检索结果-内蒙古大学图书馆

Electronic Communications, Internet of Things and Big Data (ICEIB), International Conference on

作者： Shang-Te Tsai Yu-Cheng Chang Chao-Yi Huang Fang-Yuan Yang Wei Chien Zong-Rong Wu School Art and Design Sanming University Fujian China Department of Computer Science and Information Engineering National Taipei University of Technology Taipei Taiwan Department of Information Management National Yunlin University of Science and Technology Yunlin Taiwan Department of Computer Information and Network Engineering Lunghwa University of Science and Technology Taoyuan Taiwan Department of Technical and Vocational Program in Artificial Intelligence National Yunlin University of Science and Technology Yunlin Taiwan

ISBN: (数字)9798350360721

ISBN: (纸本)9798350360738

Innovative safety in the workplace is vital as the high safety risks associated with electrical engineering construction can lead to injuries or even fatalities. Using computer vision technology, we experimented with scenarios such as “normal operations” and “unexpected incidents” to enhance safety measures. We integrated an Internet of Things system into the setup, enabling the system to quickly detect and alert to unexpected events in real-time, thereby improving workplace safety.

关键词： computer vision Prevention and mitigation Employment Real-time systems Production facilities Safety Internet of Things

来源：评论

学校读者我要写书评

暂无评论

ATP_mCNN: Predicting ATP binding sites through pretrained language models and multi-window neural networks

引用

computers in Biology and Medicine 2025年 185卷 109541-109541页

作者： Le, Van-The Malik, Muhammad-Shahid Lin, Yi-Jing Liu, Yu-Chen Chang, Yan-Yun Ou, Yu-Yen Department of Computer Science and Engineering Yuan Ze University Chung-Li32003 Taiwan Graduate Program in Biomedical Informatics Yuan Ze University Chung-Li32003 Taiwan Department of Computer Sciences Karakoram International University Gilgit-Baltistan 15100 Pakistan

Adenosine triphosphate plays a vital role in providing energy and enabling key cellular processes through interactions with binding proteins. The increasing amount of protein sequence data necessitates computational methods for identifying binding sites. However, experimental identification of adenosine triphosphate-binding residues remains challenging. To address the challenge, we developed a multi-window convolutional neural network architecture taking pre-trained protein language model embeddings as input features. In particular, multiple parallel convolutional layers scan for motifs localized to different window sizes. Max pooling extracts salient features concatenated across windows into a final multi-scale representation for residue-level classification. On benchmark datasets, our model achieves an area under the ROC curve of 0.95, significantly improving on prior sequence-based models and outperforming convolutional neural network baselines. This demonstrates the utility of pre-trained language models and multi-window convolutional neural networks for advanced sequence-based prediction of adenosine triphosphate-binding residues. Our approach provides a promising new direction for elucidating binding mechanisms and interactions from primary structure. © 2024 Elsevier Ltd

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Age Effects on Decision-Making, Drift Diffusion Model

arXiv

引用

arXiv 2023年

作者： Kavian, Zahra Hajisadeghi, Kimia Shahir, Yashar Rezazadeh Faraji, Mehrbod Ebrahimpour, Reza Department of Electrical Engineering Sharif University of Technology Tehran Iran Department of Computer Engineering Shahid Rajaee Teacher Training University Tehran Iran Center for Cognitive Science Institute for Convergence Science and Technology Sharif University of Technology Tehran Iran

Training can improve human decision-making performance. After several training sessions, a person can quickly and accurately complete a task. However, decision-making is always a trade-off between accuracy and response time. Factors such as age and drug abuse can affect the decision-making process. This study examines how training can improve the performance of different age groups in completing a random dot motion (RDM) task. The participants are divided into two groups: old and young. They undergo a three-phase training and then repeat the same RDM task. The hierarchical drift-diffusion model analyzes the subjects’ responses and determines how the model’s parameters change after training for both age groups. The results show that after training, the participants were able to accumulate sensory information faster, and the model drift rate increased. However, their decision boundary decreased as they became more confident and had a lower decision-making threshold. Additionally, the old group had a higher boundary and lower drift rate in both pre and post-training, and there was less difference between the two group parameters after training. © 2023, CC BY-NC-SA.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Enhancing Acute Ischemic Stroke Diagnosis Using IoMT and Deep Learning Technologies

Enhancing Acute Ischemic Stroke Diagnosis Using IoMT and Dee...

引用

Telecommunications Conference (ITC-Egypt), International

作者： Mohamed M. El-Sheikh Aya Bayoumy Nada M. Ahmed Amany Mohamed Eldeeb Fatma I. Rabea Amira A. Nawar Mohamed G. Khattap Hend Galal Eldeen Mohamed Ali Hassan Mariam Mostafa Nayra Ibrahim Reem Ramadan Yomna Refaat Mennatallah Khaled Ali Maher Mohamed Abd Elaziz Ahmed Gamal Abdellatif Ibrahim Radiology and Medical Imaging Faculty of Applied Health Sciences Galala University Suez Egypt Biomedical Informatics Faculty of Computer Science and Engineering Galala University Suez Egypt Artificial Intelligence Science Program Faculty of Computer Science and Engineering Galala University Suez Egypt Department of Electronics and Electrical Communications Engineering Air Defense College Alexandria Egypt

ISBN: (数字)9798350351408

ISBN: (纸本)9798350351415

This paper introduces an alternative technique for diagnosing Acute Ischemic Stroke within the IoMT environment. In the proposed approach, the collected data is transmitted to a cloud-based center where the technique utilizes EfficientNet, a deep learning model, designed to extract features from MRI images thereby enhancing the detection of acute ischemic infarctions. The performance of EfficientNet is compared against two other models, CNN and MobileNet, demonstrating its superior efficacy through metrics such as accuracy, precision, recall, and F1-score, which stand at 92.31%, 92.28%, 92.33%, and 92.30%, respectively.

关键词： Deep learning Accuracy Magnetic resonance imaging Soft sensors Medical services Feature extraction Regulation

来源：评论

学校读者我要写书评

暂无评论

Exp[licit] An Educational Robot Modeling Software based on Exponential Maps

Exp[licit] An Educational Robot Modeling Software based on E...

引用

IEEE/ASME (AIM) International Conference on Advanced Intelligent Mechatronics

作者： Johannes Lachner Moses C. Nah Stefano Stramigioli Neville Hogan Department of Mechanical Engineering Massachusetts Institute of Technology Cambridge MA USA Department of Brain and Cognitive Sciences Massachusetts Institute of Technology Cambridge MA USA Faculty of Electrical Engineering Mathematics and Computer Science University of Twente Enschede Netherlands

ISBN: (数字)9798350355369

ISBN: (纸本)9798350355376

Deriving a robot’s equations of motion typically requires placing multiple coordinate frames, commonly using the Denavit-Hartenberg convention to express the kinematic and dynamic relationships between segments. This paper presents an alternative using the differential geometric method of Exponential Maps, which reduces the number of coordinate frame choices to two. The traditional and differential geometric methods are compared, and the conceptual and practical differences are detailed. The open-source software, $\operatorname{Exp}[\text { licit }]^{\mathrm{TM}}$, based on the differential geometric method, is introduced. It is intended for use by researchers and engineers with basic knowledge of geometry and robotics and aims to serve as a supportive resource during the study of differential geometric approaches. Code snippets and an example application are provided to demonstrate the benefits of the differential geometric method and assist users to get started with the software.

关键词： Knowledge engineering Geometry Mechatronics Educational robots Robot kinematics Motion segmentation Dynamics

来源：评论

学校读者我要写书评

暂无评论

Cell segmentation in fluorescence microscopy images

Cell segmentation in fluorescence microscopy images

引用

IET International Conference on engineering Technologies and Applications (ICETA 2024)

作者： Shao-Yun Yin Wei-Wen Hsu Chih-Hsien Hsia Master Program of Artificial Intelligence National Ilan University Ilan Taiwan Department of Computer Science and Information Engineering National Taitung University Taitung Taiwan

ISBN: (数字)9781837242252

For microscopic cells images, cells’ morphologies are widely varied among different imaging modalities and staining methods. For fluorescence microscopy images, Poisson noises present in images due to the lightening, causing photobleaching, which makes it challenging in analysis with the deep learning models. Traditionally, median filtering can be applied to the original image for denoising, however, it also results in a blurry image, which is harmful to segmentation. In this study, the Haar Wavelet Transform is used to alleviate the photobleaching problem for cell segmentation, integrated to the framework without interfering with feature extraction by the backbone model. For our experiments, instance segmentation for fluorescence-stained cells was performed based on U-Net architecture with the method of gradient flow tracking proposed by Cellpose. And the Haar wavelet downsampling is embedded in the skip connections to verify if it can improve the segmentation performance for fluorescence images. The experimental results show that the approach of Haar wavelet downsampling embedded in the skip connections achieve superior performance among the other settings. Compared with the performance of the baseline model, the performance of the proposed model reached 0.732 in F1-score, which surpassed the one of baseline model (0.6341) by almost 0.1.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A tiny cnn architecture for medical face mask detection for resource-constrained endpoints 2nd

A tiny cnn architecture for medical face mask detection for ...

引用

2nd International Conference on Electrical and Electronics engineering, ICEEE 2021

作者： Mohan, Puranjay Paul, Aditya Jyoti Chirania, Abhay Cognitive Applications Research Lab Chennai India Department of Electronics and Communication Engineering SRM Institute of Science and Technology Kattankulathur Tamil Nadu603203 India Department of Computer Science and Engineering SRM Institute of Science and Technology Kattankulathur Tamil Nadu603203 India

ISBN: (纸本)9789811607486

The world is going through one of the most dangerous pandemics of all time with the rapid spread of the novel coronavirus (COVID-19). According to the World Health Organization, the most effective way to thwart the transmission of coronavirus is to wear medical face masks. Monitoring the use of face masks in public places has been a challenge because manual monitoring could be unsafe. This paper proposes an architecture for detecting medical face masks for deployment on resource-constrained endpoints having extremely low memory footprints. A small development board with an ARM Cortex-M7 microcontroller clocked at 480 MHz and having just 496 KB of framebuffer RAM has been used for the deployment of the model. Using the TensorFlow-Lite framework, the model is quantized to further reduce its size. The proposed model is 138 KB post-quantization and runs at the inference speed of 30 FPS. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2021.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

Passive Versus Active: Frameworks of Active Learning for Linking Humans to Machines 43

Passive Versus Active: Frameworks of Active Learning for Lin...

引用

43rd Annual Meeting of the cognitive science Society: Comparative Cognition: Animal Minds, CogSci 2021

作者： Lim, Jaeseo Jo, Hwiyeol Zhang, Byoung-Tak Park, Jooyong Interdisciplinary Program in Cognitive Science Seoul National University Seoul Korea Republic of Institute of Computer Technology Seoul National University Seoul Korea Republic of Department of Computer Science and Engineering Seoul National University Seoul Korea Republic of Department of Psychology Seoul National University Seoul Korea Republic of

There are numerous studies that show that the more learner actively participate in the learning process, the more they learn. Although the use of active learning to increase learning outcomes has been recently introduced in a variety of methods, empirical experiments are lacking. In this study, we introduce two frameworks of human active learning and then conducted two experiments to determine how these frameworks can be used as leaning tools. In experiment 1, we compared three types of active learning and passive learning in order to empirically confirm the effect of active learning. In experiment 2, based on the results of experiment 1, we explored through simulation on machine learning with the frameworks that the more active the learners are, the better outcomes can be obtained. Both experiments showed that active learning both also effective in human and machine learning. Therefore, our analyses of the two experiments fit within the taxonomy and classification of the frameworks of active learning. This result is further significant in that it gives practical implications on human and machine learning methods. © cognitive science Society: Comparative Cognition: Animal Minds, CogSci *** rights reserved.

关键词： Knowledge management

来源：评论

学校读者我要写书评

暂无评论

Acoustic Scene Classification Using Perceptually Weighted Log Mel Spectrogram and Buttom-up Broadcast Neural Network

Acoustic Scene Classification Using Perceptually Weighted Lo...

引用

IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW)

作者： Riyad Ali Ahmad Abuirbaiha Chang-Hsing Lee Cheng Chang Lien Ph.D. Program in Engineering Science Chung Hua University Hsinchu Taiwan Bachelor Program in Industrial Artificial Intelligence Ming Chi University of Technology New Taipei City Taiwan Department of Computer Science and Information Engineering Chung Hua University Hsinchu Taiwan

ISBN: (数字)9798350386844

ISBN: (纸本)9798350386851

The study explores various 2D feature representations including spectrogram, MFCC spectrogram, log Mel-spectrogram, and the perceptual weighted log Mel-spectrogram (PW-LMSP) for acoustic scene classification (ASC). These 2D feature representations were classified using a bottom-up broadcast neural network (BBNN). The experimental results have shown that PW-LMSP outperforms other 2D representations. Further, the proposed method (PW-LMSP with BBNN) achieves accuracies of 91.2% and 91.6% respectively on the DCASE2018 and DCASE2019 development datasets, outperforming all the submissions in DCASE2018 and DCASE2019, as well as state-of-the-art approaches.

关键词： Scene classification Accuracy Neural networks LoRa Feature extraction Acoustics Mel frequency cepstral coefficient

来源：评论

学校读者我要写书评

暂无评论

Enhanced Keypoint-Based Approach for Identifying Copy-Move Forgery in Digital Images

Enhanced Keypoint-Based Approach for Identifying Copy-Move F...

引用

International Conference on Contemporary Computing and Informatics (IC3I)

作者： Girish Singh Bisht Arpit Jain Vandna Bansla Khemraj Sharma Rudramani Bhutia Vikas Kumar Department of Computer Science & Engineering Tula’s Institute Dehradun India Department of Computer Science & Engineering Koneru Lakshamaiah Education Foundation Vadessahwaram A.P. India Shivalik Engineering College Dehradun India Department of Business Administration Doctoral Program in Management Sciences Nanhua University Dalin Chiayi Taiwan R.O.C. Department of Computer Science & Engineering Koneru Lakshmaiah Education Foundation A.P. India School Engineering and Computing Dev Bhoomi Uttrakhand University Dehradun Uttrakhand India

ISBN: (数字)9798350350067

ISBN: (纸本)9798350350074

Copy-move forgeries often exploit homogeneous regions in images with large-scale attacks to either highlight or conceal target objects. These manipulations are simple to execute but challenging to notice. Forgery detection techniques like Copy-Move Forgery Detection (CMFD) cannot detect these forged documents because they are unable to identify a sufficient number of effective keypoints in homogeneous areas, leading to inaccurate and inefficient results. SURF stands for Speeded-Up Robust Features and is used in this paper along with A-KAZE and Scale-Invariant Feature Transforms. According to our experiment, A-KAZE offers superior detection performance under diverse attacks, especially when it comes to large-scale attacks targeting homogeneous regions. A-KAZE is found to be more accurate than SIFT, SURF, and A-KAZE when applied to the NB-CASIA dataset, achieving detection accuracies of $\mathbf{8 9. 2 \%}, \mathbf{9 3. 9 \%}$ and $\mathbf{9 8. 9 8 \%}$.)

关键词： Accuracy Digital images Forensics Transforms Forgery Computational efficiency Reliability Informatics Software development management

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：