检索结果-内蒙古大学图书馆

2021 IEEE International Conference on Electrical, computer, Communications and Mechatronics Engineering, ICECCME 2021

作者： Otaru, Musa Adinoyi, Abdulkareem Ajiya, Mohammed Aljlayl, Mohammed Yanikomeroglu, Halim Bayero University Kano Department of Electrical Engineering Nigeria Technology Strategy Architecture Saudi Telecommunications Company Saudi Arabia Carleton University Dept. of Systems and Computer Engineering Ottawa Canada

ISBN: (纸本)9781665412629

We use fixed relays deployed by network operators to reduce re-transmission (thereby reducing network power requirements) in addition to providing excellent end-to-end error performance in a revisit to automatic repeat request-based cooperative relaying. The new relaying scheme facilitates the creation of a connectivity suitable for delay tolerant internet-of-things (IoT)-type services. For IoT devices, link reliability and power efficiency are a major system design consideration. The proposed scheme operates in the following fashion. The source (e.g., a sensor) transmits for a certain time window. During this period, the source and the relays do not require per transmission acknowledgment (ACK) from the destination. At the end of a transmission window, the destination sends a 'group' ACK. If negative, relays are invited to help. Depending on the cooperation strategy, each relay transmits in either one transmission time slot or a few time slots, using a suitably chosen higher-order modulation constellation. If no error occurs, the source continues its transmission. Furthermore, we devise a novel strategy for selecting the best relay for this new way of exploiting the benefits of multiple relays in a network. In the process, we reclaim the bandwidth expansion that comes with multi-relay system but still maintaining E2E bit error rate that is superior to that of a single relay cooperation. Numerical results that reveal the benefits of the new and modified ARQ cooperative relaying scheme are presented. © 2021 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Real-time Vital Signs Monitoring Based on COTS WiFi Devices

Real-time Vital Signs Monitoring Based on COTS WiFi Devices

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Gu, Yu Zhang, Xiang Yan, Huan Liu, Zhi Ji, Yusheng Hefei University of Technology School of Computer and Information Hefei China The University of Electro-Communications Dept. of Computer and Network Engineering Tokyo Japan National Institute of Informatics Information Systems Architecture Science Research Division Tokyo Japan

ISBN: (纸本)9781665401265

Real-time vital signs (breathing and heartbeat) monitoring is essential for patient care and sleep disease prevention. Current solutions are mostly based on wearable sensors or cameras, the former affects the quality of sleep, while the latter is not conducive to privacy protection, and the cost of these methods is usually expensive. In this paper, we propose Wital, a real-time vital signs monitoring system based on the low-cost and widespread COTS WiFi device. Most of the existing WiFi-based vital signs monitoring solutions utilize the line of sight (LOS) WiFi signals to achieve powerful performance. However, in our daily environments, NLOS sensing is more common. In this article, we first model the relationship between the energy ratio of LOS/NLOS signals and the ability to monitor vital signs based on the Ricean-K theory and theoretically prove that blocking LOS signals in NLOS sensing is more beneficial. We have also established a real-time vital signs monitoring system to verify our method, and the experimental results prove the effectiveness of our method. © 2021 IEEE.

关键词： Wi-Fi

来源：评论

学校读者我要写书评

暂无评论

Recommendation System Towards Residential Energy Saving Based on Anomaly Detection 5

Recommendation System Towards Residential Energy Saving Base...

引用

5th International Conference on Signal Processing and Information Security, ICSPIS 2022

作者： Atalla, Shadi Himeur, Yassine Mansoor, Wathiq Amira, Abbes Fadli, Fodil Copiaco, Abigail Sohail, Shahab Saquib University of Dubai College of Engineering and IT Dubai United Arab Emirates University of Sharjah Department of Computer Science Sharjah United Arab Emirates Qatar University Dept. of Architecture & Urban Planning Doha2713 Qatar Jamia Hamdard School of Engineering Sciences & Technology New Delhi110062 India

ISBN: (纸本)9781665492652

This paper presents a recommender system to promote energy consumption reduction behaviors in residential buildings. The system exploits data stream processing methods jointly with machine learning algorithms on real-time residential data. Specifically, the data stream includes disaggregated power consumption, context, and weather conditions data. Internally the system converts time-series data streams into discrete ordered data points, which serve as inputs for training ML models. This method is used to predict power consumption anomalies. Gradually, the system helps to shape its users' activities into more energy-efficient ones. The experimental evaluation on real and simulated datasets demonstrates the promising performance of the proposed method, primarily when the K-neighbors neighbors' algorithm is used to classify the features extracted with interleaving current with the previous data points. The performance assessment of the machine learning algorithms shows the suitability of our implementation for Edge and Fog platforms in terms of accuracy, latency, and model size. © 2022 IEEE.

关键词： Electric power utilization

来源：评论

学校读者我要写书评

暂无评论

Reconstruction of the Mosul Old City by Procedural Modelling

SSRN

引用

SSRN 2024年

作者： Hussein, Khalid Ahmed Ismaeel, Emad Hani Ihsan, Rasheed Rebar Sadeeq, Haval Tariq Architecture Engineering Department College of Engineering Nawroz University KRD Duhok Iraq Dept. of Architecture Coll. of Engineering University of Mosul Iraq Computer and Communication Department College of Engineering Nawroz University KRD Duhok Iraq Information Technology Department Technical College of Duhok Duhok Polytechnic University KRD Region Iraq

The old city of Mosul possesses a rich built heritage, featuring distinct architectural styles evolved, incorporating indigenous knowledge and expertise to address functional, climatic, economic, and construction requirements. Tragically, during the military operations in 2016-2017, Mosul Old City experienced extensive devastation, resulting in the loss of numerous landmarks and the irreplaceable built heritage of this city. However, digitization has emerged as a potent heritage preservation and restoration tool. It serves as a vital initial step in reviving deteriorated heritage by providing invaluable information to specialists. In light of this, the present study aims to regenerate the urban facades of Mosul's old city automatically, ensuring they retain their original characteristics. This objective will be accomplished by utilizing procedural modelling techniques and algorithms incorporating specific characteristics as constraints within the regeneration process. The research makes a notable contribution to digital architectural design by employing Shape Grammar analysis to derive rules. Subsequently, these rules are implemented through Python to facilitate the automatic generation of 750 heritage facade designs. Ultimately, the study demonstrates the feasibility of using procedural modelling to recreate the decimated urban fabric, ensuring the restored structures exhibit the same formal and structural characteristics as their predecessors. © 2024, The Authors. All rights reserved.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Efficient Concept Drift Handling for Batch Android Malware Detection Models

SSRN

引用

SSRN 2023年

作者： Molina-Coronado, Borja Mori, Usue Mendiburu, Alexander Miguel-Alonso, Jose Dept. of Computer Architecture and Technology University of the Basque Country UPV/EHU Ps. Manuel Lardizabal 1 Donostia-San Sebastián Gipuzkoa20018 Spain Dept. of Computer Science and Artificial Intelligence University of the Basque Country UPV/EHU Ps. Manuel Lardizabal 1 Donostia-San Sebastián Gipuzkoa20018 Spain

The rapidly evolving nature of Android apps poses a significant challenge to static batch machine learning algorithms employed in malware detection systems, as they quickly become obsolete. Despite this challenge, the existing literature pays limited attention to addressing this issue, with many advanced Android malware detection approaches, such as Drebin, DroidDet and MaMaDroid, relying on static models. In this work, we show how retraining techniques are able to maintain detector capabilities over time. Particularly, we analyze the effect of two aspects in the efficiency and performance of the detectors: 1) the frequency with which the models are retrained, and 2) the data used for retraining. In the first experiment, we compare periodic retraining with a more advanced concept drift detection method that triggers retraining only when necessary. In the second experiment, we analyze methods to reduce the amount of data used to retrain models. Specifically, we compare fixed sized windows of recent data with a more advanced method that selects those apps that help keep the training dataset small but diverse. Our experiments show that concept drift detection and sample buffer management mechanisms result in very efficient retraining strategies which can be successfully used to maintain the performance of the static Android malware state-of-the-art detectors in changing environments. © 2023, The Authors. All rights reserved.

关键词： Mobile security

来源：评论

学校读者我要写书评

暂无评论

Efficient Concept Drift Handling for Batch Android Malware Detection Models

arXiv

引用

arXiv 2023年

The rapidly evolving nature of Android apps poses a significant challenge to static batch machine learning algorithms employed in malware detection systems, as they quickly become obsolete. Despite this challenge, the existing literature pays limited attention to addressing this issue, with many advanced Android malware detection approaches, such as Drebin, DroidDet and MaMaDroid, relying on static models. In this work, we show how retraining techniques are able to maintain detector capabilities over time. Particularly, we analyze the effect of two aspects in the efficiency and performance of the detectors: 1) the frequency with which the models are retrained, and 2) the data used for retraining. In the first experiment, we compare periodic retraining with a more advanced concept drift detection method that triggers retraining only when necessary. In the second experiment, we analyze sampling methods to reduce the amount of data used to retrain models. Specifically, we compare fixed sized windows of recent data and state-of-the-art active learning methods that select those apps that help keep the training dataset small but diverse. Our experiments show that concept drift detection and sample selection mechanisms result in very efficient retraining strategies which can be successfully used to maintain the performance of the static Android malware state-of-the-art detectors in changing environments. © 2023, CC BY.

关键词： Mobile security

来源：评论

学校读者我要写书评

暂无评论

Fall Detection System for Elderly (FDS-E) using Low-cost Camera Based on LSTM and OpenPose

Fall Detection System for Elderly (FDS-E) using Low-cost Cam...

引用

IEEE Instrumentation and Measurement technology Conference

作者： Herti Miawarni Tri Arief Sardjono Eko Setijadi Wijayanti Mauridhi Hery Purnomo Dept. of Electrical Engineering Faculty of Intelligent Electrical and Informatics Technology (F-Electics) Institut Teknologi Sepuluh Nopember Surabaya Indonesia Dept. of Electrical Engineering Dept. of Biomedical Engineering Faculty of Intelligent Electrical and Informatics Technology (F-Electics) Institut Teknologi Sepuluh Nopember Surabaya Indonesia Dept. of Architecture Faculty of Engineering Universitas Diponegoro Semarang Indonesia Dept. of Electrical Engineering Dept. of Computer Engineering Faculty of Intelligent Electrical and Informatics Technology (F-Electics) Institut Teknologi Sepuluh Nopember University Center of Excellence on Artificial Intelligence for Healthcare and Society (UCE AIHeS) Surabaya Indonesia

Recently, many countries have been dealing with an increasing amount of elderly who are living alone. Unfortunately, fall incidents in the elderly tend to happen, and without proper dependable care would lead to fatal injuries. The elderly must be closely monitored under constant observation. Accidental falls are a leading cause of injury, mortality, and mobility limitations in the elderly. The expenses of national healthcare systems are also significantly impacted by accidental falls. These findings highlight the importance of investing heavily in the study and advancement of fall detection and intervention technologies. It is essential to recognize them early and provide fast assistance by developing technologies that can simultaneously improve the standard and the safety of the elderly's living environment. In this paper, we present a computer vision algorithm for falling incident detection using a low-cost camera and deep learning model. Ultimately, this algorithm can be used for the cases of elderly, in which falling risk is high and fatal. Furthermore, one self-developed dataset was used to validate the suggested approach experimentally. We used an OpenPose-based feature using a low-cost camera input and then classified each event or activity as either fall or non-fall. Classification tasks are carried out by Long Short-Term Memory (LSTM) with multiple validation metrics. The LSTM in this work is also optimized using Bayesian method. Finally, our approach to recognize falls has accuracy of 99.5%, which is distinct from other past works.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intermittent Fault Diagnosis of Analog Circuit Based on Enhanced One-Dimensional Vision Transformer and Transfer Learning Strategy

SSRN

引用

SSRN 2023年

作者： Wang, Shengdong Liu, Zhenbao Jia, Zhen Vong, Chi-Man Li, Zihao School of Civil Aviation Northwestern Polytechnical University Xi'An710072 China School of Mechanical and Electrical Engineering Xi'an University of Architecture and Technology Xi'An710055 China Dept. of Computer and Information Science University of Macau 999078 China

Intermittent faults of analog circuits are major causes of built-in test (BIT) false alarms. To enhance the reliability and maintainability of electronic system, an end-to-end approach based on enhanced one-dimensional Vision Transformer (1DViT) is constructed to realize intelligent diagnosis of intermittent faults. One multiscale convolution fusion module (MSC) is introduced into 1DViT to mine fault features on multiple time scales to enhance the interaction between global and local information. In addition, due to the complex operation and measurement conditions, it is difficult and time-consuming to obtain a large amount of data from practical test. To cope with this problem, transfer learning is introduced. The model will be first pre-trained with adequate simulation data which is readily accessible, and then fine-tuned with actual test data to match the practical distribution. Experiments on two typical circuits demonstrate that the proposed method could achieve excellent diagnostic result in practical test. © 2023, The Authors. All rights reserved.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

A Deep Neural Network for Detecting Broken and Scattered Power Lines in Complex Aerial Images

A Deep Neural Network for Detecting Broken and Scattered Pow...

引用

International Conference on Artificial Intelligence and computer Information technology (AICIT)

作者： Qiugen Pei Yuxuan Lai Nianxing Wei Shiting Wu Enterprise Architecture and Digitalization Department Guangdong Power Grid Co. Ltd. Guangzhou China Dept. School of Computer Science Guangdong University of Technology Guangzhou China Huizhou Boluo Power Supply Bureau Guangdong Power Grid Co. Ltd. Huizhou China

ISBN: (数字)9798350365443

ISBN: (纸本)9798350365450

Object detection algorithms constitute a pivotal task in the realm of computer vision, aiming to precisely identify and locate objects within images across diverse scenarios. In power systems, especially in aerial images used to detect wire breaks or scattered anomalies, object detection faces significant challenges. The distribution of wires is often uneven, appearing in different sizes in high-resolution images, and the diversity of fault shapes and sizes makes it difficult for traditional object detection models to recognize accurately. Moreover, the detection of small targets also limits the precision of traditional methods. To address the issue of diversity in fault shapes and sizes in high-resolution images, which makes it difficult for traditional object detection models to recognize accurately, first, we collect fault images of wire breaks and scatter under common scenarios, constructing the “EWF _detection” (Electric wire fault) dataset, and propose a Pyramid Multi-scale Object Detection Model, establishing the Hybrid Spatial Attention Pooling module, HSAP, which significantly enhances the multi-scale feature extraction capability. It not only improves the model's ability to focus on key features, but also suppresses unnecessary features, enhancing the expressiveness of the network, and effectively adapting to complex backgrounds, variable lighting conditions, and different line scales and directions for transmission line detection needs. This improvement makes our model perform exceptionally well in detecting rare faults in wires and accurately locate fault positions. These achievements provide reliable technical support for wire anomaly detection in the power industry and indicate a broad prospect of application in future power scenarios. Our method not only improves detection accuracy, but also maintains efficient detection speed, reducing reliance on a large number of fault line images. These advantages make our model an important technical tool for pow

关键词： Adaptation models Image recognition Shape Lighting Object detection Feature extraction Power industry Robustness Maintenance Wire

来源：评论

学校读者我要写书评

暂无评论

A Machine Vision-Based Person Detection under Low-Illuminance Conditions Using High Dynamic Range Imagery for Visual Surveillance System 3

A Machine Vision-Based Person Detection under Low-Illuminanc...

引用

3rd International Conference on Smart Technologies in Computing, Electrical and Electronics, ICSTCEE 2022

作者： Susa, Julie Ann B. Militante, Sammy V. Acoba, Aimee G. Evangelista, Ryan Soriente Lacatan, Luisito Lolong Lavina, Charlemagne G. Tanguilig, Bartolome T. Southern Luzon State University Dept. of Computer Engineering Quezon Lucban Philippines College of Engineering and Architecture University of Antique Antique Philippines Technological University of the Philippines Electronics Eng'g Technology Department Manila Philippines School of Graduate Studies Sulu State College Sulu Philippines College of Computing and Engineering Pamantasan Ng Cabuyao Laguna Philippines

ISBN: (纸本)9781665456647

The most difficult component of any computer vision application objects recognition and tracking. Video surveillance is a major study subject in computer vision in a dynamic environment, especially for security purposes. Video surveillance technology is critical in preventing crime, terrorism, and other threats. Several existing technologies can accurately monitor a person's mobility in interior environments. As well as regulated outdoor settings, object recognition and tracking at night, on the other hand, remain significant challenges for visual surveillance. The objects are usually farther away, inconspicuous, and have low brightness against the background. In this paper, detecting objects specifically people under low lighting conditions with the help of deep learning algorithms was used. For applications like in-car cameras and surveillance systems that operate in low light, these algorithms might improve picture identification performance. © 2022 IEEE.

关键词： Learning algorithms

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：