Procedia Computer Science最新文献

Circular Supply Chains and Industry 4.0: An Analysis of Interfaces in Brazilian Foodtechs 循环供应链与工业 4.0：巴西食品技术公司的界面分析

Procedia Computer Science Pub Date : 2024-04-23 DOI: 10.1016/j.procs.2024.01.134

Tiago Hilário Hennemann da Silva, Simone Sehnem

引用次数: 0

Potentials of the Metaverse for Robotized Applications in Industry 4.0 and Industry 5.0 元宇宙在工业 4.0 和工业 5.0 中的机器人应用潜力

Procedia Computer Science Pub Date : 2024-03-31 DOI: 10.1016/j.procs.2024.02.005

E. Kaigom

引用次数: 0

Context-biased vs. structure-biased disambiguation of relative clauses in large language models 大型语言模型中基于上下文与基于结构的相对从句消歧

Procedia Computer Science Pub Date : 2024-01-01 DOI: 10.1016/j.procs.2024.10.217

Elsayed Issa , Noureddine Atouf

{"title":"Context-biased vs. structure-biased disambiguation of relative clauses in large language models","authors":"Elsayed Issa , Noureddine Atouf","doi":"10.1016/j.procs.2024.10.217","DOIUrl":"10.1016/j.procs.2024.10.217","url":null,"abstract":"<div><div>This work investigates the processing behavior of large language models (LLMs) in sentences involving ambiguous relative clauses (RCs). We are particularly interested in unravelling attachment preferences of LLMs in disambiguating RCs (complementizer phrases CPs modifying a genitival phrase), which are either semantically (context-biased) or syntactically (structure-biased) associated to one of the preceding NP referents. A low interpretation of the RC occurs when it is joined to the local NP (low attachment). A high interpretation is provided when the RC modifies the distant NP (high attachment). We create a small dataset of parallel low- and high-attachment sentences. We use zero-shot prompting to evaluate a set of LLMs based on insights from psycholinguistic experiments. Our results show variability in the performance of some models that favor low attachment (semantically-related meanings in the CP) while other models can resolve ambiguity by choosing high-attachment (structure-biased CPs). The findings are discussed in light of directing future experimental studies to consider a comparative paradigm encompassing both multi-modal LLMs and human subjects.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"244 ","pages":"Pages 425-431"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142529025","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Arabic Historical Documents Layout Analysis using Mask RCNN 使用掩码 RCNN 进行阿拉伯语历史文献布局分析

Procedia Computer Science Pub Date : 2024-01-01 DOI: 10.1016/j.procs.2024.10.220

Latifa Aljiffry , Hassanin Al-Barhamtoshy , Felwa Abukhodair , Amani Jamal

{"title":"Arabic Historical Documents Layout Analysis using Mask RCNN","authors":"Latifa Aljiffry , Hassanin Al-Barhamtoshy , Felwa Abukhodair , Amani Jamal","doi":"10.1016/j.procs.2024.10.220","DOIUrl":"10.1016/j.procs.2024.10.220","url":null,"abstract":"<div><div>In recent times, there has been a notable surge in the interest of researchers in the realm of document analysis and optical character recognition (OCR). Significant advancements have been made in OCR engines across various languages, encompassing both printed and handwritten documents. However, there has been a comparatively lower focus on processing documents written in Arabic when juxtaposed with languages like English. This discrepancy arises from several factors, including the inherent challenges posed by the Arabic language and the limited availability of Arabic document datasets. To implement any OCR engine, the initial step involves analyzing the layout of images before subjecting them to the OCR process. This thesis specifically delves into the realm of layout analysis for historical Arabic documents, employing a deep learning (DL) approach. The chosen methodology utilizes the Mask Region-based Convolutional Neural Network (RCNN). The dataset employed consists of historical Arabic documents, particularly early printed ones, each characterized by unique sizes, structures, and processing prerequisites. Processing historical documents is inherently more challenging due to factors such as the document's layout structure, distinctive handwriting styles of the authors, paper aging, historical timeframe, ink properties, and more. The achieved accuracy result is 51.14%. When juxtaposed with other existing models, it becomes evident that this work attains a state-of-the-art status, showcasing an impressive outcome.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"244 ","pages":"Pages 453-460"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142529030","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Design and Implementation of Foreign Language Recognition and Translation APP Based on Artificial Intelligence 基于人工智能的外语识别与翻译 APP 的设计与实现

Procedia Computer Science Pub Date : 2024-01-01 DOI: 10.1016/j.procs.2024.09.078

Jie Tang

{"title":"Design and Implementation of Foreign Language Recognition and Translation APP Based on Artificial Intelligence","authors":"Jie Tang","doi":"10.1016/j.procs.2024.09.078","DOIUrl":"10.1016/j.procs.2024.09.078","url":null,"abstract":"<div><div>Globalization has created the demand for cross-language communication, which has promoted the development of machine translation applications (APPs) based on artificial intelligence (AI) for foreign language recognition and translation. The purpose of this study is to develop and implement a mobile application program that can accurately identify and translate foreign languages. APP adopts advanced artificial intelligence technology, uses optical character recognition (OCR) technology to identify the text in images, and uses neural network architecture based on transformer for machine translation. In the data preprocessing stage, text cleaning, word segmentation and other preprocessing steps are performed to create accurate translation input. A translation model is trained on a large bilingual mapping data set to learn the mapping knowledge relationship between the source language and the target language. After a series of tests and experiments, the application of foreign language identification and translation shows the high accuracy and speed of multilingual input and output. The accuracy of this application is 0.9, and the maximum delay is only 180 milliseconds. Although there is still room for improvement in the background of professional fields or complex scenes, this application is an effective tool for cross-language communication. Future work should focus on further optimizing translation models, improving the accuracy of translation for specific domain terms, and enhancing the personalized service capabilities of the APP.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"243 ","pages":"Pages 647-654"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142446856","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Design of Translation Error Correction System Based on Improved Seq2Seq 基于改进型 Seq2Seq 的翻译纠错系统设计

Procedia Computer Science Pub Date : 2024-01-01 DOI: 10.1016/j.procs.2024.09.080

Ting Chen

{"title":"Design of Translation Error Correction System Based on Improved Seq2Seq","authors":"Ting Chen","doi":"10.1016/j.procs.2024.09.080","DOIUrl":"10.1016/j.procs.2024.09.080","url":null,"abstract":"<div><div>Speech translation technology is an important booster for promoting social communication and advancing human civilization. With the solid advancement of theories and technologies such as speech processing and machine translation, as well as the continuous deepening and development of computer science, the computing power and storage capacity have been further improved. Speech translation systems widely used in English, French, English and Chinese have successively reached a commercial level. However, the development of speech translation systems is limited by corpus resources and a lack of bilingual language research. The experiments and applications of speech translation in some languages are still in its early stages. In addition, existing research mostly adopts a cascading voice translation system as the basis, breaking through the key issues individually, and less adopts direct voice translation methods without relying on intermediate text representation, which brings problems such as cumbersome research content, complex translation models, and long translation delays. This article mainly focuses on the design of a translation error correction system based on improved Seq2Seq. Firstly, relevant research is summarized, relevant application methods are proposed, and the results are discussed. I hope to bring some inspiration to relevant researchers and provide assistance for the development of related fields.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"243 ","pages":"Pages 663-669"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142446699","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Impact of Consumer Perceived Characteristics on Fruit Sales: Evidence from Community Group-buying 消费者感知特征对水果销售的影响：社区团购的证据

Procedia Computer Science Pub Date : 2024-01-01 DOI: 10.1016/j.procs.2024.08.133

Hailiang Jiang , Xin Tian , Ye Tao , Lulu Wang

引用次数: 0

Brand Subsidy Strategies for Mitigating Agricultural Product Supply Risks Under Capital Limitation 资本限制下化解农产品供应风险的品牌补贴策略

Procedia Computer Science Pub Date : 2024-01-01 DOI: 10.1016/j.procs.2024.08.141

Jiyao Feng , Chunbing Bao , Qingchun Meng

引用次数: 0

BEVEFNet: A Multiple Object Tracking Model Based on LiDAR-Camera Fusion BEVEFNet：基于激光雷达与相机融合的多目标跟踪模型

Procedia Computer Science Pub Date : 2024-01-01 DOI: 10.1016/j.procs.2024.08.106

Yi Yuan , Ying Liu

{"title":"BEVEFNet: A Multiple Object Tracking Model Based on LiDAR-Camera Fusion","authors":"Yi Yuan , Ying Liu","doi":"10.1016/j.procs.2024.08.106","DOIUrl":"10.1016/j.procs.2024.08.106","url":null,"abstract":"<div><p>As a crucial task in the field of computer vision, object tracking models are widely used in various application domains, such as autonomous driving. However, existing multiple object tracking methods still face challenges in accurately and efficiently tracking moving multi-targets in real time. This paper presents BEVEFNet, a camera-LiDAR multi-target tracking model based on multistage fusion, which effectively utilizes the semantic information from optical images and the spatial and geometric information from LiDAR data to unify multi-modal features in a shared Bird’s Eye View(BEV) representation space. By leveraging LiDAR data to complement optical images, multi-level fusion is achieved at both the feature and decision levels. The proposed efficient sparse 3D feature extraction network significantly enhances the speed of multiple object tracking by incorporating sparse convolution. Experiments conducted on the nuSences dataset demonstrate that BEVEFNet achieves an AMOTA of 69.7, improving the accuracy of multiple object tracking.</p></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"242 ","pages":"Pages 560-567"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1877050924018258/pdf?md5=7a04b4b2bac5a8561eb27e503466319f&pid=1-s2.0-S1877050924018258-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142039669","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Network analysis of economic sectors in the world economy 世界经济部门网络分析

Procedia Computer Science Pub Date : 2024-01-01 DOI: 10.1016/j.procs.2024.08.165

Fuad Aleskerov , Yetkin Cinar , Ivan Deseatnicov , Elena Sergeeva , Daniil Tkachev , Vyacheslav Yakuba

引用次数: 0