- Privacy-Preserving Technologies in Data
- Energy Harvesting in Wireless Networks
- Advanced Wireless Communication Technologies
- Stochastic Gradient Optimization Techniques
- Advanced MIMO Systems Optimization
- Antenna Design and Analysis
- Indoor and Outdoor Localization Technologies
- Antenna Design and Optimization
- Artificial Intelligence in Healthcare
- IoT and Edge/Fog Computing
- Adversarial Robustness in Machine Learning
- Millimeter-Wave Propagation and Modeling
- Poxvirus research and outbreaks
- Telecommunications and Broadcasting Technologies
- Advanced Photonic Communication Systems
- Brain Tumor Detection and Classification
- Vehicular Ad Hoc Networks (VANETs)
- COVID-19 diagnosis using AI
- Wireless Body Area Networks
- Organic Electronics and Photovoltaics
- Machine Learning and Data Classification
- Optical Network Technologies
- Advanced Graph Neural Networks
- Ga2O3 and related materials
- UAV Applications and Optimization
Noakhali Science and Technology University
2018-2025
Kyung Hee University
2022-2025
Old Dominion University
2023-2024
Virginia Tech
2024
University of Houston
2024
Khulna University
2018-2023
Universiti Malaysia Pahang Al-Sultan Abdullah
2023
Bangladesh Agricultural University
2021
In the wake of COVID-19, rising monkeypox cases pose a potential pandemic threat. While less severe than its increasing spread underscores urgency early detection and isolation to control disease. The main difficulty in diagnosing arises from prolonged diagnostic process symptoms that are similar those other skin diseases, making challenging. To address this, deployment deep learning models on edge devices presents viable solution for rapid accurate monkeypox. However, resource constraints...
Explainable artificial intelligence (XAI) twin systems will be a fundamental enabler of zero-touch network and service management (ZSM) for sixth-generation (6G) wireless networks. Thus, reliable XAI system becomes essential to discretizing the physical behavior Internet Everything (IoE) identifying reasons behind that enabling ZSM. To address challenges extensible, modular, stateless functions in ZSM, novel neuro-symbolic framework is proposed enable trustworthy ZSM IoE. The consists two...
Semantic communication will considerably enhance transmission efficiency by exploring and only transmitting semantic information. However, most of the previous work in this field is limited to particular applications such as text, audio, or images does not consider task-oriented communications, where effectiveness transmitted information must be taken into account for completing a specific task. This paper focuses on developing framework high altitude platform (HAP)-supported fully connected...
The forth-coming 6G wireless communication systems are required to meet the increasing demand for network connectivity that requires power savings generating effective beamforming. Therefore, joint sensing and framework is proposed with coexistence between holographic MIMO (HMIMO) Intelligent Omni-Surface (IOS) which ensures extension of coverage area resulting in lower consumption An optimization problem formulated maximizing utility function considering channel capacity, beampattern gains...
Abstract The thyroid gland is the crucial organ in human body, secreting two hormones that help to regulate body’s metabolism. Thyroid disease a severe medical complaint could be developed by high Stimulating Hormone (TSH) levels or an infection tissues. Hypothyroidism and hyperthyroidism are critical conditions caused insufficient hormone production excessive production, respectively. Machine learning models can used precisely process data generated from different sectors build model...
The future sixth-generation (6G) wireless communication networks are expected to provide massive connectivity with lower power requirements for generating the desired beamforming. Therefore, holographic MIMO assisted integrated sensing and framework is proposed that ensures activate minimum number of grids from grid array (HGA) effective An optimization problem formulated maximizes signal noise-interference ratio (SNIR) users which in turn utility function (UFS) considering beampattern...
The impending sixth-generation wireless communication networks are anticipated to guarantee mass connectivity, high integration, and lower power consumption for generating the required beamforming. To achieve these goals, an artificial intelligence (AI) framework is proposed by utilizing holographic MIMO-assisted integrated sensing, localization, communication. AI ensures activate minimum number of grids from grid array generation An optimization problem formulated maximize...
This paper aims to improve the robustness of a small global model while maintaining clean accuracy under adversarial attacks and non-IID challenges in federated learning. By leveraging concise knowledge embedded class probabilities from pre-trained for both image classification, we propose Pre-trained Model-guided Adversarial Federated Learning (PM-AFL) training paradigm. paradigm integrates vanilla mixture distillation effectively balance promoting local models learn diverse data....
빔포밍은 초고속 데이터 속도를 달성하기 위해 테라헤르츠 및 밀리미터파(mmWave) 주파수 대역을 활용하는 차세대 무선 통신 분야의 발전에 있어서 중요한 역할을 한다. 하지만 이러한 대역은 빔 트레이닝과 관련된 비용으로 인해 문제가 발생할 수 있으며, 특히 드론 무인 항공기(UAV) 통신과 같이 높은 이동성을 필요로 하는 응용 분야에서 초신뢰 저지연 통신(URLLC)을 실현하는데 어려움이 있다. 본 논문에서는 UAV를 위한 상황 정보 기반 mmWave 빔포밍을 제안하며 이동성이 UAV 환경에서 UAV의 전송률을 최대화하기 최적화 문제를 정의한다. URLLC를 유지하면서 최적의 빔을 예측하기 경량 트랜스포머를 설계한다. 트랜스포머의 self-attention 메커니즘은 모델이 정보의 가장 특징에 선택적으로 집중할 있도록 트랜스포머 모델은 개선하는 이상적인 정확하게 예측한다. 시뮬레이션 결과는 논문의 설계는 효과를 입증한다. 기준 방법과 비교할 때, 17.8%의 더 Top-1...
Hepatitis is a widespread inflammatory condition of the liver, presenting formidable global health challenge. Accurate and timely detection hepatitis crucial for effective patient management, yet existing methods exhibit limitations that underscore need innovative approaches. Early-stage now possible with recent adoption machine learning deep With this in mind, study investigates use traditional models, specifically classifiers such as logistic regression, support vector machines (SVM),...
The growing global populations, particularly in major cities, have created new problems, notably terms of public safety regulation and optimization. As a result, this paper, strategy is provided for predicting crime occurrences city based on historical events demographic observation. In particular, study proposes prediction evaluation framework machine learning algorithms the network edge. Thus, complete analysis four distinct sorts crimes, such as murder, rapid trial, repression women...
Federated learning-assisted edge intelligence enables privacy protection in modern intelligent services. However, not independent and identically distributed (non-IID) distribution among clients can impair the local model performance. The existing single prototype-based strategy represents a class by using mean of feature space. spaces are usually clustered, prototype may represent well. Motivated this, this article proposes multiprototype federated contrastive learning approach (MP-FedCL)...
Parkinson's disease (PD) is a neurodegenerative disorder responsible for shaking, rigidity, and trouble in walking patients' coordination ability physical stability deteriorate day by day. Bipolar (BD) psychiatric which the reason behind extreme shiftiness mood, frequent mood inversion may reach too high called mania. People with BD have greater chance of developing PD during follow-up period. A lot work has been done to understand key factors these 2 diseases. But molecular functionalities...
Edge intelligence becomes the enabler to fulfill privacy-preserving intelligent services and applications for next-generation networking. However, heterogeneous data distribution of distributed edge clients often hinders convergence rate test accuracy. Federated Learning (FL), as a new paradigm edge-artificial (edge-AI) that enables model training without raw leaving their local sides. The differences in can easily lead biased inference results, especially when inferring through classifiers....
The sixth-generation wireless networks are required to satisfy the ever-increasing demands of diverse applications guarantee power savings, energy efficiency, mass connectivity, and higher integration devices. To accomplish these goals, in this paper, an artificial intelligence (AI)-based holographic MIMO (HMIMO)-empowered cell-free (CF) network is proposed while leveraging integrated sensing communication (ISAC). AI-based framework allocates desired for beamforming by activating number...
The 6G wireless communication networks need an intelligent networking system to meet the ever-increasing demands of various applications and mobile devices ensure power savings, energy efficiency (EE), high integration devices, mass connection. To achieve these aims, artificial intelligence (AI)-based holographic MIMO (HMIMO)-aided cell-free (CF) network is suggested allocate desired for beamforming by activating required number grids from serving HMIMOs users. An optimization problem...