检索结果-内蒙古大学图书馆

SFA-Net: A Selective Features Absorption Network for Object Detection in Rainy Weather Conditions

IEEE Transactions on Neural Networks and Learning Systems 2023年第8期34卷 5122-5132页

作者： Huang, Shih-Chia Hoang, Quoc-Viet Le, Trung-Hieu National Taipei University of Technology Department of Electronic Engineering Taipei10608 Taiwan National Taipei University of Technology International Graduate Program in Electrical Engineering and Computer Science Taipei10608 Taiwan Hung Yen University of Technology and Education Faculty of Information Technology Hungyen 17000 Viet Nam

In recent years, object detection approaches using deep convolutional neural networks (CNNs) have derived major advances in normal images. However, such success is hardly achieved with rainy images due to lack of visibility. Aiming to bridge this gap, in this article, we present a novel selective features absorption network (SFA-Net) to improve the performance of object detection not only in rainy weather conditions but also in favorable weather conditions. SFA-Net accomplishes this objective by utilizing three subnetworks, where the feature selection subnetwork is concatenated with the object detection subnetwork through the feature absorption subnetwork to form a unified model. To promote further advancement in object detection impaired by rain, we propose a large-scale rainy image dataset, named srRain, which contains both synthetic rainy images and real-world rainy images for training and testing purposes. srRain is comprised of 25 900 rainy images depicting diverse driving scenarios in the presence of rain with a total of 181 164 instances interpreting five common object categories. Experimental results display that our SFA-Net reaches the highest mean average precision (mAP) of 77.53% on a normal image set, 62.52% on a synthetic rainy image set, 37.34% on a collected natural rainy image set, and 32.86% on a published real rainy image set, surpassing current state-of-the-art object detectors and the combination of image deraining and object detection models while retaining a high speed. © 2012 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Experiment and simulation to determine the optimum orientation of building-integrated photovoltaic on tropical building façades considering annual daylight performance and energy yield

引用

Energy and Built Environment 2024年第3期5卷 414-425页

作者： Rizki A.Mangkuto Dhian Nur Aziz T.Tresna Ikhwan M.Hermawan Justin Pradipta Nurul Jamala Beta Paramita Atthaillah Building Physics Research Group Faculty of Industrial TechnologyInstitut Teknologi BandungLabtek VIJl.Ganesha 10Bandung 40132Indonesia Engineering Physics Program Faculty of Industrial TechnologyInstitut Teknologi BandungLabtek VIJl.Ganesha 10Bandung 40132Indonesia Engineering Physics Research Group Faculty of Industrial TechnologyInstitut Teknologi BandungLabtek VIJl.Ganesha 10Bandung 40132Indonesia Department of Architecture Faculty of EngineeringHasanuddin UniversityJl.Poros Malino Km.6Gowa 92171Indonesia Architecture Study Program Faculty of Technology and Vocational EducationUniversitas Pendidikan IndonesiaJl.Dr.Setiabudhi 229Bandung 40152Indonesia Architecture Program Faculty of EngineeringUniversitas MalikussalehJl.Cot Teungku NieAceh Utara 24355Indonesia

Building-Integrated Photovoltaic(BIPV)on vertical façades is a potential PV application in today’s *** performance of BIPV on façades is significantly influenced by the façade *** tropical cities,the optimum façade orientation,in terms of maximum energy yield and daylight performance,cannot be simply determined,due to relatively symmetrical sun path throughout the *** study therefore aims to determine the optimum orientation for BIPV on tropical building faç*** achieve the objective,experiment,modelling,and computational simulation are conducted to evaluate the BIPV energy yield and to predict the indoor daylight performance in a scale-model building with a 105Wp monocrystalline silicon PV,facing each cardinal orienta-tion in Bandung,*** South orientation yields practically zero ASE_(1000,250),providing the best annual daylight performance,and yielding the most desirable value in four out of five daylight *** greatest annual energy yield is at the North orientation,providing 179-186 kWh(95%prediction interval)per year,but with larger uncertainty compared to that at the South,due to direct sunlight *** on three different objective functions,the South orientation is considered optimum for placing the BIPV panel on the prototype façade in the location.

关键词： Building-integrated photovoltaic Orientation Daylight metric Energy yield Tropical building façade

来源：评论

学校读者我要写书评

暂无评论

Design Implementation of Flood Early Warning System for Residential Monitoring

Design Implementation of Flood Early Warning System for Resi...

引用

International Conference on Radar, Antenna, Microwave, Electronics, and Telecommunications (ICRAMET)

作者： Joni Welman Simatupang Thariq Auliya Arrazaq Electrical Engineering Study Program Faculty of Engineering President University Cikarang Indonesia

The efforts to mitigate floods are necessary. One of the tools that can contribute to flood mitigation is the Flood Early Warning System (FEWS). The main goal of this study is to design a prototype of FEWS that can be easily used anywhere, anytime, and provide accurate water level readings. The prototype system is designed using an Ultrasonic Sensor for water level detection, an alarm system, and Blynk as a web and mobile dashboard. The prototype consists of four main components: Ultrasonic Sensor HC-SR04, Arduino Nano, NodeMCU, and HC-12. It comprises two units: a transmitter unit and a receiver unit. To determine the accuracy and consistency of the Ultrasonic Sensor, the author conducted testing using calibration, non-continuous, and continuous methods. The accuracy obtained was 99.71%. Additionally, the author observed high consistency in the readings of the ultrasonic sensor, as evident from continuous sensor reading test results. Furthermore, the receiver unit successfully displayed output according to the water level threshold for each condition. Additionally, the Blynk web and mobile dashboard were able to display output as per the design. However, we suggest adding data logging features and also solar panels as a renewable power source to support the improved prototype system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of Color Detection Based on Camera Infrared Filter with Python Image Processing 22

Development of Color Detection Based on Camera Infrared Filt...

引用

22nd IEEE Student Conference on Research and Development, SCOReD 2024

作者： Leonardy, Joshu Aflah, Nawal Zuhdaniel Salim, Mohd Rashidi Bin Ibrahim, Mohd Haniff Bin Manap, Hadi Bin Tresna, Wildan Panji Universiti Teknologi Malaysia Faculty of Electrical Engineering Johor Bahru Malaysia The Republic of Indonesia Defense University Military Physics Study Program Bogor Indonesia University Malaysia Pahang Al Sultan Abdullah Faculty of Electrical & Electronic Engineering Technology Pekan Malaysia National Research and Inovation Agency Indonesia Research Center for Photonics South Tangerang Indonesia

ISBN: (纸本)9798331510077

This research explores the use of a modified infrared (IR) camera equipped with a high-pass filter to distinguish between natural objects (vegetation) and artificial objects (synthetic military uniforms) in an environment where vegetation makes objects difficult to detect. In military operations, especially guerrilla warfare in tropical forests, detecting enemies camouflaged in vegetation makes it difficult to distinguish targeted objects. Visible light cameras usually struggle to distinguish between synthetic and natural colors. This methodology involves the use of Python programming and various libraries, such as Computer Vision (CV), to process images captured by modified cameras. A graphical user interface (GUI) was developed to analyze color values, focusing on the red, green, and blue spectra. The results show that the modified IR camera can more effectively separate synthetic and natural object color peaks compared to a standard visible light camera, offering potential applications in military reconnaissance and sniper operations. This research demonstrates how image processing can improve object detection in complex environments. © 2024 IEEE.

关键词： High pass filters

来源：评论

学校读者我要写书评

暂无评论

Application of the K-Medoids Clustering Model and Borda Decision Group in Viewing Flood Area Groupings in North Aceh Regency

Application of the K-Medoids Clustering Model and Borda Deci...

引用

Artificial Intelligence and Image Processing (IWAIIP), International Workshop on

作者： Wahyu Fuadi Ilham Sahputra Dedi Fariadi Agustinar Informatics Engineering Study Program Faculty of Engineering Universitas Malikussaleh Lhokseumawe Indonesia Information Systems Study Program Faculty of Engineering Universitas Malikussaleh Lhokseumawe Indonesia Electrical Engineering Study Program Faculty of Engineering Universitas Malikussaleh Lhokseumawe Indonesia

The importance of the K-Medoid model in viewing disaster-prone areas in each sub-district in North Aceh. The advantage of the k-medoid model results is that it has better cluster centers than other models. The novelty of this research is the cluster results are assessed by each decision maker using the Borda group model in providing flood disaster assistance or areas that are a priority for handling, which are included in the flood-prone cluster. Therefore, this research is important because it can be used to identify areas most severely affected by flooding. This research aims to analyze and identify the impact of flood hazards based on grouping and decision-making using the Borda group model in each sub-district in North Aceh. The results of the k-medoids model show 3 clusters that can see potential areas for flood disasters, namely very vulnerable. There are six sub-districts. For the k-medoids results, ten sub-districts are vulnerable. Lastly, the safe zones are 11 sub-districts. This research’s k-medoid model analysis is more precise in seeing clusters of places that are potentially affected by flooding based on spatial maps of their nearest neighboring areas. The percentage of each cluster is as follows: Cluster 1 is 4%, Cluster 2 is 55%, and Cluster 3 is 41%. The k-medoid model provided this result after three iterations, with a closeness difference of 1.594510537. The results of the Borda model group research can be used as a recommendation for the areas that receive the highest priority in disaster management.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Echoes of Tradition: Virtual-Reality Media in Improving Spatial Space Experience 3D Virtual Tour of Kampung Adat Pulo Garut, West Java, Indonesia

Echoes of Tradition: Virtual-Reality Media in Improving Spat...

引用

STEM education Conference (iSTEM-Ed), International

作者： M.F. Rahman A.Y. Permana I Susanti J. Akbardin K. Wijaya S. Handayani Architecture Study Program Faculty of Technology and Vocational Education Universitas Pendidikan Indonesia Bandung Indonesia Civil Engineering Study Program Faculty of Technology and Vocational Education Universitas Pendidikan Indonesia Bandung Indonesia Architecture Study Program Faculty of Civil Engineering and Planning Universitas Kebangsaan Republik Indonesia Indonesia Bandung Indonesia Agro-industrial Education Study Program Faculty of Technology and Vocational Education Universitas Pendidikan Indonesia Bandung Indonesia

ISBN: (数字)9798350365979

ISBN: (纸本)9798350365986

In the current digital era, virtual reality (VR) technology is rapidly expanding across various fields, including education and cultural preservation. This technology offers immersive opportunities to explore and experience architectural spaces, promising increased understanding and learning motivation. Despite being relatively new in Indonesia, the application of VR has shown significant potential for education and cultural preservation through the implementation of a 3D virtual tour in Kampung Adat Pulo Garut. Therefore, this research aimed to develop VR media to enhance users' spatial experience and preserve the cultural values of Kampung Adat Pulo Garut through interactive learning. The method used was Research and Development (R&D) through the Multimedia Development Life Cycle (MDLC) model. The equipment used was LiDAR Scanner FJD Trion P1 Series, DJI Mavic Air 2S Drone, and Sony A6000 Camera. The method used included aerial and terrestrial mapping, 3D modeling, and the development of virtual environments through Unreal Engine. The developmental process included various stages, namely concept, design, material collection, compilation, testing, and distribution. The result showed an interactive 3D virtual tour of Kampung Adat Pulo Garut, called “Echoes of Tradition.” Unreal Engine was found to enable detailed visualization of traditional architecture and village environments with high accuracy and interactivity. The final product offered an immersive learning experience, enriching users' experience, and enabling digital preservation of cultural heritage. The next step, to get an overview of the research results, used a questionnaire as an instrument which was distributed to a total of 250 respondents. Furthermore, the potential implication of VR in education and cultural preservation was identified, guiding similar applications in the future. By improving accessibility and engagement in spatial and cultural learning, VR offered new avenues in education and cultu

关键词： Visualization Three-dimensional displays education Virtual environments Media User experience Cultural differences

来源：评论

学校读者我要写书评

暂无评论

ML-Agents in Kart Racing Game using Microgame 17

ML-Agents in Kart Racing Game using Microgame

引用

17th International Conference on Telecommunication Systems, Services, and Applications, TSSA 2023

作者： Ana, Afina Anfa Pratama, Vitradisa Sukoco, Agus Prihatmanto, Ary Setijadi Nurmalasari, Rin Rin Juhana, Agus Institut Teknologi Bandung School of Electrical Engineering and Informatics Bandung Indonesia Universitas Mayasari Bakti Departement of Informatics Tasikmalaya Indonesia UIN Sunan Gunung Djati Department of Electrical Engineering Bandung Indonesia Universitas Pendidikan Indonesia Multimedia Education Study Program Bandung Indonesia

ISBN: (纸本)9798350309164

This paper presents an innovative approach to integrating ML-Agents into a microgame-based kart racing environment, showcasing the potential for enhancing gameplay experiences through AI-driven opponents. Kart Unity Game is a racing game that uses small motorized vehicles but still uses the concept of racing in the real world. One of the racing game development platforms is Unity. Unity has developed a platform, Unity Karting Microgame, which users can modify. Unity Karting Microgame applies self-driving to ML-Agents trained and designed to drive their karts with suitable sensors and actuators. The method used to develop the game is to modify the racetrack and modify ML-Agents to make the game more exciting and fun. As a result of this study, successful implementation of ML-Agents in a microgame-based kart racing environment. The study highlights the potential of using Unity ML-Agents to create AI-driven opponents that enrich gameplay experiences. Games can run well and seem varied. ML-Agents can also control their karts on their lanes. Thus, kart racing games can be implemented. © 2023 IEEE.

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

Mapping the Research Landscape : A Bibliometric study of Flow Rate Sensors and Horizontal Water Pipe

Mapping the Research Landscape : A Bibliometric Study of Flo...

引用

International Conference on Computing, engineering, and Design (ICCED)

作者： Anang Suryana Anggy Pradiftha Junfithrana Abd Kadir Mahamad Wahyu Mulyo Utomo Osep Hijuzaman Panji Narputro Faculty of Electrical and Electronics Engineering Universiti Tun Hussein Onn Malaysia Batu Pahat Malaysia Faculty of Electrical and Electronics Engineering Nusa Putra University Sukabumi Indonesia Industrial Engineering Study Program STT Wastukancana Bandung Indonesia Electrical Engineering Study Program Nusa Putra University Sukabumi Indonesia

ISBN: (数字)9798331529376

ISBN: (纸本)9798331529383

The significance of flow rate sensors and horizontal water pipes in various applications highlights their crucial role in enhancing fluid dynamics monitoring and management. This study aims to map the research landscape through a bibliometric analysis of flow rate sensors and horizontal water pipes. The analysis includes author analysis, affiliation analysis, country or territory analysis, source analysis, keyword analysis, trend topic analysis, and thematic map analysis. Bibliometric analysis helps policymakers, industry professionals, and researchers navigate the extensive body of literature, ensuring that efforts in flow rate sensor technology and horizontal water pipe research align with current trends and contribute effectively to advancing knowledge in these areas. The results will serve as a valuable guide, helping stakeholders understand the evolving research landscape, make informed decisions, and gain deeper insights into the trajectory of research in flow rate sensors and horizontal water pipes.

关键词： Industries Waste reduction Fluid dynamics System performance Bibliometrics Market research Sensors Trajectory Optimization Monitoring

来源：评论

学校读者我要写书评

暂无评论

Challenging body shaming with grading techniques in the fashion industry

引用

Social Sciences and Humanities Open 2025年 11卷

作者： Supadmi Irianti, Agus Hery Marniati Wiana, Winwin Nafiah, Annisau Department of Culinary and Fashion Education Faculty of Engineering Universitas Negeri Malang Malang Indonesia Fashion Technology Education Study Program Faculty of Engineering State University of Surabaya Surabaya Indonesia Fashion Education Study Program Faculty of Engineering and Industry Education Universitas Pendidikan Indonesia Bandung Indonesia

Body shaming remains a prevalent concern in the fashion business, as conventional beauty standards sometimes exclude persons with varied body shapes. This study investigates the effect of pattern grading and motif grading approaches on reducing body shaming, particularly in the context of batik shirt production. The research highlights how various grading systems improve garment fit and cater to a broader range of body shapes, thereby challenging body shaming and promoting body inclusivity. The research examines the impact of grading methods on tailors' engagement, skill level, and self-assurance, showing that these methods enhance garment quality and empower industry professionals. This study employed a mixed-method approach, combining the creation of graded batik shirt prototypes with quantitative analysis using Partial Least Squares Structural Equation Modeling (PLS-SEM). The research indicates that motif grading maintains the traditional validity of batik designs while facilitating size modifications. Tailors expressed strong interest in adopting grading techniques, and the study proposes inclusive design solutions that effectively address body shaming in a traditional manner. The results suggest that integrating grading methodologies into fashion processes can foster a more inclusive and diverse business. Suggestions are offered for fashion designers, educational institutions, and companies to promote the implementation of grading techniques that accommodate body variation. This research identifies future research opportunities, such as incorporating technology in grading and formulating design methods to mitigate body shaming in the fashion industry. © 2025 The Authors

关键词： Batik shirts Body inclusivity Body shaming Motif grading Pattern grading

来源：评论

学校读者我要写书评

暂无评论

Emerging Potential on Laser Engraving Method in Fabricating Mold for Microfluidic Technology 1

引用

2nd International Conference on Electronics, Biomedical engineering, and Health Informatics, ICEBEHI 2021

作者： Yusro, Muhammad Biomedical Engineering Study Program Faculty of Telecommunication and Electrical Engineering Institut Teknologi Telkom Purwokerto Jalan D.I. Panjaitan 128 Purwokerto Indonesia

ISBN: (数字)9789811918049

ISBN: (纸本)9789811918032

The microfluidic device needs multi-step fabrication, and this process relatively takes time because it requires meticulous treatment. This approach, using laser engraving, reduces the conventional mold fabrication step which is created by soft lithography in the cleanroom. For biomedical research purposes, a certain dimension of the microfluidic design needs to be achieved. Meanwhile, different material needs different variable setting in laser engraving. This article’s research objectives are seeking the optimum variable to achieve targeted dimension and investigating the influenced parameters lead to better understand the laser engraving fabrication process. The Poly (methyl methacrylate) (PMMA) sheets had been engraved to a particular dimension refers to the mold design that uses in the microfluidic device. The result showed that parameters meet the desired dimension found at values: 1000 for resolution, 95 for power, 500 for frequency, and 60 for speed. It can be noted that these adjusted parameters were performed for a single passage. Moreover, these influenced parameters also had been investigated to see their effect related to the engraving result. The result showed that the speed was the most significant parameter meanwhile the frequency has a stagnant value in the laser engraving process. This study also observed that higher resolution could smoother the rough surface. This study emerges the potential of laser engraving as rapid prototyping machinery for microfluidic technology. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Microfluidics

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：