检索结果-内蒙古大学图书馆

International Conference on Control, Instrumentation, Energy and Communication (CIEC)

作者： Abhrodeep Das Ayushman Agrawal Nishkarsh Kundoliya Ananta Dutta Surjya K Pal Rishi Kumar Dept. of Computer Science and Engineering Jalpaiguri Government Engineering College WB India Dept. of Mechanical Engineering Indian Institute of Technology Kharagpur WB India Dept of Ocean Engg & Naval Architecture Indian Institute of Technology Kharagpur WB India Research & Development Centre for Iron & Steel Steel Authority of India Limited (SAIL) Ranchi Jharkhand India

Exhausters are very crucial components in sinter plant of steel manufacturing industries. Problems in fan or motor side of the exhausters lead to machine stoppages or reduced speed, resulting in stoppage of the system and decreased sinter production. Common issues include imbalance, misalignments, looseness, eccentricity, and motor bearing failure. The proposed IoT-based system aims to continuously analyze vibration signals, predict issues, and prevent sudden stoppages and exhauster tripping, thereby enhancing overall plant efficiency. This study focuses on online monitoring and health prediction of industrial exhausters by selection of statistical features extracted from triaxial time-series vibration data by using multiple optimizers, followed by implementation of machine learning classifiers. By incorporating a novel feature selection process based on nature-inspired optimizers, this methodology aims to enhance the overall generalization performance of classification. The retrained models with cross-validation were evaluated with real-time industrial data, which shows 99.5% cross-validation accuracy and 95.83% real-time prediction accuracy. The proposed methodology holds great potential for detecting machine faults in industrial applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Energy efficiency in Edge TPU vs. embedded GPU for computer-aided medical imaging segmentation and classification

arXiv

引用

arXiv 2023年

作者： Corral, José María Rodríguez Civit-Masot, Javier Luna-Perejón, Francisco Díaz-Cano, Ignacio Morgado-Estévez, Arturo Domínguez-Morales, Manuel 10 Spain Architecture and Computer Technology Dept. E.T.S. Ingeniería Informática University of Seville Avda. Reina Mercedes s/n Sevilla Spain

In this work, we evaluate the energy usage of fully embedded medical diagnosis aids based on both segmentation and classification of medical images implemented on Edge TPU and embedded GPU processors. We use glaucoma diagnosis based on color fundus images as an example to show the possibility of performing segmentation and classification in real time on embedded boards and to highlight the different energy requirements of the studied implementations. Several other works develop the use of segmentation and feature extraction techniques to detect glaucoma, among many other pathologies, with deep neural networks. Memory limitations and low processing capabilities of embedded accelerated systems (EAS) limit their use for deep network-based system training. However, including specific acceleration hardware, such as NVIDIA’s Maxwell GPU or Google’s Edge TPU, enables them to perform inferences using complex pre-trained networks in very reasonable times. In this study, we evaluate the timing and energy performance of two EAS equipped with Machine Learning (ML) accelerators executing an example diagnostic tool developed in a previous work. For optic disc (OD) and cup (OC) segmentation, the obtained prediction times per image are under 29 and 43 ms using Edge TPUs and Maxwell GPUs, respectively. Prediction times for the classification subsystem are lower than 10 and 14 ms for Edge TPUs and Maxwell GPUs, respectively. Regarding energy usage, in approximate terms, for OD segmentation Edge TPUs and Maxwell GPUs use 38 and 190 mJ per image, respectively. For fundus classification, Edge TPUs and Maxwell GPUs use 45 and 70 mJ, respectively. © 2023, CC BY-NC-ND.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Sixteen years of sound and music computing: A look into the history and trends of the conference and community 17

Sixteen years of sound and music computing: A look into the ...

引用

17th Sound and Music Computing Conference, SMC 2020

作者： Mauro, Davide Andrea Avanzini, Federico Baraté, Adriano Ludovico, Luca Andrea Ntalampiras, Stavros Dimitrov, Smilen Serafin, Stefania Dept. of Computer & Information Technology Marshall University United States Dept. of Computer Science University of Milano Italy Dept. of Architecture Design and Media Technology Aalborg University Copenhagen Denmark

ISBN: (纸本)9788894541502

This contribution provides an overview of the Sound and Music Computing conference and community over the course of its sixteen years. As a sequel to a previous corresponding contribution investigating the community ten years ago, here we analyze the proceedings of the past editions, as well as the changes in the organization of the conference itself. The analysis reveals the growth of the SMC community in terms of attendees and countries represented at the conference, highlights the changes in trends and topics, and provides insights on the directions of the conference. A reflection is made with regards to the SMC roadmap originally conceived in 2004. Motivated by similar initiatives in "sister"communities, this resource is made available to the community at http://***/. Copyright © 2020 Davide Andrea Mauro et al.

关键词： computer programming

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

Modified ARQ-based cooperative relaying scheme for a delay tolerant network

Modified ARQ-based cooperative relaying scheme for a delay t...

引用

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

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

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：