检索结果-内蒙古大学图书馆

Generic object detection using deep learning

AIP Conference Proceedings 2022年第1期2444卷

作者： M. Malathi C. Paramasivam K. Nagalakshmi Gospeline Christiana S. Sangeetha 1Department of Computer Science and Engineering Sethu Institute of Technology Virudhu Nagar Tamilnadu India 2Department of Mechanical Engineering Thiagarajar College of Engineering Madurai Tamilnadu India

Object discovery is one of the very important and challenging problems in computer computing, seeks to obtain the properties of objects from a large number of categories previously described in natural images. In particular, image classification that aims to see the semantic categories of objects in a given image. Object discovery is not only identifies item categories but also predicts the location of each item with a mandatory box. Semantic separation process aims to predict intelligent pixel separation to assign a specific category label to each pixel, thus providing a richer and more comprehensive understanding of the image. In depth learning strategies have emerged as a powerful strategy for reading presentations directly from the data and have led to significant success in the field of general acquisition. Given this period of rapid evolution, the aim of this paper is to provide a comprehensive analysis of the latest achievements in this field brought about in-depth learning strategies. Here, the deep learning object detection algorithm is implemented for accuracy and time effectiveness to show the correct label for a character of interest in a movie which will be more useful in surveillance of building, ATM centres etc. Finally, it concludes with a promising indication for future research.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Student’s academic performance prediction by using ensemble techniques

引用

AIP Conference Proceedings 2022年第1期2555卷

作者： Nidhi Mukesh Kumar Disha Handa Shweta Agarwal 1Department of Computer Science and Engineering Chandigarh University Punjab India 140413 2Department of Computer Science and Engineering Chitkara University Institute of Engineering and Technology Chitkara University Himachal Pradesh India 173212

Data Mining is a discipline of Machine Learning which is used to find or extract the information from the huge database of any organization by using some informative techniques. These informative techniques are then divided into different categories like clustering, classification, regression and association rule mining etc. Data Mining is widely used techniques in different fields like education, telecommunication, hospital, hospitality industry etc. As education plays a crucial role in the life of a human being therefore its proper monitoring is also very important. Thus, to predict the academic performance of any student on time and to help students improve their academic perform different researcher is working in the field and tried to develop a system which help to improve the prediction result. In this paper, different classification algorithms are used on academic dataset of the student in conjunction with different ensemble learning algorithm to improve the prediction result as compared to prediction result given by simple classification algorithm. At the end a comparison is also given which show the performance improvement by ensemble learning as compared to simple classification. The maximum improvement is shown by Multilayer perceptron algorithm and it is up to 15%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Theoretical investigation of a nano scale all-optical 1 × 2 demultiplexer

引用

AIP Conference Proceedings 2023年第1期2651卷

作者： Saif Hasan Abdulnabi Mohammed Nadhim Abbas 1Department of Electronic and Communications Engineering Faculty of Engineering University of Kufa Iraq 3Department of Computer Technical Engineering College of Information Technology Imam Ja'afar Alsadiq University / Al-Najaf Al-Ashraf Iraq 2Department of Electrical Engineering College of Engineering University of Baghdad Iraq

In this paper, we have suggest, design, and simulate an all optical 1*2 demultiplexer (Demux) depended on Insulator-Metal-Insulator (IMI) plasmonic multilayer structure. The proposed structure offers an operating wavelength at 1550 nm and the design area is (350 nm* 350 nm). In this work, Finite Element Method (FEM) is used by using COMSOL Multiphasic software (version 5.4). The working principle of the proposed device (plasmonic Demux) depends on destructive and constructive interference, which occurs on input signal, selector signal, and control signal. The borderline between Logic 0 and Logic 1 at the output is 0.5 that is called transmission threshold. The performance of the proposed structure is measured by three parameters; Transmission, Extension Ratio, and Modulation Depth (MD). This devise shows, in some cases, the transmission value reaches more than 80%, Extension Ratio (3.5 dB), and very high MD value (97.6%). The proposed structure has a major role in building the arithmetic logic unit (ALU) and photonics integrated circuits (ICs).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Energy-management system for plug-in hybrid electric vehicle using optimized artificial neural networks

引用

AIP Conference Proceedings 2022年第1期2519卷

作者： Balachandra Pattanaik Mukil Alagirisamy 1Department of Electrical and Computer Engineering Wollega University Nekemte Ethiopia Africa 2Department of Electrical Engineering Faculty of Engineering Lincoln University College Wisma Lincoln Malaysia

Hybrid Plug-in Electric vehicles (HPEV) are new automobiles that can operate on gasoline and electricity stored in a battery pack. As a result, by utilizing the cheaper renewable and nonrenewable energy sources accessible at the household electric outlet, these cars may considerably cut their fuel usage. As a result, PHEVs have the potential to reduce overall greenhouse gas emissions from vehicles dramatically. A simplified power train of a power split PHEV is modeled in this study. The primary goal of the research is to improve the PHEV’s fuel economy. To accomplish this, the aforementioned simplified model has been used to implement the Optimized Neural Network approach. An optimization problem is developed with Equivalent Fuel Consumption Minimization (EFCM) as the primary objective function and various constraints. The particle swarm optimization (PSO) methodology is used to improve the efficiency of HPEV, estimates by optimizing the process parameters of the ANN. In comparison to existing approaches, the suggested method can produce optimistic outcomes based on the simulation studies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The persistence and bifurcation analysis of an ecological model with fear effect involving prey refuge and harvesting

引用

AIP Conference Proceedings 2022年第1期2394卷

作者： Azhar A. Majeed Zina Kh. Alabacy 1Department of Mathematics College of Science University of Baghdad Baghdad Iraq 2Department of Control and Systems Engineering University of Technology Baghdad Iraq.

In this work, the sufficient conditions for uniformly persistence of a food chain prey-predator model with prey refuge and harvesting have been found. By creating suitable Lyapunov functions, a set of sufficient conditions that can be checked easily are gotten for the global asymptotic stability of the model. The conditions of the local bifurcation are determined, it’s noticed that near axial and free-second predator equilibrium points there is a transcritical bifurcation, otherwise near the free-second predator equilibrium point there is a pitchfork bifurcation, while near the coexistence equilibrium point there is a saddle-node bifurcation . Additional realizations for the Hopf bifurcation close to coexistence equilibrium point have been done. The validity of our main results was demonstrated by numerical analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Robustness Metrics for Defense of Machine Learning Systems

Evaluation of Robustness Metrics for Defense of Machine Lear...

引用

International Conference on Military Communications and Information Systems (ICMCIS)

作者： J. DeMarchi R. Rijken J. Melrose B. Madahar G. Fumera F. Roli E. Ledda M. Aktaş F. Kurth P. Baggenstoss B. Pelzer L. Kanestad Collaborative Engineering Systems & Aerospace Systems Information Supremacy Royal Netherlands Aerospace Centre NLR Amsterdam NLD Cyber & Information Systems Division Defence Science and Technology Laboratory Portondown GBR Department of Electrical and Electronic Engineering University of Cagliari Cagliari ITA Department of Informatics Bioengineering Robotics and Systems Engineering University of Genoa Genoa ITA Department of Computer Control and Management Engineering Sapienza University of Rome Rome ITA Defence Systems Technologies Division ASELSAN Ankara TUR Fraunhofer Institute for Communication Information Processing and Ergonomics Bonn DEU Swedish Defence Research Agency Cyber Defence and C2 Technology Division Stockholm SWE

In this paper we explore some of the potential applications of robustness criteria for machine learning (ML) systems by way of tangible “demonstrator” scenarios. In each demonstrator, ML robustness metrics are applied to real-world scenarios with military relevance, indicating how they might be used to help detect and handle possible adversarial attacks on ML systems. We conclude by sketching promising future avenues of research in order to: (1) help establish useful verification methodologies to facilitate ML robustness compliance assessment; (2) support development of ML accountability mechanisms; and (3) reliably detect, repel, and mitigate adversarial attack.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ensemble learning-based deep neural network model for face recognition

引用

AIP Conference Proceedings 2022年第1期2463卷

作者： G. Priyanka J. Senthil Kumar 1Department of Computer Science and Engineering Mepco Schlenk Engineering College Sivakasi-626005 India 2Department of Electronics and Communication Engineering Mepco Schlenk Engineering College Sivakasi- 626005 India

Due to the poor regularization capability of single Convolutional Neural Network (CNN), the performance of face recognition system is severely affected. Also, the input facial image data for recognition is influenced by surrounding information like light, expression, brightness, contrast, pose variations and other factors. This issue is overcome by using ensemble-based feature learning ofCNN and local binary patterns (LBP). It also aids in improving the occlusion-related low pedestrian detection rate. To begin, the LBP operator is used to extract texture features from the face and by using different 10 CNN architectures, different part of facial information is learnt. This is mainly used to improve the performance of underlying networking attributes and thereby it leads to enhanced classification results using the Softmaxactivation function. With the introduced new form of face recognition focused on parallel ensemble learning of convolutional neural network and local binary pattern for feature extraction, the obtained results outperforms the existing state-of-art techniques. Finally, utilizing majority voting, the approach of parallel ensemble learning is employed to obtain the final result of face recognition. The ORL and Yale-B face datasets identification rates climb to 98.1% and 99.2 percent, respectively, for our propose system. The proposed approach is demonstrated in the experiments to improve not only the model’s immunity to withstand with different illumination, expression, lighting, brightness and posture conditions, but also the accuracy of face recognition with the poor regularization metrics, which denies in reaching the global solution in the solution space.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Guidance control for Parallel Parking Tasks

引用

IEEE/CAA Journal of Automatica Sinica 2020年第1期7卷 301-306页

作者： Jiyuan Tan Chunling Xu Li Li Fei-Yue Wang Dongpu Cao Lingxi Li Key Laboratory of Urban Intelligent Traffic Control Technology North China University of TechnologyBeijing 100144China Beijing Transport Institute Beijing 100073China Department of Automation BNRistTsinghua UniversityBeijing 100084China Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100080China Driver Cognition and Automated Driving Laboratory University of WaterlooWaterloo N2L 3G1Canada Department of Electrical and Computer Engineering Purdue School of Engineering and TechnologyIndiana University-Purdue University IndianapolisIndiana 46202-5132 USA

Parking into small berths remains difficult for unskilled drivers. Researchers had proposed different automatic parking systems to solve this problem. The first kind of strategies(called parking trajectory planning) designs a detailed reference trajectory that links the start and ending points of a special parking task and let the vehicle track this reference trajectory so as to park into the berth. The second kind of strategies(called guidance control) just characterizes several regimes of driving actions as well as the important switching points in certain rule style and let the vehicle follows the pre-selected series of actions so as to park into the berth. Parking guidance control is simpler than parking trajectory planning. However, no studies thoroughly validated parking guidance control before. In this paper, a new automatic parking method is presented, which could characterize the desired control actions directly. Then the feasibility is examined carefully. Tests show that a simple parking guidance control strategy can work in most parallel parking tasks, if the available parking berth is not too small. This finding helps to build more concise automatic parking systems that can efficiently guide human drivers.

关键词： Automatic parking guidance control trajectory planning

来源：评论

学校读者我要写书评

暂无评论

Channel separation with CNN model for glaucoma color spectral detection

引用

AIP Conference Proceedings 2022年第1期2519卷

作者： Anisha Rebinth S. Mohan Kumar 1Department of Information Science and Engineering New Horizon College of Engineering Bangalore Karnataka India 2Department of Computer Science and Engineering Nagarjuna College of Engineering & Technology Beedaganahalli Karnataka India

Glaucoma is a leading type of eye disease that affects the optic nerve causing permanent vision loss. As this optic nerve is important for good vision safety, glaucoma can be prevented only if detected earlier. Optic disc to cup ratio is one of the key factors for glaucoma diagnosis with abnormally high eye pressure. A descriptive analysis of glaucoma diagnosis using Convolutional Neural Network (CNN) for spectral color detection of the eye is presented in this study. Initially, the color components are separated as red, green, and blue. Then, the region of Interest (ROI) is obtained from the green channel of the fundus image for the feature extraction. The Green channel is used for the fundus image analysis and detection because it is the only sensitive and high contrast color that the other two components for humans. Finally, the proposed system’s glaucoma color spectral diagnosis and its performance are analyzed using CNN with accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Designing a Trajectory control System for Wheelchairs with a Combination of Automatic and Manual Steering Methods

引用

Periodica Polytechnica Transportation engineering 2024年第4期52卷 412-422页

作者： Vu, Van Tan Nguyen, Quang Thinh Nakagawa, Chihiro Nguyen, Trung Nguyen Le, Thanh Long Nguyen, Van Vinh Hoang, Thi Lan Anh Do, Trong Tu Mihály, András Gáspár, Péter Department of Automotive Mechanical Engineering Faculty of Mechanical Engineering University of Transport and Communications Building A6 no. 3 Cau Giay Street Lang Thuong Ward Dong Da District Hanoi100000 Viet Nam Japan Technology Solution Joint Stock Company 9 Dau Ma Street Section 2 Thi Cau Ward Bac Ninh Bac Ninh222000 Viet Nam School of Engineering Osaka Metropolitan University 1-1 Gakuen-cho Nakaku Sakai Osaka599-8531 Japan Emergency abdominal surgery Department Viet Duc University Hospital no. 40 Trang Thi Street Hanoi100000 Viet Nam Mechanical and Power Engineering Faculty Electric Power University no. 235 Hoang Quoc Viet Street Co Nhue Ward Bac Tu Liem District Hanoi100000 Viet Nam Systems and Control Laboratory Institute for Computer Science and Control Hungarian Research Network Kende u. 13-17 Budapest1111 Hungary

A wheelchair is a specialized form of Personal Mobility Vehicle (PMV) designed to help people with disabilities move safely to their desired locations. Unlike conventional PMVs, wheelchairs for people with disabilities are challenging to manually control in environments with heavy traffic. This study focuses on designing and feasibility testing of control systems for PMVs to meet safety and efficiency standards, even in complex environments. First, a control structure model for PMVs is proposed. This is followed by the application of a combination of First In First Out (FIFO) and Dijkstra traffic control methods to determine effective trajectories for PMVs. The proposed control system is then tested on the campus of the University of Transport and Communications. Simulation results show that when comparing the travel time of 10 PMVs, the order execution time for each PMV remains stable (within 10%) for up to 20 PMVs. However, when the number of PMVs increases to 25, 30, 35, and 40 vehicles, the order execution time increases by 35%, 55%, 103%, and 119%, respectively. These results demonstrate that the system can control a large number of PMVs, ensuring safety, flexibility, and efficiency. © 2024 Budapest University of Technology and Economics. All rights reserved.

关键词： Travel time

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：