检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2021年第4期2卷 299-313页

作者： Bae, Ho Lee, Younghan Kim, Yohan Hwang, Uiwon Yoon, Sungroh Paek, Yunheung Department of Cyber Security EwhaWomans University Seoul03760 Korea Republic of Department of Electrical and Computer Engineering Seoul National University Seoul08826 Korea Republic of Department of Electrical and Computer Engineering Interdisciplinary Program in Bioinformatics Interdisciplinary Program in Artificial Intelligence Automation and Systems Research Institute Institute of NewMedia and Communications Institute of Engineering Research Seoul National University Seoul08826 Korea Republic of

Recent research has shown that a small perturbation to an input may forcibly change the prediction of a machine learning (ML) model. Such variants are commonly referred to as adversarial examples. Early studies have focused mostly on ML models for image processing and expanded to other applications, including those for malware classification. In this article, we focus on the problem of finding adversarial examples against ML-based portable document format (PDF) malware *** deem that our problem is more challenging than those againstMLmodels for image processing because of the highly complex data structure of PDF and of an additional constraint that the generated PDF should exhibit malicious behavior. To resolve our problem, we propose a variant of generative adversarial networks that generate evasive variant PDF malware (without any crash), which can be classified as benign by various existing classifiers yetmaintaining the original malicious behavior. Our model exploits the target classifier as the second discriminator to rapidly generate an evasive variant PDF with our new feature selection process that includes unique features extracted from malicious PDF files. We evaluate our technique against three representative PDF malware classifiers (Hidost 13, Hidost 16, and PDFrate-v2) and further examine its effectiveness with AntiVirus engines from VirusTotal. To the best of our knowledge, our work is the first to analyze the performance against the commercial AntiVirus engines. Our model finds, with great speed, evasive variants for all selected seeds against state-of-The-Art PDF malware classifiers and raises a serious security concern in the presence of adversaries. © 2021 Institute of electrical and Electronics Engineers Inc.. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Separation of Heart and Lung Sounds by A Deep Network-Based Model

Separation of Heart and Lung Sounds by A Deep Network-Based ...

引用

IEEE International Conference on Knowledge Innovation and Invention (ICKII)

作者： Tung-Sheng Tsai Chun-Chieh Hsu Ching-Lung Hsieh Yi-Jui Liu Ph.D. Program of Electrical and Communications Engineering Feng Chia University Feng Chia University Chung Shan Medical University Hospital

Breath and heart sounds are the two main biological sound signals. Heart sounds are produced by the beating of the heart caused by blood flows in the heart valves and blood vessels, while lung sounds are produced by the flow of air in and out of the airways during the breathing cycle. Both signals are recorded from the chest area. However, these two signals are mostly superimposed on each other, so it is of great research interest to separate these heart sound signals (HSS) and lung sound signals (LSS). A "Looking to Listen" model developed by Google, is a joint audiovisual model for isolating a single speech signal from a mix of sounds such as other speakers and background noise. In this study, we evaluated the feasibility of separating HSS and LSS by the audio part of the "Looking to Listen" model. We collected the pure HSS (PHSS) and pure LSS (PLSS) data from the public website (kaggle dataset, CoronaHack Respiratory Sound Dataset). Then, heart and lung sounds (MHLS) were combined HSS and LSS with different weighting power (3:7, 5:5, and 7:3). A total of 8076 MHLSs were generated with 72% of the data in the training set, 10% in the validation set, and 18% in the test set. The cross-correlation coefficient (CC) of pure sound and mixed sound and CC of separated and pure sounds were compared to evaluate the efficacy of extraction HSS or LSS from MHLS. The results showed the mean CC was 0.4, 0.7, and 0.9 for pure HSS and MHLS with 3:7, 5:5, and 7:3, respectively; and the mean CC was 0.79, 0.87, and 0.97 for pure HSS and predicted HSS with 3:7, 5:5, and 7:3, respectively. The mean CC was 0.9, 0.7, and 0.4 for pure LSS and MHLS with 3:7, 5:5, and 7:3, respectively. The mean CC was 0.95, 0.91, and 0.81 for pure LSS and predicted LSS with 3:7, 5:5, and 7:3, respectively. The feasibility of separating HSS and LSS by the audio part of the "Looking to Listen" model was validated.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Investigation of Induced EFT Transient Noise and Effect on Chip and Package Level 13

Investigation of Induced EFT Transient Noise and Effect on C...

引用

13th Asia-Pacific International Symposium on Electromagnetic Compatibility and Technical Exhibition, APEMC 2022

作者： Lin, Han-Nien Ho, Tzu-Hao Syu, Wan-Yu Wei, Yu-Ming Lee, Yueh-Hsun Ye, Qain-Yu Huang, Cheng-Hao Ku, Yuan-Fu Lin, Liang-Yang Lin, Jeffreyyen-Ting Feng Chia University Department of Communications Engineering Taichung City Taiwan Ph.D. Program of Electrical and Feng Chia University Communications Engineering Taichung City Taiwan Electronics Testing Center Taiwan Ministry of Economic Affairs Bureau of Standards Taipei City Taiwan ECE. University at Albany New York United States

ISBN: (数字)9781665416719

ISBN: (纸本)9781665416719

This paper investigates the noise induced from EFT Burst transient IEC61000-4-4 on the chip and package levels and analyzes its degradation effect. We first introduce the EFT Burst transient generator model previously established published with ANSYS Designer, which has later been adopted into ANSYS Electronics Desktop serving for immunity effect and protection measure analysis. We then describe how electromagnetic simulations can provide chip-level immunity analysis for IEC 62215-3. The analysis of EFT pulse propagation can be extended to package level with its impact on clock waveforms of different frequencies. With the help of established model, the residual transient noise energy due to normally found decoupling capacitor will be observed to show its effectiveness on noise filtering and the significant benefits to EMS protection. This study intends to provide an efficient simulation model to help IC and package designers enhancing their design capability against EFT disturbance. © 2022 IEEE.

关键词： Electromagnetic simulation

来源：评论

学校读者我要写书评

暂无评论

Corrugated Quad-Ridged Dual-Polarized Wideband Horn Antenna For mm-Wave Applications

Corrugated Quad-Ridged Dual-Polarized Wideband Horn Antenna ...

引用

National Conference on Radio Science (NSRC)

作者： Mohamed N. Salem Mohamed I. Ahmed Amr H. Hussein Department of Electronics and communication Engineering Institute of Aviation Engineering and Technology (IAET) Giza Egypt Microstrip department Electronics Research Institute El-Nuzha Cairo Electronics and Communication Program Faculty of Engineering Egypt University of informatics New Administrative Capital Knowledge City Egypt Electronics and Electrical Communications Engineering Dept. Faculty of Engineering Tanta University Tanta Egypt Electronics and Electrical Communications Engineering Department Faculty of Engineering Horus University Egypt New Damietta Egypt

This paper showcases the development of a wideband Dual-polarized horn antenna for mm-wave applications. It can be used for reflector feeding, imaging, satellite communication and power transmission due to its enhanced parameters. The working bandwidth is 10 GHz from 4 GHz to 14 GHz (VSWR $\lt1.9)$. This design is formed of three parts: 1) the waveguide is designed to support the entire bandwidth and to improve the impedance matching 2) four ridges to enable Dual-polarized antenna 3) the flared part is corrugated to enhance the side lobe level (SLL). The insertion between the two ports is less than -25 dB for most frequencies. The SLL is less than -25 dB for the low frequencies and -30 dB for the high frequencies. The co- and cross-pol radiation pattern simulation shows that the cross-pol magnitude is 20-30 dB less than the co-pol magnitude. These results have been proved using the CST MWS and Ansys HFSS software.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Preliminary Design for Reference tracking feedback for Medical Cyber-Physical Pharmacokinetic Systems 26

Preliminary Design for Reference tracking feedback for Medic...

引用

2024 IEEE International Conference on Automation/26th Congress of the Chilean Association of Automatic Control, ICA-ACCA 2024

作者： Oliveira, Pedro M. Bustos, Daniel Lobo, Rodolfo Lacerda, Marcio J. Palma, Jonathan M. Federal University of Minas Gerais Graduate Program in Electrical Engineering Belo Horizonte Brazil Universidad Católica Del Maule Dept. of Translational Medicine Talca Chile Universidad Diego Portales Ingenieria en Telecomunicaciones e Informática Santiago Chile London Metropolitan University Centre for Communications Technology School of Computing and Digital Media London United Kingdom Universidad de Talca Faculty of Engineering Curicó Chile

ISBN: (纸本)9798350378115

This paper addresses the reference tracking control problem for Medical Cyber-Physical Systems (MCPS). The control theory is employed to guarantee the suitable concentration of drugs in the body of patients to guarantee a safe treatment. The MCPS is modeled as a switched system, and the modes consider the different scenarios for the problem. A discrete-time model is utilized for the pharmacokinetic process, and the zero input control strategy is employed to design state-feedback controllers with a guaranteed exponential convergence rate. A numerical experiment is presented to illustrate the validity and effectiveness of our method. © 2024 IEEE.

关键词： State feedback

来源：评论

学校读者我要写书评

暂无评论

Evaluation of an Intelligent Edge Computing System for the Hospital Intensive Care Unit 3

Evaluation of an Intelligent Edge Computing System for the H...

引用

3rd IEEE Eurasia Conference on Biomedical engineering, Healthcare and Sustainability, ECBIOS 2021

作者： Zida, Serge Ismael Lin, Yue-Der Lee, Cheng Lin Tsai, Yi Lun Program of Electrical and Communications Engineering Feng Chia University Taichung Taiwan Program of Biomedical Informatics and Biomedical Engineering Feng Chia University Taichung Taiwan Department of Automatic Control Engineering Feng Chia University Taichung Taiwan

ISBN: (纸本)9781728193045

The evolution of medical technology along with information and communication technologies has accelerated the development and operationalization of smart hospitals recently. Traditionally, such hospitals typically rely on cloud computing platforms for data treatment and processing. However, the expansion and popularization of Internet of Medical Things (IoMT) devices and constant data monitoring have resulted in massive amounts of generated data, leading to the overload of the cloud infrastructure. This results in high power consumption and latency in data transmission, which is critical especially in a healthcare environment where data flow must be particularly responsive. Thus, we proposed and designed a Raspberry Pi-based edge computing system to computer-intensive care unit (ICU) data at the periphery of the network to offload the hospital cloud platform. ICU medical data were simulated from the PhysioNet MIMIC III database and transferred to the edge platform for computation and identification of emergency cases that were then sent to the cloud level. We further discuss the current issues and prospects of edge computing in hospitals. © 2021 ECBIOS 2021. All rights reserved.

关键词： Intensive care units

来源：评论

学校读者我要写书评

暂无评论

Visual Field Examination Technology Based on Semi-transparent Elliptical Mirror

Visual Field Examination Technology Based on Semi-transparen...

引用

Educational Innovation (ECEI), IEEE Eurasian Conference on

作者： Chao-Kai Chang Chun-Yu Chiang Feng-Ming Yeh Chi-Hung Lee Chuen-Lin Tien Der-Chin Chen Department of Optometry Yuanpei University of Medical Technology Hsinchu Taiwan Ph.D. Program of Electrical and Communications Engineering Feng Chia University Taichung Taiwan Department of Electrical Engineering Feng Chia University Taichung Taiwan

In this study, the human visual field test technology is established by using an optoelectrical system consisting of a translucent ellipsoid, an area light source, and a landscape scene with an indicator. During the test, the subjects stared at the indicator directly in front of them with one eye and kept their eyeballs still, scanning the light strip with peripheral vision and using the mouse button plus the playback program to record the start and end positions of the scanning light strip in the landscape scene. This method is tested subjectively, and the subject needs to respond during the test. Therefore, before the test, the subject needs to understand the test process and be trained in advance to improve the exam accuracy. In the experiment, fifteen subjects with normal vision and no eye disease were selected. Their visual fields were confirmed normal after a preliminary assessment. The test results showed that the subjects' eyes were within the normal visual field, indicating that this method was feasible. In this research, a digital optical platform for the near visual field is proposed to establish an optoelectric visual field measurement technology. The proposed method is characterized by small size, rapid operation, and easy portability. With the digital LCD and visual imaging technology, both dynamic and static visual fields can be tested. The test data on the eyes' upper, lower, nasal, and temporal sides were consistent with the normal visual field. This shows that this method is feasible and worthy of promotion in the optometry industry.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Quality Improvements in the electrical Design of Typical DC-DC Electronic Power Converter for High-Voltage Applications 8

Quality Improvements in the Electrical Design of Typical DC-...

引用

8th International Conference on engineering and Emerging Technologies, ICEET 2022

作者： Recto, King Harold A. Escoto, Miguel T. Hernandez, Noel B. Ateneo de Manila University Department of Electronics Computer and Communications Engineering Quezon City Philippines Electrical and Electronics Engineering Institute University of the Philippines Diliman Quezon City Philippines Centro Escolar University Post-doctoral Program in Quality Management of the Graduate School Manila Philippines

ISBN: (纸本)9781665491068

The green transition has brought about a worldwide-shift to the use of renewables as alternative energy sources. Because of this, high voltage DC has been a field of interest in power electronics due to its capability in efficiently transmitting power to reach remote areas. Typical DC-DC electronic power converter design has the capability of boosting voltage level to a certain extent but not enough for high-voltage applications. Using the DMAIC Approach of the Six Sigma, quality improvements in the design was proposed to stabilize operating frequency, bring up the output voltage from 100 VDC to 4,000 VDC and provide at least 10% margin of error in the apparent power measured at the output side to offset inherent losses in the electrical design. These proposed quality improvements were sustained by designing a control circuit that would ensure the attainment of the parameters set in the Define Phase of the DMAIC Approach. The result of the study is a practical 12 VDC to 4,000 VDC boost converter design that has incorporated all the proposed quality improvements. © 2022 IEEE.

关键词： Six sigma

来源：评论

学校读者我要写书评

暂无评论

Spleen-preserving distal pancreatectomy from multi-port to reducedport surgery approach

引用

World Journal of Gastrointestinal Surgery 2023年第7期15卷 1501-1511页

作者： Ching-Lung Hsieh Tung-Sheng Tsai Cheng-Ming Peng Teng-Chieh Cheng Yi-Jui Liu Department of Computer Science and Information Engineering Feng Chia UniversityTaichung 40724TaiwanChina Department of Surgery Chung Shan Medical University HospitalTaichung 40201TaiwanChina PhD Program of Electrical and Communications Engineering Feng Chia UniversityTaichung 40724Taiwan School of Medicine Chung Shan Medical UniversityTaichung 40201Taiwan Da Vinci Minimally Invasive Surgery Center Chung Shan Medical University HospitalTaichung 40201Taiwan Department of Automatic Control Engineering Feng Chia UniversityTaichung 407Taiwan

BACKGROUND Minimally invasive pancreatic surgery via the multi-port approach has become a primary surgical method for distal pancreatectomy(DP)due to its advantages of lower wound pain and superior cosmetic *** studies have applied reduced-port techniques for DP in an attempt to enhance cosmetic outcomes due to the minimally invasive *** recent review studies have compared multi-port laparoscopic DP(LDP)and multi-port robotic DP(RDP);most of these studies concluded multi-port RDP is more beneficial than multi-port LDP for spleen ***,there have been no comprehensive reviews of the value of reduced-port LDP and reduced-port *** To search for and review the studies on spleen preservation and the clinical outcomes of minimally invasive DP that compared reduced-port DP surgery with multi-port DP *** The PubMed medical database was searched for articles published between 2013 and *** search terms were implemented using the following Boolean search algorithm:(“distal pancreatectomy”OR“left pancreatectomy”OR“peripheral pancreatic resection”)AND(“reduced-port”OR“single-site”OR“single-port”OR“dual-incision”OR“single-incision”)AND(“spleen-preserving”OR“spleen preservation”OR“splenic preservation”).A literature review was conducted to identify studies that compared the perioperative outcomes of reduced-port LDP and reduced-port *** Fifteen articles published in the period from 2013 to 2022 were retrieved using three groups of search *** studies were added after manually searching the related ***,10 papers were selected after removing case reports(n=3),non-English language papers(n=1),technique papers(n=1),reviews(n=1),and animal studies(n=1).The common items were defined as items reported in more than five papers,and data on these common items were extracted from all *** ten studies included a total of 337 patients(females/males:231/106)who underwent *** total,166 patients(females/male

关键词： Minimally invasive surgery Robotic distal pancreatectomy Laparoscopic distal pancreatectomy Spleen preservation Reduced-port Multi-port

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Key Features Analysis and Recommendations based Cyber Intrusion Detection for Satellite-Terrestrial Networks

A Comprehensive Key Features Analysis and Recommendations ba...

引用

Novel Intelligent and Leading Emerging Sciences Conference (NILES)

作者： Esraa Shehab Shaimaa Ahmed Elsaid Ahmed M. Mattar Dept. of Electrical Engineering Computer Engineering and Systems program Badr University in Cairo (BUC) Cairo Egypt Dept. of Electronics and Communications Engineering Zagazig University Zagazig Egypt Dept. of Computer engineering and artificial intelligence military technical college Cairo Egypt

ISBN: (数字)9798350378511

ISBN: (纸本)9798350378528

The integration of Satellite-Terrestrial Networks (ISTN) necessitates advanced security measures, particularly Intrusion Detection Systems (IDSs). This study introduces hybrid sequential intrusion detection models for ISTNs, combining Deep Learning (DL) and Machine Learning (ML) techniques. The models employ both anomaly-based and signature-based detection to enhance accuracy, utilizing methods such as Extra Trees (ET), Decision Trees (DT), Random Forest (RF), XGBoost (XGB), and Gated Recurrent Units (GRU). These models are chosen for their superior performance and are used sequentially to improve IDSs effectiveness. RF-based Sequential Feature Selection (RF-SFS) is also utilized to reduce dataset dimensionality, which in turn decreases the computational costs for each model. Evaluations using UNSW-NB15 and STIN datasets-representing terrestrial and satellite traffic, respectively-demonstrate the models' superiority over traditional IDSs. The XGB-ET model achieved 99.99% accuracy in anomaly detection, while the XGB-GRU model attained 89% accuracy in signature-based detection on the UNSW-NB15 dataset. On the STIN dataset, the ET-DT-GRU model reached 96.47% accuracy in signature-based detection. Additionally, RF-SFS reduced execution times, with training and testing speedups up to 2.8x.

关键词： Training Accuracy Satellites Computational modeling Intrusion detection Space-air-ground integrated networks Feature extraction Security Random forests Testing

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：