检索结果-内蒙古大学图书馆

Telecommunications and Intelligent systems (ICTIS), International Conference on

作者： Ahmed Tibermacine Djouher Akrour Rofeida Khamar Imad Eddine Tibermacine Abdelaziz Rabehi Department of Computer Science University of Biskra Biskra Algeria Department of Computer Automation and Management Engineering Sapienza University of Rome Rome Italy Laboratory of Telecommunications and Smart Systems Faculty of Sciences and Technology Zian Achour University of Djelfa Djelfa Algeria

ISBN: (数字)9798331527396

ISBN: (纸本)9798331527402

This study aims to classify brainwave patterns using electroencephalogram (EEG) signals in response to various auditory stimuli, specifically Quran recitation, participants’ favorite music, and Interstellar’s main theme. By analyzing the unique EEG responses elicited by these stimuli, the study explores cognitive and emotional processing differences. Two prominent classifiers, Support Vector Machine (SVM) and Convolutional Neural Networks (CNN), were utilized. SVM, combined with Power Spectral Density (PSD) features, achieved the highest accuracy of 95% when distinguishing Quran recitation from rest. CNN, particularly with Kernel Density Estimation (KDE) features, exhibited strong performance in distinguishing between different auditory stimuli, with an average accuracy exceeding 90%. These results highlight the critical role of feature extraction techniques, such as PSD and KDE, in improving classification performance and deepening our understanding of EEG-based emotional and cognitive responses to auditory stimuli.

关键词： Support vector machines Accuracy Recurrent neural networks Pattern classification Brain modeling Feature extraction Electroencephalography Telecommunications Convolutional neural networks Object recognition

来源：评论

学校读者我要写书评

暂无评论

Detecting Obstacles within the Driving Lane and Vehicle Speed Adjustment

Detecting Obstacles within the Driving Lane and Vehicle Spee...

引用

2021 Zooming Innovation in Consumer Technologies Conference, ZINC 2021

作者： Ljepic, Srdan Grbic, Ratko Kovacevic, Jelena Krunic, Momcilo RT-RK Institute for Computer Based Systems Osijek Croatia Computer Science and Information Technology Osijek Faculty of Electrical Engineering Osijek Croatia University of Novi Sad Faculty of Technical Sciences Novi Sad Serbia

ISBN: (纸本)9781665404174

Driving lane detection and collision avoidance are common Advanced Driving Assistant systems in modern vehicles. In this paper the algorithm for obstacle detection inside driving lane and vehicle speed adjustment is proposed. The proposed algorithm processes an image from a front view camera using traditional computer vision algorithms such as color filtering, Canny edge detection and Random sample consensus (RANSAC) to detect driving lane and to detect possible obstacle inside the driving lane. The abovementioned algorithms are implemented in the C++ programming language using a OpenCV library. The estimation of the obstacle distance from vehicle as well as automatic braking is based on data obtained using Carla simulator. The evaluation of the proposed algorithm is performed on still images taken from Carla simulator to show the effectiveness of obstacle detection and distance estimation while driving simulations are performed in order to evaluate vehicle speed adjustment in case of an obstacle within the driving lane. © 2021 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Comparative Evaluation of Machine Learning-Based Controller Area Network Intrusion Detection systems

Comparative Evaluation of Machine Learning-Based Controller ...

引用

International Conference on Information and Communication systems (ICICS)

作者： Omar Y. Al-Jarrah Omar A. Ramadan Baha Alsaify Suboh Alkhushayni Dept. Network Engineering and Security Faculty of Computer and Information Technology Jordan University of Science and Technology Irbid Jordan Dept. Mechanical Engineering Faculty of Engineering Jordan University of Science and Technology Irbid Jordan Dept. Information Systems Yarmouk University Irbid Jordan

The controller area network (CAN) protocol is widely used in vehicle networks. However, it lacks essential security features like confidentiality and authentication. To enhance vehicle security, researchers have proposed and developed various methods, including intrusion detection systems (IDSs). These IDSs play a key role in early detection of potential cyberattacks, safeguarding vehicles, passengers, and road users. Machine learning (ML) algorithms are increasingly employed in CAN IDSs but they face challenges due to diverse experimental settings, datasets, and metrics used for evaluation, impeding progress and comparison of different approaches in this field. This study aims to benchmark well-recognized ML algorithms, including gaussianNB, k-nearest neighbors (KNN), decision trees (DT), random forest (RF), long short-term memory (LSTM), and convolutional neural networks (CNN), for intrusion detection in CAN. We evaluate the performance of these algorithms using seven evaluation metrics on the real ORNL automotive dynamometer (ROAD) dataset, a state-of-the-art benchmark in this field. Experimental results demonstrate that KNN, DT, RF, LSTM, and CNN can detect various types of attacks (e.g., Fuzzing, targeted ID, and masquerade attacks) with high accuracy. However, the computational and time efficiency of tree-based classifiers, namely DT and RF, makes them a potentially appealing choice for real-time intrusion detection tasks in CAN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Joint Message Detection and Channel Estimation for Unsourced Random Access in Cell-Free User-Centric Wireless Networks

arXiv

引用

arXiv 2023年

作者： Çakmak, Burak Gkiouzepi, Eleni Opper, Manfred Caire, Giuseppe The Faculty of Electrical Engineering and Computer Science Technical University of Berlin Berlin10587 Germany Faculty of Electrical Engineering and Computer Science Technical University of Berlin Berlin10587 Germany The Centre for Systems Modelling and Quantitative Biomedicine University of Birmingham BirminghamB15 2TT United Kingdom

We consider unsourced random access (uRA) in a cell-free (CF) user-centric wireless network, where a large number of potential users compete for a random access slot, while only a finite subset is active. The random access users transmit codewords of length L symbols from a shared codebook, which are received by B geographically distributed radio units (RUs) equipped with M antennas each. Our goal is to devise and analyze a centralized decoder to detect the transmitted messages (without prior knowledge of the active users) and estimate the corresponding channel state information. A specific challenge lies in the fact that, due to the geographically distributed nature of the CF network, there is no fixed correspondence between codewords and large-scale fading coefficients (LSFCs). This makes current activity detection approaches which make use of this fixed LSFC-codeword association not directly applicable. To overcome this problem, we propose a scheme where the access codebook is partitioned in location-based subcodes, such that users in a particular location make use of the corresponding subcode. The joint message detection and channel estimation is obtained via a novel Approximated Message Passing (AMP) algorithm for a linear superposition of matrix-valued sources corrupted by noise. The statistical asymmetries in the fading profile and message activity lead to different statistics for the matrix sources, which distinguishes the AMP formulation from previous cases. In the regime where the codebook size scales linearly with L, while B and M are fixed, we present a rigorous high-dimensional (but finite-sample) analysis of the proposed AMP algorithm. Exploiting this, we then present a precise (and rigorous) large-system analysis of the message missed-detection and false-alarm rates, as well as the channel estimation mean-square error. The resulting system allows the seamless formation of user-centric clusters and very low latency beamformed uplink-downlink communicat

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Deer Hunting Optimization with Deep Learning Enabled Emotion Classification on English Twitter Data

引用

computer systems science & engineering 2023年第12期47卷 2741-2757页

作者： Abdelwahed Motwakel Hala J.Alshahrani Jaber S.Alzahrani Ayman Yafoz Heba Mohsen Ishfaq Yaseen Amgad Atta Abdelmageed Mohamed I.Eldesouki Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia Department of Applied Linguistics College of LanguagesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Industrial Engineering College of Engineering at AlqunfudahUmm Al-Qura UniversityMakkahSaudi Arabia Department of Information Systems Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddahSaudi Arabia Department of Computer Science Faculty of Computers and Information TechnologyFuture University in EgyptNew Cairo11835Egypt Department of Information System College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia

Currently,individuals use online social media,namely Facebook or Twitter,for sharing their thoughts and *** of emotions on social networking sites’finds useful in several applications in social welfare,commerce,public health,and so *** is expressed in several means,like facial and speech expressions,gestures,and written *** recognition in a text document is a content-based classification problem that includes notions from deep learning(DL)and natural language processing(NLP)*** article proposes a Deer HuntingOptimizationwithDeep Belief Network Enabled Emotion Classification(DHODBN-EC)on English Twitter Data in this *** presented DHODBN-EC model aims to examine the existence of distinct emotion classes in *** the introductory level,the DHODBN-EC technique pre-processes the tweets at different ***,the word2vec feature extraction process is applied to generate the word embedding *** emotion classification,the DHODBN-EC model utilizes the DBN model,which helps to determine distinct emotion class ***,the DHO algorithm is leveraged for optimal hyperparameter adjustment of the DBN *** extensive range of experimental analyses can be executed to demonstrate the enhanced performance of the DHODBN-EC approach.A comprehensive comparison study exhibited the improvements of the DHODBN-EC model over other approaches with increased accuracy of 96.67%.

关键词： Deer hunting optimization deep belief network emotion classification Twitter data sentiment analysis english corpus

来源：评论

学校读者我要写书评

暂无评论

Study on material removal mechanism for Cu-CMP on a patterned silicon wafer 10

Study on material removal mechanism for Cu-CMP on a patterne...

引用

10th International Conference on Leading Edge Manufacturing Technologies in 21st Century, LEM 2021

作者： Bakier, Mohammed A.Y.A. Matsumoto, Ryuunosuke Fuchiwaki, Masaki Khajornrungruang, Panart Suzuki, Keisuke Department of Mechanical Information Science and Technology Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology 820-8502 Japan Department of Mathematics Faculty of Science Assiut University Egypt

Pattern effect as dishing and erosion on Cu-CMP process become a serious problem to fabricate multilevel interconnect in advanced ULSI devices. In the current study, planarization models using patterned wafer and ANSYS software are suggested to make precise predictions of the post-CMP surface height to support optimize the layout design. The slurry flow effect on the copper body has been investigated and the removed mass character is monitored through the stress distribution at the solid domain. By determination of the removal regions by the calculation, we can avoid the dishing and erosion areas in the patterned area from the post-CMP process. © 2021 The Japan Society of Mechanical Engineers.

关键词： Silicon wafers

来源：评论

学校读者我要写书评

暂无评论

Sustainable Smart Road: A Unified Cost Estimation Model for Renewable-Powered Smart Roads

Sustainable Smart Road: A Unified Cost Estimation Model for ...

引用

Electrical, computer and Energy Technologies (ICECET), International Conference on

作者： Cristian Giovanni Colombo Michela Longo Leonardo Nocera Ryosuke Ota Dario Zaninelli Department of Energy Politecnico di Milano Milan Italy Politecnico di Milano Milan Italy Department of Electrical Engineering and Computer Science Faculty of Systems Design Tokyo Metropolitan University Tokyo Japan

ISBN: (数字)9798350395914

ISBN: (纸本)9798350395921

With new stringent policies affecting the transport and generation sectors, new technologies have emerged to drive the electric and technological transition. One of these is the smart road, a highly sensorised system to enable the integration of new vehicles and safety technologies. In this paper, the implementation of a smart road is simulated, first from an energy point of view and then from an economic point of view, by identifying the power demand of components and their cost. Next, the energetic core of the smart road is implemented. The energy core consists of a PV plant capable of powering the infrastructure. In this paper a simulation to test the proposed methodology is implemented. In the case study, a 280.05 kW smart road is powered by an optimally dimensioned PV plant. The production guaranteed by the 283.8 kWp plant will be 389.49 MW $h$ /year and requires $5723\mathrm{m}^{2}$ . Furthermore, the 234.57 $\mathrm{k}\unicode{x20AC}$ investment for the plant will represent less than 10% of the total investment, highlighting how renewable integration can be an economic sustainable purpose. Finally, another method to return the investment as quickly as possible will be proposed.

关键词： Renewable energy sources Costs Power demand Roads Net zero Estimation Production Safety Solar radiation Investment

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Face Detection by Corner Detection using Special Morphological Masking System and Fast Algorithm 2

An Intelligent Face Detection by Corner Detection using Spec...

引用

2nd International Conference on Smart Electronics and Communication, ICOSEC 2021

作者： Arulkumar, V. Jaya Prakash, S. Subramanian, E.K. Thangadurai, N. Sri Krishna College of Engineering and Technology Computer Science and Business Systems Coimbatore India Sir CR Reddy College of Engineering Department of Computer Science and Engineering Andhra Pradesh Eluru India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India Electronic and Communication Engineering Faculty of Engineering and Technology !!!Centre For Emerging Technologies Karnataka India

ISBN: (纸本)9781665433686

This research study has applied facial recognition techniques using the angle detection algorithm. Also, a fast angle detection algorithm has been used here, but modified it by applying a shielding technique to create a technique related to loud noise. This article describes twelve facial signs that include the corner of the left eye, the corner of the right eye, the left eyebrow, the right eyebrow, the corner of the lip, and the nostril. It consists of two parts;first, a private browsing technique has been performed to filter the image from noise. The proposed method is based on the assumption that an image is available from the front (fully front). Skin areas were first detected using a color-based learning algorithm and six sigma techniques on RGB, HSV, and NTSC scales. Other analyzes involve morphological processing using the detection of the borderline and the detection of the reflection from the light source of the eye commonly referred to as the eye point. In the second step, a fast angle detection algorithm has been used to detect the placeholders on the face. The Fast Angle Finder works on the Angular Response Function (CRF) which is calculated as the minimum change in intensity in all possible directions. Finally, a comparison has been made with other filtering techniques based on the proposed protection techniques. This article has performed different experiments by using the IRIS Face Database, BioID, and the Cohn Canada Database. The recognition rate obtained by the proposed method is appreciable. © 2021 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Depth Based Region Proposal: Multi-Stage Real- Time Object Detection

SSRN

引用

SSRN 2022年

作者： Ayman, Shehab Eldeen Hussein, Walid Karam, Omar H. Department of Software Engineering Faculty of Informatics and Computer Science The British University in Egypt Cairo Egypt Department of Computer Science Faculty of Informatics and Computer Science The British University in Egypt Cairo Egypt Department of Information Systems Faculty of Informatics and Computer Science The British University in Egypt Cairo Egypt

The majority of real-time object recognition systems operate on two-dimensional images, degrading the influence of the involved objects' third-dimensional (i.e., depth) information. The depth information of a captured scene provides a thorough understanding of an object in full-dimensional space. During the last decade, several region proposal techniques have been integrated into object detection. scenes’ objects are then localized and classified but only in a twodimensional space. Such techniques exist under the umbrella of two-dimensional object detection models such as YOLO and SSD. However, these techniques have the issue of being uncertain that an object's boundaries are properly specified into the particular scene. This paper proposes a unique region proposal and object detection strategy based on retrieving depth information for localization and segmentation of the scenes’ objects in real-time manner. The obtained results on different datasets show superior accuracy in comparison to the commonly implemented techniques with regards to not only detection but also a pixel-bypixel accurate localization of objects. © 2022, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Joint Energy Harvesting, Semantic Transmission Selection, Channel Allocation and Power Control for Resource-Constrained IoT Networks

Joint Energy Harvesting, Semantic Transmission Selection, Ch...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Nguyen Huu Sang Nguyen Duc Hai Nguyen Duc Duy Anh Nguyen Cong Luong Shimin Gong Dusit Niyato Faculty of Computer Science PHENIKAA University Hanoi Vietnam School of Intelligent Systems Engineering Sun Yat-sen University Guangzhou China College of Computing and Data Sciene Nanyang Technological University Singapore

ISBN: (数字)9798350387414

ISBN: (纸本)9798350387421

In this work, we propose the use of energy harvesting and semantic communication for Internet of Things (IoT) systems. The system allows IoT devices to harvest energy from a base station and then uses the harvested energy for extracting and transmitting semantic information, i.e., scene graphs, to the base station. The proposed network thus copes with the energy and network resource constraints of the IoT devices. To maximize the total image data or scene graph transmitted to the base station, we formulate a problem that optimizes the energy harvesting duration, the selection of original image or portions of scene graphs, transmit power, and channel allocation to the IoT devices. Under the high dynamics and uncertainty of the context and size of the collected images as well as the wireless channels and computing resources, we propose two advanced deep reinforcement learning (DRL) algorithms, i.e., advantage Actor-Critic (A2C) and proximal policy optimization (PPO), to solve the problem. Simulation results are implemented on the real dataset clearly showing that the performance achieved by the proposed algorithms is much higher than that achieved by the baseline scheme. This implies that more original images or triplets are transmitted.

关键词： Wireless communication Base stations Uncertainty Heuristic algorithms Simulation Semantics Channel allocation

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：