检索结果-内蒙古大学图书馆

IEEE International Conference on Big Data

作者： Francesco De Santis Danilo Giordano Marco Mellia Alessia Damilano Department of Control and Computer Engineering Politenico di Torino Torino Italy Quality & Process Digitalization Deparment Electronic Division Bitron Grugliasco Italy

In the era of Big Data, effective data reduction through feature selection is of paramount importance for machine learning. This paper presents GLEm-Net (Grouped Lasso with Embeddings Network), a novel neural framework that seamlessly processes both categorical and numerical features to reduce the dimensionality of data while retaining as much information as possible. By integrating embedding layers, GLEm-Net effectively manages categorical features with high cardinality and compresses their information in a less dimensional space. By using a grouped Lasso penalty function in its architecture, GLEm-Net simultaneously processes categorical and numerical data, efficiently reducing high-dimensional data while preserving the essential information. We test GLEm-Net with a real-world application in an industrial environment where 6 million records exist and each is described by a mixture of 19 numerical and 7 categorical features with a strong class imbalance. A comparative analysis using state-of-the-art methods shows that despite the difficulty of building a high-performance model, GLEm-Net outperforms the other methods in both feature selection and classification, with a better balance in the selection of both numerical and categorical features.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Smart Meter Analytics for Residential Energy Efficiency

Smart Meter Analytics for Residential Energy Efficiency

引用

Global Energy Conference (GEC)

作者： Tahir Cetin Akinci Erhan Sengezer Erkan Dursun Musa Yilmaz Gokhan Gokmen Alfredo A. Martinez-Morales Miroslav Penchev Arun S.K. Raju College of Engineering - Center for Environmental Research and Technology (CE-CERT) University of California Riverside CA USA Rimer Electric Electronic Consulting Services Company Istanbul Turkey Department of Electrical and Computer Engineering Western Michigan University Kalamazoo Michigan Department of Mechatronic Engineering Marmara University Istanbul Turkey

ISBN: (数字)9798331532611

ISBN: (纸本)9798331532628

Smart meters, in addition to measuring users' energy consumption, provide high-resolution, real-time energy usage data, enabling advanced analyses to uncover patterns, detect anomalies, and optimize residential energy usage. This study analyzes data representing one-hour segments of voltage and current waveforms collected over 96 days from a single-family household in Portugal. The data was converted into MP3 format for analysis and processed using the MATLAB© software package to extract hourly energy consumption metrics, including active power, reactive power, and RMS values, scaled to megawatt-hours (MWh). The conducted analyses included fundamental evaluations and anomaly detection. Statistical analysis revealed consistent consumption patterns tightly concentrated within a narrow range (75.10–75.90 MWh). The average energy consumption across the datasets was approximately 75.5 MWh, with a low standard deviation (∼0.2 MWh), indicating stable usage trends. While timeseries graphs effectively visualized these patterns and deviations, histograms provided limited insights due to the narrow data distribution. This study demonstrates the potential of smart meter data for identifying inefficiencies and enabling data-driven energy management strategies. The methodology supports advanced analyses such as load profiling, anomaly detection, and consumption optimization, showcasing scalability and applicability to larger datasets. Additionally, this research contributes to identifying hidden usage patterns and advancing smart meter methodologies.

关键词： Measurement Energy consumption Reactive power Statistical analysis Data visualization Market research Smart meters Energy efficiency Standards Optimization

来源：评论

学校读者我要写书评

暂无评论

A Dominant Interferer-Based Approximation for Uplink SINR Meta Distribution in Cellular Networks

A Dominant Interferer-Based Approximation for Uplink SINR Me...

引用

International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt)

作者： Yujie Qin Mustafa A. Kishk Mohamed-Slim Alouini Computer Electrical and Mathematical Sciences and Engineering (CEMSE) Division King Ab-dullah University of Science and Technology (KAUST) Thuwal Saudi Arabia Department of Electronic Engineering Maynooth University Maynooth Ireland

This work studies the signal-to-interference-plus-noise-ratio (SINR) meta distribution for the uplink transmission of a Poisson network with Rayleigh fading by using the dominant interferer-based approximation. The proposed approach relies on computing the mix of exact and mean-field analysis of interference. In particular, it requires the distance distribution of the nearest interferer and the conditional average of the rest of the interference. Using the widely studied fractional path-loss inversion power control and modeling the spatial locations of base stations (BSs) by a Poisson point process (PPP), we obtain the meta distribution based on the proposed method and compare it with the traditional beta approximation, as well as the exact results obtained via Monte-Carlo simulations. Our numerical results validate that the proposed method shows good matching and is time competitive.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modal Dispersion Performance of Mode Vector Modulation

Modal Dispersion Performance of Mode Vector Modulation

引用

International Conference on Transparent Optical Networks

作者： F. Barbosa F. Ferreira A. Brisson A. Biswas M. Dadras E. Fink I. Roudas X. Jiang Dept. of Electronic & Electrical Engineering University College London London Dept. of Electrical & Computer Engineering Montana State University Bozeman MT Dept. of Mathematical Sciences Montana State University Bozeman MT Dept. of Engineering and Environmental Science CUNY Staten Island NY

ISBN: (数字)9798350377323

ISBN: (纸本)9798350377330

Mode vector modulation (MVM) is a new spatial modulation scheme suitable for few-mode/multicore fibers or for multimode transmission in optical wireless links. When used in conjunction with direct-detection in short-haul optical links, MVM offers significantly higher sensitivity compared to M-ary pulse amplitude modulation (M-PAM).Since MVM uses several spatial and polarization modes simultaneously for transmission of a single data stream, modal effects in few-mode fibers, such as mode coupling and modal dispersion, are potentially of paramount importance and their impact on MVM system performance should be thoroughly *** this invited paper, we study by simulation, for the first time, the transmission of MVM through a few-mode fiber (FMF) with six spatial and polarization modes. We show that, by employing a suitable combination of optical and electronic equalization techniques, the impact of mode coupling and modal dispersion on MVM performance can be significantly reduced. Consequently, it is theoretically possible to replace multiple M-PAM tributaries transmitted in parallel over a fiber bundle with one MVM channel launched over a single FMF in order to decrease the bit SNR and the fiber count in future ultra-high-data-rate, direct-detection optical interconnects.

关键词： Optical fiber polarization Integrated optics Optical fiber sensors Optical polarization Optical interconnections Optical fiber networks Vectors

来源：评论

学校读者我要写书评

暂无评论

Battle Against Fluctuating Quantum Noise: Compression-Aided Framework to Enable Robust Quantum Neural Network 23

Battle Against Fluctuating Quantum Noise: Compression-Aided ...

引用

Proceedings of the 60th Annual ACM/IEEE Design Automation Conference

作者： Zhirui Hu Youzuo Lin Qiang Guan Weiwen Jiang Electrical and Computer Engineering Department George Mason University Fairfax VA US and Quantum Science and Engineering Center George Mason University Fairfax VA US Earth and Environmental Sciences Division Los Alamos National Laboratory NM US Department of Computer Science Kent State University Kent OH

ISBN: (纸本)9798350323481

Recently, we have been witnessing the scale-up of superconducting quantum computers; however, the noise of quantum bits (qubits) is still an obstacle for real-world applications to leveraging the power of quantum computing. Although there exist error mitigation or error-aware designs for quantum applications, the inherent fluctuation of noise (a.k.a., instability) can easily collapse the performance of error-aware designs. What's worse, users can even not be aware of the performance degradation caused by the change in noise. To address both issues, in this paper we use Quantum Neural Network (QNN) as a vehicle to present a novel compression-aided framework, namely QuCAD, which will adapt a trained QNN to fluctuating quantum noise. In addition, with the historical calibration (noise) data, our framework will build a model repository offline, which will significantly reduce the optimization time in the online adaption process. Emulation results on an earthquake detection dataset show that QuCAD can achieve 14.91% accuracy gain on average in 146 days over a noise-aware training approach. For the execution on a 7-qubit IBM quantum processor, ibm-jakarta, QuCAD can consistently achieve 12.52% accuracy gain on earthquake detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MedIAnomaly: A comparative study of anomaly detection in medical images

arXiv

引用

arXiv 2024年

作者： Cai, Yu Zhang, Weiwen Chen, Hao Cheng, Kwang-Ting Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Department of Chemical and Biological Engineering The Hong Kong University of Science and Technology Hong Kong Division of Life Science The Hong Kong University of Science and Technology Hong Kong

Anomaly detection (AD) aims at detecting abnormal samples that deviate from the expected normal patterns. Generally, it can be trained merely on normal data, without a requirement for abnormal samples, and thereby plays an important role in rare disease recognition and health screening in the medical domain. Despite the emergence of numerous methods for medical AD, the lack of a fair and comprehensive evaluation causes ambiguous conclusions and hinders the development of this field. To address this problem, this paper builds a benchmark with unified comparison. Seven medical datasets with five image modalities, including chest X-rays, brain MRIs, retinal fundus images, dermatoscopic images, and histopathology images, are curated for extensive evaluation. Thirty typical AD methods, including reconstruction and self-supervised learning-based methods, are involved in comparison of image-level anomaly classification and pixel-level anomaly segmentation. Furthermore, for the first time, we systematically investigate the effect of key components in existing methods, revealing unresolved challenges and potential future directions. The datasets and code are available at https://***/caiyu6666/MedIAnomaly. Copyright © 2024, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Spatial and temporal characteristics of PM2.5 sources and pollution events in a low industrialized city

引用

Nature Environment and Pollution Technology 2021年第3期20卷 1087-1096页

作者： Xu, R. Tian, Q. Wan, H. Wen, J. Zhang, Q. Zhang, Y. College of Computer and Information Security Guilin University of Electronic Technology Guilin541004 China Key Laboratory for City Cluster Environmental Safety Green Development of the Ministry of Education Institute of Environmental and Ecological Engineering Guangdong University of Technology Guangzhou510006 China Guilin Environmental Monitoring Center Station Guilin541002 China

In recent years, cities in southern China have experienced severe air pollution, despite having few sources of pollutants. To study the pollution characteristics of PM2.5 in these "low industrialized" cities, a numerical method based on the HYSPLIT4 Model and Kriging Spatial Interpolation Technology was established. Simulation results showed that the PM2.5 pollution in Guilin was affected by both internal and external sources. The backward air mass trajectory from July 2017 to June 2018 was simulated using the HYSPLIT model. The cluster analysis results indicated that the direction of trajectory accounted for 63.09% of the air pollution in the city. The average concentration of PM2.5 pollution was 45.94 μg.m-3. The pollutant originated from the "Xiang-Gui Corridor." The location of the sources was collocated with high industry regions. The spatial characteristics of the four pollution processes in the winter of 2017 were analyzed using a spatial interpolation method. The results showed that the transport of air masses in the direction of trajectory 2 was obstructed by a mountain system in the northeast. Therefore, two air pollution accumulation centers and a topographic weakening zone dominated by internal and external sources were formed. It can be inferred that the air pollution in Guilin is affected by both internal and external factors. These results provide important theoretical and technical support for regional air pollution control and environmental protection. © 2021 Technoscience Publications. All rights reserved.

关键词： Air pollution

来源：评论

学校读者我要写书评

暂无评论

A Novel Electromagnetic Voltage Transformer Based on Magnetic Valve

A Novel Electromagnetic Voltage Transformer Based on Magneti...

引用

IEEE Conference on Electromagnetic Field Computation

作者： Jiaxin Yuan Guangchen Ma Hang Zhou Jingwen Hou Yanhui Gao Kazuhiro Muramatsu State Key Laboratory of Power Grid Environmental Protection School of Electrical Engineering and Automation Wuhan University Wuhan P.R.China Division of Mechatronics Oita University Oita Japan Department of Electrical and Electronic Engineering Saga University Saga Japan

ISBN: (数字)9798350348958

ISBN: (纸本)9798350348965

Voltage transformers are crucial components of power systems, which serve various purposes. However, traditional electromagnetic voltage transformers suffer from saturation issues due to the presence of magnetic cores. It can result in inaccurate voltage measurements, overheating, or damage to the transformer. Meanwhile, it can even pose risks to the power system due to ferroresonance. In this paper, a novel electromagnetic voltage transformer utilizing a magnetic valve is proposed, which is capable of compensating for distorted voltage after saturation and extending the measuring range. The anti-DC bias capability of the proposed voltage transformer is improved by including a magnetic valve and magnetic field sensor. Finite element simulations and prototype experiments verified the correctness of the proposed transformer's principle.

关键词： Magnetic field measurement Voltage measurement Voltage transformers Magnetic cores Prototypes Valves Power systems

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Approach for Identification of SIM Box Bypass Fraud in a Telecom Network Based on CDR Analysis: Case of a Fixed and Mobile Operator in Cameroon

引用

Journal of computer and Communications 2023年第2期11卷 142-157页

作者： Eric Michel Deussom Djomadji Kabiena Ivan Basile Tchapga Tchito Christian Ferry Vaneck Kouam Djoko Michael Ekonde Sone Department of Electrical and Electronic Engineering College of Technology University of Buea Buea Cameroon Division of Information and Communications Technology National School of Posts Telecommunications and Information and Communication Technologies University of Yaoundé I Yaoundé Cameroon Department of Computer Engineering and Telecommunications National Advanced School of Engineering University of Douala Douala Cameroon

In the telecommunications sector, companies suffer serious damages due to fraud, especially in Africa. One of the main types of fraud is SIM box bypass fraud, which includes using SIM cards to divert incoming international calls from mobile operators creating massive losses of revenue. In order to provide a solution to these shortcomings that apply almost to all network operators, we developed intelligent algorithms that exploit huge amounts of data from mobile operators and that detect fraud by analyzing CDRs from voice calls. In this paper we used three classification techniques: Random Forest, Support Vector Machine (SVM) and XGBoost to detect this type of fraud;we compared the performance of these different algorithms to evaluate the model by using data collected from an operator’s network in Cameroon. The algorithm that produced a better performance was the Random Forest with 92% accuracy, so we effectuated the detection of existing fraudulent numbers on the telecommunications operator’s network.

关键词： CDR Fraud Detection Machine Learning Voice Calls

来源：评论

学校读者我要写书评

暂无评论

Integration of Median Filter and K-means Clustering Technique for Ultrasound Tomography

Integration of Median Filter and K-means Clustering Techniqu...

引用

International Conference on Communications and electronics, ICCE

作者： Luong Thi Theu Tran Quang-Huy Viet Bac T. Phung Tran Duc-Tan Hoa Binh University Hanoi Vietnam Faculty of Physics Hanoi Pedagogical University 2 Hanoi Vietnam Center for Environmental Intelligence and College of Engineering & Computer Science Vin University Hanoi Vietnam Faculty of Electrical and Electronic Engineering Phenikaa University Hanoi Vietnam

ISBN: (数字)9798350379792

ISBN: (纸本)9798350379808

Ultrasound tomography is a powerful imaging modality widely employed in medical diagnostics due to its non-invasiveness and small object detection capabilities. However, the reconstructed images often suffer from the presence of noise, compromising the accuracy and interpretability of diagnostic information. In this paper, we propose and evaluate the application of a median filter to address noise artifacts in the reconstructed images obtained through the distorted Born iterative method (DBIM). Quantitative assessment of the proposed approach involves the utilization of evaluation metric, normalized error, to measure its effectiveness. Furthermore, the application of a basic machine learning technique, K-means clustering, assists in automatically dividing the reconstructed image into distinct segments representing objects, background, and noise. The outcomes demonstrate that K-means clustering effectively delineates these regions in images generated through the proposed method, with minimal presence of noise in the recovered images.

关键词： Image segmentation Ultrasonic imaging Noise Machine learning Object detection Tomography Iterative methods

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：