Loading [MathJax]/extensions/MathZoom.js
Ka Lok Man - IEEE Xplore Author Profile

Showing 1-25 of 170 results

Filter Results

Show

Results

Waterway perception is critical for the special operations and autonomous navigation of Unmanned Surface Vessels (USVs), but current perception schemes are sensor-based, neglecting the interaction between humans and USVs for embodied perception in various operations. Therefore, inspired by visual grounding, we present WaterVG, the inaugural visual grounding dataset tailored for USV-based waterway ...Show More
Conventional sensor-based solar tracking systems face limitations in accurately tracking the maximum output power position under partial shading conditions (PSCs). The primary challenge of current solar tracking methods is to minimize global search efforts while efficiently tracking the optimal position with lower energy consumption. This paper introduces a beta-particle-filter (β-PF) sensorless s...Show More
Internet of Things (IoT) technology can provide real-time public facilities data to Intelligent Transportation Systems (ITS), especially the surveillance cameras' video data. With the popularity of video surveillance systems, Video Anomaly Detection (VAD) has become more important in society and traffic management. However, the traditional, highly manual-dependent VAD method and the neural network...Show More
This research uncovers a pioneering method for distinguishing mosaic augmentation in datasets, an area yet to be thoroughly investigated. Utilizing conventional visual preprocessing tactics, such as Gaussian blurring and Canny Edge Detection, together with a Convolutional Neural Network (CNN), we develop a strategy for detecting mosaic enhancements in datasets. This methodology achieved an remarka...Show More
As the Internet continues to evolve rapidly, the accuracy and efficiency of recommendation systems are crucial for Internet platforms. Concurrently, the continuous advancement of deep learning has led to the emergence of various recommendation system models based on Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and attention mechanisms. This model diversity presents a cha...Show More
Within the ever-changing environment of Wireless Power Transmission (WPT), the goal of increased efficiency and charging range has gained significant interest. A significant difficulty is the inherent reduction in energy transmission with increasing distance and decreasing coupling coefficients. Metamaterials (MTMs), designed objects with remarkable electromagnetic characteristics, represent a pos...Show More
We propose the design of a low-cost dual-band transponder for calibrating C-band and X-band Synthetic Aperture Radar (SAR) satellites. The production costs are reduced since the design was done on an FR4 substrate. The amplifiers utilize a multistage common emitter (CE) topology while antennas consist of an 8-element concentric circular array.Show More
Accurate State of Charge (SoC) estimation is essential for efficient battery management systems (BMS). In this study, we propose a novel hybrid neural network architecture, combining the Informer and Long Short-Term Memory (LSTM) networks. Our hybrid network captures temporal dependencies and nonlinear characteristics inherent in battery data, enhancing sequence integration capabilities and comput...Show More
The path loss contribution in a modern telecommunications system is particularly critical due to the higher frequencies employed. However, this can be mitigated by improving the antenna section gain. Adaptive beam steering systems are an enabling technology to seek for this objective, by focusing the antenna pattern towards a given position in the space. In this work, we propose a novel architectu...Show More
The Flexible Power Point Tracking (FPPT) algorithm is vital in managing the active power output of grid-connected photovoltaic (PV) systems to align with grid require-ments. However, conventional FPPT algorithms encounter chal-lenges with tracking misjudgments under fluctuating irradiance conditions. To enhance control of photovoltaic systems in such fluctuating environments, this paper proposes a...Show More
Intellectual Property (IP) is a special type of data that has broad and high trading demands. Existing blockchain-based IP data trading schemes can promote the IP data trading market by removing the dependence on centralized platforms. However, the problem of trading fairness among sellers and buyers is more challenging compared to centralized approaches. This paper addresses the trading fairness ...Show More
Missing data in building energy time series is a pervasive issue, which leads to data format inconsistencies and hindrances in energy prediction and management. The most common approach to addressing missing data in building energy data is through data imputation. The critical challenge of data imputation is ensuring that the imputed data closely approximates the real values. This paper proposes a...Show More
The integration of Digital Twin (DT) technology into the photovoltaic (PV) sector represents a significant advancement in energy management, optimization, servicing, and maintenance. This comprehensive literature review aims to enhance understanding, categorization, and adoption of DT and data fusion technologies within the PV industry to guide future research endeavors. The review categorizes PV ...Show More
Autonomous driving on water surfaces plays an essential role in executing hazardous and time-consuming missions, such as maritime surveillance, survivor rescue, environmental monitoring, hydrography mapping and waste cleaning. This work presents WaterScenes, the first multi-task 4D radar-camera fusion dataset for autonomous driving on water surfaces. Equipped with a 4D radar and a monocular camera...Show More
Indoor multi-person tracking is a widely explored area of research. However, publicly available datasets are either oversimplified or provide only visual data. To fill this gap, our paper presents the RAV4D dataset, a novel multimodal dataset that includes data from radar, microphone arrays, and stereo cameras. This dataset is characterised by the provision of 3D positions, Euler angles and Dopple...Show More
The performance of photovoltaic (PV) systems is influenced by various factors, including atmospheric conditions, geographical locations, and spatial and temporal characteristics. Consequently, the optimization of PV systems relies heavily on the global maximum power point tracking (GMPPT) methods. In this paper, we adopt virtual reality (VR) technology to visualize PV entities and simulate their p...Show More
The prediction of bifacial photovoltaic (bPV) system performance under variable conditions has persistently challenged researchers and practitioners alike, largely due to the unstable and imprecise irradiance measurements and the extensive training processes required for machine learning-based methods. Addressing these issues, this study introduces an innovative digital twin system that integrates...Show More
Simulations of photovoltaic (PV) systems help understand the nonlinear power–voltage characteristics in real-world atmospheric conditions. However, the gaps between simulation and real-world domain are usually significant due to the modeling errors. Therefore, we propose a simulation-to-reality (sim-to-real) global maximum power point tracking (GMPPT) method with domain randomization and adaptatio...Show More
Driven by deep learning techniques, perception technology in autonomous driving has developed rapidly in recent years, enabling vehicles to accurately detect and interpret surrounding environment for safe and efficient navigation. To achieve accurate and robust perception capabilities, autonomous vehicles are often equipped with multiple sensors, making sensor fusion a crucial part of the percepti...Show More
Few-shot learning stands as a prominent trend in the field of computer vision, with substantial applications in vision tasks such as image classification and semantic segmentation. It has gained popularity due to its potential to reduce the demand for computer resources and its ability to lessen dependence on large datasets. However, generating high-performance models becomes challenging since thi...Show More
In recent years, large models have manifested unparalleled strengths in various fields and became a major trend in AI advancement. In the field of computer vision, the Segment Anything Model (SAM) has surpassed the majority of conventional models with its high generalization ability and profound understanding of the notion of “object”. However, despite its outstanding capacity in common semantic s...Show More
Current perception models for different tasks usually exist in modular forms on Unmanned Surface Vehicles (USVs), which infer extremely slowly in parallel on edge devices, causing the asynchrony between perception results and USV position, and leading to error decisions of autonomous navigation. Compared with Unmanned Ground Vehicles (UGVs), the robust perception of USVs develops relatively slowly...Show More
Our work proposes an artificial synaptic transistor fabricated with aqueous solution process. The device is in thin-film transistor structure and can potentially emulate synaptic behavior (Long-Term Potentiation - LTP) via charge transfer mechanism. The device is a potential candidate to build neuromorphic computing hardware.Show More
In this work, we propose the design of an active reflector for X-band Synthetic Aperture Radar (SAR) satellite calibration. The target requirements are low-cost and low-power consumption to be a valid alternative for passive reflectors. The amplifier has a multistage common emitter topology. The radiating section deploys a pair of 4x4 rectangular arrays. Simulations prove the device to reach a Rad...Show More
Radar point clouds are a rich source of information for various applications. However, clustering or classification of radar point clouds is challenging due to their sparsity, noise, and ambiguity. In this paper, we propose a novel approach that leverages the Segment Anything Model (SAM), a segmentation model introduced by Meta AI that can produce high-quality segment masks from 2D images, to pred...Show More