Gene Eu Jan

Prof. Dr. Gene Eu Jan


Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 May 2023 in Sensors
Verified
Journal Article
Open access
PDF file
Tingjun LeiTingjun Lei
Tingjun Lei
PCPradeep Chintam
Pradeep Chintam
CLChaomin Luo
Chaomin Luo
LLLantao Liu
Lantao Liu
Gene Eu JanGene Eu Jan
Gene Eu Jan
In real-world applications, multiple robots need to be dynamically deployed to their appropriate locations as teams while the distance cost between robots and goals is minimized, which is known to be an NP-hard problem. In this paper, a new framework of team-based multi-robot task allocation and path planning is developed for robot exploration missions through a convex optimization-based distance optimal model. A new distance optimal model is proposed to minimize the traveled distance between robots and their goals. The proposed framework fuses task decomposition, allocation, local sub-task allocation, and path planning. To begin, multiple robots are firstly divided and clustered into a variety of teams considering interrelation and dependencies of robots, and task decomposition. Secondly, the teams with various arbitrary shape enclosing intercorrelative robots are approximated and relaxed into circles, which are mathematically formulated to convex optimization problems to minimize the distance between teams, as well as between a robot and their goals. Once the robot teams are deployed into their appropriate locations, the robot locations are further refined by a graph-based Delaunay triangulation method. Thirdly, in the team, a self-organizing map-based neural network (SOMNN) paradigm is developed to complete the dynamical sub-task allocation and path planning, in which the robots are dynamically assigned to their nearby goals locally. Simulation and comparison studies demonstrate the proposed hybrid multi-robot task allocation and path planning framework is effective and efficient.

18 October 2024 in Biomimetic Intelligence and Robotics
Verified
Journal Article
Open access
TSTimothy Sellers
Timothy Sellers
Tingjun LeiTingjun Lei
Tingjun Lei
CLChaomin Luo
Chaomin Luo
Zhuming BiZhuming Bi
Zhuming Bi
Gene Eu JanGene Eu Jan
Gene Eu Jan


Bor-Shing LinBor-Shing Lin
Bor-Shing Lin
YLYu-Ting Liu
Yu-Ting Liu
CYChu Yu
Chu Yu
Gene Eu JanGene Eu Jan
Gene Eu Jan
BHBo-Tang Hsiao
Bo-Tang Hsiao
Cardiovascular patients consult doctors for advice regarding regular exercise, whereas obese patients must self-manage their weight. Because a system for permanently monitoring and tracking patients’ exercise intensities and workouts is necessary, a system for recognizing gait and estimating walking exercise intensity was proposed. For gait recognition analysis, αβ filters were used to improve the recognition of athletic attitude. Furthermore, empirical mode decomposition (EMD) was used to filter the noise of patients’ attitude to acquire the Fourier transform energy spectrum. Linear discriminant analysis was then applied to this energy spectrum for training and recognition. When the gait or motion was recognized, the walking exercise intensity was estimated. In addition, this study addressed the correlation between inertia and exercise intensity by using the residual function of the EMD and quadratic approximation to filter the effect of the baseline drift integral of the acceleration sensor. The increase in the determination coefficient of the regression equation from 0.55 to 0.81 proved that the accuracy of the method for estimating walking exercise intensity proposed by Kurihara was improved in this study.

21 April 2023 in Sensors
Verified
Journal Article
Open access
PDF file
Chi-Chia SunChi-Chia Sun
Chi-Chia Sun
YLYong-Ye Lin
Yong-Ye Lin
WHWei-Jia Hong
Wei-Jia Hong
Gene Eu JanGene Eu Jan
Gene Eu Jan
In this article, a novel heterogeneous fusion of convolutional neural networks that combined an RGB camera and an active mmWave radar sensor for the smart parking meter is proposed. In general, the parking fee collector on the street outdoor surroundings by traffic flows, shadows, and reflections makes it an exceedingly tough task to identify street parking regions. The proposed heterogeneous fusion convolutional neural networks combine an active radar sensor and image input with specific geometric area, allowing them to detect the parking region against different tough conditions such as rain, fog, dust, snow, glare, and traffic flow. They use convolutional neural networks to acquire output results along with the individual training and fusion of RGB camera and mmWave radar data. To achieve real-time performance, the proposed algorithm has been implemented on a GPU-accelerated embedded platform Jetson Nano with a heterogeneous hardware acceleration methodology. The experimental results exhibit that the accuracy of the heterogeneous fusion method can reach up to 99.33% on average.

1 October 2017
Verified
Conference Paper
Closed access
CYChan-Yun Yang
Chan-Yun Yang
Gene Eu JanGene Eu Jan
Gene Eu Jan
HSHooman Samani
Hooman Samani
LYLiyu Yu
Liyu Yu
As the emerging development of IoT circumstance, on-line detections or observations of a system states become easier by facilitating its corresponding multi-sensory responses, and thus the description of a system behavior becomes clearer. Abundant on-line multi-channel information from the embedded sensors would be advantageous to the understanding of the system. Though having the information, it is still uneasy to thoroughly assess the integrity behavior of the system without a eligible system identification method. In the study, through a recurrent function approximation by an integrated multi-regression of support vector regression (SVR), the identification has been developed and represented as a family of characteristic functions. With the set of characteristic functions, a design of IoT based live interaction of adaptive control or human-machine system could hereafter followed up. The study constructed primarily the SVR based framework of the recurrent multi-sensor system identification. There are two major contributions of the study: First, an IoT aspect for the discovery of the multiple regression extended from an underlying SVR, second, a technical overcoming in the realization of the recurrent framework of SVR.