A5032770006- Optimization and Search Problems
- Machine Learning and Algorithms
- Network Security and Intrusion Detection
- Data Stream Mining Techniques
- Cloud Computing and Resource Management
- Anomaly Detection Techniques and Applications
- IoT and Edge/Fog Computing
- Internet Traffic Analysis and Secure E-voting
- Advanced Malware Detection Techniques
- Advanced Bandit Algorithms Research
- EEG and Brain-Computer Interfaces
- Software-Defined Networks and 5G
- Caching and Content Delivery
- Time Series Analysis and Forecasting
- Topic Modeling
- Machine Learning and Data Classification
- Network Packet Processing and Optimization
- Fault Detection and Control Systems
- Face and Expression Recognition
- Neural Networks and Applications
- Advanced Memory and Neural Computing
- Advanced Text Analysis Techniques
- Target Tracking and Data Fusion in Sensor Networks
- Network Traffic and Congestion Control
- Distributed Sensor Networks and Detection Algorithms
OsloMet – Oslo Metropolitan University
2016-2025
657 Oslo
2022-2024
Simula Metropolitan Center for Digital Engineering
2024
Oslo University Hospital
2021-2023
Norwegian University of Science and Technology
2020-2023
Bridge University
2022
KTH Royal Institute of Technology
2022
Karolinska Institutet
2022
Rutgers Sexual and Reproductive Health and Rights
2022
University of California, San Diego
2022
Depression is a common reason for an increase in suicide cases worldwide. Thus, to mitigate the effects of depression, accurate diagnosis and treatment are needed. An electroencephalogram (EEG) instrument used measure record brain's electrical activities. It can be utilized produce exact report on level depression. Previous studies proved feasibility usage EEG data deep learning (DL) models diagnosing mental illness. Therefore, this study proposes DL-based convolutional neural network (CNN)...
An image is worth a thousand words; hence, face illustrates extensive details about the specification, gender, age, and emotional states of mind. Facial expressions play an important role in community-based interactions are often used behavioral analysis emotions. Recognition automatic facial from challenging task computer vision community admits large set applications, such as driver safety, human-computer interactions, health care, science, video conferencing, cognitive others. In this...
Emotion recognition plays a significant role in cognitive psychology research. However, measuring emotions is challenging task. Thus, several approaches have been designed for facial expression (FER). Although, the challenges increase further as data transit from laboratory-controlled environment to in-the-wild circumstances, nowadays, applications are overwhelmed by profusion of deep learning (DL) techniques real-world problems. DL networks steadily led better understanding low-dimensional...
Abstract Advances in Deep Learning (DL), Big Data and image processing have facilitated online disinformation spreading through Deepfakes. This entails severe threats including public opinion manipulation, geopolitical tensions, chaos financial markets, scams, defamation identity theft among others. Therefore, it is imperative to develop techniques prevent, detect, stop the of deepfake content. Along these lines, goal this paper present a big picture perspective paradigm, by reviewing...
Nowadays, automatic deception detection has received considerable attention in the machine learning community owing to this research interest its vast applications fields of social media, interviews, law enforcement, and military. In study, a novel deep convolution neural network (DCNN) named LieNet is proposed precisely detect multiscale variations automatically. Our approach combination contact noncontact-based approaches. First, 20 frames from each video are fetched concatenated form...
With the advent of deep learning, research on facial expression recognition (FER) has received a lot interest. Different convolutional neural network (DCNN) architectures have been developed for real-time and efficient FER. One challenges in FER is obtaining trustworthy features that are strongly associated with changes. Furthermore, traditional DCNNs problems two significant issues: insufficient training data, which leads to overfitting, intra-class appearance variations. FLEPNet,...
More than 10 million Europeans show signs of mild cognitive impairment (MCI), a transitional stage between normal brain aging and dementia memory disorder. The path MCI takes can be divergent; while some maintain stability or even revert to norms, alarmingly, up half the cases progress within 5 years. Current diagnostic practice lacks necessary screening tools identify those at risk progression. European patient experience often involves long journey from initial eventual diagnosis dementia....
Pairwise preference information, which involves users expressing their preferences by comparing items, plays a crucial role in decision-making and has recently found application recommendation systems. In this study, we introduce GcPp, clustering algorithm that leverages pairwise data to generate recommendations for user groups. Initially, construct individual graphs each based on utilize graph convolutional network predict similarities between all pairs of graphs. These predicted similarity...
Artificial Intelligence (AI) is reshaping healthcare through advancements in clinical decision support and diagnostic capabilities. While human expertise remains foundational to medical practice, AI-powered tools are increasingly matching or exceeding specialist-level performance across multiple domains, paving the way for a new era of democratized access. These systems promise reduce disparities care delivery demographic, racial, socioeconomic boundaries by providing high-quality at scale....
A large number of emerging applications, such as autonomous navigation, space exploration, surveillance, military target detection, and remote sensing, use outdoor images to monitor various activities interest. However, acquired under unfavorable weather conditions usually suffer from atmospheric scattering due environmental pollution causing color-shift low-contrast images. Dehazing is an research area in the computer vision domain that intends restore visibility by eliminating latter types...
Abstract Artificial intelligence-based algorithms are widely adopted in critical applications such as healthcare and autonomous vehicles. Mitigating the security privacy issues of AI models, enhancing their trustworthiness have become paramount importance. We present a detailed investigation existing security, privacy, defense techniques strategies to make machine learning more secure trustworthy. focus on new paradigm called federated learning, where one aims develop models involving...
In recent years, the number of image fusion schemes presented by research community has increased significantly. Measuring performance these is an important issue. this work, we introduce three quantitative metrics to assess quality algorithm. The proposed rely on edge information that obtained using fractional order differentiation. Edge and orientation strengths are fed into sigmoidal functions separately for estimating values normalized weighted fused corresponding source images....
Human personality plays a crucial role in decision-making and it has paramount importance when individuals negotiate with each other to reach common group decision. Such situations are conceivable, for instance, of want watch movie together. It is well known that people influence other's decisions, the more assertive person is, they will have on final In order obtain realistic recommendation system (GRS), we need accommodate assertiveness different members' personalities. Although pairwise...
In this study, we explore the potential of using functional near-infrared spectroscopy (fNIRS) signals in conjunction with modern machine-learning techniques to classify specific anatomical movements increase number control commands for a possible fNIRS-based brain-computer interface (BCI) applications. The study focuses on novel individual finger-tapping, well-known task fNIRS and fMRI studies, but limited left/right or few fingers. Twenty-four right-handed participants performed...