检索结果-内蒙古大学图书馆

15th International Conference on computer Science and its Applications, CSA 2023 and 17th KIPS International Conference on Ubiquitous Information Technologies and Applications, CUTE 2023

作者： Ahn, Jungsub Cho, Taeho Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of College of Computing and Informatics Sungkyunkwan University Suwon16419 Korea Republic of

ISBN: (纸本)9789819724468

With the increasing complexity of systems, various studies are being conducted to accurately express and solve problems. Discrete Event System Specification (DEVS), one of the simulation theories, expresses a problem as a hierarchical model. The Behavior Monitoring-DEVS (BM-DEVS) theory is an extension of DEVS. It monitors the behavior of interest by expressing it as temporal rules in the model. In BM-DEVS, the defined temporal rules need to be converted into Büchi automata and applied to the model to evaluate the behavior expressed by the rules. To achieve this, modelers need to translate temporal rules into automata and verify these. This consumes a substantial amount of time. To solve this problem, this paper proposes a method to automatically translate temporal rules into automata for rule evaluation. In this proposed method, when temporal rules are input, structuring work is performed to match the rule structure and model structure. Moreover, a more convenient modeling environment is provided to modelers through the rule expansion function. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Automata theory

来源：评论

学校读者我要写书评

暂无评论

Wrapper-Based Feature Selection to Improve The Accuracy of Intrusion Detection System (IDS) 10

Wrapper-Based Feature Selection to Improve The Accuracy of I...

引用

10th International Conference on Wireless and Telematics, ICWT 2024

作者： Jupriyadi Budiman, Arief Hamidi, Eki Ahmad Zaki Ahdan, Syaiful Negara, Ridha Muldina Institut Teknologi Bandung School of Electrical Engineering and Informatics Bandung Indonesia Universitas Teknokrat Indonesia Faculty of Engineering and Computer Science Bandarlampung Indonesia Universitas Gadjah Mada Department Computer Science and Electronics Yogyakarta Indonesia UIN Sunan Gunung Djati Bandung Electrical Engineering Department Bandung Indonesia Telkom University School of Electrical Engineering Bandung Indonesia

ISBN: (纸本)9798350377057

An Intrusion Detection System (IDS) is a system that can detect attacks on a network. IDS systems can be built using machine learning approaches. However, significant network traffic and many features cause machine learning algorithms to work slowly. Not all available features are essential for use as a reference in an intrusion detection system. Feature selection is important because it can reduce the dataset and speed up computing time in building models and detection systems. In this paper, feature selection using the wrapper method is proposed. Its performance is compared with filter-based feature selection, such as chi-square, information gain, gain ratio, and correlation-based feature selection (CFS). Based on the exploration, the results showed that the feature selection algorithm using the wrapper method was superior to other algorithms. The number of critical features discovered and the detection system's precision serve as proof of the wrapper approach. With only three features as a reference, the detection system produces an accuracy of 96.22%. It increases 5.84% from 90.38% to 96.22%. Computation time also increases because the number of features used is tiny compared to other algorithms and uses all features. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Trimmed Non-Local Means Filtering for the Suppression of Mixed Noise in Color Images

Trimmed Non-Local Means Filtering for the Suppression of Mix...

引用

2023 International Conference on electrical, computer, Communications and Mechatronics engineering, ICECCME 2023

作者： Kusnik, Damian Smolka, Bogdan Smolka, Milena Silesian University of Technology Faculty of Automatics Electronics and Informatics Gliwice Poland Agh University of Science and Technology Faculty of Electrical Engineering Automatics Computer Science and Biomedical Engineering Krakow Poland

ISBN: (纸本)9798350322972

In this paper, a novel approach to the problem of mixed Gaussian and impulsive noise reduction in color images is proposed. The elaborated denoising framework is based on the Non-Local Means technique, which has been shown to effectively suppress Gaussian noise. To overcome the inability of this filter to deal with impulsive distortions, a robust similarity measure between image patches, that is insensitive to the impact of impulsive distortions, was developed. First, the distorted pixels of the image are detected using the concept of a peer group. If the number of neighbors of a pixel at the center of a filtering window, whose Euclidean distance in the RGB color space does not exceed a threshold value, is smaller than a predefined value, then the considered pixel is treated as corrupted. Afterwards, the similarity between image patches are calculated in a standard way omitting the noisy pixels. In this way, only the average of distances between pairs of unaffected pixels are calculated. Thus, the closeness measure of the patches, which serves as the coefficient in weighted averaging of pixels in the processing block, is not affected by impulsive noise and is still able to cope with the Gaussian noise component. The proposed filtering design is capable of reducing even strong mixed noise while preserving image details and edges. Moreover, it is not computationally intensive, so it can be used in real-time image processing scenarios. © 2023 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Assessing the stiffness of intact bone marrow with non-contact optical coherence elastography 12

Assessing the stiffness of intact bone marrow with non-conta...

引用

Optical Elastography and Tissue Biomechanics XII 2025

作者： Singh, Amandeep Singh, Manmohan Aglyamov, Salavat R. Mayerich, David Larin, Kirill V. Department of Biomedical Engineering University of Houston TX77204 United States Department of Mechanical and Aerospace Engineering University of Houston TX77204 United States Department of Electrical and Computer Engineering University of Houston TX77204 United States

ISBN: (纸本)9781510683907

Bone marrow plays an important role in regulating immunity for homeostasis and controlling stromal cell trafficking. Bone marrow cells are sustained by the framework of connective tissues that preserve the mechanical and functional integrity of the tissue. Optical coherence elastography (OCE) is a potential method to measure the biomechanical properties of bone marrow with high spatio-temporal resolution. In this work, we demonstrate the quantification of wave speed at different locations along the diaphysis of mice femur samples using non-contact air-coupled ultrasound OCE (ACUS-OCE). The preliminary results from the current approach show that the ACUS-OCE can characterize the mechanical stiffness of intact bone marrow and can be used for minimally invasive and ex vivo clinical applications. © 2025 SPIE.

关键词： Bone

来源：评论

学校读者我要写书评

暂无评论

SinAr Mobile Application for Learning the Javanese Letters: A Case Study

SinAr Mobile Application for Learning the Javanese Letters: ...

引用

2023 IEEE Symposium on Wireless Technology and Applications, ISWTA 2023

作者： Husniah, Lailatul Pratama, Dimas Agung Nuryasin, Ilyas Yuhana, Umi Laili Yuniarno, Eko Mulyanto Purnomo, Mauridhi Hery Institut Teknologi Sepuluh Nopember Department of Electrical Engineering Surabaya Indonesia Universitas Muhammadiyah Malang Department of Informatics Malang Indonesia Institut Teknologi Sepuluh Nopember Department of Informatics Surabaya Indonesia Institut Teknologi Sepuluh Nopember Department of Electrical Engineering Department of Computer Engineering Surabaya Indonesia

ISBN: (纸本)9798350310955

The Javanese language is a local subject taught in almost all elementary schools on the island of Java. Most students have difficulties learning Javanese, especially the Javanese letters. They can hardly read and write the Javanese traditional scripts as they are no longer for daily reading and writing. Therefore, this research develops attractive Javanese letters learning medium to ease the students studying the Javanese letters independently and improve their understanding and learning outcomes as an Android-based mobile application. This study involved 57 students (28 students in the experimental group and 29 students in the control group), two Javanese language teachers, and two media experts. Experiments and testing were conducted for approximately two weeks, with the experimental group using the SinAr application and the control group using textbooks during the learning process. The result is that the experimental group show a higher increase in learning outcomes than the control group, so it approached the ability of the control group, which was superior in Javanese lessons based on the pretest and post-test results. The SinAr application also supports understanding of the material, student learning independence, and interesting learning, based on the results of trials on 57 students who overall received and gave good responses to the SinAr application for each aspect of learning design, operational, and visual communication with scores of 4.29 (85%). © 2023 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Adaptive Technique of Impulsive Noise Removal in Color Digital Images 10

Adaptive Technique of Impulsive Noise Removal in Color Digit...

引用

10th International Conference on electrical and Electronics engineering, ICEEE 2023

作者： Smolka, Bogdan Mendrela, Monika Kusnik, Damian Smolka, Milena Silesian University of Technology Faculty of Automatics Electronics and Informatics Gliwice Poland Agh University of Science and Technology Faculty of Electrical Engineering Automatics Computer Science and Biomedical Engineering Krakow Poland

ISBN: (纸本)9798350304299

This paper describes a new technique for removing impulsive noise in digital color images. The proposed method uses a measure of the pixel distortion caused by the impulsive noise, expressed as the sum of the Euclidean distances between the central pixel and its closest neighbors in the filtering window. This corruption measure is used to determine a weighted average of the pixels from the local neighborhood that is not affected by the distorted pixels. The filtering output is obtained using a soft switching scheme, where the denoising result is determined as a weighted average of the central pixel of a processing window and its robust estimate. The weighting coefficient is calculated based on the amount of distortion of the central pixel. Thus, if the central pixel is highly distorted, it is replaced by its robust estimate, otherwise it is not significantly changed. The parameters that determine the image enhancement result are adaptively adjusted by using a noise-resistant image contrast measure. The proposed filter design is able to effectively suppress impulsive noise while preserving fine image details and edges. Comparison with existing algorithms shows that the proposed method provides better denoising results than the most efficient filters designed for impulsive noise suppression in color images. Moreover, the new method is very fast and can be used in real-time denoising scenarios. © 2023 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Deep Transfer Learning Techniques in Intrusion Detection System-Internet of Vehicles: A State-of-the-Art Review

引用

computers, Materials & Continua 2024年第8期80卷 2785-2813页

作者： Wufei Wu Javad Hassannataj Joloudari Senthil Kumar Jagatheesaperumal Kandala N.V.P.SRajesh Silvia Gaftandzhieva Sadiq Hussain Rahimullah Rabih Najibullah Haqjoo Mobeen Nazar Hamed Vahdat-Nejad Rositsa Doneva School of Information Engineering Nanchang UniversityNanchang330031China Department of Computer Engineering Technical and Vocational University(TVU)Tehran***Iran Department of Computer Engineering University of BirjandBirjand***Iran Department of Computer Engineering Babol BranchIslamic Azad UniversityBabol***Iran Department of Electronics&Communication Engineering Mepco Schlenk Engineering CollegeSivakasi626005India School of Electronics Engineering VIT-AP UniversityNear Vijayawada522237India Faculty of Mathematics and Informatics University of Plovdiv Paisii HilendarskiPlovdiv4000Bulgaria Examination Branch Dibrugarh UniversityDibrugarh786004India Department of Computer Engineering Faculty of EngineeringUniversity of BirjandBirjand***Iran Faculty of Electrical and Computer Engineering University of BirjandBirjand***Iran Malaysian Institute of Information Technology Universiti Kuala LumpurKuala Lumpur50250Malaysia Faculty of Physics and Technology University of Plovdiv Paisii HilendarskiPlovdiv4000Bulgaria

The high performance of IoT technology in transportation networks has led to the increasing adoption of Internet of Vehicles(IoV)*** functional advantages of IoV include online communication services,accident prevention,cost reduction,and enhanced traffic *** these benefits,IoV technology is susceptible to cyber-attacks,which can exploit vulnerabilities in the vehicle network,leading to perturbations,disturbances,non-recognition of traffic signs,accidents,and vehicle *** paper reviews the state-of-the-art achievements and developments in applying Deep Transfer Learning(DTL)models for Intrusion Detection Systems in the Internet of Vehicles(IDS-IoV)based on anomaly ***-IoV leverages anomaly detection through machine learning and DTL techniques to mitigate the risks posed by *** systems can autonomously create specific models based on network data to differentiate between regular traffic and *** these techniques,transfer learning models are particularly promising due to their efficacy with tagged data,reduced training time,lower memory usage,and decreased computational *** evaluate DTL models against criteria including the ability to transfer knowledge,detection rate,accurate analysis of complex data,and *** review highlights the significant progress made in the field,showcasing how DTL models enhance the performance and reliability of IDS-IoV *** examining recent advancements,we provide insights into how DTL can effectively address cyber-attack challenges in IoV environments,ensuring safer and more efficient transportation networks.

关键词： Cyber-attacks internet of things internet of vehicles intrusion detection system

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Meets Sparse Regularization: A Signal Processing Perspective

引用

arXiv 2023年第6期40卷 63页

作者： Parhi, Rahul Nowak, Robert D. The Biomedical Imaging Group École Polytechnique Fédérale de Lausanne Lausanne Switzerland The Department of Electrical and Computer Engineering University of Wisconsin–Madison MadisonWI United States

Deep learning has been wildly successful in practice and most state-of-the-art machine learning methods are based on neural networks. Lacking, however, is a rigorous mathematical theory that adequately explains the amazing performance of deep neural networks. In this article, we present a relatively new mathematical framework that provides the beginning of a deeper understanding of deep learning. This framework precisely characterizes the functional properties of neural networks that are trained to fit to data. The key mathematical tools which support this framework include transform-domain sparse regularization, the Radon transform of computed tomography, and approximation theory, which are all techniques deeply rooted in signal processing. This framework explains the effect of weight decay regularization in neural network training, the use of skip connections and low-rank weight matrices in network architectures, the role of sparsity in neural networks, and explains why neural networks can perform well in high-dimensional problems. Copyright © 2023, The Authors. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Experiment on Multi-hop LoRa for Tracking Application

引用

International Journal of Sensors, Wireless Communications and Control 2023年第1期13卷 29-39页

作者： Sagala, Albert Lubis, Ramot Silalahi, Gomgom Ginting, Estika V. Simorangkir, Andreas J. D. Faculty of Informatics and Electrical Engineering Institut Teknologi Del Toba Samosir Indonesia Department of Computer Science Binus University West Jakarta Indonesia

Background: The Internet of Things (IoT) is an embryonic model that converts real-world things (objects) into smarter devices. IoT is applicable to a variety of application domains, including healthcare, smart grid, and agriculture. Low Power Wide Area Network (LPWAN) technology can transmit data over long distances with a low data rate without using the internet. There-fore, this technology is suitable for sending sensor measurement data in Internet of Things (IoT) applications. LPWANs, such as LoRa, use a star topology to reach their coverage to the maximum power that can be transmitted, considering the environmental conditions in the test area and the LoRa parameters used. Whereas for application development in rural areas, there is no internet connection, and often longer coverage is required from the sensor node to the gateway. Objective: This study aims to increase the transmission range from the end node to the gateway by adding an intermediate node. It is used as a relay from the end node to the gateway. Method: Static routing was applied so that any broadcast data from the end node would be for-warded first to the intermediate node and then to the gateway. Results: The LoRa transmission range expanded by changing the topology from peer-to-peer to multi-hop. An intermediate node between the transmitter (end node) and the gateway is available. In the experiment performed, a multi-hop with static routes successfully expanded the distance from 150 meters (single hop) to 250 meters (multi-hop), with a packet delivery ratio of 97%. In this experiment, GPS Ublox Neo was used for the sensor position and was successfully tested on the end node with an accuracy rate of 2.4% for latitude and 0.2% for longitude. Conclusion: The transmission range from the sensor node to the gateway can be extended using static routing by installing an intermediate node between the gateway and the sensor node. The data from the end node is successfully received by the gateway. © 2023 Be

关键词： energy efficiency GPS ublox neo internet of things LoRa tracking LPWAN multi-hop wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Channel selection and wavelet transformation-based data compression preserve motor unit information 46

Channel selection and wavelet transformation-based data comp...

引用

46th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2024

作者： Wang, Siyu Quinn, Kiara N. Slepyan, Ariel Qin, Lang Thakor, Nitish V. Johns Hopkins Whiting School of Engineering Department of Biomedical Engineering BaltimoreMD21218 United States Johns Hopkins Whiting School of Engineering Department of Electrical and Computer Engineering BaltimoreMD21218 United States

ISBN: (纸本)9798350371499

Both motor unit-based control algorithms and implantable interfaces are promising approaches to improve current prosthetic limbs by allowing control of more movements. However, combining the two methods poses a challenge due to the current wireless transmission capabilities which limits the amount of data that can be processed. Capturing the motor unit requires a higher sampling rate and higher channel counts. Thus, this paper investigates a data compression strategy comprised of two independent stages: recording data reduction by selecting fewer channels to be 'active' and minimization of the transmitting data through compression with wavelet transformation. We have demonstrated a promising wavelet compression pipeline using db4, which can compress the raw EMG signal 0.63% of its original size while maintaining low WMSE error (0.109) and high heatmap reconstruction correlation coefficient (0.9741±0.972). In addition, placing high-density electrodes along the muscle fibers during channel selection while utilizing wavelet transformation can compress 99.82% of transmitted data while preserving a MCC of 0.706 ± 0.169. © 2024 IEEE.

关键词： Data compression

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：