检索结果-内蒙古大学图书馆

International Conference on Signal Processing and Information Security (ICSPIS)

作者： Shadi Atalla Yassine Himeur Wathiq Mansoor Abbes Amira Fodil Fadli Abigail Copiaco Shahab Saquib Sohail College of Engineering and IT University of Dubai Dubai UAE Department of Computer Science University of Sharjah Sharjah UAE Dept. of Architecture & Urban Planning Qatar University Doha 2713 Qatar School of Engineering Sciences & Technology Jamia Hamdard New Delhi 110062 India

ISBN: (纸本)9781665492669

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.

关键词： Training Power demand Machine learning algorithms Shape Signal processing algorithms Signal processing Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Double Layer Frequency Selective Surface using Interdigital Split Ring Resonators and Applications

A Double Layer Frequency Selective Surface using Interdigita...

引用

2020 International Conference on Power, Energy and Innovations, ICPEI 2020

作者： Archevapanich, Tuanjai Chomtong, Pongsathorn Akkaraekthalin, Prayoot Rajamagala University of Technology Suvarnabhumi Faculty of Engineering and Architecture Dept. of Electronics and Communication Engineering Nonthaburi Thailand King Mongkut's University of Technology North Bangkok Faculty of Technical Education Dept. of Teacher Training in Electrical Engineering Bangkok Thailand King Mongkut's University of Technology North Bangkok Faculty of Engineering Dept. of Electrical and Computer Engineering Bangkok Thailand

ISBN: (纸本)9781728172408

This paper proposes a split ring resonator unit cell using interdigital structure. The size can be reduced from λ/2 to about λ/4 caused by the slow wave effect. An array of 14×14 unit cells can be formed to act as a frequency selective surface (FSS). The proposed FSS is designed at frequency of 1.8 GHz, which the length of unit cell is 11.48 mm and the length of FSS is 172.50 mm. Using double layer FSS, the effect of coupling between layers will result in a larger bandwidth from 1.8 GHz to 2.45 GHz. The simulation results when applying a dipole antenna over the double layer FSS show that the high antenna gains of 8.34 dB and 9.75 dB are obtained at 1.8 GHz to 2.45 GHz, respectively. The proposed double layer FSS with a dipole can be applied for modern communication systems including LTE and WLAN. © 2020 IEEE.

关键词： Frequency selective surfaces

来源：评论

学校读者我要写书评

暂无评论

A Dual Band Split Ring Electromagnetic Band Gap using Interdigital Technique and its Applications

A Dual Band Split Ring Electromagnetic Band Gap using Interd...

引用

2020 International Conference on Power, Energy and Innovations, ICPEI 2020

ISBN: (纸本)9781728172408

This paper proposes the electromagnetic band gap (EBG) reflector using split ring resonator with interdigital technique. The capacitive value between split ring gaps has the results of slow-wave effect in transmission line, that can reduce the size of split ring resonator unit cell from λ/2 to about λ/4. Moreover, it can control the second harmonics to resonance at the required frequency for the second band operation. The unit cell will be designed at the fundamental frequency of 1.8 GHz and the second resonance frequency of 2.4 GHZ, which are the frequency bands of LTE and WLAN systems. The unit cells are arranged in an array to act as a reflector for a dipole antenna. The simulation results at both operating frequency bands show the antenna gains of 8.17 dB and 8.29 dB at 1.8 GHz (460 MHz bandwidth) and 2.4 GHz (470 MHz bandwidth), respectively. © 2020 IEEE.

关键词： Dipole antennas

来源：评论

学校读者我要写书评

暂无评论

KM3NeT acquisition electronics: status and upgrade 38

KM3NeT acquisition electronics: status and upgrade

引用

38th International Cosmic Ray Conference, ICRC 2023

作者： Calvo, D. Real, D. Jansweijer, P. van Beveren, V. Schmelling, J.W. Pellegrini, G. Diaz, A. Colonges, S. Champion, C. Benfenati, F. Filippini, F. Chiarusi, T. Musico, P. Litrico, P. Zornoza, J.D. Gozzini, R. c/ Catedrático José Beltrán 2 Paterna Valencia46980 Spain Nikhef National Institute for Subatomic Physics PO Box 41882 Amsterdam1009 DB Netherlands University of Granada Dept. of Computer Architecture and Technology/CITIC Granada18071 Spain APC Université Paris Diderot CNRS IN2P3 CEA/IRFU Observatoire de Paris Sorbonne Paris Cité Paris75205 France INFN Sezione di Bologna v.le C. Berti-Pichat 6/2 Bologna40127 Italy INFN Sezione di Genova Via Dodecaneso 33 Genova16146 Italy INFN Laboratori Nazionali del Sud Via Santa Sofia62 CataniaCT - 95123 Italy

The KM3NeT Collaboration is building and operating two deep-sea neutrino telescopes at the bottom of the Mediterranean Sea. The telescopes consist of lattices of light detectors housed in pressure-resistant glass spheres, the so-called digital optical modules, which house 31 3-inches of diameter photomultipliers, as well as the acquisition electronics. The so-called detection units are vertical strings along which digital optical modules are installed. For the first phase of the construction of the telescopes, several tens of detection units have been produced, out of which almost 40 have already been deployed with more than 20,000 photomultipliers installed and taking data. Once finished, the two telescopes will have installed more than ten thousand acquisition nodes, completing one of the more complex networks in the world in terms of operation and synchronisation. This work presents the current status of the acquisition electronics, including the upgrade of the principal components such as the central logic board, the signal collecting board, switching core board and Glenair back plane. © Copyright owned by the author(s) under the terms of the Creative Commons.

关键词： Optical telescopes

来源：评论

学校读者我要写书评

暂无评论

Auditory models comparison for horizontal localization of concurrent speakers in adverse acoustic scenarios 23

Auditory models comparison for horizontal localization of co...

引用

23rd International Congress on Acoustics: Integrating 4th EAA Euroregio, ICA 2019

作者： Barumerli, Roberto Almenari, Andrea Geronazzo, Michele Di Nunzio, Giorgio Maria Avanzini, Federico Dept. of Information Engineering University of Padova Italy Dept. of Architecture Design and Media Technology Aalborg University Denmark Dept. of Computer Science University of Milano Italy

ISBN: (纸本)9783939296157

This paper aims at comparing and reproducing the predictions of two public available computational auditory models for speaker localization in different simulated environments. The direction-of-arrival (DOA) of sound sources in the horizontal plane can be extracted by using binaural spatial cues from room and user acoustics. Since our predictions consider the specificity of both models at the level of peripheral processing, the proposed solution for DOA extraction also provides a common multi-conditional training for the Gaussian Mixture Model (GMM) approach. A set of acoustic simulations of adverse conditions (i.e. multi speakers or high reverberant scenarios) supports the evaluation phase on robustness of the synthetic auditory process. Our analysis reproduces two case studies from the scientific literature in order to investigate the reliability of localization predictions in the frontal horizontal plane. Finally, a newly defined acoustic scenario allows to identify differences between auditory models outcome in the entire horizontal plane. The results show a good agreement with previous literature and our machine learning approach emphasizes peculiarities of each approach for auditory peripheral processing. © 2019 Proceedings of the International Congress on Acoustics. All rights reserved.

关键词： Auditory model Binaural processing Room acoustic simulation

来源：评论

学校读者我要写书评

暂无评论

On the evaluation of head-related transfer functions with probabilistic auditory models of human sound localization 23

On the evaluation of head-related transfer functions with pr...

引用

23rd International Congress on Acoustics: Integrating 4th EAA Euroregio, ICA 2019

作者： Geronazzo, Michele Barumerli, Roberto Avanzini, Federico Dept. of Architecture Design and Media Technology Aalborg University Denmark Dept. of Information Engineering University of Padova Italy Dept. of Computer Science University of Milano Italy

ISBN: (纸本)9783939296157

Understanding spatial hearing leads to implement efficient and effective auralization rendering algorithms with headphones. Two important aspects contribute to sound localization: (i) acoustic filtering of listener body, and (ii) non-acoustic factors introduced by auditory periphery. Accordingly, head-related transfer functions (HRTFs) describe users acoustics in terms of their spatial filtering. Binaural synthesis through generic HRTFs (commonly a dummy head) is the most simple solution for an auralization framework. In this scenario, a high variability in localization tasks between subjects yields to an unreliable rendering. Listener's acoustic and perceptual characterization require HRTF modeling and auditory models predictions in order to provide an effective auralization on individual basis. Systemic comparisons of HRTF approximations and different user profiles can help to predict listener's performances. We consider a case study on both vertical and horizontal localization with different HRTFs and two probabilistic auditory models. In our analysis, spatial audio rendering with non-individual HRTFs has a special attention for its commercial relevance compared to unpractical and questionable use of individual HRTFs. © 2019 Proceedings of the International Congress on Acoustics. All rights reserved.

关键词： Auditory model Head-related transfer function Localization Non-individual HRTF

来源：评论

学校读者我要写书评

暂无评论

Reliability assurance in early-life-failure test through improved nearest neighbor regression

引用

IEICE Electronics Express 2020年第2期17卷

作者： Song, Tai Liang, Huaguo Huang, Zhengfeng Hou, Jie Dept. of Electronic Science and Applied Physics Hefei University of Technology Hefei230009 China Institute of Computer Architecture and Computer Stuttgart University StuttgartD-70569 Germany

During manufacturing test, researchers usually overlook the importance of process variation defects and marginal defects, which can seriously affect test results of Early-Life-Failure (ELF). Theoretically, machine learning classification methods can be used to identify these two defects. In fact, when features overfitting or data distribution overlap seriously, classifiers perform poorly, it will not achieve the desired results. This paper first-ever proposes a kind of data preprocessing method combines improved K-Nearest Neighbors (KNN) regression classifier, so that the classification results will be enhanced in terms of classification performance. Experiment results demonstrate that the predictive accuracy is 45% higher than the traditional logistic regression method. This proposed method will drive critical new requirements for fault modeling, test generation and test application, and implementing them effectively will require a new level of collaboration between process and product developers. © 2020 Institute of Electronics Information Communication Engineers. All rights reserved.

关键词： Defects

来源：评论

学校读者我要写书评

暂无评论

JKinect: A new Java Software for Designing and Assessing Gross Motor Activities in children with autism based on JFML

JKinect: A new Java Software for Designing and Assessing Gro...

引用

IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

作者： Juan Carlos Gámez-Granados Francisco Javier Rodriguez-Lozano Giovanni Acampora Chang-Shing Lee Jose Manuel Soto-Hidalgo Dept. Electr. & Computer Engineering University of Córdoba Spain Dept. Physics Ettore Pancini University of Naples Federico II Italy Dept. Computer Science & Information Engineering National University of Tainan Taiwan Dept. Computer Architecture and Computer Technology University of Granada Spain

ISBN: (数字)9781728169323

ISBN: (纸本)9781728169330

Motor therapies can be considered as one of the social challenges that have a great impact in children with autism. Traditionally, exercises and activities as therapies have been used to mitigate and to rehabilitate problems related to gross motor skills. Nevertheless, from the perspective of children, these therapies are often repetitive, boring and they need an extra motivation aspect due to the target: children with autism. From the point of interaction with the target population, the use of technology is a key issue in these therapies. In this scenario, a new software named JKinect which is based on RGB-D sensors and computer based games. JKinect helps children with gross motor problems and presents great flexibility in the therapy design and game sharing among specialists. Additionally, a new module for linking JKinect with both fuzzy systems based on the IEEE std 1855-2016 and the JFML library to support experts' decision making in therapies on the basis of fuzzy rules is also included.

关键词： Medical treatment Libraries Games Autism XML Fuzzy logic IEEE Standards

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

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

引用

Smart Technologies in Computing, Electrical and Electronics (ICSTCEE), International Conference on

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

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.

关键词： Deep learning Training Visualization computer vision Heuristic algorithms Computational modeling Lighting

来源：评论

学校读者我要写书评

暂无评论

On robot compliance. A cerebellar control approach

arXiv

引用

arXiv 2020年

作者： Abadía, Ignacio Naveros, Francisco Garrido, Jesús A. Ros, Eduardo Luque, Niceto R. Research Centre for Information and Communication Technologies Dept. Computer Architecture and Technology U. Granada Granada18014 Spain

The work presented here is a novel biological approach for the compliant control of a robotic arm in real time (RT). We integrate a spiking cerebellar network at the core of a feedback control loop performing torque driven control. The spiking cerebellar controller provides torque commands allowing for accurate and coordinated arm movements. To compute these output motor commands, the spiking cerebellar controller receives the robot’s sensorial signals, the robot’s goal behaviour, and an instructive signal. These input signals are translated into a set of evolving spiking patterns, representing univocally a specific system state at every point of time. Spike Timing-Dependent Plasticity (STDP) is then supported, allowing for building adaptive control. The spiking cerebellar controller continuously adapts the torque commands provided to the robot from experience as STDP is deployed. Adaptive torque commands, in turn, help the spiking cerebellar controller to cope with built-in elastic elements within the robot’s actuators mimicking human muscles (inherently elastic). We propose a natural integration of a bio-inspired control scheme, based on the cerebellum, with a compliant robot. We prove that our compliant approach outperforms the accuracy of the default factory-installed position control in a set of tasks used for addressing cerebellar motor behaviour: controlling six degrees of freedom (DoF) in (i) smooth movements, (ii) fast ballistic movements and (iii) unstructured scenario compliant movements. Copyright © 2020, The Authors. All rights reserved.

关键词： Brain

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：