2023 IEEE 21st International Conference on Industrial Informatics (INDIN)最新文献

Automatic Generation of Visual Concept-based Explanations for Pest Recognition 基于视觉概念的害虫识别解释自动生成

2023 IEEE 21st International Conference on Industrial Informatics (INDIN) Pub Date : 2023-07-18 DOI: 10.1109/INDIN51400.2023.10217975

Zhipeng Yuan, Kang Liu, Shunbao Li, Po Yang

{"title":"Automatic Generation of Visual Concept-based Explanations for Pest Recognition","authors":"Zhipeng Yuan, Kang Liu, Shunbao Li, Po Yang","doi":"10.1109/INDIN51400.2023.10217975","DOIUrl":"https://doi.org/10.1109/INDIN51400.2023.10217975","url":null,"abstract":"Pest management is an important factor affecting agricultural and food industry products. A large number of insect species and the subtle differences bring a challenge to the accurate recognition of pests. Many studies tackle the challenge of pest recognition through deep neural networks (DNNs) and achieve significant success in terms of accuracy. However, the complex structure and a large number of parameters make DNNs difficult for end users to understand the reasons for the decision of models, which causes distrust in the classification of harmful insects and overuse of insecticides. To address the lack of explainability of DNNs, we propose an explanation generation workflow to generate concept-based explanations for pest recognition. Specifically, the concept extraction method uses a clustering algorithm to extract image segments with meaningful concepts from a portion of the training dataset. Then, concept models are trained to detect the presence of concepts in the image. Finally, the explanation generation method provides concept-based global and local explanations in the form of weighted directed graphs and concept importances, respectively. Through qualitative and quantitative analysis, the proposed workflow extracts meaningful concepts for pest recognition effectively and detects the presence of concepts in images.","PeriodicalId":174443,"journal":{"name":"2023 IEEE 21st International Conference on Industrial Informatics (INDIN)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114983031","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

Enhancing Crane Handling Safety: A Deep Deterministic Policy Gradient Approach to Collision-Free Path Planning 提高起重机操作安全性:基于深度确定性策略梯度的无碰撞路径规划

2023 IEEE 21st International Conference on Industrial Informatics (INDIN) Pub Date : 2023-07-18 DOI: 10.1109/INDIN51400.2023.10218087

Rafaela Iovanovichi Machado, M. Machado, S. Botelho

引用次数: 0

An end to end workflow for synthetic data generation for robust object detection* 一个端到端工作流合成数据生成鲁棒对象检测*

2023 IEEE 21st International Conference on Industrial Informatics (INDIN) Pub Date : 2023-07-18 DOI: 10.1109/INDIN51400.2023.10218035

Johannes Metzler, Fouad Bahrpeyma, Dirk Reichelt

{"title":"An end to end workflow for synthetic data generation for robust object detection*","authors":"Johannes Metzler, Fouad Bahrpeyma, Dirk Reichelt","doi":"10.1109/INDIN51400.2023.10218035","DOIUrl":"https://doi.org/10.1109/INDIN51400.2023.10218035","url":null,"abstract":"Object detection is a task in computer vision that involves detecting instances of visual objects of a particular class in digital images. Numerous computer vision tasks highly depend on object detection such as instance segmentation, image captioning and object tracking. A major purpose of object detection is to develop computational models that provide inputs crucial to computer vision applications. Convolutional Neural Networks (CNNs) have recently become popular due to their key roles in enabling object detection. However, the performance of CNNs is largely dependent upon the quality and quantity of training datasets, which are often difficult to obtain in real-world applications. In order to ensure the robustness of such models, it is vital that training instances are provided under various randomized conditions. These conditions are typically a combination of a variety of factors, including lighting conditions, object location, the presence of multiple objects in the scene, varieties of backgrounds, and the angle of the camera. In particular, companies, depending on their applications (such as fault detection, anomaly detection, condition monitoring, predictive quality and so on), require specialized models for their custom products and so always face difficulties in providing a large number of randomized conditioned instances of their objects. The primary reason is that the process of capturing randomized conditioned images of real objects is usually costly, time-consuming, and challenging in practice. Due to the efficiency gained so far via the use of synthetic data for training such systems, synthetic data has recently attracted considerable attention. This paper presents an end-to-end synthetic data generation method for building a robust object detection model for customized products using NVIDIA Omniverse and CNNs. In this paper, we demonstrate and evaluate our contribution to the modeling of chess pieces, where a total accuracy of 98.8 % was obtained.","PeriodicalId":174443,"journal":{"name":"2023 IEEE 21st International Conference on Industrial Informatics (INDIN)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125038486","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

From Hardware-Functional to Software-Defined Vehicles and their Security Issues 从硬件功能到软件定义车辆及其安全问题

2023 IEEE 21st International Conference on Industrial Informatics (INDIN) Pub Date : 2023-07-18 DOI: 10.1109/INDIN51400.2023.10217971

C. Bodei, Marco De Vincenzi, I. Matteucci

引用次数: 0

Learning Emergent Digital Technologies: The Experience in the Internet of Things Course Unit 学习新兴数字技术:物联网的经验课程单元

2023 IEEE 21st International Conference on Industrial Informatics (INDIN) Pub Date : 2023-07-18 DOI: 10.1109/INDIN51400.2023.10218278

Paulo Leitão, Luis Piardi, Lucas Sakurada, André Mendes

{"title":"Learning Emergent Digital Technologies: The Experience in the Internet of Things Course Unit","authors":"Paulo Leitão, Luis Piardi, Lucas Sakurada, André Mendes","doi":"10.1109/INDIN51400.2023.10218278","DOIUrl":"https://doi.org/10.1109/INDIN51400.2023.10218278","url":null,"abstract":"Industry 4.0 is re-shaping the way companies and individuals operate, but it is also introducing strong demands in education processes to train professionals with adequate competencies in emergent digital technologies, e.g., Internet of Things (IoT), Artificial Intelligence and collaborative robotics. In the last decade, innovative educational methods are being applied, e.g., problem-based learning and project-based learning, to move the traditional education approach into a more student-centric process where the student has a more active role. Recent studies point out that the combination of such educational methods is beneficial, each one selected according to the particularities of the learning subject and objective. Having this in mind, this paper describes the application of a learning methodology that combines different educational methods, namely face-to-face, problem-based learning and project-based learning, in a teaching course unit focusing on IoT technologies. The achieved results show an increase of the student’s assessment performance, motivation and satisfaction, and the opportunity to consolidate their acquired knowledge with hands-on practice. This approach also stimulates the acquisition of soft skills, mainly teamwork, communication, creativity and critical thinking.","PeriodicalId":174443,"journal":{"name":"2023 IEEE 21st International Conference on Industrial Informatics (INDIN)","volume":"R-24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126625857","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

Combining Models for Safety and Security Concerns in Automating Digital Production 自动化数字生产中安全与保障问题的组合模型

2023 IEEE 21st International Conference on Industrial Informatics (INDIN) Pub Date : 2023-07-18 DOI: 10.1109/INDIN51400.2023.10218184

S. Kropatschek, Siegfried Hollerer, David Hoffman, D. Winkler, A. Lüder, T. Sauter, W. Kastner, S. Biffl

{"title":"Combining Models for Safety and Security Concerns in Automating Digital Production","authors":"S. Kropatschek, Siegfried Hollerer, David Hoffman, D. Winkler, A. Lüder, T. Sauter, W. Kastner, S. Biffl","doi":"10.1109/INDIN51400.2023.10218184","DOIUrl":"https://doi.org/10.1109/INDIN51400.2023.10218184","url":null,"abstract":"The IEC 62061:2021 standard requires production owners to ensure both functional safety and information security for their industrial applications. Unfortunately, traditional models of functional safety and information security have been designed in isolation and are difficult to combine. This paper introduces the Safety & Security Combination (SafeSecCombi) approach to combine models for functional safety and security concerns in automating digital production. SafeSecCombi (i) validates causes for desired and undesired effects regarding safety in an industrial production process by linking these causes to products, production processes, and production resources; (ii) identifies Industrial Internet of Things (IIoT) assets that can cause unsafe behavior in case of a successful security attack; and (iii) analyzes risks of security attacks to these IIoT assets. Therefore, SafeSecCombi provides a model for the combined analysis of safety and security concerns regarding a Cyber-Physical Production System (CPPS). In a feasibility study on an industrial work cell for metal processing with a collaborative robot, we evaluated the effectiveness and efficiency of the SafeSecCombi approach. Results indicate that the SafeSecCombi approach is feasible and effective, and provides safety and security experts with actionable, context-specific causes for security-related safety issues and countermeasures that are well grounded in engineering models, as a foundation to address the IEC 62061:2021 requirements.","PeriodicalId":174443,"journal":{"name":"2023 IEEE 21st International Conference on Industrial Informatics (INDIN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129862546","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

Formalization of a Product-Process-Resource Model within Aircraft Component Maintenance, Repair, and Overhaul 飞机部件维护、修理和大修中的产品-过程-资源模型的形式化

2023 IEEE 21st International Conference on Industrial Informatics (INDIN) Pub Date : 2023-07-18 DOI: 10.1109/INDIN51400.2023.10218093

Maximilian Rappl, Max Luca Bergmann, A. Fay

{"title":"Formalization of a Product-Process-Resource Model within Aircraft Component Maintenance, Repair, and Overhaul","authors":"Maximilian Rappl, Max Luca Bergmann, A. Fay","doi":"10.1109/INDIN51400.2023.10218093","DOIUrl":"https://doi.org/10.1109/INDIN51400.2023.10218093","url":null,"abstract":"Maintenance, Repair and Overhaul (MRO) of aircraft components is a complex and critical process with high product and process variability. To ensure the safety and reliability of aircraft, it is crucial to have accurate and up-to-date information about components throughout their life-cycle. However, this information is often scattered across various systems and stakeholders, resulting in data fragmentation and inconsistency. Data integration is needed to create a unified and comprehensive view of the components life-cycle. The Product-Process-Resource (PPR) modeling framework is a cross-industry framework that provides a comprehensive view of the various dimensions involved. The framework is applied to the MRO service provider domain. This paper explores the use of standards and norms to formalize an information model based on the PPR approach to improve data integration and ensure a high level of reuse. The proposed model integrates several community maintained standards such as VDI/VDE 3682, EASA Part 145, EASA Part M, DIN 13306, DIN EN 61512, and IATA’s ONE Record to provide a standardized and consistent representation of component MRO data.","PeriodicalId":174443,"journal":{"name":"2023 IEEE 21st International Conference on Industrial Informatics (INDIN)","volume":"7 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124631835","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 Container-based Architecture to Provide Services from SDR Devices 基于容器的架构，从SDR设备提供服务

2023 IEEE 21st International Conference on Industrial Informatics (INDIN) Pub Date : 2023-07-18 DOI: 10.1109/INDIN51400.2023.10217954

E. R. Machado, M. Feldman, I. Müller

{"title":"A Container-based Architecture to Provide Services from SDR Devices","authors":"E. R. Machado, M. Feldman, I. Müller","doi":"10.1109/INDIN51400.2023.10217954","DOIUrl":"https://doi.org/10.1109/INDIN51400.2023.10217954","url":null,"abstract":"The growing use of Software-Defined Radio (SDR) in computational environments has brought flexibility to the development of applications compared to traditional radio implementation. However, with the hardware-to-software trend, the diversity of current technologies, such as Network Function Virtualization (NFV), cloud computing, Software-Defined Networking (SDN), and emerging Industry 4.0 impose an integration challenge to the SDR. This work presents a method of integrating SDR into network environments through full application containerization. A container-based architecture is proposed, with a possible topology for container storage and management. The architecture was applied to generate two SDR-based applications, a real-time flight tracker web page and a LoRa-based text transfer application. In addition, the appliance of different types of COTS SDRs, USRP 2932, RTL-SDR, and LimeSDR, with the architecture was demonstrated. The results show that the architecture imposes a maximum overhead of 5.1% of CPU utilization and 8.38 s for service startup time, compared to a traditional non-virtualized SDR implementation. The architecture also brings non-functional benefits such as ease of service management, replicability, network isolation options, and a set of features inherited from container virtualization.","PeriodicalId":174443,"journal":{"name":"2023 IEEE 21st International Conference on Industrial Informatics (INDIN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129933314","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

Supervised Time Series Segmentation as Enabler of Multi-Phased Time Series Classification: A Study on Hydraulic End-of-Line Testing 有监督时间序列分割作为多阶段时间序列分类的实现——液压末端检测的研究

2023 IEEE 21st International Conference on Industrial Informatics (INDIN) Pub Date : 2023-07-18 DOI: 10.1109/INDIN51400.2023.10218185

S. Gaugel, Binlan Wu, Adarsh Anand, M. Reichert

{"title":"Supervised Time Series Segmentation as Enabler of Multi-Phased Time Series Classification: A Study on Hydraulic End-of-Line Testing","authors":"S. Gaugel, Binlan Wu, Adarsh Anand, M. Reichert","doi":"10.1109/INDIN51400.2023.10218185","DOIUrl":"https://doi.org/10.1109/INDIN51400.2023.10218185","url":null,"abstract":"Multi-phased time series are found in many industrial processes. Their classification still poses a big challenge for algorithms compared to single-phased time series forms. To overcome this issue, this paper suggests using deep learning to generate timestamp-wise state labels that serve as semantic annotations for all measured data points. We investigate whether the availability of state labels can boost the performance of machine learning classifiers by enabling state-wise feature extraction in multi-phased time series. The study is performed on a real-world industrial classification problem in a hydraulic pump factory. Various state label predictions with different accuracy scores are created via deep learning-based time series segmentation. We evaluate how the accuracies of the state label predictions affect the results of the binary classification. Our results show that in settings where accurate state labels are present the classification Fl-scores were significantly higher compared to baseline approaches. Therefore, we emphasized the need to find well performing time series segmentation methods.","PeriodicalId":174443,"journal":{"name":"2023 IEEE 21st International Conference on Industrial Informatics (INDIN)","volume":"223 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127037737","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

Measurement Methods for Software Execution Time on Heterogeneous Edge Devices 异构边缘设备上软件执行时间的测量方法

2023 IEEE 21st International Conference on Industrial Informatics (INDIN) Pub Date : 2023-07-18 DOI: 10.1109/INDIN51400.2023.10218136

Bernhard Rupprecht, Birgit Vogel-Heuser, E. Neumann

{"title":"Measurement Methods for Software Execution Time on Heterogeneous Edge Devices","authors":"Bernhard Rupprecht, Birgit Vogel-Heuser, E. Neumann","doi":"10.1109/INDIN51400.2023.10218136","DOIUrl":"https://doi.org/10.1109/INDIN51400.2023.10218136","url":null,"abstract":"Due to emerging data-driven approaches in factory automation in the course of Industry 4.0, automated Production Systems must incorporate additional algorithms for data collection and processing tasks. However, strict real-time requirements, resource constraint devices, such as Programmable Logic Controllers or low-power edge devices, and network bandwidth limitations pose a challenge to selecting suitable algorithms for specific edge devices and vice-versa, also known as software-hardware co-design. Measuring the execution time of an algorithm or code snippet is therefore a crucial part of algorithm and hardware assessment and is incorporated in numerous benchmarks. However, this is not trivial since most existing time measurement methods are designed with specific devices in mind with limited portability to different hardware platforms. Thus this paper provides an overview of the properties of selected execution time measurement methods to support their feasible deployment in edge computing, including legacy systems. A time measurement code snippet for Beckhoff Programmable Logic Controllers and recommendations for implementing software-based timing functions for heterogeneous devices help shorten development times. Besides, comparing execution time measurement methods highlights the challenges of creating a generic cross-platform benchmark in future research.","PeriodicalId":174443,"journal":{"name":"2023 IEEE 21st International Conference on Industrial Informatics (INDIN)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116491720","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