检索结果-内蒙古大学图书馆

computer System, Information Technology, and electrical engineering (COSITE), International Conference on

作者： Gregorius Natanael Elwirehardja Mahmud Isnan Anzaludin Samsinga Perbangsa Kahlil Muchtar Bens Pardamean Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Information System Department School of Information Systems Bina Nusantara University Jakarta Indonesia Department of Electrical and Computer Engineering Universitas Syiah Kuala Banda Aceh Indonesia Computer Science Department BINUS Graduate Program -Master of Computer Science Bina Nusantara University Jakarta Indonesia

Depressive Disorders (DD) is one of the most prevalent mental disorders in the world that may lead to suicide cases. To prevent the latter, ubiquitous early detection systems may be effective. Recent studies have since researched the development of such systems by exploiting several forms of data, including video, audio, Ecological Momentary Assessments (EMA), and passive sensing data using sensors embedded in mobile devices. To summarize the trends, opportunities, and existing challenges in this field, this study reviewed 15 papers to answer four research questions. EMA was the most popular data to be used in this task, but other approaches, such as using video, audio, and typing behaviors, may be considered due to the subjectivity of EMA. These data were typically recorded using smartphones and analyzed using Machine Learning (ML). However, most of the developed systems had yet to be implemented. Overall, it was concluded that further studies may need to explore usages of more objective data in multimodal approaches as well as consider using Mobile Cloud Computing (MCC) to deploy these systems to provide more effective and efficient diagnoses. Future studies must also take into account the existing challenges of the data and infrastructures, such as the weaknesses of several data types, limitations of mobile devices, as well as the challenges of diagnosis approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sodium-ion battery cycle life prediction using machine learning

Sodium-ion battery cycle life prediction using machine learn...

引用

International Conference on Green Energy, Computing and Intelligent Technology 2024 (GEn-CITy 2024)

作者： Linfeng Liu Filbert H. Juwono W. K. Wong Erick Purwanto Tingyan Jin Yuyang Zhen Sustainable Energy Technology Program Xi'an Jiaotong-Liverpool University Suzhou People's Republic of China Department of Electrical and Electronic Engineering Xi'an Jiaotong-Liverpool University Suzhou People's Republic of China Department of Electrical and Computer Engineering Curtin University Malaysia Miri Malaysia Department of Computing Xi'an Jiaotong-Liverpool University Suzhou People's Republic of China School of Mechanical and Electrical Engineering Beijing Information Science and Technology University Beijing People's Republic of China School of Instrument Science and Technology Beijing University of Technology Beijing People's Republic of China

ISBN: (数字)9781837242863

In this study, we explore the classification and prediction capabilities of three models—Genetic programming (GP), Logistic Regression (LR), and the Kolmogorov-Arnold Network (KAN)—on the task of sodium-ion battery life prediction. By leveraging a dataset composed of multiple battery characteristics, we aim to determine the remaining power of sodium-ion batteries using these machine learning models. The KAN model, being a novel approach, demonstrates superior performance across various metrics, including accuracy, precision, recall, and F1 score, when compared to the other two models. This highlights the potential of KAN as a robust model for complex classification tasks in the field of battery life prediction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluating Conveyor Belt Health With Signal Processing Applied to Inertial Sensing

Evaluating Conveyor Belt Health With Signal Processing Appli...

引用

International Workshop on Secure Internet of Things (SIoT)

作者： Saulo Neves Matos Otávio Ferracioli Coletti Fernando Ugucioni Filho Ricardo C. C. L. de Carvalho Thomas V. B. Pinto Luiz G. D. de Barros Caetano Mazzoni Ranieri Bruno Eduardo Lopes Jó Ueyama Gustavo Pessin Institute of Mathematics and Computer Science University of sao Paulo Brazil Sao Carlos School of Engineering University of Sao Paulo Brazil Vale Institute of Technology Ouro Preto Brazil Graduate Program in Electrical Engineering Universidade Federal of Minas Gerais Belo Horizonte MG Brazil Vale -SA Vitoria Brazil

Conveyor belts are commonly used in the mining industry for efficient material transport. However, they are prone to failures such as idler anomalies, belt tears, and misalignment. Current monitoring systems only evaluate the conveyor or idle belt's condition at the installation point. This study proposes a method to detect faults in conveyor belts, specifically idler anomalies and belt deviation, using two IMUs installed at the lateral extremities of the belt to evaluate its health along its route. In a reduced-scale conveyor belt, we conducted experiments by collecting gyroscopes and accelerometer data in various scenarios, including normal conditions and anomaly situations. We modified the idlers' physical structure or changed the belt tracks to create these scenarios. We used similarity analysis techniques to compare the data collected and performed statistical hypothesis analysis to observe the influence of the anomaly scenarios on the gyroscope and accelerometer data. We used Dynamic Time Warping (DTW) for gyroscope data to compare ground truth with anomaly scenarios. For the acceleration data, we performed vibration analysis by converting the time domain data to the frequency using Fast Fourier Transform (FFT) and evaluating the difference in spectral density between the reference and anomaly data. Statistical hypothesis analysis revealed that anomaly scenar-ios influenced the gyroscope x-axis and z-axis more. According to the spectral density analysis of the accelerometer, it was revealed that belt misalignment on the y-axis may be detected.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Noise-Robust Deep Spiking Neural Networks with Temporal Information 21

Noise-Robust Deep Spiking Neural Networks with Temporal Info...

引用

Proceedings of the 58th Annual ACM/IEEE Design Automation Conference

作者： Seongsik Park Dongjin Lee Sungroh Yoon Department of Electrical and Computer Engineering Seoul National University Seoul South Korea and Institute of New Media and Communications Seoul National University Seoul South Korea Department of Electrical and Computer Engineering Seoul National University Seoul South Korea Department of Electrical and Computer Engineering Seoul National University Seoul South Korea and Institute of New Media and Communications Seoul National University Seoul South Korea and ASRI and Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul South Korea

ISBN: (纸本)9781665432740

Spiking neural networks (SNNs) have emerged as energy-efficient neural networks with temporal information. SNNs have shown a superior efficiency on neuromorphic devices, but the devices are susceptible to noise, which hinders them from being applied in real-world applications. Several studies have increased noise robustness, but most of them considered neither deep SNNs nor temporal information. In this paper, we investigate the effect of noise on deep SNNs with various neural coding methods and present a noise-robust deep SNN with temporal information. With the proposed methods, we have achieved a deep SNN that is efficient and robust to spike deletion and jitter.

关键词： neural coding

来源：评论

学校读者我要写书评

暂无评论

The Effects of Boron Doping on the Bulk and Surface Acoustic Phonons in Single-Crystal Diamond

arXiv

引用

arXiv 2022年

作者： Guzman, Erick Kargar, Fariborz Angeles, Frank Meidanshahi, Reza Vatan Grotjohn, Timothy A. Hardy, Aaron Muehle, Matthias Wilson, Richard B. Goodnik, Stephen Balandin, Alexander A. Nano-Device Laboratory Phonon Optimized Engineered Materials Center Department of Electrical and Computer Engineering University of California RiversideCA92521 United States Department of Mechanical Engineering Materials Science and Engineering Program University of California RiversideCA92521 United States School of Electrical Computer and Energy Engineering Arizona State University TempeAZ85281 United States Department of Electrical and Computer Engineering Michigan State University East LansingMI48824 United States Fraunhofer USA Center Midwest East LansingMI48824 United States

We report the results of the investigation of bulk and surface acoustic phonons in the undoped and boron-doped single-crystal diamond films using the Brillouin-Mandelstam light scattering spectroscopy. The evolution of the optical phonons in the same set of samples was monitored with Raman spectroscopy. It was found that the frequency and the group velocity of acoustic phonons decrease non-monotonically with the increasing boron doping concentration, revealing pronounced phonon softening. The change in the velocity of the shear horizontal and the high-frequency pseudo-longitudinal acoustic phonons in the degenerately doped diamond, as compared to the undoped diamond, was as large as ~ 15% and ~12%, respectively. As a result of boron doping, the velocity of the bulk longitudinal and transverse acoustic phonons decreased correspondingly. The frequency of the optical phonons was unaffected at low boron concentration but experienced a strong decrease at the high doping level. The density-functional-theory calculations of the phonon band structure for the pristine and highly-doped sample confirm the phonon softening as a result of boron doping in diamond. The obtained results have important implications for thermal transport in heavily doped diamond, which is a promising material for ultra-wide-band-gap electronics. Copyright © 2022, The Authors. All rights reserved.

关键词： Density functional theory

来源：评论

学校读者我要写书评

暂无评论

Low-coherence semiconductor light sources: devices and applications

npj Nanophotonics

引用

npj Nanophotonics 2024年第1期1卷 1-19页

作者： Hang Lu Omar Alkhazragi Yue Wang Nawal Almaymoni Wenbo Yan Wahyu Hendra Gunawan Heming Lin Tae-Yong Park Tien Khee Ng Boon S. Ooi Photonics Laboratory Electrical and Computer Engineering Program Division of Computer Electrical and Mathematical Sciences and Engineering (CEMSE) King Abdullah University of Science and Technology (KAUST) Thuwal 23955-6900 Kingdom of Saudi Arabia

Since the invention of the laser, there have been countless applications that were made possible or improved through exploiting its multitude of unique advantages. Most of these advantages are mainly due to the high degree of coherence of the laser light, which makes it directional and spectrally pure. Nevertheless, many fields require a moderate degree of temporal or spatial coherence, making conventional lasers unsuitable for these applications. This has brought about a great interest in partially coherent light sources, especially those based on semiconductor devices, given their efficiency, compactness, and high-speed operation. Here, we review the development of low-coherence semiconductor light sources, including superluminescent diodes, highly multimode lasers, and random lasers, and the wide range of applications in which they have been deployed. We highlight how each of these applications benefsits from a lower degree of coherence in space and/or time. We then discuss future potential applications that can be enabled using new types of low-coherence light.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Lesion-symptom mapping with NIHSS sub-scores in ischemic stroke patients

引用

Stroke & Vascular Neurology 2022年第2期7卷 124-131页

作者： Deepthi Rajashekar Matthias Wilms M Ethan MacDonald Serena Schimert Michael D Hill Andrew Demchuk Mayank Goyal Sean P Dukelow Nils Daniel Forkert Biomedical Engineering Graduate Program Hotchkiss Brain InstituteUniversity of CalgaryCalgaryAlbertaCanada Department of Radiology Cumming School of MedicineUniversity of CalgaryCalgaryAlbertaCanada Hotchkiss Brain Institute University of CalgaryCalgaryAlbertaCanada Department of Clinical Neurosciences University of CalgaryCalgaryAlbertaCanada Department of Electrical and Computer Engineering University of CalgaryCalgaryAlbertaCanada Department of Community Health Sciences Cumming School of MedicineUniversity of CalgaryCalgaryAlbertaCanada Department of Medicine Cumming School of MedicineUniversity of CalgaryCalgaryAlbertaCanada Alberta Children's Hospital Research Institute University of CalgaryCalgaryABCanada

Background Lesion-symptom mapping(LSM)is a statistical technique to investigate the population-specific relationship between structural integrity and post-stroke clinical *** clinical practice,patients are commonly evaluated using the National Institutes of Health Stroke Scale(NIHSS),an 11-domain clinical score to quantitate neurological deficits due to *** far,LSM studies have mostly used the total NIHSS score for analysis,which might not uncover subtle structure–function relationships associated with the specific sub-domains of the NIHSS ***,the aim of this work was to investigate the feasibility to perform LSM analyses with sub-score information to reveal category-specific structure–function relationships that a total score may not *** Employing a multivariate technique,LSM analyses were conducted using a sample of 180 patients with NIHSS assessment at 48-hour post-stroke from the ESCAPE *** NIHSS domains were grouped into six categories using two *** was conducted for each category of the two groupings and the total NIHSS *** Sub-score LSMs not only identify most of the brain regions that are identified as critical by the total NIHSS score but also reveal additional brain regions critical to each function category of the NIHSS assessment without requiring extensive,specialised *** These findings show that widely available sub-scores of clinical outcome assessments can be used to investigate more specific structure–function relationships,which may improve predictive modelling of stroke outcomes in the context of modern clinical stroke assessments and neuroimaging.

关键词： patients score category

来源：评论

学校读者我要写书评

暂无评论

Brain Tumor Detection and Segmentation Using Deep Learning Models

Brain Tumor Detection and Segmentation Using Deep Learning M...

引用

Artificial Intelligence (WSAI), World Symposium on

作者： Moses Kazeem Abiodun Abidemi Emmanuel Adeniyi Joseph Bamidele Awotunde Halleluyah Aworinde George Tinuoye Agbotiname Lucky Imoize Chun-Ta Li Cheng-Chi Lee Department of Computer Science Landmark University Omu-Aran Kwara State Nigeria Department of Computer Science Bowen University Iwo Osun State Nigeria Department of Computer Science University of Ilorin Ilorin Kwara State Nigeria Department of Electrical and Electronics Engineering Faculty of Engineering University of Lagos Akoka Nigeria Bachelor's Program of Artificial Intelligence and Information Security Fu Jen Catholic University New Taipei City Taiwan Department of Library and Information Science Fu Jen Catholic University New Taipei City Taiwan

ISBN: (数字)9798350374162

ISBN: (纸本)9798350374179

This study focuses on brain tumor detection and segmentation using Convolutional Neural Networks (CNN) with architectures of Fully Convolutional Net-work (FCN) and VGG16. The dataset imported for this study consists of brain MRI images, which were preprocessed to improve the overall image resolution. Data augmentation techniques were applied to heighten the variability and volume of the training data. For feature extraction, CNN models were utilized, specifically the VGG16 architectures. This model was trained on a preprocessed dataset to learn the important features associated with the presence of brain tumor. Image segmentation was performed to precisely outline and identify the tumor region within the brain images. FCN architecture was employed for this task, which allowed pixel-level classification of tumor regions. Finally, image classification was carried out to group brain images based on the absence or presence of a tumor. The trained models were evaluated using accuracy, precision, recall and F1score as the performance metrics. The results of the study demonstrated promising outcomes, achieving an accuracy score of 93% and a precision, recall and f1score ranging from 75% to 100% based on the specific type of tumor enlisted. This indicates that the developed CNN models, with the FCN and VGG16 architectures, effectively detect and segment brain tumors from MRI images. The findings of this study contribute to the field of medical image analysis and gives a foundation for further research and development in brain tumor diagnosis and treatment. The study recommends the use of more deep learning algorithms for the process of detecting brain tumors.

关键词： Deep learning Image segmentation Accuracy Magnetic resonance imaging Computational modeling Brain tumors Brain modeling Distance measurement Classification algorithms Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Interpretable Machine Learning for Multi-Class Crop Yield Prediction

Interpretable Machine Learning for Multi-Class Crop Yield Pr...

引用

Intelligent Cybernetics Technology & Applications (ICICyTA), International Conference on

作者： Aldian Nurcahyo Yaya Heryadi Lukas Wayan Suparta Ilvico Sonata Compuer Science Binus Graduate Program Bina Nusantara University Jakarta Indonesia Cognitive Engineering Research Group (CERG) Universitas Katolik Indonesia Atma Jaya Jakarta Indonesia Department of Electrical Engineering Faculty of Industrial Technology Institut Teknologi Nasional Yogyakarta Yogyakarta Indonesia Compuer Science Departement Binus Graduate Program Doctor of Computer Science Bina Nusantara University Jakarta Indonesia

Crop Yield Analysis and Prediction is a fast-expanding discipline that is critical for optimizing agricultural methods. A lack of trustworthy data is one of the challenges in estimating crop yields. We develop predictive models for 22 different fruits and vegetables data. The goals of this study are to create accurate and interpretable crop recommendation models. We used multiple machine learning (ML) models for multi-class crop production prediction to fulfill our research goal. We thoroughly examined the influence of climate and nutrient factors on crop yield, considering their complex interactions. To improve the dataset, augmented data techniques were applied. Configuring the parameters and fine-tuning the hyperparameters is our technique to increase the model performance. Furthermore, we employ explainable artificial intelligence (XAI) techniques and interpretability tools like Shapley Additive exPlanations (SHAP) to improve the interpretability of our prediction model. Our findings reveal that the XGBoost model has the best performance model with 99.86% accuracy, followed by SVM Poly Kernel with 99.32% and Random Forest with 98.82%. Feature selection and analysis are emphasized, particularly in regional agricultural contexts. This study contributes to the creation of accurate and interpretable crop recommendation models while also addressing the issue of untrustworthy data, providing useful insights for optimizing agricultural practices.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Influence of Crystallographic Orientation on the Deformation of Ag Nanoparticles During High-Speed Impact

SSRN

引用

SSRN 2022年

作者： Becker, Michael F. Kovar, Desiderio Chitrakar, T.V. The University of Texas at Austin AustinTX78712 United States Materials Science and Engineering Program Texas Materials Institute United States Department of Electrical and Computer Engineering United States Department of Mechanical Engineering Center for Additive Manufacturing and Design Innovation

Several related aerosol processes utilize high velocity impact of solid nanoparticles to produce nanograined films including the aerosol deposition method, jet molding, vacuum kinetic spraying, and micro cold spray. Although the influence of important variables such as particle size and particle impact velocity, on particle deformation and film formation have been previously explored, other variables have not been systematically explored. Because particles impact with a full range of orientations, an understanding of the effect of particle orientation is required to predict film microstructures. Molecular dynamics simulations were conducted to determine the influence of particle crystallographic orientation on the particle deformation upon impact and the resulting microstructure of the deposit. We show that the orientations that produce the largest overall particle deformation are not correlated to orientations where initiation of plastic deformation is easiest. Rather, the deformation is heterogenous and depends on the mechanisms responsible for deformation. Two deformation mechanisms are identified: 1) dislocation plasticity and 2) disordering followed by viscous flow. The fraction of the atoms in the impacting particle that experience permanent deformation by each mechanism is quantified as a function of particle orientation. The implications of the effects of particle crystallographic orientation on film microstructures are also discussed. © 2022, The Authors. All rights reserved.

关键词： Molecular dynamics

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：