities have increased recent past. detection has become an important area for researchers looked upon. This survey gives overview existing techniques, is further kept under two different types, structural based and behavioral techniques anomaly network. It also discusses major problem/s...
The across the board reception of android devices and their ability to get critical private secret data have brought about these being focused by malware engineers. Existing analysis techniques categorized into static dynamic analysis. In this paper, we introduce two machine learning supported methodologies for malware. First approach based on statically analysis, content is found through probability statistics which reduces uncertainty information. Feature extraction were proposed existing...
With the rapid spread of novel COVID-19 virus, there is an increasing demand for screening patients. Typical methods coronavirus patients have a large false detection rate. An effective and reliable method detecting required. For this reason, some other such as Computed Tomography (CT) imaging employed to detect accurately. In paper, we present 3D-Deep learning based that automatically screens using 3D volumetric CT image data. Our proposed system assists medical practitioners effectively...
Distributed data stream mining has gained increasing attention in recent years since many organizations collect tremendous amounts of streaming from different locations. Existing studies mainly focus on learning evolving concepts distributed streams, while the privacy issue is little investigated. In this article, for first time, we develop a federated framework concept-drifting called FedStream. The proposed method allows capturing by dynamically maintaining set prototypes with error-driven...
Gesture-based control systems have drawn a lot of interest in this age touchless technology and human-computer connection. This paper proposes revolutionary method that uses the OpenCV computer vision library Python to alter volume, contrast, brightness screen real time using hand gestures. The system webcam record video time, it makes use OpenCV's image processing features identify interpret motions. suggested focuses on identifying particular motions connected orders for control. With...
In the context of streaming data, learning algorithms often need to confront several unique challenges, such as concept drift, label scarcity, and high dimensionality. Several drift-aware data stream have been proposed tackle these issues over past decades. However, most existing utilize a supervised framework require all true class labels update their models. Unfortunately, in environment, requiring is unfeasible not realistic many real-world applications. Therefore, streams with minimal...