检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Na, Byunggook Jang, Jaehee Park, Seongsik Kim, Seijoon Kim, Joonoo Jeong, Moon Sik Kim, Kwang Choon Heo, Seon Kim, Yoonsang Yoon, Sungroh Dept. of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of Korea Institute of Science and Technology Seoul Korea Republic of Samsung Advanced Institute of Technology Samsung Electronics Suwon Korea Republic of Mobile Communications Business Samsung Electronics Suwon Korea Republic of ASRI INMC ISRC Interdisciplinary Program in AI Seoul National University Seoul Korea Republic of

Various deep learning applications on smartphones have been rapidly rising, but training deep neural networks (DNNs) has too large computational burden to be executed on a single smartphone. A portable cluster, which connects smartphones with a wireless network and supports parallel computation using them, can be a potential approach to resolve the issue. However, by our findings, the limitations of wireless communication restrict the cluster size to up to 30 smartphones. Such small-scale clusters have insufficient computational power to train DNNs from scratch. In this paper, we propose a scalable smartphone cluster enabling deep learning training by removing the portability to increase its computational efficiency. The cluster connects 138 Galaxy S10+ devices with a wired network using Ethernet. We implemented large-batch synchronous training of DNNs based on Caffe, a deep learning library. The smartphone cluster yielded 90% of the speed of a P100 when training ResNet-50, and approximately 43x speed-up of a V100 when training MobileNet-v1. © 2021, CC BY-NC-ND.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Applying mobility business intelligence concept in analyzing oil palm plantation productivity

引用

AIP Conference Proceedings 2024年第1期3026卷

作者： Andreas Wahyu Krisdiarto Irya Wisnubhadra Anzaludin Samsinga Perbangsa Teddy Suparyanto Bens Pardamean Faculty of Agricultural Technology STIPER Institute of Agriculture Yogyakarta Indonesia Informatics Engineering Department Atma Jaya Yogyakarta University Yogyakarta Indonesia Information Systems Department School of Information Systems Bina Nusantara University Jakarta Indonesia BDSRC Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia

The palm oil business employs almost 20 million people, generates USD 21 billion in revenue, and plays a vital role in Indonesia’s social economy. The Fresh Fruit Bunches (FFB) to Palm Oil Mills (POM) distribution system is one important aspect of fruit quality. Three steps are involved in getting Oil Palm FFB from the plantation to the POM. The first part of the procedure involves cutting FFB from the tree, the second stage involves gathering the fruit at a fruit collection point (FCP), and the third stage involves transporting the fruit to the palm oil mill (POM). As of now, the cost of the FFB transportation is still considerable, accounting for roughly 15% to 20% of the FFB pricing. The use of the Business Intelligence (BI) idea in the oil palm harvesting system is presented in this study as a foundation for creating web-based applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Glaucoma identification with retinal fundus images using deep learning: Systematic review

引用

Informatics in Medicine Unlocked 2025年 56卷

作者： Meedeniya, Dulani Shyamalee, Thisara Lim, Gilbert Yogarajah, Pratheepan Department of Computer Science and Engineering University of Moratuwa Moratuwa 10400 Sri Lanka First-Year Division Faculty of Computing Sri Lanka Institute of Information Technology Malabe 10115 Sri Lanka SingHealth AI Health Program SingHealth Group Singapore 168582 Singapore School of Computing Engineering and Intelligent System Ulster University Londonderry BT48 7JL United Kingdom

Glaucoma is a leading cause of blindness, affecting millions of people worldwide. It is a chronic eye condition that damages the optic nerve and, if left untreated, can lead to vision loss and a decreased quality of life. Therefore, there is a need to explore practical and reliable mechanisms for glaucoma identification. This study systematically reviews deep-learning approaches for glaucoma identification using retinal fundus images from 2018 to 2024. Compared to existing survey studies, we cover the latest research, including several public retinal fundus image datasets, and focus on segmentation, classification based on convolutional neural networks and vision transformers, and explainability. The findings of this study, including comparisons of existing methods and key insights, will assist researchers and developers in identifying the most suitable techniques for glaucoma detection. © 2025 The Authors

关键词： Artificial intelligence Classification Deep learning Explainability Glaucoma Segmentation Trustworthiness

来源：评论

学校读者我要写书评

暂无评论

Nonreciprocal transport in a bilayer of MnBi2Te4 and Pt

arXiv

引用

arXiv 2022年

作者： Ye, Chen Xie, Xiangnan Lv, Wenxing Huang, Ke Yang, Allen Jian Jiang, Sicong Liu, Xue Zhu, Dapeng Qiu, Xuepeng Tong, Mingyu Zhou, Tong Hsu, Chuang-Han Chang, Guoqing Lin, Hsin Li, Peisen Yang, Kesong Wang, Zhenyu Jiang, Tian Wang, Xiao Renshaw Division of Physics and Applied Physics School of Physical and Mathematical Sciences Nanyang Technological University 21 Nanyang Link 637371 Singapore State Key Laboratory of High Performance Computing College of Computer Science and Technology National University of Defense Technology Changsha410073 China Physics Laboratory Industrial Training Center Shenzhen Polytechnic Guangdong Shenzhen518055 China Department of NanoEngineering Program of Chemical Engineering University of California La Jolla San DiegoCA92093-0448 United States Program of Materials Science and Engineering University of California La Jolla San DiegoCA92093-0418 United States Institutes of Physical Science and Information Technology Anhui University Hefei230601 China Fert Beijing Institute MIIT Key Laboratory of Spintronics School of Integrated Circuit Science and Engineering Beihang University Beijing100191 China Beihang-Goertek Joint Microelectronics Institute Qingdao Research Institute Beihang University Qingdao266000 China Shanghai Key Laboratory of Special Artificial Microstructure Materials and Technology School of Physics Science and Engineering Tongji University Shanghai200092 China College of Advanced Interdisciplinary Studies National University of Defense Technology Changsha410073 China Insitute of Physics Academia Sinica Taipei115229 Taiwan College of Intelligence Science and Technology National University of Defense Technology Changsha410073 China National Innovation Institute of Defense Technology Academy of Military Sciences PLA China Beijing100010 China Beijing Academy of Quantum Information Sciences Beijing100084 China Beijing Institute for Advanced Study National University of Defense Technology Changsha410073 China School of Electrical and Electronic Engineering Nanyang Technological University 50 Nanyang Ave 639798 Singapore

MnBi2Te4 (MBT) is the first intrinsic magnetic topological insulator with the interaction of spin-momentum locked surface electrons and intrinsic magnetism, and it exhibits novel magnetic and topological phenomena. Recent studies suggested that the interaction of electrons and magnetism can be affected by the Mn-doped Bi2Te3 phase at the surface due to inevitable structural defects. Here we report an observation of nonreciprocal transport, i.e. current-direction-dependent resistance, in a bilayer composed of antiferromagnetic MBT and nonmagnetic Pt. The emergence of the nonreciprocal response below the Néel temperature confirms a correlation between nonreciprocity and intrinsic magnetism in the surface state of MBT. The angular dependence of the nonreciprocal transport indicates that nonreciprocal response originates from the asymmetry scattering of electrons at the surface of MBT mediated by magnon. Our work provides an insight into nonreciprocity arising from the correlation between magnetism and Dirac surface electrons in intrinsic magnetic topological insulators. © 2022, CC BY.

关键词： Magnetism

来源：评论

学校读者我要写书评

暂无评论

Abnormal association between neural activity and genetic expressions of impulsivity in attention deficit hyperactivity disorder: an Adolescent Brain Cognitive Development study

引用

Biological psychiatry. Cognitive neuroscience and neuroimaging 2025年

作者： Soohyun Jeon Jae-Eon Kang Jundong Hwang Vince D Calhoun Jong-Hwan Lee Department of Brain and Cognitive Engineering Korea University Seoul South Korea. Center for Translational Research in Neuroimaging and Data Science (TReNDS): Georgia State University Georgia Institute of Technology and Emory University Atlanta USA Department of Electrical and Computer Engineering Georgia Institute of Technology Atlanta USA. Department of Brain and Cognitive Engineering Korea University Seoul South Korea Interdisciplinary Program in Precision Public Health Korea University Seoul South Korea McGovern Institute for Brain Research Massachusetts Institute of Technology Boston MA. Electronic address: jonghwan_lee@korea.ac.kr.

BACKGROUND:Impulsivity in highly heritable attention deficit hyperactivity disorder (ADHD) has been studied using neural activity via fMRI or genetic data, but rarely with multivariate methods linking both. We investigated coupled neural activity and gene expression signatures, using parallel independent component analysis (pICA) and Adolescent Brain Cognitive Development data. METHODS:Children with ADHD (n = 394; 63% males) and healthy controls (n = 1,000; 47% males) of European ancestry were included. The subjects were randomly divided into 80% discovery and 20% replication datasets with demographic stratification. We analyzed neural activity and gene expressions from the discovery datasets using pICA and extracted paired independent components (pICs). The loading coefficients of the pICs were utilized to predict behavioral and cognitive data for stop signal task (SST) in replication datasets. RESULTS:We identified three pICs estimated from gene expression in the cortex, cerebellum, and nucleus accumbens. Significant neural activity was mainly localized to the orbital/inferior/middle frontal gyri, rectal gyrus, precuneus, inferior temporal gyrus, inferior parietal lobule, and cerebellum. Significant gene components were associated with immunoglobulin, taste receptor, and immunity-related terms and were overlapped with ADHD-related genes. The extracted fMRI-/Gene-ICs were significantly correlated with mean reaction time, stop signal reaction time of SST, and behavioral inhibition with a large boost in sensitivity when both the paired fMRI-/Gene-ICs and their interaction were used in a multimodal regression analysis. CONCLUSION:We reported biologically plausible pairs of neural activity and gene sets using pICA, which were significantly associated with ADHD impulsivity-related behavioral and cognitive data.

关键词： Attention deficit hyperactivity disorder functional magnetic resonance imaging gene expression imaging genetics parallel independent component analysis stop signal task

来源：评论

学校读者我要写书评

暂无评论

Blueshift: Rebalancing engineering engagement, integrity, and learning outcomes across an electronically-enabled remediation hierarchy

引用

computers in Education Journal 2019年第1期10卷 1-12页

作者： DeMara, Ronald F. Sheikhfaal, Shadi Wilder, Paul J. Chen, Baiyun Hartshorne, Richard Department of Electrical Engineering and Computer Science University of Central Florida OrlandoFL32816 United States Department of Engineering Computer Program and Technology Valencia College OrlandoFL32811 United States Center for Distributed Learning University of Central Florida OrlandoFL32816 United States Division Dean for Learning Sciences Educational Research University of Central Florida OrlandoFL32816 United States

With a growing number of enrollments in engineering programs, more time and energy for tutoring and grading exams/quizzes is necessary. The BLUESHIFT framework utilizes a synergistic combination of faculty, Graduate Teaching Assistants, and educational technologies to provide reliable approaches to not only meet the increased time, cost, and energy efficiency needed for increasing numbers of engineering students, but also to focus on improving the quality of education, skills, and employability of our graduates in computing-related fields. An Evaluation and Proficiency Center (EPC) has been piloted at a large state university, where key elements of the BLUESHIFT learning flow have been integrated into selected undergraduate engineering courses. The EPC integrates computer-based evaluation with a close-knit review and learning cycle based on directed and open tutoring. This approach has received overwhelmingly positive responses from students regarding the effectiveness of pedagogical approaches (i.e., Exemplar Vignettes, content tutoring), assessment models (i.e., electronically delivered quizzes, flexible scheduling, use of testing center), and tutoring strategies (i.e., self-paced, exam results review). Survey results have been positive with respect to student perceptions across a variety of perspectives compared to paper-based delivery. In this manuscript, the BLUESHIFT framework and process, as well as results collected from student performance and perceptions of the initial implementation, will be addressed. © 2019 American Society for engineering Education. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Magneto-optics in a van der Waals magnet tuned by self-hybridized polaritons

arXiv

引用

arXiv 2023年

作者： Dirnberger, Florian Quan, Jiamin Bushati, Rezlind Diederich, Geoffrey Florian, Matthias Klein, Julian Mosina, Kseniia Sofer, Zdenek Xu, Xiaodong Kamra, Akashdeep García-Vidal, Francisco J. Alù, Andrea Menon, Vinod M. Department of Physics City College of New York New YorkNY10031 United States Department of Physics The Graduate Center City University of New York New YorkNY10016 United States Photonics Initiative CUNY Advanced Science Research Center New YorkNY10031 United States Department of Electrical Engineering City College of the City University of New York New YorkNY10031 United States Intelligence Community Postdoctoral Research Fellowship Program University of Washington SeattleWA United States Department of Physics Department of Materials Science and Engineering University of Washington SeattleWA United States Department of Electrical and Computer Engineering Department of Physics University of Michigan Ann ArborMI48109 United States Department of Materials Science and Engineering Massachusetts Institute of Technology CambridgeMA02139 United States Department of Inorganic Chemistry University of Chemistry and Technology Prague Technickaá 5 Prague 6166 28 Czech Republic Universidad Autónoma de Madrid MadridE- 28049 Spain

Controlling quantum materials with light is of fundamental and technological importance. By utilizing the strong coupling of light and matter in optical cavities [1–3], recent studies were able to modify some of their most defining features [4–6]. In this work, we study the magneto-optical properties of a van der Waals magnet that supports strong coupling of photons and excitons even in the absence of external cavity mirrors. In this material – the layered magnetic semiconductor CrSBr – emergent light-matter hybrids called polaritons are shown to significantly increase the spectral bandwidth of correlations between the magnetic, electronic, and optical properties, enabling largely tunable optical responses to applied magnetic fields and magnons. Our results highlight the importance of exciton-photon self-hybridization in van der Waals magnets and motivate novel directions for the manipulation of quantum material properties by strong light-matter coupling. © 2023, CC BY.

关键词： Van der Waals forces

来源：评论

学校读者我要写书评

暂无评论

Mathematical representation of emotion using multimodal recognition model with deep multitask learning

IEEJ Transactions on Electronics, Information and Systems

引用

IEEJ Transactions on Electronics, Information and Systems 2020年第12期140卷 1343-1351页

作者： Harata, Seiichi Sakuma, Takuto Kato, Shohei Computer Science Program Department of Engineering Graduate School of Engineering Nagoya Institute of Technology Gokiso-cho Showa-ku Nagoya-city Aichi466-8555 Japan Frontier Research Institute for Information Science Nagoya Institute of Technology Gokiso-cho Showa-ku Nagoya-city Aichi466-8555 Japan

To emulate human emotions in robots, the mathematical representation of emotion is important for each component of affective computing, such as emotion recognition, generation, and expression. In a method that learns DNN from unimodality and represents emotions by vectors of continuous values (Emotional Space), the acquired Emotional Space is likely to depend on the modality, and considering the number of dimensions of Emotional Space is necessary. In this study, we aim at the acquisition of modality independent Emotional Space. We propose a method of acquiring Emotional Space by integrating multimodalities on a DNN and combining the emotion recognition task and unification task of Emotional Space of each modality. Through the experiments with audio-visual data, we confirmed in various dimensions of Emotional Space that there are differences in Emotional Space acquired from unimodality, and the proposed method can acquire a modality independent Emotional Space. We also investigated the compatibility of the recognition and the unification score by changing the number of dimensions of Emotional Space. Finally, we indicate the proposed method can acquire sufficient Emotional Space with a small number of dimensions, such as five or six dimensions, under this paper's experimental conditions. © 2020 The Institute of Electrical Engineers of Japan.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Outliers detection in time series data: Case study: Provincial waterworks authority 4

Outliers detection in time series data: Case study: Provinci...

引用

4th Joint International Conference on Digital Arts, Media and technology and 2nd ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications engineering, ECTI DAMT-NCON 2019

作者： Khongsrabut, Isara Waiyamai, Kitsana Science Program in Information Technology Computer Engineering Kasetsart University 343/313 Plum Condo Chaengwattana Chaengwattana Rd. Talat Bang Khen Lak Si10210 Thailand

ISBN: (纸本)9781538680728

One main cause of inaccurate forecasts is that data may contain noises and outliers. In the case of the Provincial Waterworks Authority (PWA), the inaccuracy of analyzing and forecasting the number of water users is due to outliers contained in data sources. Some branches of PWA collected errors such as the very high or very low number of water users. This has a direct impact on the quality and reliability of the predictive accuracy output. The removal of the 'outliers' is thus critical for accurate interpretation of the data. The purpose of this paper is to detect outliers in water consumption time series data. We examined two techniques: (1) a method based on autoregressive integrated moving average (ARIMA) time series modeling and (2) median absolute deviation (MAD). A clustering technique (K-Mean) is used as a pre-processing step in order to identify appropriate parameters for the two outliers detection techniques. The results showed that, with the precise parameter values obtained from K-Mean, both ARIMA and MAD performed very well on water consumption time series data. The two techniques are able to generate high sensitivity and specificity outputs. © 2019 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

City scale energy demand forecasting using machine learning based models: A comparative study 2

City scale energy demand forecasting using machine learning ...

引用

2nd International Conference on Data Science, E-Learning and Information Systems, DATA 2019

作者： Al-Bayaty, Hussein Mohammed, Tareq Wang, Weimin Ghareeb, Ahmed Engineering College University of Kirkuk Kirkuk Iraq College of Computer Science and Information Technology University of Kirkuk Kirkuk Iraq Department of Engineering Technology University of North Carolina at Charlotte Charlotte United States Program University of North Carolina at Charlotte Charlotte United States

ISBN: (纸本)9781450372848

The rapid change during the last decades in the activities of people and the global energy trends in the usage of daily equipment, led to massive shortage not just in the energy sector, but almost in all of the related sectors, especially in the developing countries. Consequently, predicting energy demand is a vital issue in order to fulfill the future strategy of any country. In this study, four machine learning algorithms have been deployed in order to forecast the short-term demand load for the city of Kirkuk based on hourly recorded real data. This data-driven study has taken in count the metrological weather data as a function of electrical energy demand. The stages of developing the models are discussed, and the forecasting models validated using 6 months of out-of-sample data. Among the four (Machine Learning (ML) models, two predictive algorithms (i.e. Artificial Neural Network (ANN) and Decision Trees (DTs)) showed better predictive capabilities achieving lower error rates. © 2019 Association for Computing Machinery. ACM

关键词： Data mining

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：