A5085388618- Advanced Text Analysis Techniques
- Sentiment Analysis and Opinion Mining
- AI in cancer detection
- Gene expression and cancer classification
- Hate Speech and Cyberbullying Detection
- Mosquito-borne diseases and control
- Insect Resistance and Genetics
- Bioinformatics and Genomic Networks
- Text and Document Classification Technologies
- Spam and Phishing Detection
- Digital Imaging for Blood Diseases
- Advanced Malware Detection Techniques
- Data Mining Algorithms and Applications
- Malaria Research and Control
- Genomics and Chromatin Dynamics
- Topic Modeling
- Artificial Intelligence in Healthcare
- Evolutionary Algorithms and Applications
- Video Analysis and Summarization
- RNA and protein synthesis mechanisms
- Hand Gesture Recognition Systems
- Gestational Diabetes Research and Management
- Biomedical Text Mining and Ontologies
- Misinformation and Its Impacts
- Cutaneous Melanoma Detection and Management
Liverpool School of Tropical Medicine
2024-2025
University of California, Riverside
2023-2024
BRAC University
2019-2023
Jinnah Postgraduate Medical Center
2022-2023
Weatherford College
2022
Liverpool John Moores University
2022
Bangladesh University of Engineering and Technology
2021
Uttara University
2017
Islamic University of Technology
2017
Sindh Agriculture University
2017
Yoga has become an integral part of human life to maintain a healthy body and mind in recent times. With the growing, fast-paced work from home, it difficult for people invest time gymnasium exercises. Instead, they like do assisted exercises at home where pose recognition techniques play most vital role. Recognition different poses is challenging due proper dataset classification architecture. In this work, we have proposed deep learning-based model identify five yoga comparatively fewer...
Breast cancer, a significant threat to women's health, demands early detection. Automating histopathological image analysis offers promising solution enhance efficiency and accuracy in diagnosis. This study addresses the challenge of breast cancer classification by leveraging ResNet architecture, known for its depth skip connections. In this work, two distinct approaches were pursued, each driven unique motivations. The first approach aimed improve learning process through self-supervised...
Musculoskeletal disorder is increasing in humans due to accidents or aging which a great concern for future world. Physical exercises can reduce this disorder. Yoga medium of physical exercise. For doing yoga trainer important who monitor the perfectness different poses. In paper, we have proposed system human body parts movement and accuracy poses aids user practice yoga. We used Microsoft Kinect detect joint points real time from those calculate various angles measure certain user. Our...
Cyberbullying or Online harassment detection on social media for various major languages is currently being given a good amount of focus by researchers worldwide. Being the seventh most speaking language in world and increasing usage online platform among Bengali people urge to find effective technique handle harassment. In this paper, we have proposed binary multiclass classification model using hybrid neural network bully expression language. We used 44,001 users comments from popular...
The SARS-CoV-2 3CLpro protein is one of the key therapeutic targets interest for COVID-19 due to its critical role in viral replication, various high-quality crystal structures, and as a basis computationally screening compounds with improved inhibitory activity, bioavailability, ADMETox properties. ChEMBL PubChem database contains experimental data from small molecules against 3CLpro, which expands opportunity learn pattern design computational model that can predict potency any drug...
The primary control methods for the African malaria mosquito, Anopheles gambiae, are based on insecticidal interventions. Emerging resistance to these compounds is therefore of major concern programs. organophosphate (OP), pirimiphos-methyl, a relatively new chemical in vector armory but now widely used indoor-residual spray campaigns. While generally effective, phenotypic has developed some areas vectors. Here, we population genomic approach identify novel mechanisms pirimiphos-methyl A....
The recent outburst of online shopping, commonly known as e-shopping, has added a new dimension in the business sector. In these days, people tend to explore for finding items they need and buy through transaction. It made their life more easy comfortable. At same time, it become great sellers know patterns intentions different types customers. customer's purchase intention can be predicted by analyzing history this study, we have analyzed empirical data shoppers building better prediction...
The emergence of insecticide resistance is threatening the efforts malaria control programmes, which rely heavily on a limited arsenal insecticidal tools, such as insecticide-treated bed nets. Importantly, genomic surveillance vectors can provide critical, policy-relevant insights into presence and evolution resistance, allowing us to maintain extend shelf life these interventions. Yet complex genetic architecture combined with resource constraints in malaria-endemic settings, have thus far...
While warm season heat waves are extensively studied, winter waves, which extended periods of above-average temperature during months, largely remain overlooked. These events can disrupt typical water availability patterns and degrade quality, particularly in regions already facing environmental stress.The identification varies depending on the context objective. For example, variable percentile thresholds used to study wave mechanisms, while fixed often applied assess their ecological...
The invasion of Africa by the Asian urban malaria vector, Anopheles stephensi, endangers 126 million people across a rapidly urbanising continent where is primarily rural disease. Control An. stephensi requires greater understanding its origin, dynamics, and mechanisms widespread resistance to vector control insecticides. We present genomic surveillance study 551 sampled invasive native ranges in Asia. Our findings support hypothesis that an initial from Asia Djibouti seeded separate...
<para xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> In the past few years, there has been an exponential increase in amount of information available on World Wide Web. This plethora can be extremely beneficial for users. However, human intervention that is currently required this inconvenient. Information extraction (IE) systems try to solve problem by making task as automatic possible. Most existing approaches, however, require user feedback one...
The primary control methods for the African malaria mosquito, Anopheles gambiae, are based on insecticidal interventions. Emerging resistance to these compounds is therefore of major concern programmes. organophosphate, pirimiphos-methyl, a relatively new chemical in vector armoury but now widely used indoor residual spray campaigns. Whilst generally effective, phenotypic has developed some areas vectors. Here, we population genomic approach identify novel mechanisms pirimiphos-methyl...
E-commerce is gaining attraction in today's digital environment by making products closer to customers without forcing them leave their homes. A customer has go through hundreds of reviews before a purchase. The number for single product can easily approach millions and becomes difficult understand the overall client feedback. However, machine learning techniques learn from big data. Consequently, sentiment analysis new study area combining natural language processing text analytic extract...
The importance of online news article has evolved notably with the advancement information and technology. However, some are violent as well obnoxious. So, identifying categorizing automatically is important remains challenging. Using opinion mining sentiment analysis, we propose an intuitive approach detecting positive or negative from article. Our consists a sentence identification phase, followed by dynamic library predefined strings at last marking whether paragraph positive, neutral....
Cancer is a life-threatening disease, which considered incurable most of the time. Hence, an early prediction for possible risk cancer can be very helpful in order to start treatment as soon possible. One such Cervical Cancer. Here, we have used data about lifestyle and previous medical history women try predict if woman susceptible cervical or not. However, dataset needed lot preprocessing handling missing values. Four different techniques were fill Soon after, correlation among variables...
Identification of short repeating patterns in biological sequences, mostly known as motif, is important for understanding the genetic regulatory system a living being. But weak conservation motifs makes it an NP-hard problem and poses challenge computational biology. In this work, we have modeled motif search from meta-heuristic perspective. We proposed evaluated evolutionary approach, which, will candidate with heuristic so that can find real data set without exploring rigorously. Our...
Being the seventh most spoken language in world, use of Bangla online has increased recent times. Hence, it become very important to analyze text data maintain a safe and harassment-free place. The that been made accessible this article gathered marked from comments people public posts by celebrities, government officials, athletes on Facebook. total amount collected is 44001. dataset compiled with aim developing ability machines differentiate whether comment bully expression or not help...
Due to the rapid development of advanced world technology, there is a high increase in devices such as smart-phones and tablets, which number applications used. Though an application has pass malware detection test before appearing play store, many successfully get trusted accepted even though they contain malicious software variants that are challenging detect. The requires physical execution see these contents, undetected during first screening test. implementation application, it may be...
<ns4:p>The major malaria mosquitoes, <ns4:italic>Anopheles gambiae s.l</ns4:italic> and funestus</ns4:italic>, are some of the most studied organisms in medical research also genetically diverse. When designing polymerase chain reaction (PCR) or hybridisation-based molecular assays, reliable primer probe design is crucial. However, single nucleotide polymorphisms (SNPs) binding sites can prevent binding, leading to null alleles, bind suboptimally, preferential amplification specific alleles....
At present, we have seen everything is getting digitized where technology almost takes full control over our life. As a result, massive number of textual documents are generated on online platforms and news articles no exception. People prefer to get connected with portals as they updated every single hour. Newspaper so many categories such politics, sports, business, entertainment etc. Recently, noticed the rapid growth increase Bangla internet. It will be helpful for readers recommended...
Internet of Things (IoT) and Blockchain technologies have been utilized heavily in diverse domains, including remote patient monitoring (RPM). Expeditious development wearable IoT medical devices with a variety functionality, real-time sensory data from patients can be provided further processed. are centrally collected, processed, stored. But this centralization may face different problems single-point failure, tampering, privacy issues, etc. address these using its decentralized...
Leishmaniasis control often relies upon insecticidal of phlebotomine sandfly vector populations. Such methods are vulnerable to the evolution insecticide resistance via a range molecular mechanisms. There is evidence that two major mechanisms, target site insensitivity and metabolic resistance, have evolved in some populations further genetic characterization would be useful understand combat it. To facilitate study mechanisms here we improved annotation characterized detoxification gene...
k-means is the most widely used clustering algorithm which an unsupervised technique that needs assumptions of centroids to begin process. Hence, problem NP-hard and careful consideration optimization get a better quality clusters data. In this work, meta-heuristic based genetic proposed optimize centroid initialization The method includes tournament selection, probability-based mutation, elitism leads finding optimal for given dataset. Nine different diversified datasets were test...