检索结果-内蒙古大学图书馆

4th IEEE International Conference on Artificial Intelligence in Engineering and Technology, IICAIET 2022

作者： Polumpung, Alixson Angeline, Lorita Ee Chuo, Helen Sin Tan, Min Keng Lim, Kit Guan Tze Kin, Kenneth Teo Universiti Malaysia Sabah Modelling Simulation & Computing Laboratory Faculty of Engineering Kota Kinabalu Malaysia School of Computer Science Taylor's University Faculty of Innovation & Technology Subang Jaya Malaysia

ISBN: (数字)9781665468374

ISBN: (纸本)9781665468374

This project proposes a human facial features detection based on color segmentation via skin color and Viola-Jones algorithm for real time application. YCbCr color space is used to detect the presence of skin in an image where the image is normalized, and luminance is removed to increase face detection accuracy. The second method, Viola-Jones which use Haar feature to detect facial feature such as face and eye also developed and tested. To perform in real time detection, CamShift algorithm and template matching are used to track face and eyes sequentially in Android platform. Then, the real time detection and tracking are evaluated to assess its performance. Finally, the algorithm is applied to drowsiness detection using PERCLOS. © 2022 IEEE.

关键词： Template matching

来源：评论

学校读者我要写书评

暂无评论

AloT-Driven Machine Learning for Anomaly Detection in Structural Health Monitoring

AloT-Driven Machine Learning for Anomaly Detection in Struct...

引用

IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)

作者： Lorita Angeline Kit Guan Lim Min Keng Tan Muhd. Nur Afnan Uda Joaquim Abel Jenarun Kenneth Tze Kin Teo Modelling Simulation & Computing Laboratory Faculty of Engineering Universiti Malaysia Sabah Kota Kinabalu Malaysia Faculty of Engineering Universiti Malaysia Sabah Kota Kinabalu Malaysia

ISBN: (数字)9798350389692

ISBN: (纸本)9798350389708

Structural health monitoring (SHM) is crucial for real-time assessment of structures to preemptively detect anomalies that may lead to failures. This study explores the integration of Artificial Intelligence of Things (AIoT) principles to enhance anomaly detection using acceleration and gyroscopic sensor data. The study involved setting up hardware comprising acceleration and gyroscopic sensors, integrated with a web server for real-time data monitoring. Issues with the raw dataset, including noise and variability, were addressed through preprocessing techniques. Four machine learning models, Support Vector Machine (SVM), Random Forest, Gradient Boosting, and Neural Network were evaluated on preprocessed data, focusing on recall as critical for anomaly detection in SHM. Models trained on reduced datasets showed varied performance compared to those using large, raw datasets, which, while computationally intensive, exhibited similar performance. SMOTE significantly improved recall, achieving 93.94% in Random Forest after correcting class imbalance and reducing dataset size. The findings underscore the potential of AIoT-driven machine learning approaches, to significantly enhance SHM modelling. By leveraging these technologies, infrastructure management can be fortified with more reliable anomaly detection capabilities, ensuring heightened safety and resilience in the AIoT era.

关键词： Support vector machines Computational modeling Focusing Real-time systems Web servers Safety Internet of Things Anomaly detection Monitoring Random forests

来源：评论

学校读者我要写书评

暂无评论

Effect of Cooling Channel Structure on Permanent Magnet Synchronous Motor

Effect of Cooling Channel Structure on Permanent Magnet Sync...

引用

IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)

作者： Zhencai Huang Hui Chen Kit Guan Lim Min Keng Tan Bih Lii Chua Kenneth Tze Kin Teo Modelling Simulation & Computing Laboratory Faculty of Engineering Universiti Malaysia Sabah Kota Kinabalu Malaysia School of Automotive Engineering Liuzhou Polytechnic University Liu Zhou China

ISBN: (数字)9798350389692

ISBN: (纸本)9798350389708

Taking the 135kW magnet synchronous motor as the research object, the CFD simulation was used to analyze the influence of spiral-type runner, single-channel circumferential Z-type runner, and axial Z-type runner on the heat dissipation performance of the motor. The maximum temperature of the inner wall of the shell is 358.93K, compared with the single-channel circumferential Z-type runner and axial Z-type runner decreased by 1.69K, 10.65K and 46.47K, respectively. The velocity uniformity and pressure loss of the helical runner is optimal, and the coefficient of velocity uniformity and the difference between import and export pressure are 0.948 and 14.78kpa, respectively; the runner structure of the PM synchronous motor can be preferred to consider the use of the helical runner form.

关键词： Heating systems Resistance Spirals Fluids Cooling Synchronous motors Permanent magnet motors Magnetic analysis Eddy currents Periodic structures

来源：评论

学校读者我要写书评

暂无评论

Impact of Helical Channel Number on Synchronous Motor Cooling Performance

Impact of Helical Channel Number on Synchronous Motor Coolin...

引用

IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)

作者： Xiang Lei Meng Hui Chen Min Keng Tan Kit Guan Lim Bih Lii Chua Kenneth Tze Kin Te Modelling Simulation & Computing Laboratory Faculty of Engineering Universiti Malaysia Sabah Kota Kinabalu Malaysia School of Automotive Engineering Liuzhou Polytechnic University Liu Zhou China

ISBN: (数字)9798350389692

ISBN: (纸本)9798350389708

In order to deeply explore the specific influence of the number of helical channels on the cooling performance of a motor, we carefully constructed a three-dimensional fluid-solid coupling calculation model of the flow channel with the help of CFD simulation technology. For the helical flow channels of the 135-k water-cooled permanent magnet synchronous motor shell, we conducted detailed numerical simulation calculations of the temperature field, velocity field, and pressure field. The results show that the number of helical channels has a direct impact on the cooling performance of the motor. Specifically, when the number of channels increases from 3 to 7, the maximum temperature on the inner wall of the shell decreases significantly by 94.41-k, and the velocity uniformity coefficient also increases by 0.05. However, this change also leads to an increase in the flow resistance within the channels, resulting in an increase in the pressure difference between the inlet and outlet of the channels by 4.73-kpa. These findings provide powerful data support for us to further optimize motor design and improve cooling performance.

关键词： Resistance Technological innovation Solid modeling Cooling Predictive models Motors Synchronous motors Robustness Vehicle dynamics Sustainable development

来源：评论

学校读者我要写书评

暂无评论

Discrete Particle simulation of Gas-Solid Flow in Air-Blowing Seed Metering Device

引用

Computer Modeling in Engineering & Sciences 2021年第6期127卷 1119-1132页

作者： Zhengquan Li Pei Zhang Yongchang Sun Chenglin Zheng Liang Xu Dianyu E Jiangxi Provincial Key Laboratory for Simulation and Modelling of Particulate Systems Jiangxi University of Science&TechnologyGanzhou341000China Energy Materials Computing Center Jiangxi University of Science&TechnologyNanchang330013China

In this paper,the gas and seed flow characters in the air-blowing seed metering device are investigated by using the coupled computational fluid dynamics and discrete element method(CFD-DEM)in three dimensions(3D).The method of establishing boundary model based on the computer-aided design(CAD)drawing,has been used to build the boundary model of seed metering *** 3D laser scanning technique and multi-element method are adopted to establish the particle *** a combined numerical and experimental effort,using 3D CFD-DEM software,which is based on the in-house codes,the mechanisms governing the gas and solid dynamic behaviors in the seed metering device have been *** gas velocity field and the effect of different rotational speeds and air pressures on the seeding performance and particle velocity have been studied,similar agreements between numerical and experimental results are *** reveals that the 3D CFD-DEM model established is able to predict the performance of the air-blowing seed metering *** can be used to design and optimize the air-blowing seed metering device and other similar agriculture devices.

关键词： Seed metering device CFD-DEM CAD simulation gas-solid flow

来源：评论

学校读者我要写书评

暂无评论

Yield Optimization for Exothermic Batch Process Using Particle Swarm Optimization

Yield Optimization for Exothermic Batch Process Using Partic...

引用

IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)

作者： Min Keng Tan Matthew Laurentius Bansing Huiyi Xu Helen Sin Ee Chuo Heng Jin Tham Kenneth Tze Kin Teo Modelling Simulation & Computing Laboratory Faculty of Engineering Universiti Malaysia Sabah Kota Kinabalu Malaysia School of Marine Science and Engineering Hainan Tropical Ocean University Hainan China

ISBN: (数字)9798350389692

ISBN: (纸本)9798350389708

Modern advancements in optimizing processes have been explored by various researchers, particularly for exothermic batch processes, which are prolific in the chemical and pharmaceutical industries. This paper proposes using artificial intelligence, specifically particle swarm optimization (PSO), to enhance these exothermic batch processes. Given that most exothermic batch processes utilize generic model control (GMC), the PSO algorithm will primarily focus on optimizing the control of the GMC within the process. The precise control of the controllers will aim to maintain the reactor temperature during the processes, ensuring stability and efficiency. This approach leverages AI to improve process performance, highlighting the potential of PSO in industrial applications. The proposed algorithm is shown to be able to produce a result of an increase of 4.5% of production of the desired product, while decreasing by-product production of 97%. The time it takes for the production of the desired product is also improved by 11.8%. This shows an efficiency increase of the entire exothermic batch processes, The results show that an improvement of the efficiency of the process makes the proposed algorithm a great method to improve the controller of the processes.

关键词： Batch production systems Process control Production Space exploration Particle swarm optimization Artificial intelligence Inductors Optimization Chemicals Thermal stability

来源：评论

学校读者我要写书评

暂无评论

Adaptive Exponential Feeding Control for a Fedbatch Yeast Fermentation Process Using Reinforcement Learning

Adaptive Exponential Feeding Control for a Fedbatch Yeast Fe...

引用

IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)

作者： Khairul Aznizam Sodiwal Wan Ying Chai Min Keng Tan Kenneth Tze Kin Teo Heng Jin Tham Chemical Engineering Programme Faculty of Engineering Universiti Malaysia Sabah Kota Kinabalu Malaysia Modelling Simulation & Computing Laboratory Faculty of Engineering Universiti Malaysia Sabah Kota Kinabalu Malaysia

ISBN: (数字)9798350389692

ISBN: (纸本)9798350389708

The fermentation process is complex and nonlinear because the growth pattern of microorganisms is sensitive to environmental conditions. Exponential feeding (EF) is a common and simple control strategy for regulating substrate feed flow rates using a pre-determined calculation based on growth kinetics. However, this method does not adapt to changes in the fermentation process. Reinforcement Learning (RL) is a subset of Artificial Intelligence (AI) that focuses on teaching optimal behaviors through interaction with an environment using rewards or penalties. This work explores an Adaptive Exponential Feeding (AEF) control using RL to determine the gain value of the feeding rate, aimed at maximizing yeast concentration and minimizing the by-product formation in a fed-batch baker's yeast fermentation. The kinetic and dynamic behavior of the fermentation process was modeled and simulated using MATLAB. The AEF approach uses an RL agent to optimize the feeding rate by interacting with the fermentation environment and selecting actions based on yeast concentration, glucose levels, and ethanol changes. The gain value ranges from 0 to 2.5 with a 0.1 interval. After iterations, the optimal policy is obtained. simulations with four different initial yeast and substrate concentrations showed that AEF significantly improved the fermentation performance, yielding a higher yeast concentration of 64.86 g/L compared to 44.68 g/L with EF, a 45.17 % increase, and reducing ethanol formation by 0.15 g/L. This adaptive approach demonstrates potential for enhanced efficiency and productivity in industrial fermentation processes.

关键词： Productivity Adaptation models Ethanol Reinforcement learning Real-time systems Kinetic theory Fermentation Artificial intelligence Substrates Resilience

来源：评论

学校读者我要写书评

暂无评论

Ant Colony Optimization Based Multi-Hop Wireless Transmission for Enhanced Network Reliability

Ant Colony Optimization Based Multi-Hop Wireless Transmissio...

引用

IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)

作者： Kit Guan Lim Mohd Fikry Fazri bin Sakimin Longxin Wei Min Keng Tan Soo Siang Yang Kenneth Tze Kin Teo Modelling Simulation & Computing Laboratory Faculty of Engineering Universiti Malaysia Sabah Kota Kinabalu Malaysia Faculty of The Internet of Things and Artificial Intelligence Fujian Polytechnic of Information Technology Fuzhou China

ISBN: (数字)9798350389692

ISBN: (纸本)9798350389708

Wireless multi-hop transmission is a new technology that has been used for data transfer in no internet connectivity and electricity area. Wireless sensor networks are being created for many different purposes, both for everyday civilian uses and military applications. Multi-hop transmissions are popular with challenges like shape of terrain, low data transfer rate and loss connectivity easily when it comes to design. The main problem is current control for routing in multi-hop wireless sensor networks works as what it has been initialized and the nodes only communicate with preset nodes. Malfunction of a single transceiver can cause connection losses and decrease network reliability. This report will explore the optimization of multi-hop wireless communication by implementing ACO in omnidirectional transceiver. The aim is to develop wireless sensor network model, compute control strategy for routing in random topology, to optimize wireless transmission by implementing artificial intelligence and analyze the performance of proposed algorithm. To achieved these goals, a simulation has been designed in MATLAB to represent the real situation virtually. Several parameters such as number of nodes, area size and transmission range must be considered in the simulation to get optimum result. Conventional routing protocol such as Distance-Vector is used as a comparison to ACO control strategy with the help of Euclidean distance formula. This project focus on optimizing routing strategy from source node to target node without considering pathloss and line of sight. Then, the results are performance comparison of Distance-Vector, Randomized Multi-Path and Ant Colony Optimization in 100 iterations. After simulation, Ant Colony Optimization does improve Distance-Vector by increasing network lifetime with 1st ‘dead node’ appear at 100th iteration but still maintaining as least average hops path as possible. The number of hops and ‘dead node’ for a single complete transmission fro

关键词： Wireless communication Wireless sensor networks Ant colony optimization Network topology Spread spectrum communication Routing Transceivers Routing protocols Topology Optimization

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Logic Based Perturb-and-Observe Algorithm for Minimizing Output Fluctuation of a PV System

Fuzzy Logic Based Perturb-and-Observe Algorithm for Minimizi...

引用

IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)

作者： Min Keng Tan Braindane Owin Moloney Kit Guan Lim Soo Siang Yang Hui Hwang Goh Kenneth Tze Kin Teo Modelling Simulation & Computing Laboratory Faculty of Engineering Universiti Malaysia Sabah Kota Kinabalu Malaysia School of Electrical Engineering Guangxi University Nanning China

Photovoltaic systems generate direct current (DC) power by absorbing sunlight through photovoltaic cells. However, under non-uniform irradiance, multiple peaks in the Maximum Power Point Tracking (MPPT) pose challenges for precisely tracking the global maximum power point. Traditional methods often focus on local maximum power points instead of the global ones. This research aims to enhance the Perturb and Observe (P&O) approach and model the PV module to accurately track the Maximum Power Point (MPP). The study investigates the performance of PV arrays using models with non-uniform characteristics. While traditional MPPT techniques like perturb and observe (P&O) can track the MPP, they struggle with non-uniform irradiance, leading to output power fluctuations and losses. simulation results demonstrate that the P&O-based MPPT algorithm, tailored for maximum power production, adjusts the operational point effectively. Comparing the conventional MPPT output voltage 17.8V under non-uniform irradiance of conventional P&O MPPT output voltage and a non-conventional Fuzzy Logic 33.8V under non-uniform irradiance indicates that the Fuzzy MPPT achieves 52.66% of the output voltage obtained by the non-conventional MPPT comparing to conventional MPPT. These algorithms offer improved precision and flexibility, although their implementation may require higher processing power and computational capabilities. Therefore, the next focus will be on developing a fuzzy logic based MPPT and enhancing the photovoltaic system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Electrical Impedance Tomography with Fuzzy Logic Classification in Lung Image Reconstruction 3

Electrical Impedance Tomography with Fuzzy Logic Classificat...

引用

3rd IEEE International Conference on Artificial Intelligence in Engineering and Technology, IICAIET 2021

作者： Yong, Cassandra Sze Jin Chong, Soon Yee Raman, Chelvam Dasaratha Chin, Renee Ka Yin Gopalakrishnan, Sainarayanan Teo, Kenneth Tze Kin Modelling Simulation Computing Laboratory Universiti Malaysia Sabah Faculty of Engineering Kota Kinabalu Malaysia Hcl Technologies Ltd. Chennai India

ISBN: (纸本)9781665428996

Electrical Impedance Tomography (EIT) estimates the electrical impedance distribution within a medium and produces cross-sectional images of an admittivity distribution inside an electrically conducting object. EIT in biomedicine application was first applied in lung due to it being large organs that allow large conductivity changes and is a promising technique since it allows continuous monitoring of the ventilation distribution. This study aims to explore the potential EIT technique in medical applications, with strategies to enhance the image reconstruction of the lung images. Performance of the enhanced image reconstruction is analyzed through simulation on the thorax Finite Element Model (FEM) based on a thorax CT image generated using NETGEN Mesher. To integrate and simulate EIT image of the thorax model, data are obtained from the forward and inverse model. Graz consensus Reconstruction algorithm for EIT (GREIT) technique is then applied as the consensus linear reconstruction algorithm for lung EIT images. Subsequently, the involvement of 3D imaging opens the opportunity to explore more electrode placement strategies for enhancement in image reconstruction. Performance of the reconstructed images based on electrode numbers and placement strategies are analyzed using the five figures of merits and classified into poor, average and good using Fuzzy Logic (FL). From the analysis, planar-offset configuration with 16-electrodes outperforms all others while planar configuration with 16-electrodes followed closely. © 2021 IEEE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：