Pub Date : 2019-07-01DOI: 10.1109/INDIN41052.2019.8972199
Yu-Lin Liang, Chih-Chi Kuo, Chun-Cheng Lin
In Industry 4.0, various types of IoT sensors which are installed on machines to collect data for predictive maintenance. As the collected data increases, there are more missing values and noisy data. Related studies have already proposed various methods to solve the problems in big data. Among them, most studies focused on either feature selection or instance selection for data preprocessing before training forecast models. Metaheuristic algorithm is one of the mainstream methods in data preprocessing. However, most of these studies rarely considered feature and instance selection simultaneously. In addition, they seldom focused on noisy data. Therefore, this work combines the UCI datasets with noisy data to simulate the real situation. Memetic algorithm (MA) has excellent performance in machine learning of data selection, and variable neighborhood search (VNS) was also proved to be widely applied to the systematic change of local search algorithms. This work proposes a hybrid MA and VNS to find a new subset that maximizes the accuracy of the classifier while preserving the minimum amount of data by feature and instance selection simultaneously. Experimental results show that the proposed method can efficiently reduce the amount of data and the ratio of noisy data. By comparison with other metaheuristic algorithms, the proposed method has good performance by an excellent balance between exploration and exploitation.
{"title":"A Hybrid Memetic Algorithm for Simultaneously Selecting Features and Instances in Big Industrial IoT Data for Predictive Maintenance","authors":"Yu-Lin Liang, Chih-Chi Kuo, Chun-Cheng Lin","doi":"10.1109/INDIN41052.2019.8972199","DOIUrl":"https://doi.org/10.1109/INDIN41052.2019.8972199","url":null,"abstract":"In Industry 4.0, various types of IoT sensors which are installed on machines to collect data for predictive maintenance. As the collected data increases, there are more missing values and noisy data. Related studies have already proposed various methods to solve the problems in big data. Among them, most studies focused on either feature selection or instance selection for data preprocessing before training forecast models. Metaheuristic algorithm is one of the mainstream methods in data preprocessing. However, most of these studies rarely considered feature and instance selection simultaneously. In addition, they seldom focused on noisy data. Therefore, this work combines the UCI datasets with noisy data to simulate the real situation. Memetic algorithm (MA) has excellent performance in machine learning of data selection, and variable neighborhood search (VNS) was also proved to be widely applied to the systematic change of local search algorithms. This work proposes a hybrid MA and VNS to find a new subset that maximizes the accuracy of the classifier while preserving the minimum amount of data by feature and instance selection simultaneously. Experimental results show that the proposed method can efficiently reduce the amount of data and the ratio of noisy data. By comparison with other metaheuristic algorithms, the proposed method has good performance by an excellent balance between exploration and exploitation.","PeriodicalId":260220,"journal":{"name":"2019 IEEE 17th International Conference on Industrial Informatics (INDIN)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116979051","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}
Pub Date : 2019-07-01DOI: 10.1109/INDIN41052.2019.8972262
Awais Tanveer, R. Sinha, Stephen G. MacDonell, P. Leitão, V. Vyatkin
Programmable Logic Controllers (PLCs) execute critical control software that drives Industrial Automation and Control Systems (IACS). PLCs can become easy targets for cyber-adversaries as they are resource-constrained and are usually built using legacy, less-capable security measures. Security attacks can significantly affect system availability, which is an essential requirement for IACS. We propose a method to make PLC applications more security-aware. Based on the well-known IEC 61499 function blocks standard for developing IACS software, our method allows designers to annotate critical parts of an application during design time. On deployment, these parts of the application are automatically secured using appropriate security mechanisms to detect and prevent attacks. We present a summary of availability attacks on distributed IACS applications that can be mitigated by our proposed method. Security mechanisms are achieved using IEC 61499 Service-Interface Function Blocks (SIFBs) embedding Intrusion Detection and Prevention System (IDPS), added to the application at compile time. This method is more amenable to providing active security protection from attacks on previously unknown (zero-day) vulnerabilities. We test our solution on an IEC 61499 application executing on Wago PFC200 PLCs. Experiments show that we can successfully log and prevent attacks at the application level as well as help the application to gracefully degrade into safe mode, subsequently improving availability.
{"title":"Designing Actively Secure, Highly Available Industrial Automation Applications","authors":"Awais Tanveer, R. Sinha, Stephen G. MacDonell, P. Leitão, V. Vyatkin","doi":"10.1109/INDIN41052.2019.8972262","DOIUrl":"https://doi.org/10.1109/INDIN41052.2019.8972262","url":null,"abstract":"Programmable Logic Controllers (PLCs) execute critical control software that drives Industrial Automation and Control Systems (IACS). PLCs can become easy targets for cyber-adversaries as they are resource-constrained and are usually built using legacy, less-capable security measures. Security attacks can significantly affect system availability, which is an essential requirement for IACS. We propose a method to make PLC applications more security-aware. Based on the well-known IEC 61499 function blocks standard for developing IACS software, our method allows designers to annotate critical parts of an application during design time. On deployment, these parts of the application are automatically secured using appropriate security mechanisms to detect and prevent attacks. We present a summary of availability attacks on distributed IACS applications that can be mitigated by our proposed method. Security mechanisms are achieved using IEC 61499 Service-Interface Function Blocks (SIFBs) embedding Intrusion Detection and Prevention System (IDPS), added to the application at compile time. This method is more amenable to providing active security protection from attacks on previously unknown (zero-day) vulnerabilities. We test our solution on an IEC 61499 application executing on Wago PFC200 PLCs. Experiments show that we can successfully log and prevent attacks at the application level as well as help the application to gracefully degrade into safe mode, subsequently improving availability.","PeriodicalId":260220,"journal":{"name":"2019 IEEE 17th International Conference on Industrial Informatics (INDIN)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123426243","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}
Pub Date : 2019-07-01DOI: 10.1109/INDIN41052.2019.8972263
A. Brusaferri, L. Fagiano, M. Matteucci, Andrea Vitali
The availability of accurate day-ahead price forecasts is crucial to achieve an effective participation to electricity markets. Starting from available state of the art, we propose a forecast technique exploiting a nonlinear auto regressive model with exogenous input, including a feature selection mechanism based on the Least Absolute Shrinkage and Selection Operator (LASSO). The rationale behind such a choice is twofold. On the one hand, we aim to target potential increase of forecast accuracy by learning complex non-linear mappings. On the other hand, we want to increase the interpretability of the resulting model and minimize the effort needed to properly set up the forecaster. A framework such as the LASSO, capable to self-extract features from spot price multi-variate time series, might represent a very useful tool for industrial practitioners. Experiments have been performed on Italian market dataset, demonstrating that the proposed method can extract useful features and achieve robust performance. Moreover, we show how the proposed method can support interpretation of forecaster structure and it can reveal interesting correlations within the regression set.
{"title":"Day ahead electricity price forecast by NARX model with LASSO based features selection","authors":"A. Brusaferri, L. Fagiano, M. Matteucci, Andrea Vitali","doi":"10.1109/INDIN41052.2019.8972263","DOIUrl":"https://doi.org/10.1109/INDIN41052.2019.8972263","url":null,"abstract":"The availability of accurate day-ahead price forecasts is crucial to achieve an effective participation to electricity markets. Starting from available state of the art, we propose a forecast technique exploiting a nonlinear auto regressive model with exogenous input, including a feature selection mechanism based on the Least Absolute Shrinkage and Selection Operator (LASSO). The rationale behind such a choice is twofold. On the one hand, we aim to target potential increase of forecast accuracy by learning complex non-linear mappings. On the other hand, we want to increase the interpretability of the resulting model and minimize the effort needed to properly set up the forecaster. A framework such as the LASSO, capable to self-extract features from spot price multi-variate time series, might represent a very useful tool for industrial practitioners. Experiments have been performed on Italian market dataset, demonstrating that the proposed method can extract useful features and achieve robust performance. Moreover, we show how the proposed method can support interpretation of forecaster structure and it can reveal interesting correlations within the regression set.","PeriodicalId":260220,"journal":{"name":"2019 IEEE 17th International Conference on Industrial Informatics (INDIN)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121965826","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}
Pub Date : 2019-07-01DOI: 10.1109/INDIN41052.2019.8972242
R. Luo, H. Lin, Yu-Ting Hsu
Household chores service is one of the desirable functions for a service robot. Object classification is the most important function when searching for objects. We consider that the major concern is that the robot should not misclassify the object. If the robot misclassifies household object images, it will then perform the household tasks with the wrong object. This may cause serious damages to a service robot and to the user. This concept gives us the insight that the precision of the classification must be very high by setting a confidence threshold so that it then can claim a reliable service robot. By exploring this concept, we develop a more convincing indicator, Classification Reliability, to reveal the reliability of deep learning model. Moreover, we develop a fine-tune rule base to continuously regenerate more proper training dataset for the CNN model to increase reliability. Experimental results demonstrate that the CNN model fine-tuned by our closed-loop system achieves the reliability which is higher than the other similar effects such as DenseNet on the CIFAR-10 dataset.
{"title":"CNN Based Reliable Classification of Household Chores Objects for Service Robotics Applications","authors":"R. Luo, H. Lin, Yu-Ting Hsu","doi":"10.1109/INDIN41052.2019.8972242","DOIUrl":"https://doi.org/10.1109/INDIN41052.2019.8972242","url":null,"abstract":"Household chores service is one of the desirable functions for a service robot. Object classification is the most important function when searching for objects. We consider that the major concern is that the robot should not misclassify the object. If the robot misclassifies household object images, it will then perform the household tasks with the wrong object. This may cause serious damages to a service robot and to the user. This concept gives us the insight that the precision of the classification must be very high by setting a confidence threshold so that it then can claim a reliable service robot. By exploring this concept, we develop a more convincing indicator, Classification Reliability, to reveal the reliability of deep learning model. Moreover, we develop a fine-tune rule base to continuously regenerate more proper training dataset for the CNN model to increase reliability. Experimental results demonstrate that the CNN model fine-tuned by our closed-loop system achieves the reliability which is higher than the other similar effects such as DenseNet on the CIFAR-10 dataset.","PeriodicalId":260220,"journal":{"name":"2019 IEEE 17th International Conference on Industrial Informatics (INDIN)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124846356","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}
Pub Date : 2019-07-01DOI: 10.1109/INDIN41052.2019.8972179
M. Mamun, Afroza Rahman, M. A. Khaleque, Md. Abdul Hamid, M. Mridha
Autism is a complex and developmental neurobehavioral disorder which indicates difficulties with communication skills and social interactions. Because of various types of symptoms, this condition is also refers to as autism spectrum disorder (ASD). There are many autism centers to help and facilitate children with autism. To make an autism center automatic and capable of responsive in real time, the next generation of cellular network, i.e. 5G can play a vital role. We have found minor contribution towards healthcare monitoring system for autism centers in a network that offers ultra-reliable and low-latency communication (uRLLC), higher data rates and massive connectivity of devices in Internet of Things (IoT) and Internet of Medical things (IoMT). Therefore, we have proposed "AutiLife"- an impeccable healthcare monitoring system for autism centers in 5G cellular network using Machine Learning algorithm, Support Vector Machine (SVM). Our proposed system model will collect health related data (Blood Pressure, Heart Rate, Body Temperature, Body Motion, Speech Signals) using various sensors and devices from autistic children. Then using ML algorithm the system will accomplish some course of actions and alert the controllers and nearby hospitals if any health falling issues are found. We resolutely believe, our proposed system "AutiLife" may handle any emergency issues for example epilepsy, heart stroke, heart attack, anxiety, hysteria that can occur on any sudden moment in an autism center and may save inestimable life of children with autism.
{"title":"AutiLife: A Healthcare Monitoring System for Autism Center in 5G Cellular Network using Machine Learning Approach","authors":"M. Mamun, Afroza Rahman, M. A. Khaleque, Md. Abdul Hamid, M. Mridha","doi":"10.1109/INDIN41052.2019.8972179","DOIUrl":"https://doi.org/10.1109/INDIN41052.2019.8972179","url":null,"abstract":"Autism is a complex and developmental neurobehavioral disorder which indicates difficulties with communication skills and social interactions. Because of various types of symptoms, this condition is also refers to as autism spectrum disorder (ASD). There are many autism centers to help and facilitate children with autism. To make an autism center automatic and capable of responsive in real time, the next generation of cellular network, i.e. 5G can play a vital role. We have found minor contribution towards healthcare monitoring system for autism centers in a network that offers ultra-reliable and low-latency communication (uRLLC), higher data rates and massive connectivity of devices in Internet of Things (IoT) and Internet of Medical things (IoMT). Therefore, we have proposed \"AutiLife\"- an impeccable healthcare monitoring system for autism centers in 5G cellular network using Machine Learning algorithm, Support Vector Machine (SVM). Our proposed system model will collect health related data (Blood Pressure, Heart Rate, Body Temperature, Body Motion, Speech Signals) using various sensors and devices from autistic children. Then using ML algorithm the system will accomplish some course of actions and alert the controllers and nearby hospitals if any health falling issues are found. We resolutely believe, our proposed system \"AutiLife\" may handle any emergency issues for example epilepsy, heart stroke, heart attack, anxiety, hysteria that can occur on any sudden moment in an autism center and may save inestimable life of children with autism.","PeriodicalId":260220,"journal":{"name":"2019 IEEE 17th International Conference on Industrial Informatics (INDIN)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124956477","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}
Pub Date : 2019-07-01DOI: 10.1109/INDIN41052.2019.8972165
Michael Sollfrank, Frieder Loch, B. Vogel‐Heuser
The automation pyramid is shifting and will most likely not have a stock in rigid form. The shift is towards Cyber-Physical Systems (CPS) and Cyber-Physical Production Systems (CPPS). Some components in CPPS have to meet real-time requirements. One trend coming along with the change in automation architectures is the virtualization of applications. This enables platform independent development and deployment of secure and isolated applications. Yet, virtualization of applications comes with additional software components and therefore, additional processing effort. For web-services, virtualization is widespread, for embedded systems virtualization development and deployment is not common due time constraints of applications. The use of virtualized applications in embedded systems would have significant benefits like less effort in cross-platform development and cross compiling to state two examples. The method of virtualization in CPPS have to be evaluated concerning time-sensitive applications. In this approach, the time delays occurring through the additional virtualization layer with Docker containers are explored.
{"title":"Exploring Docker Containers for Time-sensitive Applications in Networked Control Systems","authors":"Michael Sollfrank, Frieder Loch, B. Vogel‐Heuser","doi":"10.1109/INDIN41052.2019.8972165","DOIUrl":"https://doi.org/10.1109/INDIN41052.2019.8972165","url":null,"abstract":"The automation pyramid is shifting and will most likely not have a stock in rigid form. The shift is towards Cyber-Physical Systems (CPS) and Cyber-Physical Production Systems (CPPS). Some components in CPPS have to meet real-time requirements. One trend coming along with the change in automation architectures is the virtualization of applications. This enables platform independent development and deployment of secure and isolated applications. Yet, virtualization of applications comes with additional software components and therefore, additional processing effort. For web-services, virtualization is widespread, for embedded systems virtualization development and deployment is not common due time constraints of applications. The use of virtualized applications in embedded systems would have significant benefits like less effort in cross-platform development and cross compiling to state two examples. The method of virtualization in CPPS have to be evaluated concerning time-sensitive applications. In this approach, the time delays occurring through the additional virtualization layer with Docker containers are explored.","PeriodicalId":260220,"journal":{"name":"2019 IEEE 17th International Conference on Industrial Informatics (INDIN)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128713841","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}
Pub Date : 2019-07-01DOI: 10.1109/indin41052.2019.8972287
P. Leitão
{"title":"Integration of Software Agents and Low-Level Automation Functions","authors":"P. Leitão","doi":"10.1109/indin41052.2019.8972287","DOIUrl":"https://doi.org/10.1109/indin41052.2019.8972287","url":null,"abstract":"","PeriodicalId":260220,"journal":{"name":"2019 IEEE 17th International Conference on Industrial Informatics (INDIN)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128257395","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}
Pub Date : 2019-07-01DOI: 10.1109/INDIN41052.2019.8972026
Liu Liu, Rujing Wang, Chengjun Xie, Po Yang, S. Sudirman, Fangyuan Wang, Rui Li
Monitoring pest in agriculture has been a high-priority issue all over the world. Computer vision techniques are widely utilized in practical crop pest prevention applications due to the rapid development of artificial intelligence technology. However, current deep learning image analytic approaches achieve low accuracy and poor robustness in agriculture pest monitoring task. This paper targets at this challenge by proposing a novel two-stage deep learning based automatic pest monitoring system with hybrid global and local activated feature. In this approach, a Global activated Feature Pyramid Network (GaFPN) is firstly proposed for extracting highly representative features of pests over both depth and spatial position activation levels. Then, an improved Local activated Region Proposal Network (LaRPN) augmenting contextual and attentional information is represented for precisely locating pest objects. Finally, we design a fully connected neural network to estimate the severity of input image under the detected pests. The experimental results on our 88.6K images dataset (with 16 types of common pests) show that our approach outweighs the state-of-the-art methods in industrial circumstances.
{"title":"Deep Learning based Automatic Approach using Hybrid Global and Local Activated Features towards Large-scale Multi-class Pest Monitoring","authors":"Liu Liu, Rujing Wang, Chengjun Xie, Po Yang, S. Sudirman, Fangyuan Wang, Rui Li","doi":"10.1109/INDIN41052.2019.8972026","DOIUrl":"https://doi.org/10.1109/INDIN41052.2019.8972026","url":null,"abstract":"Monitoring pest in agriculture has been a high-priority issue all over the world. Computer vision techniques are widely utilized in practical crop pest prevention applications due to the rapid development of artificial intelligence technology. However, current deep learning image analytic approaches achieve low accuracy and poor robustness in agriculture pest monitoring task. This paper targets at this challenge by proposing a novel two-stage deep learning based automatic pest monitoring system with hybrid global and local activated feature. In this approach, a Global activated Feature Pyramid Network (GaFPN) is firstly proposed for extracting highly representative features of pests over both depth and spatial position activation levels. Then, an improved Local activated Region Proposal Network (LaRPN) augmenting contextual and attentional information is represented for precisely locating pest objects. Finally, we design a fully connected neural network to estimate the severity of input image under the detected pests. The experimental results on our 88.6K images dataset (with 16 types of common pests) show that our approach outweighs the state-of-the-art methods in industrial circumstances.","PeriodicalId":260220,"journal":{"name":"2019 IEEE 17th International Conference on Industrial Informatics (INDIN)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128734775","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}
Pub Date : 2019-07-01DOI: 10.1109/INDIN41052.2019.8971966
Akira Takahashi, S. Yokota, A. Matsumoto, D. Chugo, H. Hashimoto
The purpose of this research is to develop the wheelchair system for hemiplegic users. The proposed system is configured by the front wheel with active steering and hand rim for detecting user’s driving force. The user’s operational intention is distinguished by the sign and amplitude of force along the rotational axis of the hand rim. The steering angle of the front wheel is controlled by an actuator based on extracted intention from the hand rim. By proposed system, user can operate the wheelchair by using only single side hand rim. In particular, in this paper, we evaluate the designed hand rim by conducting some experiments.
{"title":"Development of One Hand Drive Wheelchair System : 2nd report : Evaluation of the designed hand rim","authors":"Akira Takahashi, S. Yokota, A. Matsumoto, D. Chugo, H. Hashimoto","doi":"10.1109/INDIN41052.2019.8971966","DOIUrl":"https://doi.org/10.1109/INDIN41052.2019.8971966","url":null,"abstract":"The purpose of this research is to develop the wheelchair system for hemiplegic users. The proposed system is configured by the front wheel with active steering and hand rim for detecting user’s driving force. The user’s operational intention is distinguished by the sign and amplitude of force along the rotational axis of the hand rim. The steering angle of the front wheel is controlled by an actuator based on extracted intention from the hand rim. By proposed system, user can operate the wheelchair by using only single side hand rim. In particular, in this paper, we evaluate the designed hand rim by conducting some experiments.","PeriodicalId":260220,"journal":{"name":"2019 IEEE 17th International Conference on Industrial Informatics (INDIN)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129351803","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}
Pub Date : 2019-07-01DOI: 10.1109/INDIN41052.2019.8972261
Marcel Otte, S. Rohjans, F. Andrén, T. Strasser
The expansion of renewable energy sources, as an effort to reduce global warming and to guarantee a sustainable energy supply, forces the electrical energy systems into enhanced complexity through new requirements, actors, technological approaches or business models. This complexity is also noticed in the smart grid engineering process, resulting in increasing effort and costs. By applying machine learning concepts on the engineering process it is possible to decrease the work-effort and minimize tedious and error prone manual tasks. This work introduces three machine learning concepts and shows how they can improve the smart grid engineering process by applying a clustering approach to give recommendations of standards that are useful for the developed use case. According to their implementation-feasibility an evaluation based on the state-of-the-art is pursued. Furthermore, a tool prototype indicates current and future application possibilities of machine learning in the smart grid engineering process.
{"title":"Applying Machine Learning Concepts to Enhance the Smart Grid Engineering Process","authors":"Marcel Otte, S. Rohjans, F. Andrén, T. Strasser","doi":"10.1109/INDIN41052.2019.8972261","DOIUrl":"https://doi.org/10.1109/INDIN41052.2019.8972261","url":null,"abstract":"The expansion of renewable energy sources, as an effort to reduce global warming and to guarantee a sustainable energy supply, forces the electrical energy systems into enhanced complexity through new requirements, actors, technological approaches or business models. This complexity is also noticed in the smart grid engineering process, resulting in increasing effort and costs. By applying machine learning concepts on the engineering process it is possible to decrease the work-effort and minimize tedious and error prone manual tasks. This work introduces three machine learning concepts and shows how they can improve the smart grid engineering process by applying a clustering approach to give recommendations of standards that are useful for the developed use case. According to their implementation-feasibility an evaluation based on the state-of-the-art is pursued. Furthermore, a tool prototype indicates current and future application possibilities of machine learning in the smart grid engineering process.","PeriodicalId":260220,"journal":{"name":"2019 IEEE 17th International Conference on Industrial Informatics (INDIN)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130133670","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：