检索结果-内蒙古大学图书馆

7th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2024

作者： Lin, Xu Li, Heng Qian, Yukun Lu, Yun Wang, Mingjiang Shenzhen Key Laboratory of IoT Technology Shenzhen China Huizhou University School of Computer Science and Engineering Huizhou China

ISBN: (纸本)9798350350890

Sleep apnea syndrome (SAS) is a dangerous and high incidence sleep disorder. As more and more people are affected by SAS, monitoring SAS in family life becomes increasingly important. It is very meaningful to design an automatic SAS monitoring device. We designed a SAS detection model based on neural network, and transplanted the model to an application specific integrated circuit (ASIC). There are many problems in the process of transplanting neural network to ASIC. One of the most serious problems is the transplantation of nonlinear activation functions. We proposed a software-hardware joint optimization method to solve the problem of activation function in the SAS model transplantation. In the process of building the neural network model, our research modified the activation function in the traditional LSTM model and the attention mechanism, and adopted hard-sigmoid and LeakyReLU activation function for digital circuits. In the hardware transplantation, the activation function was constructed using the binary shift-based division, three-segment and two-segment function. A digital circuit without migration errors can be obtained with a small area and time consumption. We jointly optimized the structure of the model design and the digital circuit implementation. The model was more suitable for the digital circuit structure, so that the neural network can be transplanted more smoothly. © 2024 IEEE.

关键词： Sleep research

来源：评论

学校读者我要写书评

暂无评论

Image-Based Automatic Energy Meter Reading Using Deep Learning

引用

computers, Materials & Continua 2023年第1期74卷 203-216页

作者： Muhammad Imran Hafeez Anwar Muhammad Tufail Abdullah Khan Murad Khan Dzati Athiar Ramli Institute of Computer Sciences and Information Technology Faculty of Management and Computer SciencesThe University of AgriculturePeshawarPakistan Department of Electrical and Computer Engineering COMSATS University IslamabadAttock CampusAttock CityPakistan Kuwait College of Science and Technology Kuwait CityKuwait School of Electrical&Electronic Engineering USM Engineering CampusUniversiti Sains MalaysiaPenang14300Malaysia

We propose to perform an image-based framework for electrical energy meter *** aim is to extract the image region that depicts the digits and then recognize them to record the consumed *** the readings of serial numbers and energy meter units,an automatic billing system using the Internet of Things and a graphical user interface is deployable in a real-time ***,such region extraction and character recognition become challenging due to image variations caused by several factors such as partial occlusion due to dust on the meter display,orientation and scale variations caused by camera positioning,and non-uniform illumination caused by *** this end,our work evaluates and compares the stateof-the art deep learning algorithm You Only Look Once(YOLO)along with traditional handcrafted features for text extraction and *** image dataset contains 10,000 images of electrical energymeters and is further expanded by data augmentation such as in-plane rotation and scaling tomake the deep learning algorithms robust to these image *** training and evaluation,the image dataset is annotated to produce the ground truth of all the ***,YOLO achieves superior performance over the traditional handcrafted features with an average recognition rate of 98%for all the *** proves to be robust against the mentioned image variations compared with the traditional handcrafted *** proposed method can be highly instrumental in reducing the time and effort involved in the currentmeter reading,where workers visit door to door,take images ofmeters and manually extract readings from these images.

关键词： Convolutional neural network object localization machine learning

来源：评论

学校读者我要写书评

暂无评论

Advancing Early Detection: CNN for Automated Blood Cancer Diagnosis and Anomaly Detection 2

Advancing Early Detection: CNN for Automated Blood Cancer Di...

引用

2nd IEEE International Conference on IoT, Communication and Automation technology, ICICAT 2024

作者： Raji, V. Seetharaman, Anburaman Kasi, Baskar Govindaraju, Sakthi Paarkavy, B. S K P Engineering College Department of Computer Science and Engineering Tiruvannamalai India Sri Venkateswaraa College of Technology Department of Artificial Intelligence and Data Science Chennai India Galgotias University School of Computer Science and Engineering Greater Noida India Galgotias University School of Computer Science and Engineering Greater Noida India Saveetha Engineering College Department of AI&DS Chennai India

ISBN: (纸本)9798350368109

The evaluation and diagnosis of diseases related to blood cancer can be intricate and time-consuming. This complexity is compounded by the reliance on manual analyses employing techniques that consume a significant amount of time. Numerous methods have been created over the past ten years for the finding, analysis, and categorization of human blood cancer. The lack of methods or models that can automatically analyze human blood cells to detect the presence of cancer, however, is still a significant issue. The development of such a model holds the potential to enhance the early detection and prevention of these diseases, thereby facilitating more prompt medical diagnoses. In our ongoing research, we present our current endeavors in the creation of a Deeper with Convolutions Neural Network (DCNN) Learning Model capable of recognizing anomalies in blood cells. We employ a Hybrid Ensemble DCNN Learning technique for the identification of blood cancer. With accuracy rates surpassing 99%, this method is one of the most sophisticated deep learning models. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Trimap generation with background for natural image matting 3

Trimap generation with background for natural image matting

引用

3rd International Conference on Optics and Machine Vision, ICOMV 2024

作者： Fu, Qian Liang, Yihui Kun, Zou Feng, Fujian Xu, Xiang School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China School of Computer Science Zhongshan Institute University of Electronic Science and Technology of China Zhongshan China Guizou Key Laboratory of Pattern Recognition and Intelligent System Guizhou Minzu University Guiyang China

ISBN: (纸本)9781510680319

Image matting is a widely-used image processing technique that aims at accurately separating foreground from an image. However, this is a challenging and ill-posed problem that demands additional input, such as trimaps and background images, for providing prior knowledge. However, the manual annotation of trimaps require lots of labor, limiting the application of trimap-based methods. Some trimap-free methods explore alternatives with low labor requirements by utilizing captured background images, including background-based methods. However, the quality of alpha mattes predicted by trimap-free methods still fall short of trimap-based methods. To reduce the performance gap between background-based and trimap-based methodes, we present Trimap Generation from Background Image (TG-BG) method which can generate trimaps from the input image and a captured background image. It provides an economical solution to facilitate the application of trimap-based methods, allowing for low-cost and high-quality alpha matte predictions. TP-BG leverages a ViT backbone for feature extraction and employs the Image and Background Detail Fusion Stream (IBDFS) to capture multi-scale detail information. The introduction of foreground impact loss encourages the network to pay more attention to the foreground in the image. We validate the trimap prediction performance of TP-BG by comparing the alpha matte quality obtained by background-based methods and that obtained by trimap-based methods integrated with TP-BG. The experimental results demonstrate that TP-BG can generate high-quality trimap from a background image, and trimap-based methods integrated with TP-BG outperform the state-of-the-art background-based methods in terms of four alpha matte quality metrics. © 2024 SPIE.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

An Hybrid Stacked LSTM Approach to Forecast the Stock Prices 21

An Hybrid Stacked LSTM Approach to Forecast the Stock Prices

引用

21st OITS International Conference on Information technology, OCIT 2023

作者： Parida, Ajaya Kumar Rout, Minakhi Jena, Ajay Kumar Parida, Nirupama Parida, Raj Kumar KIIT Deemed to Be University School of Computer Engineering Bhubaneswar India National Institute of Technology Computer Science and Engineering Meghalaya Shillong India

ISBN: (纸本)9798350358230

Predicting Predicting stock market data is a challenging task due to its intricate and highly unstable nature. In this research, historical data and technical indicators are utilized to enhance the accuracy of predictions. The CNN technique is used to extract various features, and the dropout based LSTM technique is employed for making predictions. The primary objective of this work is to enhance the performance of stock price prediction by applying different technical indicators and historical data as input. The GWO-XGB ELM based Stacked LSTM, is used to replace the sub max layer. A LSTM based hybrid system is constructed and tested on a variety of sources, including different stock markets. To evaluate the accuracy of the proposed model, various matrices are employed. Two different stock market datasets (HDFC BANK and YES BANK) of Past five years are examined for this purpose. The extracted features demonstrate a more precise outcome. The implementation results of the study show that the proposed model surpasses the performance of the other methods evaluated in the paper. The evidence indicates that the proposed model outperforms the competition in terms of accuracy, precision, with minimum RMSE (Root Mean Square Error). These findings suggest that the proposed model is a more effective and efficient solution for the problem at hand than the alternatives considered in this study. © 2023 IEEE.

关键词： Financial markets

来源：评论

学校读者我要写书评

暂无评论

Virtual Viewpoint Rendering Method Based on Multi-Threshold Layering 8

Virtual Viewpoint Rendering Method Based on Multi-Threshold ...

引用

8th International Conference on Image, Vision and Computing, ICIVC 2023

作者： Wang, Jiahe Liu, Jiayue School of Computer Beijing Institute of Technology Beijing China School of Materials Science and Engineering Beijing Institute of Technology Beijing China

ISBN: (纸本)9798350335231

In order to solve the problem of artifacts and holes in virtual viewpoint rendering, this paper proposes a virtual viewpoint rendering method based on multi-threshold layering. The processing flow of the method is divided into two algorithms, the pre-algorithm solves the artifact problem, and the post-algorithm solves the hole problem. In the pre-algorithm, the depth refinement and pixel correction parts produce precise pixel alignment between color and depth image pairs, eliminating contour artifacts, and then the color correction section eliminates color aberration artifacts. In the post-algorithm, the Otsu multi-threshold layering part separates the scene by layer, and combines with selected median filtering to eliminate crack holes. Then, the depth-guided hole filling part fills in occlusion holes and out-of-field holes based on pixel categories, improving the quality of the virtual view. Experiments have shown that our method performs better than many other methods in terms of subjective visual quality and objective evaluation. © 2023 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Direction-of-Arrival Estimation Using A Uniform Linear Array Considering Antenna Radiation Patterns

Direction-of-Arrival Estimation Using A Uniform Linear Array...

引用

2024 United States National Committee of URSI National Radio science Meeting, USNC-URSI NRSM 2024

作者： Ren, Kai Department of Electrical Engineering and Computer Science South Dakota School of Mines and Technology Rapid CitySD United States

ISBN: (纸本)9781946815194

A UHF antenna array is proposed for direction-of-arrival (DOA) estimations. In conventional direction finding (DF) systems, it is assumed that antenna elements have isotropic patterns and mutual coupling among these elements are neglected, leading to compromised DF accuracies. In this work, complex radiation patterns with the presence of mutual coupling among antenna elements are simultaneously considered through full-wave numerical simulations of the antenna array. The antenna patterns rather than simplified array factors are applied in DF algorithms. Both Cramer-Rao bound (CRB) calculations and multiple signal classification (MUSIC) algorithm are implemented to validate the DF performance of the UHF antenna array. © 2024 IEEE. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Risk-Aware Real-Time Task Allocation for Stochastic Multi-Agent Systems under STL Specifications 63

Risk-Aware Real-Time Task Allocation for Stochastic Multi-Ag...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Engelaar, M.H.W. Zhang, Z. Vlahakis, E.E. Dimarogonas, D.V. Lazar, M. Haesaert, S. Netherlands Kth Royal Institute of Technology Division of Decision and Control Systems School of Electrical Engineering and Computer Science Sweden

ISBN: (纸本)9798350316339

This paper addresses the control synthesis of heterogeneous stochastic linear multi-agent systems with realtime allocation of signal temporal logic (STL) specifications. Based on previous work, we decompose specifications into subspecifications on the individual agent level. To leverage the efficiency of task allocation, a heuristic filter evaluates potential task allocation based on STL robustness, and subsequently, an auctioning algorithm determines the definitive allocation of specifications. Finally, a control strategy is synthesized for each agent-specification pair using tube-based model predictive control (MPC), ensuring provable probabilistic satisfaction. We demonstrate the efficacy of the proposed methods using a multi-shuttle scenario that highlights a promising extension to automated driving applications like vehicle routing. © 2024 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Asynchronous Distributed Learning with Quantized Finite-Time Coordination 63

Asynchronous Distributed Learning with Quantized Finite-Time...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Bastianello, Nicola Rikos, Apostolos I. Johansson, Karl H. Kth Royal Institute of Technology School of Electrical Engineering and Computer Science and Digital Futures Sweden Artificial Intelligence Thrust of the Information Hub Guangzhou China The Hong Kong University of Science and Technology Department of Computer Science and Engineering Clear Water Bay Hong Kong

ISBN: (纸本)9798350316339

In this paper we address distributed learning problems over peer-to-peer networks. In particular, we focus on the challenges of quantized communications, asynchrony, and stochastic gradients that arise in this set-up. We first discuss how to turn the presence of quantized communications into an advantage, by resorting to a finite-time, quantized coordination scheme. This scheme is combined with a distributed gradient descent method to derive the proposed algorithm. Secondly, we show how this algorithm can be adapted to allow asynchronous operations of the agents, as well as the use of stochastic gradients. Finally, we propose a variant of the algorithm which employs zooming-in quantization. We analyze the convergence of the proposed methods and compare them to state-of-the-art alternatives. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Integration of IoT-enabled UAVs in Smart Agriculture: Types, Applications, Trends, challenges 7

Integration of IoT-enabled UAVs in Smart Agriculture: Types,...

引用

7th International Conference on Circuit Power and Computing Technologies, ICCPCT 2024

作者： Prathyusha, Gajawada Krishnan, M.B.Mukesh Deepak, S.Prem Kumar SRM Institute of Science and Technology School of Computing Department of Networking and Communications India B V Raju Institute of Technology Department of Computer Science and Engineering Narsapur India

ISBN: (纸本)9798350372816

Unmanned aerial vehicles (UAVs) have garnered increasing attention in recent years due to their utilization of artificial intelligence (AI) technologies and automation processes. These vehicles are being developed for various applications, including the military, smart agriculture, rescue operations, entertainment, monitoring, and medicine delivery. In the current era, UAVs extensively employ a wide range of technologies to transmit data to base stations. The collected data undergoes processing, producing remarkable outcomes through the integration of machine learning and deep learning technologies. This paper reviews disease identification and object detection techniques and their associated applications & challenges. Additionally, the research explores recent trends and technologies in the field of smart agriculture. This research emphasizes the use of sensors in unmanned aerial vehicles (UAVs) by analyzing the methods utilized for recognizing diseased areas and things while identifying insects and sick crops. This paper also addresses the challenges encountered by existing methodologies and proposes directions for future research and development. Furthermore, this review delves into suitable techniques for heterogeneous UAVs and examines IoT-related strategies. © 2024 IEEE.

关键词： Smart agriculture

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：