检索结果-内蒙古大学图书馆

IEEE International Conference on Industrial engineering and engineering Management

作者： Nattakit Yuduang Yogi Tri Prasetyo Rachkanok Sukhavalli Michael Nayat Young Department of Supply Chain Faculty of Business Administration Suvarnabhumi Institute of Technology Samut Prakan Thailand International Bachelor Program in Engineering Yuan Ze University Chung-Li Taiwan Department of Industrial Engineering and Management Yuan Ze University Chung-Li Taiwan School of Industrial Engineering and Engineering Management Mapua University Manila Philippines

Rail freight transportation is one of the essential modes of freight transport. It is regarded as a cheap means of transportation and is appropriate for moving containers, agricultural items, and bulk materials. However, for a number of reasons, rail freight transit in Thailand has been constrained. One of the most worrisome issues from the perspective of the clients is the ability to track and trace the shipments. Due to the lack of efficient information flow among all parties involved in transportation, customers are unable to track down shipments and determine when they will arrive at their destination. This study used information flow diagrams to show where the information was lacking. As a case study, the State Railway of Thailand (SRT) practice is utilized to analyze the issues and make improvement recommendations. Finally, in order to enhance the information flow for rail freight transportation, a traceability system for rail freight has been developed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Application of Unmanned Aerial VehicleeBased Infrared Images in Determining Characteristics of Sea Surface Temperature Distribution

引用

Journal of Marine Science and Technology (Taiwan) 2023年第1期31卷 13-25页

作者： Wang, Hsing-Yu Fang, Hui-Ming Chiang, Yun-Chih Department of Shipping Technology College of Maritime National Kaohsiung University of Science and Technology Taiwan Bachelor Degree Program in Ocean Engineering and Technology National Taiwan Ocean University Taiwan Center for General Education Tzu Chi University Taiwan

This study investigated the temperature field of a body of water by using rotary-wing unmanned aerial vehicles (DJI Mavic 2 Enterprise Dual) comprising visible light and infrared cameras to determine sea temperature distribution. With a flight height of 150 metres, image overlap of 80%, and image resolution of 4.75 cm/pixel, the proposed method was more effective than the conventional portable conductivityetemperatureedepth device in rapidly measuring sea surface temperature and determining sea temperature distribution. The discharged heated water of the Hoping Power Plant traveled 100e330 metres from the wastewater outfall and then gradually diffused in the range of 100e490 metres before reaching a similar temperature to the background sea temperature. The diffusion of the thermal plume was mainly affected by regional marine meteorological conditions. © 2023 National Taiwan Ocean University.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Performance Investigation of Tri-Layer Double-Gate Ingazno Thin-Film Transistor in Synchronous Bias for Active-Matrix Lcds

SSRN

引用

SSRN 2023年

作者： Mishra, Richa Dargar, Shashi Kant Dargar, Abha Birla, Shilpi Lai, Wen-Cheng Department of Electronics Engineering Kalasalingam Academy of Research and Education TN India Department of Electronics Engineering Manipal University Jaipur India Department of Computer Science Engineering Parul University Vadodara India Bachelor Program in Industrial Projects National Yunlin University of Science and Technology Taiwan Department of Electronic Engineering National Yunlin University of Science and Technology Taiwan

In the current display electronics, a high-resolution pixel density and refresh rate ranging 7680 × 4320 pixels, 300 ppi, and 240 Hz are in high demand. The pixel-driving Thin–Film Transistors (TFTs) are primarily responsible for the switch in such displays. The amorphous Indium-Gallium-Zinc-Oxide (a-IGZO) TFTs are popular in realizing better high–speed properties in line to achieve those needs. In previous years, amorphous-IGZO channel TFTs in one-gate and dual-gate structures have exhibited improved gate control. In this paper, the authors present the analytical performance of double–gate tri-layer channel structure design of a-IGZO TFT with three stacked channel layers (IGZO/ITO/ITO1) to model and evaluate the device performance at different gate biasing. The proposed device simulation results were encouraging, in terms of high capacitance in dual gate bias (CDG) 26.2 nF/cm2, high mobility (µFE) 16.93 cm2/V.s, and steeper subthreshold swing (SS) 95 mV/decade. © 2023, The Authors. All rights reserved.

关键词： Thin film transistors

来源：评论

学校读者我要写书评

暂无评论

Dynamic Fire and Smoke Detection Module with Enhanced Feature Integration and Attention Mechanisms

SSRN

引用

SSRN 2024年

作者： Amjad, Ammar Tsung, Chang Hsien Tai, Li-Chia Department of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu300 Taiwan Department of Computer Science and Information Engineering Chang Gung Universiry Taoyuan333 Taiwan Bachelor Program in Artificial Intelligence Chang Gung Universiry Taoyuan333 Taiwan Department of Physical Medicine and Rehabilitation at Linkou Taoyuan333 Taiwan

Essential components of early fire warning systems include effective fire and smoke detection mechanisms. Despite object detection-based technologies demonstrating promising results, the unique characteristics of fire and smoke, the complexity of fire environments, the scarcity of labeled datasets, and the presence of noise in images necessitate further improvements. We have developed a YOLOv7-tiny optimized architecture called the Dynamic Fire and Smoke Detection Module (DFDM) to address these challenges. Our approach includes an asymptotic feature pyramid network (AFPN) to bridge semantic gaps, thus enhancing fire detection capabilities in complex environments. A cross-level dual attention mechanism also refines critical smoke and fire detection features. To enhance performance while reducing model complexity, we introduced a novel partial convolution module designed to filter out extraneous information effectively. Experimental results demonstrate that DFDM provides robust fire and smoke detection capabilities, giving it a competitive advantage over more complex systems. Extensive visualization studies confirm DFDM's effectiveness in object recognition across varied settings. © 2024, The Authors. All rights reserved.

关键词： Smoke

来源：评论

学校读者我要写书评

暂无评论

Player dominance adjustment in games

arXiv

引用

arXiv 2021年

作者： Xu, Junjie H. Bachelor Program in Information Science and Engineering Department of Human and Computer Intelligence College of Information Science and Engineering Ritsumeikan University

Video Games are boring when they are too easy, and frustrating when they are too hard. In terms of providing game experience such as enjoyment to the player by match players with different levels of ability to player ability, We assume that implementing DDA for providing matches between player ability and overall game difficulty to the game, especially the modern game, has limitations in terms of increasing computational cost and complexities in the design of modeling the difficulty in modern games. To overcome limitations underlying the method of providing static difficulty changes to player, and DDA, we proposed a novel idea, "Player Domination adjustment (PDA)." The proposed idea is that to control the AI’s actions based on the player’s inputs so as to adjust the player’s dominant power (e.g. the AI recognizes the player’s attack actions but defends it in a wrong side to let the player incur damage to itself), which was proved as it leads to promotion of game-related self-efficacy in our work. Several pieces of research on were conducted on a social deduction game and a fighting game respectively, show our proposed idea has its potential of promoting User Experience(UX). As in an another study, outperforms DDA in two conducted experiments in terms of health promotion. PDA also suitable in many cases of promoting the health of the player by increasing health metrics of the player such as balancedness (Bal, a term of in use of body parts in body movement). The mechanism is AIs or the whole game environment that selects next actions of AIs/ changes based on player’s health metrics analyzed from his/her input action before such action is executed. With this mechanism we can stealthy encourage players performing the motions considering more healthy. All experimental results demonstrate that PDA is capable of entertaining player, besides, benefits to the design of serious game which uses for health promotion. There is a promising direction for future research in PDA su

关键词： Health

来源：评论

学校读者我要写书评

暂无评论

Email Spam Detection Using Logistic Regression and Explainable AI

Email Spam Detection Using Logistic Regression and Explainab...

引用

International Conference on Electrical, Computer and Communication engineering (ECCE)

作者： Sumit Kanti Sarker Ratul Bhattacharjee Md Abu Sufian Md Solaiman Ahamed Md Abu Talha Faiza Tasnim K.M. Nazmul Islam Sharia Tasnim Adrita Department of Computer Science & Engineering (CSE) Faculty of Science & Technology (FST) American International University Bangladesh Dhaka Bangladesh Bachelor of Science in Information Technology (BSIT) Cybersecurity Program Concentrations Washington University of Science and Technology (WUST) VA USA Department of Electrical and Electronics Engineering (EEE) Faculty of Engineering (FE) American International University Bangladesh Dhaka Bangladesh Department of Computer Science and Engineering (CSE) Faculty of Science & Engineering Northern University Bangladesh-(NUB) Dhaka Bangladesh

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

Email spam detection is crucial for ensuring a positive user experience and maintaining communication security. This study presents a novel spam detection approach leveraging Logistic Regression, optimized through hyperparameter tuning and enhanced with Explainable Artificial Intelligence. The proposed method is evaluated on a large-scale dataset of emails collected from a real-world spam detection system. Term Frequency-Inverse Document Frequency is utilized for feature extraction, converting email text into numerical representations. XAI introduces interpretability by highlighting critical features such as "pill," "PHP," and "Businessweek," which indicate spam classification patterns. Metrics such as precision, recall, and the confusion matrix are employed to assess the model’s performance, ensuring a balanced evaluation. Hyperparameter optimization using Grid Search CV achieves an optimal regularization parameter (C = 100) and maximum iterations (maxiter=100), resulting in an impressive F1 score of 98.76%, accuracy of 98.82%, precision of 98.62%, and recall of 98.90%.

关键词： Logistic regression Explainable AI Filtering Unsolicited e-mail Computational modeling Predictive models Transformers Frequency conversion Feature extraction Tuning

来源：评论

学校读者我要写书评

暂无评论

PREFALLKD: PRE-IMPACT FALL DETECTION VIA CNN-VIT KNOWLEDGE DISTILLATION

arXiv

引用

arXiv 2023年

作者： Chi, Tin-Han Liu, Kai-Chun Hsieh, Chia-Yeh Tsao, Yu Chan, Chia-Tai Department of Biomedical Engineering National Yang Ming Chiao Tung University Taiwan Research Center for information Technology Innovation Academia Sinica Taiwan Bachelor’s Program in Medical Informatics and Innovative Applications Fu Jen Catholic University Taiwan

Fall accidents are critical issues in an aging and aged society. Recently, many researchers developed "pre-impact fall detection systems" using deep learning to support wearable-based fall protection systems for preventing severe injuries. However, most works only employed simple neural network models instead of complex models considering the usability in resource-constrained mobile devices and strict latency requirements. In this work, we propose a novel pre-impact fall detection via CNN-ViT knowledge distillation, namely PreFallKD, to strike a balance between detection performance and computational complexity. The proposed PreFallKD transfers the detection knowledge from the pre-trained teacher model (vision transformer) to the student model (lightweight convolutional neural networks). Additionally, we apply data augmentation techniques to tackle issues of data imbalance. We conduct the experiment on the KFall public dataset and compare PreFallKD with other state-of-the-art models. The experiment results show that PreFallKD could boost the student model during the testing phase and achieves reliable F1-score (92.66%) and lead time (551.3 ms). Copyright © 2023, The Authors. All rights reserved.

关键词： Fall detection

来源：评论

学校读者我要写书评

暂无评论

Analysis of Wind Wave Characteristics of Offshore Wind Farm-Case Study in Miaoli Sea Area

Analysis of Wind Wave Characteristics of Offshore Wind Farm-...

引用

International Conference on Imaging, Signal Processing and Communication (ICISPC)

作者： Wang Hsing-Yu Fang Hui-Ming Chiang Yun-Chih Department of Shipping Technology National Kaohsiung University of Science and Technology Kaohsiung Taiwan Bachelor Degree Program in Ocean Engineering and Technology National Taiwan Ocean University Keelung Taiwan Center for General Education Tzu Chi University Hualien Taiwan

Taiwan’s outer sea of Miaoli has a met mast. In order to meet the national energy policy, many offshore wind turbines will be built in the future. However, due to the unique geographical conditions in Taiwan, the northeast monsoon is strong in winter, and typhoons in summer. Special meteorological conditions will affect the hydrodynamic conditions of the sea area, further affecting the scouring conditions of offshore wind turbine foundations. To calculate the foundation scouring conditions, it is necessary to understand the local hydrodynamic conditions. This study used the 2016–2019 wave observation data of the met mast for statistical analysis. The analysis results show that the wind and wave height data in the Miaoli area are highly correlated. The direction of the significant wind speed is mainly in NE~NNE, and the considerable wave height is obtained under the same conditions. The joint probability distribution is used to describe the composition of the wave fully. By using a fixed interval, the contours show that most of the measured component waves are: the wave height is 0.5~1.0 m, and the period is 4~5 sec.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Predicting Maintenance Contract Service Renewals using the Internet of Things and Customer Behaviors: A Supplier Perspective

Predicting Maintenance Contract Service Renewals using the I...

引用

Traffic and Logistic engineering (ICTLE), International Conference on

作者： Yogi Tri Prasetyo Paul Dominic Ilagan Completado Krisna Chandra Susanto Michael Nayat Young Satria Fadil Persada Irene Dyah Ayuwati International Bachelor Program in Engineering Yuan Ze University Chung-Li Taoyuan Taiwan School of Industrial Engineering and Engineering Management Mapúa University Manila Philippines Department of Industrial Engineering and Management Yuan Ze University Chung-Li Taoyuan Taiwan Entrepreneurship Department BINUS Business School Undergraduate Program Bina Nusantara University Jakarta Indonesia Department of Information System Institut Teknologi Telkom Surabaya Surabaya Indonesia

The contract terminations for the provision of maintenance services to the tenants of the managed mall affected our organization’s planning, strategy, operations, and revenue. Being able to predict the contract renewals, prevention and readiness plans can be made. Using the data from the computer-aided facilities management (CAFM) software and the available research papers about customer behaviors; the contract renewal outcomes were predicted. In this paper, the operations data of 47 mall tenants (customers) that operates different types of retails were utilized. The data by performance, satisfaction, asset condition and relationship based on the review of the previous studies were categorized. Binary logistic regression was utilized to test the data. The results showed that communication was the strongest influencer to the customers’ behaviors in service contract renewals more than price, satisfaction, and experience. When we understood how to interpret and use the data from the internet of things (IoT), it helped suppliers not only to predict the renewal outcomes, but also build a strategic customer retention program by using the significant variables identified.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Prefallkd: Pre-Impact Fall Detection Via CNN-ViT Knowledge Distillation

Prefallkd: Pre-Impact Fall Detection Via CNN-ViT Knowledge D...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Tin-Han Chi Kai-Chun Liu Chia-Yeh Hsieh Yu Tsao Chia-Tai Chan Department of Biomedical Engineering National Yang Ming Chiao Tung University Taiwan Research Center for Information Technology Innovation Academia Sinica Taiwan Bachelor’s Program in Medical Informatics and Innovative Applications Fu Jen Catholic University Taiwan

关键词： Computational modeling System performance Aging Transformers Reliability Fall detection Usability

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：