Procedia Computer Science最新文献_第3页

A dedicated fix-and-relax decomposition method for operating room scheduling problem 手术室调度问题的专用固定松弛分解方法

Procedia Computer Science Pub Date : 2026-01-01 Epub Date: 2026-03-23 DOI: 10.1016/j.procs.2026.02.131

Grégoire Gielly , Yassine Ouazene , Nhan Quy Nguyen

引用次数: 0

DieHard: Human-Centric Responsible and Resilient Autonomy for Mission-Critical Smart Systems 《虎胆龙威：关键任务智能系统以人为中心的负责任和弹性自治》

Procedia Computer Science Pub Date : 2026-01-01 Epub Date: 2026-03-23 DOI: 10.1016/j.procs.2026.02.138

Vagan Terziyan , Ivo Bukovsky , Olena Kaikova , Florian Sobieczky , Timo Tiihonen

{"title":"DieHard: Human-Centric Responsible and Resilient Autonomy for Mission-Critical Smart Systems","authors":"Vagan Terziyan , Ivo Bukovsky , Olena Kaikova , Florian Sobieczky , Timo Tiihonen","doi":"10.1016/j.procs.2026.02.138","DOIUrl":"10.1016/j.procs.2026.02.138","url":null,"abstract":"<div><div>The rise of Industry 4.0 and the transition toward Industry 5.0 have significantly increased the reliance on mission-critical smart systems, including smart manufacturing assets. However, this shift also introduces risks associated with adversarial manipulation and malicious exploitation of control channels, particularly in systems involving human, AI, and hybrid decision-making. As AI systems grow towards increasingly powerful ones, global concerns persist about the risks of their misuse or the dangers of granting them unrestrained autonomy. The DieHard framework offers a balanced solution by equipping mission-critical smart systems with limited, yet crucial, autonomy: the ability to detect misuse and ensure resilience against exploitation for malicious purposes. This approach enables AI systems to remain under human control while safeguarding their operations from manipulation or misuse, striking a vital balance between usability and security. This paper introduces a human-centric, responsible, and resilient autonomy framework that integrates anomaly detection, ethical constraints, and mission alignment. We propose a taxonomy of adversarial anomalies, outline the role of the Learning Entropy concept for anomaly detection across diverse environments, and provide simple proof-of-concept simulation. By maintaining the operator-in-the-loop and enforcing resilience under anomalous control, DieHard ensures robust, reliable, and secure operation of mission-critical smart systems, even in adversarial scenarios.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"277 ","pages":"Pages 977-988"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147554924","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Metaverse governance: A literature review exploring ethical considerations 元环境治理：探讨伦理考虑的文献综述

Procedia Computer Science Pub Date : 2026-01-01 Epub Date: 2026-03-24 DOI: 10.1016/j.procs.2026.02.447

Phylicia Babb

引用次数: 0

GiftMatch: An AI-Powered Web Application for Personalized Gift Suggestions GiftMatch：一个人工智能驱动的个性化礼物建议Web应用程序

Procedia Computer Science Pub Date : 2026-01-01 Epub Date: 2026-03-24 DOI: 10.1016/j.procs.2026.02.433

Diana Manuela Costa , António Jorge Gouveia

引用次数: 0

Engineering the Business Layer of the Decision Enterprise 决策企业的业务层工程

Procedia Computer Science Pub Date : 2026-01-01 Epub Date: 2026-03-24 DOI: 10.1016/j.procs.2026.03.038

Deepika Prakash , Naveen Prakash

引用次数: 0

Investigating the effect of bias mitigation in machine learning algorithms 研究机器学习算法中偏见缓解的影响

Procedia Computer Science Pub Date : 2026-01-01 Epub Date: 2026-03-24 DOI: 10.1016/j.procs.2026.03.030

Clodagh Maclean-Milner, Madhushi Bandara’s, Daniel Catchpoole

引用次数: 0

Investigating Meeting Organisation as a Coordinative Work Process Using Narrative Networks 利用叙事网络研究会议组织作为协调工作过程

Procedia Computer Science Pub Date : 2026-01-01 Epub Date: 2026-03-24 DOI: 10.1016/j.procs.2026.03.017

Jens Alberts, Susan P. Williams

{"title":"Investigating Meeting Organisation as a Coordinative Work Process Using Narrative Networks","authors":"Jens Alberts, Susan P. Williams","doi":"10.1016/j.procs.2026.03.017","DOIUrl":"10.1016/j.procs.2026.03.017","url":null,"abstract":"<div><div>Meetings are a fundamental part of knowledge work and employees spend significant amounts of time organising meetings. While certain types of meetings, such as standing committees, are well organised, the processes for organising regular workgroup meetings are often poorly organised. Resulting in complaints about unnecessary and inefficient meetings and a lack of effective use of collaboration software to support the meeting organisation. In this paper, we aim to gain a richer understanding of how meetings that are supported by collaboration software are prepared, conducted, and post-processed. By using the Narrative Networks approach, we describe, visualise, and analyse the sequences of actions involved in organising regular meetings within a distributed workgroup. Although the meeting organisation process is not prescribed, formalised or instantiated and the collaboration software used is process non-aware, we nevertheless identified recurring patterns for organising regular workgroup meetings. Using (digital) trace data collected from collaboration tools and enriched with participant observations, 48 meeting performances were captured and analysed. Our analysis reveals that the process, while effective and efficient, is constantly changing and each performance is unique. The study contributes to the understanding of less well-structured digitally supported processes.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"278 ","pages":"Pages 496-506"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147555434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Data Trusts for Smart Cities: A Business Model 智慧城市的数据信任：一种商业模式

Procedia Computer Science Pub Date : 2026-01-01 Epub Date: 2026-03-24 DOI: 10.1016/j.procs.2026.02.458

David Acev, Timon T. Aldenhoff, Sankalp Biyani, Dennis M. Riehle, Maria A. Wimmer

引用次数: 0

Application of Big Data-Driven Dialect Speech Feature Extraction and Intelligent Recognition Classification Algorithm 大数据驱动的方言语音特征提取与智能识别分类算法的应用

Procedia Computer Science Pub Date : 2026-01-01 Epub Date: 2026-06-02 DOI: 10.1016/j.procs.2026.04.261

Yaohui Yuan

{"title":"Application of Big Data-Driven Dialect Speech Feature Extraction and Intelligent Recognition Classification Algorithm","authors":"Yaohui Yuan","doi":"10.1016/j.procs.2026.04.261","DOIUrl":"10.1016/j.procs.2026.04.261","url":null,"abstract":"<div><div>The limitations in dialect speech recognition include, among others, the complicated distribution of speech features, limited and diverse corpora, which influences the recognition of intelligent speech systems. The influence of nonlinear variation of dialect speech characteristics and the problem of cross-regional speech transfer is considered in this paper, by developing an algorithm of dialect speech feature extraction and smart recognition classification based on big data. The initial approach is to build a speech feature library through a large-scale speech dataset and to obtain a multi-dimensional feature representation with the help of a joint feature fusion mechanism comprising of Mel-Frequency Cepstral Coefficient (MFCC) and spectrogram. Second, a dual-channel Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) network are proposed to perform dual roles of extracting speech features and modeling temporal features respectively. Third, a mechanism of attention is used to improve feature weight distribution, thus making the model more sensitive to the minute differences in dialect speech. Lastly, a multi-class Support Vector Machine (SVM) is integrated to have intelligent recognition and classification. A self-constructed test set of samples of dialect speech were used in experiments. Findings indicated that the designed model had a recognition rate of 97.3% and an average feature extraction rate of 21.56%, which means that it has excellent generalization and real-time utilization.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"281 ","pages":"Pages 675-682"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148140859","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Fully Automated Detection System for Surface Defects of Rail Transit Wheelsets Based on Multi-Sensor Fusion 基于多传感器融合的轨道交通轮对表面缺陷全自动检测系统

Procedia Computer Science Pub Date : 2026-01-01 Epub Date: 2026-06-02 DOI: 10.1016/j.procs.2026.04.269

Shengming Tang , Lijun Zhang , Yifan Xu , Jicheng Yang

{"title":"A Fully Automated Detection System for Surface Defects of Rail Transit Wheelsets Based on Multi-Sensor Fusion","authors":"Shengming Tang , Lijun Zhang , Yifan Xu , Jicheng Yang","doi":"10.1016/j.procs.2026.04.269","DOIUrl":"10.1016/j.procs.2026.04.269","url":null,"abstract":"<div><div>Surface defects on rail transit wheelsets directly affect train operation safety and maintenance costs. To address the issues of insufficient sensitivity of single-sensor detection and difficulties in identification under complex operating conditions, a fully automated wheelset surface defect detection system based on Multi-Sensor Fusion (MSF) is constructed. The system integrates data from a laser profile sensor, a phased array ultrasonic testing (PAUT) system, and a high-definition industrial camera. A time synchronization module aligns the multi-source heterogeneous information, and a modified Kalman filter and a convolutional neural network (CNN) are used for feature-level fusion and defect prediction. In the detection process, the laser and vision modules first rapidly identify geometric anomalies in the wheel flange and tread, then the PAUT module performs depth imaging of internal cracks, and finally, the fusion decision network outputs the defect location and type results. The experiment was conducted on a CRH380A high-speed wheelset. Compared with manual inspection and a single sensor system, the fusion system achieved a surface crack recognition rate of up to 99.1% at a detection speed of 5 m/s, with a false alarm rate reduced to 1%, and maintained a stable recognition performance of 92.8% for a minimum crack depth of 0.3 mm.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"281 ","pages":"Pages 745-752"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148140955","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0