- Anomaly Detection Techniques and Applications
- Context-Aware Activity Recognition Systems
- Advanced Wireless Network Optimization
- Cognitive Radio Networks and Spectrum Sensing
- Advanced MIMO Systems Optimization
- Advanced Queuing Theory Analysis
- Advanced Data Compression Techniques
- Building Energy and Comfort Optimization
- Wireless Networks and Protocols
- Wireless Communication Networks Research
- Mobile Health and mHealth Applications
- Electricity Theft Detection Techniques
- Algorithms and Data Compression
- Energy Load and Power Forecasting
- Advanced Steganography and Watermarking Techniques
- Sentiment Analysis and Opinion Mining
- Image and Signal Denoising Methods
- Smart Agriculture and AI
- Video Coding and Compression Technologies
- Health and Conflict Studies
- Remote Sensing and Land Use
- Chaos-based Image/Signal Encryption
- Topic Modeling
- Geotechnical Engineering and Underground Structures
- Artificial Intelligence in Healthcare
Multimedia University
2014-2024
Hospital Universiti Sains Malaysia
2024
Covenant Medical Center
2024
Texas Tech University
2024
University of Alabama in Huntsville
2024
Stevens Institute of Technology
2010-2012
University of Calgary
2003
The concept of dynamic spectrum access (DSA) enables the licensed to be traded in an open market where unlicensed users can freely buy and use available bands. However, like other traditional commodity markets, trading is inevitably accompanied by various competitions challenges. In this paper, we study important business competition activity - price war DSA market. A non-cooperative pricing game formulated model contention among multiple wireless providers for higher share revenues. We...
The cognitive radio enabled IEEE 802.22 wireless regional area network (WRAN) is designed to opportunistically utilize the unused or under-utilized TV bands. However, due open nature of networks and lack proactive security protocols, are vulnerable various denial-of-service (DoS) threats. In this paper, we study coordinated DoS attacks on from malicious users' perspective. We consider both one-stage a multi-stage cases problem. scenario, formulate cooperative game among nodes derive optimal...
Cognitive radio (CR) enabled dynamic spectrum access (DSA) networks are designed to detect and opportunistically utilise the unused or under-utilised bands. However, due open paradigm of CR lack proactive security protocols, DSA vulnerable various denial-of-service threats. The authors propose a game-theoretic framework study primary user emulation attack (PUEA) on nodes. A non-cooperative multistage game between secondary nodes adversaries generating PUEA is formulated. pure-strategy...
Heart disease continues to be the leading cause of mortality in Malaysia an era industrialization, changing lifestyles and dietary habits. The rate reported government hospitals shows increase death due heart diseases, this trend is expected continue into next decades. Since increasingly affecting human lifestyle, rehabilitation practical devices are being carried out created order reduce disability from diseases. This paper proposed a wireless patient monitoring system which integrates...
In this paper, we investigate a new type of denialof- service attack in dynamic spectrum access networks - Sybilenabled attack. attack, the attacker not only launches primary user emulation (PUE) attacks but also creates and infiltrates multiple Sybil identities to compromise decision making process secondary network via Byzantine attacks. We implement our cognitive radio testbed show its feasibility impact. further analyze optimal strategy from perspective malicious attacker, i.e.,...
Behavioral changes in daily home activities may be linked with health problems. Therefore, anomaly detection on sequence pattern of is important for healthcare monitoring. In this paper, an method based Long Short-Term Memory (LSTM) neural network proposed to detect anomalies activities. A comparison study LSTM and Hidden Markov Model (HMM) was conducted evaluate their performance under different training set size model's hyperparameters. The experimental results demonstrated that comparable...
Numerous research works have been put forward over the years to advance field of facial expression recognition which until today, is still considered a challenging task. The selection image color space and use alignment as preprocessing steps may collectively pose significant impact on accuracy computational cost emotion recognition, crucial optimize speed-accuracy trade-off. This paper proposed deep learning-based pipeline that can be used predict detected face regions in video sequences....
This paper intends to bring forward an image compression method which is capable perform both lossy and lossless compression. A threshold value associated in the process, different ratios can be achieved by varying values performed if set zero. The proposed allows quality of decompressed determined during process. provides more flexibility users, not only choosing appropriate type, but users may also vary meet preferable corresponding desired images.
The number of older people is increasing in many countries. By 2030, it estimated that 15% the overall population will be comprised aged 65 and above. Hence, monitoring tracking elder activities to ensure they live an active life has become a major research topic recent years. In this work, elderly sub-activity system developed detect based on their physical indoor location. location combined project enhance context (i.e. sub-activities as defined project). An by using Bluetooth Low Energy...
The relationship between individuals and their thermal environment is pivotal not only for comfort but also health productivity. Thermal comfort, as defined by ASHRAE, reflects an individual's satisfaction with ambient conditions can be gauged using the ASHRAE scale. In past, traditional prediction models such Predicted Mean Vote (PMV) were used to evaluate comfort. Nevertheless, emergence of machine learning provides a more dynamic approach predict occupants. However, subjective nature...
Thermal comfort refers to the process of determining a pleasant working temperature by considering various environmental, occupational, and personal factors. With widespread adoption Internet Things (IoT) technologies, there is potential develop an IoT-based embedded system that directly integrates sensor data with building information collect necessary environmental factors for thermal comfort. This paper outlines development implementation remote monitoring, which gathers such as humidity...
In this paper, we investigate Sybil attacks on spectrum allocation in distributed dynamic access (DSA) networks. Using IEEE 802.11 devices as secondary nodes, demonstrate the feasibility of mounting cognitive radio testbed, which malicious node poses multiple normal nodes with different identities order to steal more bands. We also show impact attack through an example and simulation results. A defense strategy using statistics beacon intervals is proposed. Through experimental results,...
SUMMARY Applications of video streaming and real‐time gaming, which generate large amounts traffic in the network, are expected to gain considerable popularity Long Term Evolution networks. Maintaining QoS such as packet delay, loss ratio, median, cell border throughput requirements networks dominated by real time traffic, is critical. The existing dimensioning methodology does not consider parameters network dimensioning. Moreover, exhaustive time‐consuming simulations normally required...
In this paper, a self-attention based neural network architecture to address human activity recognition is proposed. The dataset used was collected using smartphone. contribution of paper multi-layer multi-head for and compared two strong baseline architectures, which are convolutional (CNN) long-short term (LSTM). dropout rate, positional encoding scaling factor also been investigated find the best model. results show that proposed model achieves test accuracy 91.75%, comparable result when...
The cognitive radio enabled IEEE 802.22 wireless regional area network (WRAN) is designed to opportunistically utilize the unused or under-utilized TV bands. However, due lack of proactive security protocols and proper interaction policies among secondary networks themselves, are vulnerable various denial-of-service (DoS) threats. In this paper, we study impact coordinated DoS attacks on from malicious nodes' perspective. Assuming that multiple nodes will launch attacks, formulate a...
This paper discusses the enhancement using blob analysis applied to automatic segmentation of "GrabCut" tool [1] for segmenting blooming flowers in color images. The is used initialize segmentation, but results are not effective and there insufficient separation foreground background distributions. In our proposed work, segmented image RGB format first converted a binary based on V plane HSV space. morphology operators combining with set operations then fill up holes blob. followed by...
This paper introduces the concept of eigenvalues in describing shape features blooming flowers, and implements idea recognizing flowers automatically. The input images are taken from natural scene form RGB images. proposed method first segments crops targeted flower object, then calculates four to a 2 × matrix. Eigenvalues matrix computed testing set used compare with those reference set. advantage utilizing is that dimension parameters comparison can be reduced. Based on experimental result...
This paper proposes a new descriptor to identify the petals' shape of blooming flower based on digital images captured in natural scene. The proposed can be used as one features computer aided recognition system beside commonly such number petals and color. Experiments were conducted Malaysia flowers with same similar color across different species flowers. 35 from 7 training set up reference values testing set. calculated is then compared achieve purpose. With given data, complete success...
In this paper, we investigate the parochialism in dynamic spectrum access networks and its effect on resource competition self-coexistence among cognitive radio secondary users. We assume that some greedy users network form a parochial community private try to maximize their own utilities without concern for interests of other outside community. A noncooperative game is formulated first analyze equilibrium strategy any network. scenario where there community, expected payoff insider who...
In most countries, the old-age people population continues to rise. Because young adults are busy with their work engagements, they have let elderly stay at home alone. This is quite dangerous, as accidents may happen anytime without anyone knowing. Although sending relatives an care center or hiring a caregiver good solutions, not be feasible since it too expensive over long-term period. The behavior patterns of during daily activities can give hints about health condition. If abnormal...
This paper studies a continuous-time single-server infinite capacity queueing system with two types of customer: positive and negative customers. Positive customers are ordinary that receives service in the server. A customer arrives to according Poisson process rate γ will remove one at head upon its arrival. By assuming interarrival time distributions tend constant when t goes infinity, set equations be derived by using an alternative approach find stationary queue length distribution....