检索结果-内蒙古大学图书馆

5th International Conference on Intelligent Computing and Control Systems, ICICCS 2021

作者： Chethana, C. BMS Institute of Technology Management Dept. of Computer Science and Engineering Avalahalli Bengaluru India

ISBN: (纸本)9781665412728

Recently, Machine learning classification algorithms are playing a vital role in analysing various data available in cloud storage and websites. In this paper, the heart disease dataset is considered and the results are predicted by using various version of the KNN classifier in MATLAB. The comparisons of the performance of all these algorithms have been evaluated for accuracy, misclassification rate. The distance metric and distance weight used by various KNN algorithms is also shown. The experiment has done with the PCA option enabled. The optimized KNN was best with an accuracy of 69% with a prediction speed of 5600 obs/sec. © 2021 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Meta Reinforcement Learning for Resource Allocation in Multi-Antenna UAV Network with Rate Splitting Multiple Access

arXiv

引用

arXiv 2024年

作者： Zarini, Hosein Dehkordi, Maryam Farajzadeh Farhadi, Armin Mili, Mohammad Robat Movaghar, Ali Rasti, Mehdi Li, Yonghui Wong, Kai-Kit Dept. of Computer Engineering Sharif University of Technology Tehran Iran Dept. of Electrical and Computer Engineering George Mason University VA United States Dept. of Electrical and Computer Engineering University of Tehran Tehran Iran Tehran Iran Centre for Wireless Communications University of Oulu Oulu Finland School of Electrical and Information Engineering University of Sydney Sydney Australia Dept. of Electronic and Electrical Engineering University College London London United Kingdom

Unmanned aerial vehicles (UAVs) with multiple antennas have recently been explored to improve capacity in wireless networks. However, the strict energy constraint of UAVs, given their simultaneous flying and communication tasks, renders the exploration of energy-efficient multi-antenna techniques indispensable for UAVs. Meanwhile, lens antenna subarray (LAS) emerges as a promising energy-efficient solution that has not been previously harnessed for this purpose. In this paper, we propose a LAS-aided multi-antenna UAV to serve ground users in the downlink transmission of the terahertz (THz) band, utilizing rate splitting multiple access (RSMA) for effective beam division multiplexing. We formulate an optimization problem of maximizing the total system spectral efficiency (SE). This involves optimizing the UAV’s transmit beamforming and the common rate of RSMA. By recasting the optimization problem into a Markov decision process (MDP), we propose a deep deterministic policy gradient (DDPG)-based resource allocation mechanism tailored to capture problem dynamics and optimize its variables. Moreover, given the UAV’s frequent mobility and consequential system reconfigurations, we fortify the trained DDPG model with a meta-learning strategy, enhancing its adaptability to system variations. Numerically, more than 20% energy efficiency gain is achieved by our proposed LAS-aided multiantenna UAV equipped with 4 lenses, compared to a single-lens UAV. Simulations also demonstrate that at a signal-to-noise (SNR) of 10 dB, the incorporation of RSMA results in a 22% SE enhancement over conventional orthogonal beam division multiple access. Furthermore, the overall system SE improves by 27%, when meta-learning is employed for fine-tuning the conventional DDPG method in literature. © 2024, CC BY.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

SpeckleDiff-2D: Complex-Valued Speckle Reduction Diffusion Network

SpeckleDiff-2D: Complex-Valued Speckle Reduction Diffusion N...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Danwei Lu Chao Liu Xunhao Lin Junjun Yin Jian Yang Dept. of Electronic Engineering Tsinghua University Beijing China School of Computer and Communication University of Science and Technology Beijing Beijing China

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

SAR despeckling is a crucial preprocessing step for various SAR applications. This work introduces SpeckleDiff2D, a complex-valued speckle reduction diffusion network. Our approach emphasizes the design of a forward noise-accumulation process that mimics the generation mechanism of speckle noise. The proposed despeckling algorithm is trained exclusively on synthesized speckled images generated by optical dataset and is validated on both simulated and real SAR images. Experimental results demonstrate the method’s efficiency and resilience to domain shifts, positioning it as a promising solution to the persistent challenge of data insufficiency in SAR despeckling design.

关键词： Noise Speckle Diffusion models Optical imaging Radar polarimetry Adaptive optics Optical sensors

来源：评论

学校读者我要写书评

暂无评论

Real-time Health Monitoring of Patients in Emergencies Through Machine Learning And IoT Integrated With Edge Computing

Real-time Health Monitoring of Patients in Emergencies Throu...

引用

International Conference on Confluence The Next Generation Information technology Summit (Confluence)

作者： Amit Kumar Mishra Rahul Sharma Jagendra Singh Prabhishek Singh Manoj Diwakar Mohit Tiwari Department of Computer Science & Engineering Graphic Era Hill University Dehradun India D. Y. Patil International University Pune India School of Computer Science Engineering and Technology Bennett University Greater Noida India Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun India Dept. of Computer Science & Engineering Bharati Vidyapeeth's College of Engineering Delhi India

With employing the Internet of Things (IoT) sensors and modern-day machine learning algorithms, this study presents a modern inquiry at the intersection of healthcare and era. This have a look at studies the capability of Long ShortTerm Memory (LSTM) and Artificial Neural Network (ANN) fashions in forecasting affected person fitness consequences by utilising the exploitation of sensor facts inclusive of temperature, blood strain, ECG, EEG, and pulse price. The study extensively examines the models' performance utilising a broad variety of performance benchmarks. Results demonstrate that once compared to the LSTM model, the ANN version performs better in terms of prediction accuracy, precision, do not forget, and Fl score. This enhanced accuracy indicates how effectively the ANN model can spot challenging patterns in the dataset. The predicted fitness possibilities for 15 human individuals also are proved in a result table, reaffirming the ANN models constant advantage in prediction. This look at proactive patient care, more intelligent treatment regimens, and improved overall patient outcomes is driving the business and is a significant step towards personalised, data-driven healthcare solutions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Experimental Demonstration of Hybrid LED-LD Based UOWC Link

Experimental Demonstration of Hybrid LED-LD Based UOWC Link

引用

International Conference on Microwave, Optical and Communication engineering (ICMOCE)

作者： Gopal Krishna Jimson Mathew T. Santhanakrishnan Sumanta Gupta Dept. of Electrical Engineering Indian Institute of Technology Patna India Dept. of Computer Science and Engineering Indian Institute of Technology Patna India Naval Physical and Oceanographic Laboratory DRDO

In this paper, we have designed and experimentally characterized a hybrid light emitting diode (LED) and laser diode (LD) based underwater optical wireless communication (UOWC) link, which can be suitable for providing high-speed optical connectivity between onshore and submerged systems. An LED-based system is efficient for short-range communication whereas an LD-based system is for long distances. In this paper, we have experimentally demonstrated the establishment of a hybrid LED-LD UOWC link at a data rate of 10 Mbps over a 2.5 m water channel using a return to zero on-off keying (RZ-OOK) modulation scheme using an FPGA-based transmitter and receiver. We have also used offline data processing to quantify the bit error rate (BER) performance as a function of received optical power for tap water and turbid water channels. For the tap water channel, we have achieved a BER as low as 3.5 ×10 −6 at - 35.1 dBm received optical power, whereas for turbid water the achieved BER is 1.8 × 10 −5 at −31. 6 dBm of received optical power in absence of air bubble. In turbid water (and tap water) channel in presence of air bubbles the minimum achievable BER is around 3 × 10 −4 (3 × 10 −4 ) for −31.5 dBm (-35.5 dBm) of received power.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Next Generation Intelligent Traffic Signal Control: Empowering Electronics Consumers with Edge-AIoT Capabilities

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Chavhan, Suresh Doswada, Rohit Gupta, Deepak Gunjal, Saymam Rodrigues, Joel J.P.C. School of Data Sciences Indian Institute of Science Education and Research Kerala Thiruvananthapuram India C-DoT Karnataka Bangalore India Dept. of Computer Science and Engineering Maharaja Agrasen Institute of Technology Delhi India Centre for Research Impact and Outcome Institute of Engineering and Technology Chitkara University Punjab India Department of Computer Science and Engineering University of Visvesvaraya College of Engineering Karnataka Bangalore India Federal University of Piaui PI Teresina Brazil

Traffic congestion has become a major issue that is being faced by the majority of road users. The increasing vehicle usage, and the lack of space and funds to construct new transport infrastructure, further complicates the issue. In this scenario, it is important to come up with an intelligent and economical solution that improves the quality of road users' service. The problem with the traffic handling framework is signal timings are fixed which is not adaptive to the density of vehicles. To address this issue we propose an Edge-Augument Artificial Intelligence of Things (AIoT) road user cooperation for traffic management. The proposed system efficiently utilizes electronic devices to learn and adapt to changing traffic conditions in real-time. By optimizing the traffic signal timings based on the actual traffic conditions, adaptive systems reduce delay, improve traffic flow, reduce fuel consumption and pollution, and improve the electronics consumers' and road users' experiences. The proposed system has been tested with real-time experiments by integrating Electronic devices like cameras, smartphones, and AGX Xavier (edge device) with Cloud (ThingSpeak). The proposed system is verified by simulating the proposed system in the SUMO traffic simulator and its reliability is concluded by comparing the waiting time, depart delay, running, and halt time with the existing traditional method. © 2025 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

FoD Enroll Image Quality Classification Method for Fingerprint Authentication System

FoD Enroll Image Quality Classification Method for Fingerpri...

引用

2021 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2021

作者： Chen, Xiu-Zhi Lin, Jhe-Li Chen, Yen-Lin National Taipei University of Technology Dept. Computer Science and Information Engineering Taipei Taiwan

ISBN: (纸本)9781665419512

Typical fingerprint authentication system flow including preprocessing, feature extraction, and feature matching. To improve the user experience of it, more intelligent process for such system is needed. Fingerprint on display (FoD) is a popular kind of sensing technique in recent years, in this research, we proposed an enroll image quality classification method for the preprocessing step of the system, which is able to reject the invalid input, in order to shorten the response time, especially for FoD applications. We had evaluated our proposed method through a self-collected FoD sensing image dataset, including 50, 130 fingerprint images, and proved that our method is able to reach 95.83% accuracy, which is really helpful for the improvement of the system's user experience. © 2021 IEEE.

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

An overview of inertia requirement in modern renewable energy sourced grid: challenges and way forward

引用

Journal of Electrical Systems and Information technology 2022年第1期9卷 1-27页

作者： Ayamolowo, Oladimeji Joseph Manditereza, Patrick Kusakana, Kanzumba Dept. of Electrical Electronic and Computer Engineering Central University of Technology Bloemfontein South Africa

As the world strives toward meeting the Paris agreement target of zero carbon emission by 2050, more renewable energy generators are now being integrated into the grid, this in turn is responsible for frequency instability challenges experienced in the new grid. The challenges associated with the modern power grid are identified in this research. In addition, a review on virtual inertial control strategies, inertia estimation techniques in power system, modeling characteristics of energy storage systems used in providing inertia support to the grid, and modeling techniques in power system operational and expansion planning is given. Findings of this study reveal that adequate system inertia in the modern grid is essential to mitigate frequency instability, thus, considering the inertia requirement of the grid in operational and expansion planning model will be key in ensuring the grid’s stability. Finally, a direction for future research has been identified from the study, while an inertial constant of between 4 and 10 s is recommended to ensure frequency stability in modern power grid.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition from Video Frame Sequence using Face Mesh and Pre-Trained Models of Convolutional Neural Network

Emotion Recognition from Video Frame Sequence using Face Mes...

引用

International Seminar on Intelligent technology and Its Applications (ISITIA)

作者： Derry Pramono Adi Eko Mulyanto Yuniarno Diah Puspito Wulandari Dept. of Electrical Engineering Faculty of Intelligent Electrical and Informatics Technology Institut Teknologi Sepuluh Nopember Surabaya Indonesia Dept. of Electrical Engineering Dept. of Computer Engineering Faculty of Intelligent Electrical and Informatics Technology Institut Teknologi Sepuluh Nopember Surabaya Indonesia Dept. of Computer Engineering Faculty of Intelligent Electrical and Informatics Technology Institut Teknologi Sepuluh Nopember Surabaya Indonesia

Emotions are a collection of subjective cognitive experiences and psychological and physiological characteristics that express a wide range of feelings, thoughts, and behaviors in human interaction. Emotions can be represented through several means, such as facial expressions, tone of voice, and behavior. Deep Learning (DL) research has focused on incorporating facial expressions. Images with facial expressions are commonly used as data input for the DL model. Unfortunately, most DL models in Facial Emotion Recognition (FER) use static images. This method does not take into consideration all conceivable facial expressions. The static image of facial expressions is insufficient for recognizing emotions, but a sequential image from a video is required. In this study, we extract MediaPipe’s face mesh feature, the state-of-the-art multidimensional expression key points embedded in the video image sequence. Furthermore, we feed sequence image data into the pre-trained Convolutional Neural Network (CNN) model. The data we used is from The Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) with the emotion classes of “Anger,” “Fearful,” “Happy,” and “Sad.” For this specific FER task, we found that the best pre-trained CNN model achieved 92.8% accuracy (using the VGG-19 model), with the fastest runtime of $\sim2.3$ seconds (achieved using the SqueezeNet model).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Characteristic Mode Analysis of Wideband Patch Antenna Using Dual-Mode Resonance

Characteristic Mode Analysis of Wideband Patch Antenna Using...

引用

Global Conference for Advancement in technology (GCAT)

作者： Vinaya Kumar S R Venkatesh T Puneeth Kumar Tharehalli Rajanna Dept. of Electrical and Electronics Engineering Ghousia College of Engineering Ramanagara Karnataka India Dept. of Computer Science Engineering Ghousia College of Engineering Ramanagara Karnataka India Dept. of Electronics and Telecommunication Engg Siddaganga Institute of Technology Tumkur Karnataka India

ISBN: (数字)9798350376685

ISBN: (纸本)9798350376692

This paper presents the characteristic mode analysis(CMA) of wideband patch antenna using dual-mode resonances. CMA is used to analyze the fundamental resonance modes of square patch antenna. It has two fundamental modes of TM01 and TM10 modes. The patch is excited using aperture coupling to excite both horizontal and vertical mode. The slot aperture length and width is optimized for better coupling. The vertical mode resonance frequency is slightly reduced by introducing the slot. These two modes combined together gives the wide bandwidth. An impedance bandwidth of 47.12%(1.93GHz-3.12GHz) is obtained. The antenna is well radiated with both modes being radiation efficiency of above 90%. The realized peak gain of 5.72dBi and 4.62dBi is obtained at 2.12GHz and 2.83GHz and good radiation pattern in the broadside direction. The cross polarization level of more than -10dB is achieved with respect to co-polarization level at resonance frequency of 2.12GHz and 2.83GHz respectively and it is suitable for WiFi and Bluetooth applications.

关键词： Couplings Surface impedance Bluetooth Patch antennas Resonant frequency Apertures Characteristic mode analysis Impedance Wideband Wireless fidelity

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：