检索结果-内蒙古大学图书馆

Temperature Dependent Anomalous Threshold Voltage Modulation of a-IGZO TFT by Incorporating Variant Gate Stresses

ECS Journal of Solid State science and Technology 2024年第6期13卷 065008-065008页

作者： Aslam, Muhammad Chang, Shu-Wei Chen, Yi-Ho Lee, Yao-Jen Li, Yiming Lee, Wen-Hsi Electrical Engineering and Computer Science International Graduate Program National Yang Ming Chiao Tung University Hsinchu 300093 Taiwan Department of Electrical Engineering National Cheng Kung University Tainan 701401 Taiwan Graduate Degree Program of College of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu 300093 Taiwan Institute of Pioneer Semiconductor Innovation Industry Academic Innovation School National Yang Ming Chiao Tung University Hsinchu 300093 Taiwan Department of Electronics and Electrical Engineering National Yang Ming Chiao Tung University Hsinchu 300093 Taiwan

Amorphous indium gallium zinc oxide (a-IGZO) has recently made significant advancement as a key material for electronic component design owing to its compatibility with complementary metal oxide semiconductor technologies. A comprehensive analysis of reliability-related issues is required to determine the true potential of a-IGZO-based devices for next-generation electronics applications. To address this objective, we electrically characterize scaled-channel a-IGZO thin film transistors (TFTs) under positive bias (temperature) stress (PB(T)S). Both PBS and PBTS are characterized by positive and negative V_th shift, respectively, during the various gate stresses. In particular, the negative V_th shift is explained by the generation of donor-like traps stimulated by ionization of oxygen vacancy/hydrogen at elevated temperature. The TFTs exhibit relatively decent stability during the PBS operation. The analysis of devices with variant channel dimensions implies that long-channel devices exhibit relatively higher stability and performance compared to the short-channel ones. We also observe that the V_th can be controllably adjusted by employing the top gate (TG) with bottom gate sweep. Moreover, the stress-induced partial recovery mechanism is experimentally observed owing to detrapping of charges. Generally, the reported results infer a perceptive understanding of scaled-channel a-IGZO-TFTs which helps with shaping performance-enhancement strategies. © 2024 The Author(s). Published on behalf of The Electrochemical Society by IOP Publishing Limited

关键词： amorphous IGZO-TFT electrical instabilities hydrogen-impact scaling impact on reliability

来源：评论

学校读者我要写书评

暂无评论

Deep Learning with Greedy Layer-Wise Compound Scaling for Temperature and Humidity Prediction in Solar Dryer Dome

SSRN

引用

SSRN 2022年

作者： Cenggoro, Tjeng Wawan Elwirehardja, Gregorius Natanael Dominic, Nicholas Setiawan, Karli Eka Rahutomo, Reza Djuana, Endang Gunawan, Fergyanto E. Budiman, Arief S. Romeli, Sugiarto Pardamean, Bens Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program Master of Computer Science Program Bina Nusantara University Jakarta11480 Indonesia Information Systems Department School of Information Systems Bina Nusantara University Jakarta11480 Indonesia Electrical Engineering Department Faculty of Industrial Technology Universitas Trisakti Jakarta11440 Indonesia Industrial Engineering Department BINUS Graduate Program Master of Industrial Engineering Bina Nusantara University Jakarta11480 Indonesia Department of Manufacturing and Mechanical Engineering and Technology Oregon Institute of Technology Klamath FallsOR97601 United States PT. Impack Pratama Industri Jakarta Indonesia

Drying has been an eco-friendly and cost-efficient method to reduce post-harvest losses of agricultural crops. In various countries, the technique has been widely utilized in the form of Solar Dryer Dome (SDD) buildings. Accurate indoor microclimate forecasting is very important to implement smart control systems in SDDs that can maintain the ideal conditions, as the availability of solar energy is limited only at daytimes and the temperature may drop significantly during nighttimes in remote areas. The microclimate variables that play an important role in maintaining ideal environmental conditions include temperature and relative humidity. © 2022, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Enhancing Diagnostic Accuracy for Knee Osteoarthritis Using a Deep Learning Approach

Enhancing Diagnostic Accuracy for Knee Osteoarthritis Using ...

引用

International Symposium on Applied science 2024, ISAS 2024

作者： Raza, Aquib Ching, Congo Tak Shing Liu, Peng-Ta Phan, Thien-Luan Tran, Ngoc-Luan Nguyen, Ha Anh T. Rameez, Mohammad Li, Hung-Chung Linh, Dao Nguyen Phuong Van Hieu, Nguyen Tran, Trung Nghia National Taiwan University Taipei City10673 Taiwan Research Center for Information Technology Academia Sinica Taipei City11529 Taiwan Graduate Institute of Biomedical Engineering National Chung Hsing University Taichung402 Taiwan Department of Electrical Engineering National Chi Nan University Nantou County Taiwan Advanced Plant and Food Crop Biotechnology Center National Chung Hsing University Taichung402 Taiwan International Doctoral Program in Agriculture National Chung Hsing University Taichung402 Taiwan Fall Prevention Center Department of Physical Medicine & Rehabilitation Changhua Christian Hospital Changhua500 Taiwan Department of Physics and Electronic Engineering University of Science Vietnam National University - Ho Chi Minh City Ho Chi Minh City70000 Viet Nam Department of Computer Science University of York York HeslingtonYO10 5DD United Kingdom Undergraduate Program of Intellectual Creativity Engineering National Chung Hsing University Taichung402 Taiwan Ho Chi Minh City72409 Viet Nam HCMUT Vietnam National University Ho Chi Minh City Thu Duc Ho Chi Minh City71308 Viet Nam

This research introduces a deep learning framework that combines convolutional neural networks with autoencoders to improve the diagnostic accuracy of knee osteoarthritis. The study utilized a publicly available dataset from the Mendeley Data repository, where knee joint images were preprocessed using Contrast Limited Adaptive Histogram Equalization to enhance contrast and ensure consistent image sizing. Initially, an autoencoder was employed in an unsupervised manner to learn compressed representations of the data. These representations were then used to train a CNN to classify knee images into 'healthy' and 'osteoarthritic' categories. The model was trained using an 80:20 split for training and testing data, incorporating early stopping and data augmentation techniques to prevent overfitting and enhance generalization. Performance metrics such as accuracy, precision, recall, and the area under the Receiver Operating Characteristic curve (ROCAUC) were used to evaluate the model, resulting in a high test accuracy of 98.95%. The high precision and recall rates further confirmed the model's robustness in diagnosing KOA. To enhance interpretability, Gradient-weighted Class Activation Mapping (Grad-CAM) was applied to identify critical regions in the images that influenced the model's decisions. Additionally, t-Distributed Stochastic Neighbor Embedding (t-SNE) was used to visualize the high-dimensional encoded features in a two-dimensional space, providing deeper insights into how the model differentiates between classes. The promising results of this deep learning approach suggest its potential for broader applications in medical imaging diagnostics. By providing healthcare professionals with a tool that enhances diagnostic accuracy and operational efficiency, this framework lays the foundation for developing scalable, AI-driven diagnostic systems for various complex medical conditions. © 2025 Institute of Physics Publishing. All rights reserved.

关键词： Joints (anatomy)

来源：评论

学校读者我要写书评

暂无评论

To Sharpen or not to Sharpen? On the Effect of Sharpening Filters Applied to Magnified Images 14

To Sharpen or not to Sharpen? On the Effect of Sharpening Fi...

引用

14th International Conference on Digital Image Processing, ICDIP 2022

作者： Emmendorfer, Leonardo R. de Olviveira, Vinicius Menezes Schein, Tatiana T. de Jesus, Junior C. Rodriguez, Bárbara D.A. Electrical Energy Processing Department Federal University of Santa Maria 97105-340 Brazil Center for Computational Science Federal University of Rio Grande 96201-900 Brazil Computational Modeling PhD Program Federal University of Rio Grande 96201-900 Brazil Computer Engineering Graduate Program Federal University of Rio Grande 96201-900 Brazil Institute of Mathematics Statistics and Physics Federal University of Rio Grande 96201-900 Brazil

ISBN: (纸本)9781510657564

Super-resolution algorithms aim to produce magnified high-resolution versions from low-resolution images. Some methods, however, are prone to generate blur during the process. Simple sharpening filters are adopted to alleviate this type of artifact. However, the actual effectiveness of this approach is not clear-cut in the literature. This work evaluates the effect of three simple sharpening filters on the quality of images obtained from super-resolution methods. Two metrics were considered in the evaluation: the Peak signal-to-noise ratio (PSNR) metric, and the Learned Perceptual Image Patch Similarity (LPIPS). One of the filters could consistently improve the LPIPS metric of magnified images from diverse benchmark sets on top of seven super-resolution methods. The increments obtained for the perceptual metric seem to occur due to the sharpening effect. Improvements on PSNR values were not as consistent. © 2022 SPIE.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

AgriField3D: A Curated 3D Point Cloud and Procedural Model Dataset of Field-Grown Maize from a Diversity Panel

arXiv

引用

arXiv 2025年

作者： Kimara, Elvis Hadadi, Mozhgan Godbersen, Jackson Balu, Aditya Jubery, Talukder Li, Yawei Krishnamurthy, Adarsh Schnable, Patrick S. Ganapathysubramanian, Baskar Department of Computer Science Iowa State University Ames United States Translational AI Research and Education Center Ames United States Department of Mechanical Engineering Iowa State University Ames United States Plant Science Institute Iowa State University Ames United States Interdepartmental Genetics and Genomics Graduate Program Iowa State University Ames United States Department of Agronomy Iowa State University Ames United States

The application of artificial intelligence (AI) in three-dimensional (3D) agricultural research, particularly for maize, has been limited by the scarcity of large-scale, diverse datasets. While 2D image datasets are abundant, they fail to capture essential structural details such as leaf architecture, plant volume, and spatial arrangements that 3D data provide. To address this limitation, we present AgriField3D (website), a curated dataset of 3D point clouds of field-grown maize plants from a diverse genetic panel, designed to be AI-ready for advancing agricultural research. Our dataset comprises over 1,000 high-quality point clouds collected using a Terrestrial Laser Scanner, complemented by procedural models that provide structured, parametric representations of maize plants. These procedural models, generated using Non-Uniform Rational B-Splines (NURBS) and optimized via a two-step process combining Particle Swarm Optimization (PSO) and differentiable programming, enable precise, scalable reconstructions of leaf surfaces and plant architectures. To enhance usability, we performed graph-based segmentation to isolate individual leaves and stalks, ensuring consistent labeling across all samples. We also conducted rigorous manual quality control on all datasets, correcting errors in segmentation, ensuring accurate leaf ordering, and validating metadata annotations. The dataset further includes metadata detailing plant morphology and quality, alongside multi-resolution subsampled versions (100k, 50k, 10k points) optimized for various computational needs. By integrating point cloud data of field grown plants with high-fidelity procedural models and ensuring meticulous manual validation, AgriField3D provides a comprehensive foundation for AI-driven phenotyping, plant structural analysis, and 3D applications in agricultural research. © 2025, CC BY-NC-SA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unmasking Illusions: Understanding Human Perception of Audiovisual Deepfakes

arXiv

引用

arXiv 2024年

作者： Hashmi, Ammarah Shahzad, Sahibzada Adil Lin, Chia-Wen Tsao, Yu Wang, Hsin-Min Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Institute of Information Science Academia Sinica Taipei11529 Taiwan Institute of Information Systems and Applications National Tsing Hua University Hsinchu300044 Taiwan Department of Computer Science National Chengchi University Taipei11529 Taiwan Department of Electrical Engineering Institute of Communications Engineering National Tsing Hua University Hsinchu300044 Taiwan Research Center for Information Technology Innovation Academia Sinica Taipei11529 Taiwan Institute of Information Science Academia Sinica Taipei11529 Taiwan

The emergence of contemporary deepfakes has attracted significant attention in machine learning research, as artificial intelligence (AI) generated synthetic media increases the incidence of misinterpretation and is difficult to distinguish from genuine content. Currently, machine learning techniques have been extensively studied for automatically detecting deepfakes. However, human perception has been less explored. Malicious deepfakes could ultimately cause public and social problems. Can we humans correctly perceive the authenticity of the content of the videos we watch? The answer is obviously uncertain;therefore, this paper aims to evaluate the human ability to discern deepfake videos through a subjective study. We present our findings by comparing human observers to five state-of-the-art deepfake detection models. To this end, we used gamification concepts to provide 110 participants (55 native English speakers and 55 non-native English speakers) with a web-based platform where they could access a series of 40 videos (20 real and 20 fake) to determine their authenticity. Each participant performed the experiment twice with the same 40 videos in different random orders. The videos are manually selected from the FakeAVCeleb dataset. We found that all AI models performed significantly better than humans when evaluated on the same 40 videos. The study also reveals that while deception is not impossible, humans tend to overestimate their detection capabilities. Our experimental results may help benchmark human versus machine performance, advance forensics analysis, and enable adaptive countermeasures. © 2024, CC BY.

关键词： Audiovisual

来源：评论

学校读者我要写书评

暂无评论

Understanding Audiovisual Deepfake Detection: Techniques, Challenges, Human Factors and Perceptual Insights

arXiv

引用

arXiv 2024年

作者： Hashmi, Ammarah Shahzad, Sahibzada Adil Lin, Chia-Wen Tsao, Yu Wang, Hsin-Min The Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Institute of Information Science Academia Sinica Taipei11529 Taiwan The Institute of Information Systems and Applications National Tsing Hua University Hsinchu300044 Taiwan The Department of Computer Science National Chengchi University Taipei11529 Taiwan The Department of Electrical Engineering The Institute of Communications Engineering National Tsing Hua University Hsinchu300044 Taiwan The Research Center for Information Technology Innovation Academia Sinica Taipei11529 Taiwan The Institute of Information Science Academia Sinica Taipei11529 Taiwan

Deep Learning has been successfully applied in diverse fields, and its impact on deepfake detection is no exception. Deepfakes are fake yet realistic synthetic content that can be used deceitfully for political impersonation, phishing, slandering, or spreading misinformation. Despite extensive research on unimodal deepfake detection, identifying complex deepfakes through joint analysis of audio and visual streams remains relatively unexplored. To fill this gap, this survey first provides an overview of audiovisual deepfake generation techniques, applications, and their consequences, and then provides a comprehensive review of state-of-the-art methods that combine audio and visual modalities to enhance detection accuracy, summarizing and critically analyzing their strengths and limitations. Furthermore, we discuss existing open source datasets for a deeper understanding, which can contribute to the research community and provide necessary information to beginners who want to analyze deep learning-based audiovisual methods for video forensics. By bridging the gap between unimodal and multimodal approaches, this paper aims to improve the effectiveness of deepfake detection strategies and guide future research in cybersecurity and media integrity. © 2024, CC BY.

关键词： Audiovisual

来源：评论

学校读者我要写书评

暂无评论

Application of factor analysis method to support the users acceptance model of ERP systems implementation 4

Application of factor analysis method to support the users a...

引用

4th International Conference on Combinatorics, Graph Theory, and Network Topology, ICCGANT 2020

作者： Sardjono, W. Sudirwan, J. Priatna, W. Putra, G.R. Information Systems Management Department BINUS Graduate Program Master of Information Systems Management Bina Nusantara University Jakarta11480 Indonesia School of Information Systems Department BINUS Undergraduate Program Bina Nusantara University Jakarta11480 Indonesia Informatics Engineering Engineering Bhayangkara University Jakarta Raya Indonesia Computer Science Study Program Faculty of Mathematics and Natural Sciences Pakuan University Bogor Indonesia

An e-Commerce company has been using an Enterprise Resource Planning (ERP) system for several years, but is still constrained in its implementation, this is reflected in the number of issue/change request tickets submitted by users who have not been able to reach ideal conditions. To overcome this problem, we need an appropriate reference model, the ERP system user acceptance model in companies. The study conducted factors that influence the level of acceptance of SAP ERP users in the XYZ group to then determine a model that is able to explain practically the level of ERP system user acceptance, which in turn can produce concrete proposals to increase ERP system user acceptance. Research is quantitative descriptive using factor analysis and regression analysis methods. The research method uses a questionnaire with a total of 107 valid respondents coming from 8 company names under the XYZ group in 6 Southeast Asian countries. The conclusion of the study is that there are 24 indicators and 4 factors that influence user acceptance of the SAP ERP system. These four factors are the low contribution of the ERP system, the quality of ERP systems and data, the development of ERP systems, and also the low quality of ERP system supporters. It is hoped that by optimizing the value of the 4 factors, the XYZ group can increase user acceptance of the SAP ERP system so that the system can provide benefits expected by the company to be competitive advantage. © 2021 Published under licence by IOP Publishing Ltd.

关键词： Factor analysis

来源：评论

学校读者我要写书评

暂无评论

computer Vision and Fuzzy Logic for Sustainable Indonesian Fisheries 3

Computer Vision and Fuzzy Logic for Sustainable Indonesian F...

引用

3rd International Conference on Eco engineering Development, ICEED 2019

作者： Liawatimena, Suryadiputra Atmadja, Wiedjaja Abbas, Bahtiar Saleh Trisetyarso, Agung Wibowo, Antoni Barlian, Erland Hardanto, Lilik Tri Saputra, Adi Sakinah, Putri Purwoko, Hery Zulardi, Indra Computer Engineering Department Faculty of Engineering Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program - Doctor Computer Science Bina Nusantara University Jakarta11480 Indonesia Industrial Engineering Department Faculty of Engineering Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia Management Department BINUS Business School - Doctor of Research in Management Bina Nusantara University Jakarta11480 Indonesia

Tuna fishing in Indonesia is excessive and if left unchecked, some types of tuna will become extinct within 3-10 years. There is an urgent need to help MMAF for producing more accurate fish catches data. This paper proposed a system that utilizes computer vision, fuzzy logic and Global Positioning System (GPS) for supporting a sustainableIndonesian fishery by recognizing and measuring fish length, determine fish age and where is the catch location. The system can help authority to manage sustainable fisheries management in Indonesia. © 2020 Published under licence by IOP Publishing Ltd.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Drones computer Vision using Deep Learning to Support Fishing Management in Indonesia 3

Drones Computer Vision using Deep Learning to Support Fishin...

引用

3rd International Conference on Eco engineering Development, ICEED 2019

作者： Liawatimena, Suryadiputra Atmadja, Wiedjaja Abbas, Bahtiar Saleh Trisetyarso, Agung Wibowo, Antoni Barlian, Erland Hardanto, Lilik Tri Triany, Natassya Afdalena Faisal Sulistiawan, Jaka Yojana, Albert Cahya Computer Engineering Department Faculty of Engineering Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program - Doctor Computer Science Bina Nusantara University Jakarta11480 Indonesia Industrial Engineering Department Faculty of Engineering Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia Management Department BINUS Business School - Doctor of Research in Management Bina Nusantara University Jakarta11480 Indonesia

It is necessary to study technical factors such as bait used, oceanographic conditions of fishing areas and skipjack tuna trade patterns (Katsuwonus pelamis) as well as other factors in Sulawesi Fisheries. Supporting data to study these technical factors need to be obtained so that it can be improved throughout the year as a skipjack fishing standard with weights taken by the skipjack weights. Therefore, drones and underwater drones with cameras with high-resolution video and images to be fed and processed by computer vision. These drones are operated via Huhate ships which are then used to test efficient technical factors as expected, can be used in determining the size, shape, and colour as well as the analysis of skipjack fish that are in the Fish Aggregating Devices (FADs or Rumpon) in order to manage the management of fisheries managed in Indonesia. © 2020 Published under licence by IOP Publishing Ltd.

关键词： Drones

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：