检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Big Data, BigData 2024

作者： Lee, Yeaeun Kim, Byeongchang Kim, Dongju Hwang, Euiseok Choi, Jaehyuk Kim, Hyunsup Gwangju Institute of Science and Technology School of Electrical Engineering and Computer Science Gwangju Korea Republic of Gwangju Institute of Science and Technology Ai Graduate School Gwangju Korea Republic of Hyundai Motors Company Korea Republic of

ISBN: (纸本)9798350362480

With global EV sales projected to reach 3.5 million units by 2023 and public charging stations increasing by 40%, effective management and optimization of charging infrastructure have become critical. While current research primarily focuses on models that address either users or charging stations, these approaches often overlook external factors such as weather and traffic conditions, which significantly impact driving patterns and energy consumption. The integration of these external variables into forecasting models is thus critical for enhancing prediction accuracy and infrastructure optimization. In this study, we conducted an in-depth analysis of EV charging patterns at highway rest areas. This study employed deep learning models, GRU, and LSTM architectures, trained using various data combinations. The experiments revealed that the inclusion of traffic data notably improves forecasting precision. In particular, the LSTM model demonstrated a 10.5% reduction in mean absolute percentage error(MAPE), decreasing the standard deviation from 4.95 to 3.87 when external factors were included. © 2024 IEEE.

关键词： deep learning demand forecasting Electric vehicle charging station external variables

来源：评论

学校读者我要写书评

暂无评论

Arabic Handwritten Document OCR Solution with Binarization and Adaptive Scale Fusion Detection 6

Arabic Handwritten Document OCR Solution with Binarization a...

引用

6th IEEE Novel Intelligent and Leading Emerging sciences Conference, NILES 2024

作者： Waly, Alhossien Tarek, Bassant Feteha, Ali Yehia, Rewan Amr, Gasser Fares, Ahmed Egypt-Japan University of Science and Technology E-JUST Faculty of Engineering Computer Science and Engineering Departement Alexandria21934 Egypt Benha University Faculty of Engineering Electrical Engineering Department Cairo11629 Egypt

ISBN: (纸本)9798350378511

The problem of converting images of text into plain text is a widely researched topic in both academia and industry. Arabic handwritten Text Recognation (AHTR) poses additional challenges due to diverse handwriting styles and limited labeled data. In this paper we present a complete OCR pipeline that starts with line segmentation using Differentiable Binarization and Adaptive Scale Fusion techniques to ensure accurate detection of text lines. Following segmentation, a CNN-BiLSTM-CTC architecture is applied to recognize characters. Our system, trained on the Arabic Multi-Fonts Dataset (AMFDS), achieves a Character Recognition Rate (CRR) of 99.20% and a Word Recognition Rate (WRR) of 93.75% on single-word samples containing 7 to 10 characters, along with a CRR of 83.76% for sentences. These results demonstrate the system's strong performance in handling Arabic scripts, establishing a new benchmark for AHTR systems. © 2024 IEEE.

关键词： Arabic Optical Character Recognition convolutional neural networks line segmentation recurrent neural networks Scene text detection

来源：评论

学校读者我要写书评

暂无评论

ESL127: Emirate Sign Language Dataset(s) and e-Dictionary (Version 2.0) Utilizing Deep Learning Recognition Models 15

ESL127: Emirate Sign Language Dataset(s) and e-Dictionary (V...

引用

15th International Conference on Innovations in Information technology, IIT 2023

作者： Ahmed, Ahmed Abdelhadi Gochoo, Munkhjargal Taghizadeh, Mohamad Otgonbold, Munkh-Erdene Batnasan, Ganzorig Department of Computer Science and Software Engineering Al Ain United Arab Emirates Iran University of Science and Technology Department of Electrical Engineering Iran

ISBN: (纸本)9798350382396

As stated by the United Arab Emirates's (UAE) Community Development Authority (CDA), there are around 3,065 individuals with hearing disabilities in the country. These individuals often struggle to communicate with broader society and rely on scarce sign language (SL) interpreters. Moreover, Arabic's dialects diversity compounds the issue by causing dialects in the Arabic Sign Language (ArSL). Hence, the call for a standardized reference for ArSL in the region is a priority. To address these challenges, we've developed an Emirate Sign Language (ESL) electronic dictionary (e-dictionary) with a dataset of 127 signs and 50 sentences, recorded by hearing-impaired individuals in the UAE with various degrees of deafness. Supervised by certified interpreters and validated by ESL's department head at CDA in Dubai, the recordings were made using Azure Kinect DK, resulting in 708 recordings. The dataset is then processed to 10fps. The e-dictionary offers features such as webcam-based sign recognition using YOLOv8 technology, voice-based signing via Arabic Automatic Speech Recognition, text-based signing, and words spelling in ArSL. © 2023 IEEE.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

How do Software engineering Researchers Use GitHub? An Empirical Study of Artifacts & Impact 24

How do Software Engineering Researchers Use GitHub? An Empir...

引用

24th IEEE International Conference on Source Code Analysis and Manipulation, SCAM 2024

作者： Alrashedy, Kamel Binjahlan, Ahmed Georgia Institute of Technology School of Computer Science AtlantaGA United States Georgia Institute of Technology School of Electrical and Computer Engineering AtlantaGA United States

ISBN: (纸本)9798331528508

Millions of developers share their code on open-source platforms like GitHub, which offer social coding opportunities such as distributed collaboration and popularity-based ranking. Software engineering researchers have joined in as well, hosting their research artifacts (tools, replication package & datasets) in repositories, an action often marked as part of the publication's contribution. Yet a decade after the first such paper-with-GitHub-link, little is known about the fate of such repositories in practice. Do research repositories ever gain the interest of the developer community, or other researchers? If so, how often and why (not)? Does effort invested on GitHub pay off with research impact? In short: we ask whether and how authors engage in social coding related to their research. We conduct a broad empirical investigation of repositories from published work, starting with ten thousand papers in top SE research venues, hand-Annotating their 3449 GitHub (and Zenodo) links, and studying 309 paper-related repositories in detail. We find a wide distribution in popularity and impact, some strongly correlated with publication venue. These were often heavily informed by the authors' investment in terms of timely responsiveness and upkeep, which was often remarkably subpar by GitHub's standards, if not absent altogether. Yet we also offer hope: popular repositories often go hand-in-hand with well-cited papers and achieve broad impact. Our findings suggest the need to rethink the research incentives and reward structure around research products requiring such sustained contributions. © 2024 IEEE.

关键词： Software engineering

来源：评论

学校读者我要写书评

暂无评论

KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache 41

KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cach...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Liu, Zirui Yuan, Jiayi Jin, Hongye Zhong, Shaochen Xu, Zhaozhuo Braverman, Vladimir Chen, Beidi Hu, Xia Department of Computer Science Rice University United States Department of Computer Science Texas A&M University United States Department of Computer Science Stevens Institute of Technology United States Department of Electrical and Computer Engineering Carnegie Mellon University United States

Efficiently serving large language models (LLMs) requires batching many requests together to reduce the cost per request. Yet, the key-value (KV) cache, which stores attention keys and values to avoid re-computations, significantly increases memory demands and becomes the new bottleneck in speed and memory usage. This memory demand increases with larger batch sizes and longer context lengths. Additionally, the inference speed is limited by the size of KV cache, as the GPU's SRAM must load the entire KV cache from the main GPU memory for each token generated, causing the computational core to be idle during this process. A straightforward and effective solution to reduce KV cache size is quantization, which decreases the total bytes taken by KV cache. However, there is a lack of in-depth studies that explore the element distribution of KV cache to understand the hardness and limitation of KV cache quantization. To fill the gap, we conducted a comprehensive study on the element distribution in KV cache of popular LLMs. Our findings indicate that the key cache should be quantized per-channel, i.e., group elements along the channel dimension and quantize them together. In contrast, the value cache should be quantized per-token. From this analysis, we developed a tuning-free 2bit KV cache quantization algorithm, named KIVI. With the hardware-friendly implementation, KIVI can enable Llama (Llama-2), Falcon, and Mistral models to maintain almost the same quality while using 2.6× less peak memory usage (including the model weight). This reduction in memory usage enables up to 4× larger batch size, bringing 2.35× ∼ 3.47× throughput on real LLM inference workload. The source code is available at https://***/jy-yuan/KIVI. Copyright 2024 by the author(s)

关键词： Cache memory

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Review on Object Detection in the Context of Autonomous Driving 4

A Comprehensive Review on Object Detection in the Context of...

引用

4th International Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2024

作者： Islam, Md Moynul Chowdhury, Ismatul Jannat Mahboob, Tanvir Zobair Mazumder, Md Shah Jalal Hossain, Mohammad Jakaria Biswas, Md Siam Rone, Poncanon Datta Maharishi International University Department of Computer Science IA United States University of North Carolina Department of Electrical Engineering CharlotteNC United States Chittagong University of Engineering and Technology Department of Computer Science and Engineering Chittagong Bangladesh

ISBN: (纸本)9798331529635

In autonomous driving, safety assessment is becoming an essential component, particularly in the perception and analysis of the environment around them. To make safe driving judgments, autonomous cars mostly rely on their capacity to observe and comprehend their environment. Detecting objects is a frequent and challenging problem in autonomous driving. Over the course of the last ten years, as deep learning has rapidly advanced, researchers have conducted numerous experiments and made significant contributions to the performance improvement of object recognition and related tasks including object categorization, localization, and segmentation. In this paper, an overview of state-of-the-art object detection algorithms is presented with in depth analysis. Region proposal-based approaches and single-shot approaches are two main frameworks of object detection which are discussed here. R-CNN, SPP-net, Fast R-CNN, and Faster R-CNN refer to region proposal-based methods while single-shot methods consist of YOLOv2, YOLOv3, YOLOv4 and SSD. The authors truly believe that this study would have a meaningful impact on the current advances in object detection algorithms. © 2024 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Integrated Method for healthcare Data Classification with Incompleteness

引用

computers, Materials & Continua 2024年第11期81卷 3125-3145页

作者： Sonia Goel Meena Tushir Jyoti Arora Tripti Sharma Deepali Gupta Ali Nauman Ghulam Muhammad Electrical and Electronics Engineering(EEE)Department Maharaja Surajmal Institute of TechnologyNew-Delhi110058India Information Technology(IT)Department Maharaja Surajmal Institute of TechnologyNew-Delhi110058India Chitkara University Institute of Engineering and Technology Chitkara UniversityRajpuraPunjab140401India Department of Computer Science and Engineering Yeungnam UniversityGyeongsan-si38541Republic of Korea Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityRiyadh11421Saudi Arabia

In numerous real-world healthcare applications,handling incomplete medical data poses significant challenges for missing value imputation and subsequent clustering or classification *** approaches often rely on statistical methods for imputation,which may yield suboptimal results and be computationally *** paper aims to integrate imputation and clustering techniques to enhance the classification of incomplete medical data with improved *** classification methods are ill-suited for incomplete medical *** enhance efficiency without compromising accuracy,this paper introduces a novel approach that combines imputation and clustering for the classification of incomplete ***,the linear interpolation imputation method alongside an iterative Fuzzy c-means clustering method is applied and followed by a classification *** effectiveness of the proposed approach is evaluated using multiple performance metrics,including accuracy,precision,specificity,and *** encouraging results demonstrate that our proposed method surpasses classical approaches across various performance criteria.

关键词： Incomplete data nearest neighbor linear interpolation imputation clustering classification

来源：评论

学校读者我要写书评

暂无评论

Innovative Colormap for Emphatic Imaging of Human Voice for UAV-Based Disaster Victim Search

Innovative Colormap for Emphatic Imaging of Human Voice for ...

引用

2023 IEEE Region 10 Symposium, TENSYMP 2023

作者： Furusawa, Tomoki Premachandra, Chinthaka Graduate School of Engineering and Science Shibaura Institute of Technology Electrical Engineering and Computer Science Tokyo Japan School of Engineering Shibaura Institute of Technology Department of Electronic Engineering Tokyo Japan

ISBN: (纸本)9781665482585

Unmanned aerial vehicles (UAVs) are being utilized for damage assessment in natural disasters and for search and rescue operations. Currently, the search for victims primarily relies on analyzing images captured by cameras mounted on UAVs. However, this approach has limitations when it comes to locating victims who are not within the camera's field of view. As a result, sound-based search methods are being considered. In this method, a voice message is transmitted to the disaster area through a speaker mounted on a UAV, and the presence of victims is confirmed by detecting their response using the onboard microphone of the UAV. Nevertheless, the UAV's microphone captures both the sound of the victim and the propeller rotation, posing a significant challenge in extracting the victim's voice from this combined audio. To address this issue, we propose a solution that involves generating spectrogram images of the sound mixture and the propeller sound, and extracting the human sound by subtracting them. We found that the conventional colormap was ineffective in emphasizing the human sound in the spectrogram images. To overcome this limitation, this paper introduces a new colormap based on the normal distribution. This colormap enhances human voices while attenuating propeller sounds by adjusting the mean and variance. Through the results of our experiments, we confirm that the proposed colormap effectively reduces propeller sound interference in the sound mixing and simultaneously emphasizes the voice of a disaster victim. By utilizing the proposed colormap, it becomes possible to visualize the victim's voice from the audio mixture acquired by the UAV's onboard microphone, enabling the identification of the victim. © 2023 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

SCCNet: An Improved Multi-Class Skin Cancer Classification Network using Deep Learning 3

SCCNet: An Improved Multi-Class Skin Cancer Classification N...

引用

3rd International Conference on Advancement in electrical and Electronic engineering, ICAEEE 2024

作者： Ahmed, Tanvir Mou, Farzana Sharmin Hossain, Amran Dhaka University of Engineering & Technology Department of Computer Science and Engineering Gazipur Bangladesh Brunel University Department of Electronic and Electrical Engineering London United Kingdom

ISBN: (纸本)9798350388282

Skin cancer is the most prevalent type of cancer worldwide, and detecting it early is crucial to a successful course of treatment. In recent years, machine learning methods have demonstrated great potential for making skin cancer detection simpler. Using a model of the fine-tuned Skin Cancer Classification Network (SCCNet) based on deep learning, we proposed a unique method for classifying skin cancer into multiple categories in this research, which is comprised of the Xception deep learning model and additional four types of fine-tuned layers. The proposed model was trained by the publicly available skin cancer dataset ISIC-2018. The dataset consists of seven classes and 21,000 images after data augmentation, with 3,000 images in each class. The proposed model achieved an accuracy, precision, recall, and F1-score of 95.20%, 95.14%, 95.00%, and 95.14% respectively, for seven-class classification. The proposed SCCNet model, achieved an impressive accuracy of 95.20% in the classification of multiple skin cancer classes, outperforms several state-of-the-art approaches, demonstrating its potential to enhance dermatological diagnostics and guide effective therapeutic interventions for patients with skin cancer. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

An Efficient Data Aggregation Solution for Smart Meters Based on Cloud-Edge Collaboration 20th

An Efficient Data Aggregation Solution for Smart Meters Bas...

引用

20th International Conference on Services Computing, SCC 2023 held as Part of the Services Conference Federation, SCF 2023

作者： Xia, Zhuoqun Zhang, Li Sangaiah, Arun Kumar The School of Computer and Communication Engineering Changsha University of Science and Technology Changsha410000 China Department of Electrical and Computer Engineering Lebanese American University Byblos83990 Lebanon

ISBN: (纸本)9783031516733

Smart meters are an important component of the smart grid, and the large-scale deployment of meters on the user side generates a large amount of data that brings huge expenses to the smart grid. In addition, attackers can monitor users’ electricity consumption based on the transmitted data, which poses a privacy threat. To solve these problems, this paper proposes a secure and efficient data aggregation scheme for smart meters based on cloud-side collaboration. Based on cloud-edge collaboration, the cloud server uses double Z-Score standardization to process the electricity consumption feature data, and at the same time uses improved Euclidean distance to obtain the number of clusters and classification results of the feature distinctions, and interacts with the edge device to respond. Based on the response information, the power provider generates confusion parameters and perturbation factors with classification information, which are sent to the meter for generating convergence values to minimize Gaussian noise and attached to the meter data to achieve the confusion processing of meter data. The aggregator receives the meter and cloud information for classification and aggregation and generates an aggregation signature to transmit the data. The results show that the scheme has high privacy security and operational efficiency. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Smart meters

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：