检索结果-内蒙古大学图书馆

E-Health and Bioengineering Conference (EHB)

作者： Emanuela Motrescu Oana Geman “Babes Bolyai” University Cluj Romania Department of Electronic Computers and Automation NeuroaestheticsLab Faculty of Electric Engineering and Computer Science “Stefan cel Mare” University Suceava Romania

ISBN: (数字)9781665485579

ISBN: (纸本)9781665485586

The following case study targets the live deconstruction of a visual experience correlating attention-related body sensations that emerge with external visual stimuli resulting the improvement of attention. The attention deficit and hyperactivity disorder (ADHD) is one of the most common mental health disorders among children. It includes symptoms such as difficulty paying attention, hyperactivity and impulsive behavior. The disease appears before age of seven and lasts till adulthood. In contrast with traditional treatment (medication) our work focuses on the usage of biometric marker such as heart rate variability, applied in recovery through other treatments such as art therapy based on cinematic language techniques. We will be able to create a database that can be used to forecast pathologies within the autism spectrum and ADHD using various machine learning algorithm, by expanding the pilot project and including more participants.

关键词： Training Visualization Pediatrics Pathology Autism Art Machine learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Electric Vehicle Charging Demand Prediction using Multiresolution Sinusoidal Neural Network Optimized with Addax Optimization

Electric Vehicle Charging Demand Prediction using Multiresol...

引用

Trends in Material science and Inventive Materials (ICTMIM), International Conference on

作者： Rajesh Munirathnam Rohit P. Jadhav Nilesh M. Mahajan Amit Barve M. E. Shashi Kumar Natrayan L Data & Analytics Division TechnoGen Inc Hillsborough New Jersey USA Department of Robotics and Automation D.Y. Patil College of Engineering Akurdi Pune Maharashtra Department of Computer Science and Engineering Parul Institute of Technology Faculty of Engineering and Technology Parul University Limda Gujarat Department of Mechanical Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Bengaluru Karnataka Department of Mechanical Engineering Saveetha School of Engineering SIMATS Chennai Tamil Nadu

ISBN: (数字)9798331501488

ISBN: (纸本)9798331501495

Electric Vehicle (EV) charging demand prediction, while essential for optimizing charging infrastructure and energy management, faces challenges such as data inaccuracies and uncertainties in user behavior patterns. These issues define inaccurate demand forecasts which cause the wrong placement of charging stations and distribution of energy. Also, as the pattern of the EV charging is not static may change due to many factors such as climate, time of day, price preference among others, the prediction models may not handle the dynamism and hence lower the reliability of the forecast results. To overcome these drawbacks, this manuscript proposes an efficient approach for EV charging demand prediction. The data is gathered from a dataset on EV charging. The data is then sent to pre-processing. Using the Maximum Correntropy Quaternion Kalman Filter (MCQKF), the pre-processing section eliminates missing values and normalizes the input. To forecast EV charging demand, the Multiresolution Sinusoidal Neural Network (MSNN) receives the results of the pre-processing data. MSNN’s weight parameter is optimized using Addax Optimization (AO). The proposed MSNN-AO is utilized within the MATLAB platform. The proposed MSNN-AO technique is compared with the existing techniques such as Long Short-Term Memory Neural Network (LSTMNN), Heterogeneous Spatial-Temporal Graph Convolutional Network (HSTGNN) and Artificial Neural Networks (ANN), respectively. The MSNN-AO method achieves an accuracy of 97%, precision of 95%, and a Root Mean Square Error (RMSE) of 2.2%, demonstrating its superior performance in predicting EV charging demand. This highlights the proposed method’s effectiveness in minimizing prediction errors, reducing RMSE by 22.36%, and improving precision by 14.89% compared to existing methods. The MSNN-AO method’s higher accuracy and precision, coupled with its robust performance, make it a reliable and efficient solution for EV charging demand forecasting.

关键词： Accuracy Uncertainty Quaternions Energy resolution Electric vehicle charging Reliability Kalman filters Spatial resolution Root mean square Optimization

来源：评论

学校读者我要写书评

暂无评论

Detection of Detonators in Baggage Using Deep CNN Architecture: A Comparative Study of Contrast Enhancement and Feature Extraction Methods

Detection of Detonators in Baggage Using Deep CNN Architectu...

引用

International Conference on Image and Signal Processing and their Applications (ISPA)

作者： Oulhissane Lynda Merah Mostefa Simona Moldovanu Luminita Moraru Laboratory of Signals and Systems LSS Faculty of Science and Technology Abdelhamid Ibn Badis University Mostaganem Algeria MSlab Department of Computer Science and Information Technology Modelling & Simulation Laboratory Faculty of Automation Computers Electrical Engineering and Electronics Dunarea de Jos University of Galati Galati Romania MSlab Department of Chemistry Physics & Environment Modelling & Simulation Laboratory Faculty of Sciences and Environment Dunarea de Jos University of Galati Galati Romania

ISBN: (数字)9798350309249

ISBN: (纸本)9798350309256

Visual inspection of dual-energy X-ray radiographic images of cabin baggage requires high performance, but is hindered by various challenges such as low target prevalence, variability in target visibility, possible presence of multiple targets, and security personnel fatigue and inattention. Artificial intelligence (AI) techniques, particularly deep convolutional neural networks (CNNs), have shown promise in improving the automatic detection of explosives, even with low-resolution radiographic images, especially in high baggage throughput scenarios. In this paper, we focus on the detection of detonators as components of improvised explosive devices. The proposed approach involves comparing two experiments implemented in a deep CNN architecture using TensorFlow and Keras libraries. In the first experiment, raw dual-energy radiographic images without any enhancement were used. The second experiment includes three methods for contrast enhancement and feature extraction: the Contrast Limited Adaptive Histogram Equalization (CLAHE) method, the wavelet transform-based method, and the mixed CLAHE RGB-Wavelet method. In the latter two methods, Haar, Db2, Coif2, and Sym2 mother wavelet functions at two levels (HH and HL) were employed. The analysis of results focuses on a comparative study of performance measures such as accuracy, precision, recall, and F1 score. It was found that the preprocessing methods used in experiment 2, for the two evaluated classes (detonator and no detonator), achieved higher accuracy compared to the raw radiographic images used in experiment 1 (98.08%). The highest accuracies in experiment 2, with a value of 100%, were obtained with the CLAHE method (green channel in grayscale, blue channel in grayscale, and RGB channels) and the wavelet transform method with Haar mother wavelet at two levels HL

关键词： Wavelet transforms Radiography Visualization Gray-scale Inspection Feature extraction Libraries

来源：评论

学校读者我要写书评

暂无评论

A Novel Attention-based Explainable Deep Learning Framework Towards Medical Image Classification

A Novel Attention-based Explainable Deep Learning Framework ...

引用

Innovative Approaches in Smart Technologies (ISAS), International Symposium on

作者： Gladys W. Muoka Ding Yi Chiagoziem Chima Ukwuoma Moindi Duke Martin Ahmet Arif Aydin Mugahed A. Al-Antari School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China College of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan Chengdu China Department of Computer Science Unicaf University Lilongwe Lilongwe Malawi Department of Computer Engineering Faculty of Engineering İnönü University Turkey Department of Artificial Intelligence College of Software & Convergence Technology Daeyang AI Center Sejong University Seoul Korea

Deep learning applications for medical image classification have shown remarkable promise, particularly incorporating attention-based neural networks. This is particularly relevant in medical imaging, where the integration of Artificial Intelligence assists with various imaging tasks, including classification, segmentation, and detection. Deep learning is revolutionizing medical research and playing a significant role in advancing personalized clinical treatment. However, the lack of interpretability in these models presents a significant obstacle to their adoption in clinical practice. Therefore, there is a growing need for a comprehensive understanding of artificial intelligence systems and their internal mechanisms, capabilities, and limitations, which is the focus of the field of explainable AI. This study proposes a novel attention-based explainable deep learning framework for medical image classification tasks, including Covid-19, breast cancer (BreakHis), lung cancer (LC2500), and Retinal optical coherence tomography (OCT). The proposed framework recorded overall accuracies of 98% (Covid-19 Radiography), 95% (BreakHis), 99.8% (LC2500), and 95%(OCT). For visual analysis of the outcomes, we employ and use the LIME, SHAP, and ELI-5 to analyze the achieved results. The study’s primary goal is to bridge the gap between the high performance achieved by attention-based models and the necessity for transparency and interpretability in medical image diagnostics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Regularly Truncated M-estimators for Learning with Noisy Labels

arXiv

引用

arXiv 2023年

作者： Xia, Xiaobo Lu, Pengqian Gong, Chen Han, Bo Yu, Jun Yu, Jun Liu, Tongliang The Sydney AI Center School of Computer Science Faculty of Engineering The University of Sydney DarlingtonNSW2008 Australia The Australian AI Institute Faculty of Engineering and IT The University of Technology Sydney BroadwayNSW2007 Australia The PCA Lab The Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China The Department of Computing Hong Kong Polytechnic University Hong Kong The Department of Computer Science Hong Kong Baptist University Hong Kong The School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China The Department of Automation University of Science and Technology of China Hefei230026 China

The sample selection approach is very popular in learning with noisy labels. As deep networks "learn pattern first", prior methods built on sample selection share a similar training procedure: the small-loss examples can be regarded as clean examples and used for helping generalization, while the large-loss examples are treated as mislabeled ones and excluded from network parameter updates. However, such a procedure is arguably debatable from two folds: (a) it does not consider the bad influence of noisy labels in selected small-loss examples;(b) it does not make good use of the discarded large-loss examples, which may be clean or have meaningful information for generalization. In this paper, we propose regularly truncated M-estimators (RTME) to address the above two issues simultaneously. Specifically, RTME can alternately switch modes between truncated M-estimators and original M-estimators. The former can adaptively select small-losses examples without knowing the noise rate and reduce the side-effects of noisy labels in them. The latter makes the possibly clean examples but with large losses involved to help generalization. Theoretically, we demonstrate that our strategies are label-noise-tolerant. Empirically, comprehensive experimental results show that our method can outperform multiple baselines and is robust to broad noise types and levels. The implementation is available at https://***/xiaoboxia/RTM_LNL. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Study on spiral winding swimming motion control of a slender legless creature model

引用

High Technology Letters 2021年第4期27卷 415-421页

作者： Lu Zhenli Ma Zhipeng Marko Pencic Maja Cavic Borovac Branislav Roumiana Ilieva Bojan Nemec Marjan Mernik School of Electrical Engineering and Automation Changshu Institute of TechnologyChangshu 215500P.R.China School of Information and Control Engineering China University of Mining and TechnologyXuzhou 221116P.R.China Faculty of Technical Sciences University of Novi SadNovi Sad 621000Serbia Faculty of Management Technical University of SofiaSofia 1000Bulgaria Department of Automatics Biocybernetics and RoboticsJožef Stefan InstituteLjubljana 1000Slovenia Faculty of Electrical Engineering and Computer Science University of MariborMaribor 462000Slovenia

Through the observation and analysis of the motion trajectory of spiral winding motion for slender legless biological creatures in water,V-REP software is adopted to build a dynamic simulator to study on the mechanism of spiral winding swimming(SWS)*** using the output of spiral function(SF),the dynamic simulation model of slender legless creature(SLC)realizes the SWS motion in *** corresponding experiments under the control of different bending angle of SF to control the dynamic model are also carried out to analyze the water performance of SWS in still *** with the output of two different bending angles of the spiral function,the dynamic model can be used to realize SWS and up/down *** work provides technical reserve and experimental platform for the corresponding study in related fields.

关键词： V-REP spiral winding swimming(SWS) motion control slender legless creature(SLC)

来源：评论

学校读者我要写书评

暂无评论

Safety System for Industrial Robots Based on Human Detection Using an RGB-D Camera

Safety System for Industrial Robots Based on Human Detection...

引用

Proceedings of the International Convention MIPRO

作者： Valentin Šimundić Dario Mihelčić Damian Svirac Petra Đurović Robert Cupec Faculty of Electrical Engineering Computer Science and Information Technology Osijek Croatia Chair of Automation and Robotics

A robotic system, in general, should be safe for the operators who are using it and, if possible, it should be safe for the system itself and the environment it interacts with. This paper investigates three methods for human detection by an RGB-D camera and their adjustments for monitored robot movement. The methods are implemented in ROS and integrated into a robotic system consisting of an industrial robot arm ABB IRB-2400L and an RGB-D camera. Validation and comparison of the implemented algorithms was performed on the recorded video dataset containing people in the robot working area with per-frame annotations of human presence, velocity and proximity to the robot. The algorithms detect humans with highest recall of 98%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ARF-NET:Method of spinal segmentation in deformed spine radiographs

ARF-NET:Method of spinal segmentation in deformed spine radi...

引用

Information Systems and Computing Technology (ISCTech), International Conference on

作者： XiaTian Lin Yingli Liu Tao Shen Ming Gao Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming China Yunnan Key Laboratory of Computer Technologies Application Kunming University of Science and Technology Kunming China Kunming China The First People's Hospital of Yunnan Province Kunming China Kunming China

Deformed spine radiograph spine segmentation can help doctors to analyze the disease site faster, which is a necessary part of the current development of competent healthcare. For scoliosis diagnosis, this paper designs an Attention-guided ResNet with an FPN-like Upsampling model(ARF-Net) for segmenting the cone part of the spine radiograph map. In this paper, ResNet50 is used as the backbone to propose the feature map. Then the Global-Coordinate Attention (GCA) attention mechanism is added to obtain the X-axis, Y-axis, and global features. Finally, through the SIMAMUP module, the feature map is upsampled to introduce more detailed information to prevent cone segmentation errors and to improve the cone segmentation capability. The final experimental findings demonstrate that the model described in this study has greater segmentation precision in the SpineWebl6 public dataset, with the Jaccard and Dice coefficients reaching 87.70% and 93.45%, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Application of Broad Learning System for Image Classification Based on Deep Features 5th

Application of Broad Learning System for Image Classificatio...

引用

5th International Conference on Cognitive Systems and Signal Processing, ICCSIP 2020

作者： Zhang, Dan Zuo, Yi Chen, Philip C. L. Wang, Chiye Li, Teishan Navigation College Dalian Maritime University Dalian116026 China Innovation and Entrepreneurship Education College Dalian Minzu University Dalian116600 China Computer Science and Engineering College South China University of Technology Guangzhou510641 China Department of Computer and Information Science Faculty of Science and Technology University of Macau 99999 China School of Automation Engineering University of Electronic Science and Technology of China Chengdu610054 China

ISBN: (纸本)9789811623356

Due to large amount of image data, the accuracy and real-time performance of classification are difficult problems in image classification. On the one hand, the broad learning system (BLS) has achieved good results in the timeliness of classification. On the other hand, deep learning feature extraction effect is good, but its structure is complex and the training time is long. Therefore, based on the above advantages of both methods, this paper proposed BLS based on deep features for image classification. Firstly, a feature extractor is constructed based on the ResNet101 to obtain the deep features of the classification image. Then, the feature nodes and enhancement nodes of BLS are constructed based on the deep features. Through the experiment, our method has two performance on benchmark datasets: high classification accuracy, good real-time. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Co-designing Artificial Intelligence Curriculum for Secondary Schools: A Grounded Theory of Teachers' Experience

Co-designing Artificial Intelligence Curriculum for Secondar...

引用

2022 International Symposium on Educational Technology, ISET 2022

作者： Yau, King Woon Chai, Ching Sing Chiu, Thomas K. F. Meng, Helen King, Irwin Wong, Savio Wai-Ho Yam, Yeung The Chinese University of Hong Kong Faculty of Engineering Shatin Hong Kong The Chinese University of Hong Kong Department of Curriculum and Instruction Shatin Hong Kong The Chinese University of Hong Kong Department of Systems Engineering and Engineering Management Shatin Hong Kong The Chinese University of Hong Kong Department of Computer Science and Engineering Shatin Hong Kong The Chinese University of Hong Kong Department of Educational Psychology Shatin Hong Kong The Chinese University of Hong Kong Department of Mechanical and Automation Engineering Shatin Hong Kong

ISBN: (数字)9781665484671

ISBN: (纸本)9781665484671

In response to the need to equip Hong Kong secondary students with Artificial Intelligence (AI) literacy, a joint effort was made by university professors from engineering and education and secondary school teachers to co-design an innovative AI curriculum. This paper investigated the experience of teachers in co-designing the curriculum. A total of 17 semi-structured interviews were conducted with 8 secondary school teachers involved in the curriculum design. Using the grounded theory approach, the teachers' perspectives and experiences during the co-design processes were unpacked. First, the teachers were motivated by the perceived need of students to join in the co-design of such AI curriculum. Second, the teachers appreciated the professor-led knowledge input that addresses their gaps in technical knowledge. Third, the teachers contributed their pedagogical knowledge and classroom experiences to guide the design of the curriculum so that it may be contextualized to the school environment and students' needs. The outcomes of the co-design were a usable curriculum and teachers' growth, which was translated to students' AI literacy and confidence in learning about AI. This paper contributes to the current educational effort in preparing students for an AI pervasive society. © 2022 IEEE.

关键词： Curricula

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：