A5009439842- Medical Image Segmentation Techniques
- Image Retrieval and Classification Techniques
- Cell Image Analysis Techniques
- Radiomics and Machine Learning in Medical Imaging
- AI in cancer detection
- Fractal and DNA sequence analysis
- Neural Networks and Applications
- Digital Imaging for Blood Diseases
- Heart Rate Variability and Autonomic Control
- Complex Systems and Time Series Analysis
- Neural dynamics and brain function
- Fuzzy Logic and Control Systems
- EEG and Brain-Computer Interfaces
- Image Processing Techniques and Applications
- Advanced Image and Video Retrieval Techniques
- Time Series Analysis and Forecasting
- Gene expression and cancer classification
- Functional Brain Connectivity Studies
- Image and Signal Denoising Methods
- Chaos control and synchronization
- Soil Geostatistics and Mapping
- COVID-19 diagnosis using AI
- Machine Learning in Bioinformatics
- Advanced Vision and Imaging
- Face and Expression Recognition
Queen Mary University of London
2023-2025
University of Utah
2024
Heart Hospital Baylor Plano
2024
Baylor Medical Center at Garland
2024
VNU University of Science
2020-2023
Prince Mohammad bin Fahd University
2019-2023
Forest Industry Research Institute
2021-2023
Providence Health & Services
2023
Vietnam Academy of Social Sciences
2023
Brown University
2023
To stimulate progress in automating the reconstruction of neural circuits, we organized first international challenge on 2D segmentation electron microscopic (EM) images brain. Participants submitted boundary maps predicted for a test set images, and were scored based their agreement with consensus human expert annotations. The winning team had no prior experience EM employed convolutional network. This "deep learning" approach has since become accepted as standard images. continued to...
Chest X-ray data have been found to be very promising for assessing COVID-19 patients, especially resolving emergency-department and urgent-care-center overcapacity. Deep-learning (DL) methods in artificial intelligence (AI) play a dominant role as high-performance classifiers the detection of disease using chest X-rays. Given many new DL models being developed this purpose, objective study is investigate fine tuning pretrained convolutional neural networks (CNNs) classification If...
Abstract The use of imaging data has been reported to be useful for rapid diagnosis COVID-19. Although computed tomography (CT) scans show a variety signs caused by the viral infection, given large amount images, these visual features are difficult and can take long time recognized radiologists. Artificial intelligence methods automated classification COVID-19 on CT have found very promising. However, current investigation pretrained convolutional neural networks (CNNs) using is limited....
Automated analysis of physiological time series is utilized for many clinical applications in medicine and life sciences. Long short-term memory (LSTM) a deep recurrent neural network architecture used classification time-series data. Here time-frequency time-space properties are introduced as robust tool LSTM processing long sequential data physiology. Based on results obtained from two databases sensor-induced signals, the proposed approach has potential (1) achieving very high accuracy,...
Abstract With the popularity of internet and smartphones, malware on smartphones has increased dramatically. In addition, ubiquity openness Android operating system have made it a lucrative platform for cybercriminals to develop malware. Traditional detection techniques require lot time manual effort classify accurately. Recently, deep learning (DL) based classification been developed solve this issue. This article proposes DL‐based two‐stage framework that detects classifies its variants...
A literature survey shows that the number of malware attacks is gradually growing over years due to trend Internet Medical Things (IoMT) devices. To detect and classify attacks, automated detection classification an essential subsystem in healthcare cyber-physical systems. This work proposes attention-based multidimensional deep learning (DL) approach for a cross-architecture IoMT system based on byte sequences extracted from Executable Linkable Format (ELF; formerly named Extensible Linking...
This article presents a deep learning-based approach for network-based intrusion detection in the Internet of medical things (IoMT) systems using features network flows and patient biometrics. The proposed effectively learns optimal feature representation by passing information biometrics into more than one hidden layer learning. includes global attention which helps to extract from spatial temporal To avoid data imbalance, cost-sensitive learning is integrated model. model showed 10-fold...
Pathological speech diagnosis is crucial for identifying and treating various disorders. Accurate aids in developing targeted intervention strategies, improving patients' communication abilities, enhancing their overall quality of life. With the rising incidence speech-related conditions globally, including oral health, need efficient reliable diagnostic tools has become paramount, emphasizing significance advanced research this field.
There are many techniques using sensors and wearable devices for detecting monitoring patients with Parkinson's disease (PD). A recent development is the utilization of human interaction computer keyboards analyzing identifying motor signs in early stages disease. Current designs classification time series computer-key hold durations recorded from healthy control PD subjects require length to be considerably long. With an attempt avoid discomfort participants performing long physical tasks...
Texture analysis of computed tomography (CT) imaging has been found useful to distinguish subtle differences, which are in- visible human eyes, between malignant and benign tissues in cancer patients. This study implemented two complementary methods texture analysis, known as the gray-level co-occurrence matrix (GLCM) experimental semivariogram (SV) with an aim improve predictive value evaluating mediastinal lymph nodes lung cancer. The GLCM was explored use a rich set its derived features,...
Abstract Cassava is a rich source of carbohydrates, and it vulnerable to virus diseases. Literature survey shows that the image recognition integrated deep learning approach successfully employed for leaf disease classification. Mostly, transfer based on convolutional neural network (CNN) models were applied However, existing approaches are not effective in identifying tiny portion overall area. Identifying focussing regions affected by vital achieving good classification accuracy. An...
Much of the complexity and diversity found in nature is driven by nonlinear phenomena, this holds true for brain. Nonlinear dynamics theory has been successfully utilized explaining brain functions from a biophysics standpoint, field statistical physics continues to make substantial progress understanding connectivity function. This study delves into complex functional using biophysical approaches. We aim uncover hidden information high-dimensional neural signals, with hope providing useful...
Abstract Motivation: Alignment-free sequence comparison methods are still in the early stages of development compared to those alignment-based analysis. In this paper, we introduce a probabilistic measure similarity between two biological sequences without alignment. The method is based on concept comparing similarity/dissimilarity constructed Markov models. Results: was tested against six DNA sequences, which thrA, thrB and thrC genes threonine operons from Escherichia coli K-12 Shigella...
The study of gait in Parkinson's disease is important because it can provide insights into the complex neural system and physiological behaviors disease, which understanding help improve treatment lead to effective developments alternative rehabilitation programs. This paper aims introduce an computational method for multichannel or multisensor data analysis dynamics disease.A model tensor decomposition, a generalization matrix-based higher dimensional analysis, designed differentiating time...
Abstract We present in this paper the application of deep convolutional neural networks (CNNs), which is a state-of-the-art artificial intelligence (AI) approach machine learning, for automated time-independent prediction burn depth. Color images four types depth injured first few days, including normal skin and background, acquired by TiVi camera were trained tested with pretrained CNNs: VGG-16, GoogleNet, ResNet-50, ResNet-101. In end, best 10-fold cross-validation results obtained from...
In this article, we propose a parallel hierarchy convolutional neural network (PHCNN) combining Long Short-Term Memory (LSTM) structure to quantitatively assess the grading of facial nerve paralysis (FNP) by considering region-based asymmetric features and temporal variation image sequences. FNP, such as Bell's palsy, is most common symptom neuromotor dysfunctions. It causes weakness muscles for normal emotional expression movements. The subjective judgement clinicians completely depends on...
Acute myeloid leukemia (AML) is a cancer of the line cells caused due to rapid increase abnormal that later interfere with healthy cells. One main reasons for in mortality cost devices used determination and late diagnosis. The most effective treatment option can be provided by accurate medical Automated segmentation blood smear images plays crucial role identification AML. This article proposes new computer-aided diagnosis model segment identifies stage methodology presented this work...