检索结果-内蒙古大学图书馆

Estimating Mutual Information for Link Adaptation in Generalized Spatial Modulation systems with Neural Networks 26

Estimating Mutual Information for Link Adaptation in General...

26th International ITG Workshop on Smart Antennas, WSA 2023 and 13th Conference on systems, Communications, and Coding, SCC 2023

作者： Bailon, Daniel Nicolas Kühn, Volker Shavgulidze, Sergo Freudenberger, Jürgen Institute for System Dynamics HTWG Konstanz University of Applied Sciences Germany Institute of Communications Engineering Faculty of Computer Science and Electrical Engineering University of Rostock Germany Faculty of Informatics and Control Systems Georgian Technical University Georgia Germany

ISBN: (纸本)9783800760510

Spatial modulation (SM) is a low-complexity multiple-input/multiple-output transmission technique that combines index modulation and quadrature amplitude modulation for wireless communications. In this work, we consider the problem of link adaption for generalized spatial modulation (GSM) systems that use multiple active transmit antennas simultaneously. Link adaption algorithms require a real-time estimation of the link quality of the time-variant communication channels, e.g., by means of estimating the mutual information. However, determining the mutual information of SM is challenging because no closed-form expressions have been found so far. Recently, multilayer feedforward neural networks were applied to compute the achievable rate of an index modulation link. However, only a small SM system with two transmit and two receive antennas was considered. In this work, we consider a similar approach but investigate larger GSM systems with multiple active antennas. We analyze the portions of mutual information related to antenna selection and the IQ modulation processes, which depend on the GSM variant and the signal constellation. © VDE VERLAG GMBH · Berlin · Offenbach.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

A Multicore Implementation of an AUTOSAR-based XCP Module 12

A Multicore Implementation of an AUTOSAR-based XCP Module

引用

12th Mediterranean Conference on Embedded Computing, MECO 2023

作者： Osama, Mahmoud Hammad, Sherif Elhady, Nancy E. El-Kharashi, M. Watheq Ain Shams University Faculty of Engineering Dept. of Computer & Systems Eng. Cairo Egypt Garraio CEO Cairo Egypt Ain Shams University Faculty of Engineering Dept. of Mechatronics Eng. Cairo Egypt

ISBN: (纸本)9798350322910

The automotive industry depends on computers to control and monitor vehicles behaviour. The Universal Measurement and Calibration Protocol (XCP) connects calibration systems to electronic control units (ECUs). Nowadays, AUTOSAR-based XCP for single core ECUs is widely used in automotive industry. As the demand for computing power is rapidly increasing in the automotive domain, car manufacturers are gradually introducing multi-core ECUs in their electronic architectures. Multi-core ECUs provide high level of parallelism. This research work aims to deliver a multi-core implementation of an AUTOSAR-based XCP module, as it is important to have an efficient process of measurement and calibration on multi-core targets. The paper results are ensuring data consistency on the application level, avoiding race conditions between writer core and reader core which might result in processing rubbish data, and decreasing data dependency between cores. © 2023 IEEE.

关键词： Automotive industry

来源：评论

学校读者我要写书评

暂无评论

Utilizing Multi-Step Loss for Single Image Reflection Removal

Utilizing Multi-Step Loss for Single Image Reflection Remova...

引用

ACS/IEEE International Conference on computer systems and Applications

作者： Abdelrahman Elnenaey Marwan Torki Department of Computer and Systems Engineering Faculty of Engineering Alexandria University Alexandria Egypt Knights Lab

ISBN: (数字)9798331518240

ISBN: (纸本)9798331518257

Image reflection removal is crucial for restoring image quality. Distorted images can negatively impact tasks like object detection and image segmentation. In this paper, we present a novel approach for image reflection removal using a single image. Instead of focusing on model architecture, we introduce a new training technique that can be generalized to image-to-image problems, with input and output being similar in nature. This technique is embodied in our multi-step loss mechanism, which has proven effective in the reflection removal task. Additionally, we address the scarcity of reflection removal training data by synthesizing a high-quality, non-linear synthetic dataset called RefGAN using Pix2Pix GAN. This dataset significantly enhances the model's ability to learn better patterns for reflection removal. We also utilize a ranged depth map, extracted from the depth estimation of the ambient image, as an auxiliary feature, leveraging its property of lacking depth estimations for reflections. Our approach demonstrates superior performance on the SIR 2 benchmark and other real-world datasets, proving its effectiveness by out-performing other state-of-the-art models.

关键词： Training Translation Depth measurement Training data Object detection Benchmark testing Feature extraction Reflection Robustness Synthetic data

来源：评论

学校读者我要写书评

暂无评论

UTILIZING MULTI-STEP LOSS FOR SINGLE IMAGE REFLECTION REMOVAL

arXiv

引用

arXiv 2024年

作者： Elnenaey, Abdelrahman Torki, Marwan Department of Computer and Systems Engineering Faculty of Engineering Alexandria University Knights Lab Alexandria Egypt

Image reflection removal is crucial for restoring image quality. Distorted images can negatively impact tasks like object detection and image segmentation. In this paper, we present a novel approach for image reflection removal using a single image. Instead of focusing on model architecture, we introduce a new training technique that can be generalized to image-to-image problems, with input and output being similar in nature. This technique is embodied in our multi-step loss mechanism, which has proven effective in the reflection removal task. Additionally, we address the scarcity of reflection removal training data by synthesizing a high-quality, nonlinear synthetic dataset called RefGAN using Pix2Pix GAN. This dataset significantly enhances the model’s ability to learn better patterns for reflection removal. We also utilize a ranged depth map, extracted from the depth estimation of the ambient image, as an auxiliary feature, leveraging its property of lacking depth estimations for reflections. Our approach demonstrates superior performance on the SIR2 benchmark and other real-world datasets, proving its effectiveness by outperforming other state-of-the-art models. © 2024, CC0.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

All-optically linearized silicon modulator with ultrahigh SFDR of 131 dB·Hz^(6/7)

引用

Photonics Research 2025年第2期13卷 433-441页

作者： QIANG ZHANG QIKAI HUANG PENGHUI XIA YAN LI XINGYI JIANG SHUYUE ZHANG SHENGYU FANG JIANYI YANG HUI YU Zhejiang Lab Hangzhou 311100China Institute of Integrated Microelectronic Systems College of Information Science and Electronic EngineeringZhejiang UniversityHangzhou 310027China Faculty of Electrical Engineering and Computer Science Ningbo UniversityNingbo 315211China

Integrated high-linearity modulators are crucial for high dynamic-range microwave photonic(MWP)*** linearization schemes usually involve the fine tuning of radio-frequency(RF)power distribution,which is rather inconvenient for practical applications and can hardly be implemented on the integrated photonics *** this paper,we propose an elegant scheme to linearize a silicon-based modulator in which the active tuning of RF power is *** device consists of two carrier-depletion-based Mach-Zehnder modulators(MZMs),which are connected in series by a 1×2 thermal optical switch(OS).The OS is used to adjust the ratio between the modulation depths of the two *** a proper ratio,the complementary third-order intermodulation distortion(IMD3)of the two sub-MZMs can effectively cancel each other *** measured spurious-free dynamic ranges for IMD3 are 131,127,118,110,and 109 d B·Hz^(6∕7)at frequencies of 1,10,20,30,and 40 GHz,respectively,which represent the highest linearities ever reached by the integrated modulator chips on all available material platforms.

关键词： microwave photonic systems ultrahigh SFDR all optical linearization silicon modulator active tuning rf power high linearity modulators third order intermodulation distortion integrated photonics

来源：评论

学校读者我要写书评

暂无评论

Scheduling Tool for Deterministic Communication in Distributed Real-Time systems 10

Scheduling Tool for Deterministic Communication in Distribut...

引用

10th Workshop on Software Quality Analysis, Monitoring, Improvement, and Applications, SQAMIA 2023

作者： Mach, Jan Tašková, Valéria Kohútka, Lukáš Institute of Computer Engineering and Applied Informatics Faculty of Informatics and Information Technologies Slovak University of Technology Bratislava Slovakia Institute of Informatics Information Systems and Software Engineering Faculty of Informatics and Information Technologies Slovak University of Technology Bratislava Slovakia

A network with critical data streams, where the timing of incoming and outgoing data is a necessity, is called a deterministic network. These networks are mostly used in association with real-time systems that use periodic hard-real-time data which need to be scheduled. The algorithm proposed in this paper is focused on achieving the lowest possible latency within the specified network topology depending on the physical parameters of the network and the periodic requirements of the communicating nodes. The algorithm allows to add priorities to the data flow between nodes and also the option to specify if preemption is allowed within the network, since not all devices support it. The result is a schedule of hard-real-time data communication within a specified network topology where all requirements of communicating nodes are met if such a solution is possible. © 2023 Copyright for this paper by its authors.

关键词： deadline deterministic scheduling Ethernet scheduling algorithm time-sensitive networking

来源：评论

学校读者我要写书评

暂无评论

Optical Hyperuricemia Sensor with Uricase Biofunctionalized Stacked Nanocomposite

Optical Hyperuricemia Sensor with Uricase Biofunctionalized ...

引用

International Conference on Photonics (ICP)

作者： O. A. Onifade M. H. B. A. Bakar M. A. Mahdi A. S. B. M Noor Department of Computer and Communication Systems Engineering Faculty of Engineering Universiti Putra Malaysia Selangor Malaysia

ISBN: (数字)9798350383164

ISBN: (纸本)9798350383171

This paper presents an advanced optical sensor based on surface plasmon resonance (SPR) designed to detect hyperuricemia, characterized by elevated uric acid (UA) levels. The sensor features a stacked nanocomposite comprising gold-graphene quantum dots (GQD) biofunctionalized with uricase enzyme, ensuring high sensitivity and selectivity for UA detection over other potentially competing interferents like ascorbic acid, glucose, D-cystine, urea, and creatinine commonly found in biological samples. The developed sensor achieves an impressive sensitivity of 0.093°/(mg/dL) for UA at 12 mg/dL, significantly higher than the recorded sensitivity of 0.015°/(mg/dL) for all other potential interferents at the same concentration. This highlights the sensor’s exceptional precision in discerning UA. Moreover, the sensor demonstrates notable selectivity for UA even at low concentrations, registering a resonance angle shift of 0.371° at 0.5 mg/dL, compared to a lower angle shift of 0.185° for other interferents at higher concentrations of 12 mg/dL. These findings emphasize the sensor’s accuracy and rapid response in distinguishing UA, positioning it as a promising tool for early diagnosis and management of hyperuricemia in clinical settings, addressing a critical need for reliable and efficient UA detection.

关键词： Integrated optics Sensitivity Biomedical optical imaging Scalability Surface plasmon resonance Resonance Optical sensors Nanobioscience Optical reflection Reliability

来源：评论

学校读者我要写书评

暂无评论

ShieldSMS Sentinel: Guardian of Your Digital Communication Bastion 2

ShieldSMS Sentinel: Guardian of Your Digital Communication B...

引用

2nd DMIHER International Conference on Artificial Intelligence in Healthcare, Education and Industry, IDICAIEI 2024

作者： Gourshettiwar, Palash Thakare, Rajesh D. Duddalwar, Prapti Shete, Rushikesh Gundewar, Swapnil Verma, Prateek Faculty of Engineering and Technology Department of Computer Science and Medical Engineering Maharashtra Wardha442001 India Yashavantrao Chavan College of Engineering Department of Electronics Engineering Maharashtra Nagpur440002 India Vishwakarma Institute of Technology Department of Electronics Engineering Maharashtra Pune411037 India St. Vincent Pallotti College of Engineering and Technology Department of Computer Science and Business Systems Maharashtra Nagpur440002 India Faculty of Engineering and Technology Department of Artificial Intelligence and Machine Learning Maharashtra Wardha442001 India

ISBN: (纸本)9798331528713

The SMS spam detection Project provides a comprehensive framework for reliably identifying and classifying spam messages sent over SMS communication channels by fusing ML algorithms with NLP techniques. Using EDA, a dataset of labelled SMS messages identified as spam or ham is thoroughly studied to reveal patterns in the word count, sentence count, and message length distributions. Then, unstructured text is transformed into structured data that may be utilized with ML models through tokenization, punctuation and stop word removal, stemming, and other text preprocessing techniques. Feature engineering, which numerically represents text data using vectorization techniques like BoW and TF-IDF, plays a significant role. Various ML algorithms, including Gaussian Naive Bayes, Multinomial Naive Bayes, SVM, and ensemble approaches, are trained and evaluated. Performance metrics, including accuracy and precision, serve as standards for model selection. © 2024 IEEE.

关键词： Text messaging

来源：评论

学校读者我要写书评

暂无评论

Tabular Dyna-Q Algorithm for Online Calculation of LQR Gains: A Simulation Study 9

Tabular Dyna-Q Algorithm for Online Calculation of LQR Gains...

引用

9th International Conference on engineering and Emerging Technology, ICEET 2023

作者： Farooghi, Kian Samadi, Mahdieh Khaloozadeh, Hamid K. N. Toosi University of Technology Department of Systems and Control Tehran Iran University of Tabriz Faculty of Electrical and Computer Engineering Tabriz Iran

ISBN: (纸本)9798350316926

This paper presents a novel approach for the online calculation of Linear Quadratic Regulator (LQR) gains using the Tabular Dyna-Q algorithm. By leveraging Q-learning, this technique enables the determination of gains for unknown dynamic systems by using input-output data only. The proposed algorithm is particularly advantageous for situations where acquiring input-output data is expensive or time-consuming, as it effectively reduces computation time by reusing previous data. To validate the accuracy of the calculations and control scheme, a simulation example is provided. The results indicate the effectiveness of the Tabular Dyna-Q algorithm in accurately computing LQR gains and its potential application in real-world scenarios. This research contributes to advancing the field of control theory by offering an efficient and reliable method for online gain calculation in dynamic systems. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Lumped Element Method for Acoustoelectric Imaging Reconstruction: A Numerical Study

A Lumped Element Method for Acoustoelectric Imaging Reconstr...

引用

2022 IEEE International Conference on systems, Man, and Cybernetics, SMC 2022

作者： Tan, Rick Hao McDermott, Conor Rossa, Carlos Ontario Tech University Faculty of Engineering and Applied Science Oshawa Canada Carelton University Systems and Computer Engineering OttawaON Canada

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

Acoustoelectric impedance tomography (AET) is a new non-invasive medical imaging procedure used to map the electrical properties of biological tissues with higher spatial resolution than traditional electrical impedance tomography (EIT). It exploits the acoustoelectric effect where modulated ultrasonic pressure changes the local tissue conductivity. This provides additional information to reconstruct a tomographic image, and has a stabilizing effect on an otherwise highly unstable inverse *** this paper, a novel approach to solving the AET inverse problem for image reconstruction is proposed. In the algorithm, the acoustoelectric effect is assumed to create small perturbations in the local resistance of the medium under observation. A lumped model consisting of a finite mesh of resistors approximates the medium under observation, through which boundary voltage differences between the excited and unexcited medium are calculated. A variation of the Modified Newton Raphson (MNR) algorithm is then proposed, where each pattern in the algorithm is created from small perturbations of the tissue conductivity. A total of eight simulation scenarios are evaluated, where the conductivity perturbations are in the order of 1%, 2.5% to 5% of the nominal tissue conductivity. The algorithm can successfully reconstruct the images in the presence of random noise. The obtained images are compared against traditional EIT where the percentage error is calculated for each simulated tomographic image. The simulation results indicate that the proposed approach is superior to traditional EIT as it constructs more distinct and high contrasting images with less percentage error. © 2022 IEEE.

关键词： Inverse problems

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：