Pub Date : 2022-07-25DOI: 10.1109/INDIN51773.2022.9976127
Shixiang Lu, Zhiwei Gao, Qifa Xu, C. Jiang, A. Zhang, Dongdong Wu
Non-rechargeable batteries remain as the main source of energy for small systems, owing to their unique advantages in energy density, safety, reliability and sustainability. Accurate prediction of the remaining useful life of the battery is not only beneficial to maintenance and production safety, but also can be regarded as a starting point for possible secondary life applications. In this study, an interactive attention sequence-to-sequence network is proposed for the remaining useful life prediction of the non-rechargeable batteries. The proposed approach can effectively extract the degenerate information of each variable-length sequence and dynamically weight the sequence features of different dimensions. For illustration, a case of primary battery dataset collected from the power supply system of 139 vibration sensors is utilized. The extensive experiments verify the effectiveness of the proposed approach.
{"title":"Non-rechargeable battery remaining useful life prediction with interactive attention sequence to sequence network","authors":"Shixiang Lu, Zhiwei Gao, Qifa Xu, C. Jiang, A. Zhang, Dongdong Wu","doi":"10.1109/INDIN51773.2022.9976127","DOIUrl":"https://doi.org/10.1109/INDIN51773.2022.9976127","url":null,"abstract":"Non-rechargeable batteries remain as the main source of energy for small systems, owing to their unique advantages in energy density, safety, reliability and sustainability. Accurate prediction of the remaining useful life of the battery is not only beneficial to maintenance and production safety, but also can be regarded as a starting point for possible secondary life applications. In this study, an interactive attention sequence-to-sequence network is proposed for the remaining useful life prediction of the non-rechargeable batteries. The proposed approach can effectively extract the degenerate information of each variable-length sequence and dynamically weight the sequence features of different dimensions. For illustration, a case of primary battery dataset collected from the power supply system of 139 vibration sensors is utilized. The extensive experiments verify the effectiveness of the proposed approach.","PeriodicalId":359190,"journal":{"name":"2022 IEEE 20th International Conference on Industrial Informatics (INDIN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127173896","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 : 2022-07-25DOI: 10.1109/INDIN51773.2022.9976160
Lukas Johannes Dust, Emil Persson, Mikael Ekström, S. Mubeen, Emmanuel Dean
Multi-agent robot systems, specifically mobile robots in dynamic environments interacting with humans, e.g., assisting in production environments, have seen an increased interest over the past years. To better understand the ROS2 communication in a network with a high load of nodes, this paper investigates the communication handling of multiple robots to a single tracking node for centralized multi-agent robot systems using ROS2. Thereore, a quantitative analysis of two publisher-subscriber communication architectures and a comparative study between DDS vendors (CycloneDDS, FastDDS and GurumDDS) using ROS2 Galactic is performed. The architectures of consideration are a many-to-one approach, where multiple robots communicate to a central node over one topic, and the one-to-one communication approach, where multiple robots communicate over particular topics to a central node. Throughout this work, the increase in the number of robots at different publishing rates is simulated on a single computer for the different DDS vendors. A further simulation is done using a distributed setup with CycloneDDS. The simulations show that with an increase in the number of nodes, the average data age and the data miss ratio in the one-to-one approach were significantly lower than in the many-to-one approach. CycloneDDS was shown as the most robust regarding crashes and response time under system launch, while FastDDS showed better results regarding the data ageing.
{"title":"Quantitative analysis of communication handling for centralized multi-agent robot systems using ROS2","authors":"Lukas Johannes Dust, Emil Persson, Mikael Ekström, S. Mubeen, Emmanuel Dean","doi":"10.1109/INDIN51773.2022.9976160","DOIUrl":"https://doi.org/10.1109/INDIN51773.2022.9976160","url":null,"abstract":"Multi-agent robot systems, specifically mobile robots in dynamic environments interacting with humans, e.g., assisting in production environments, have seen an increased interest over the past years. To better understand the ROS2 communication in a network with a high load of nodes, this paper investigates the communication handling of multiple robots to a single tracking node for centralized multi-agent robot systems using ROS2. Thereore, a quantitative analysis of two publisher-subscriber communication architectures and a comparative study between DDS vendors (CycloneDDS, FastDDS and GurumDDS) using ROS2 Galactic is performed. The architectures of consideration are a many-to-one approach, where multiple robots communicate to a central node over one topic, and the one-to-one communication approach, where multiple robots communicate over particular topics to a central node. Throughout this work, the increase in the number of robots at different publishing rates is simulated on a single computer for the different DDS vendors. A further simulation is done using a distributed setup with CycloneDDS. The simulations show that with an increase in the number of nodes, the average data age and the data miss ratio in the one-to-one approach were significantly lower than in the many-to-one approach. CycloneDDS was shown as the most robust regarding crashes and response time under system launch, while FastDDS showed better results regarding the data ageing.","PeriodicalId":359190,"journal":{"name":"2022 IEEE 20th International Conference on Industrial Informatics (INDIN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126100208","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 : 2022-07-25DOI: 10.1109/INDIN51773.2022.9976156
N. Kouvakas, F. Koumboulis, Katerina Xydi
The problem of controlling the position of a magnetically levitated ball is studied through a PD state feedback linear controller and the simultaneous satisfaction of a set of individual miscellaneous design requirements including stability, command following, model following and appropriately bounded input. The requirements are defined over the linear approximant of the magnetic levitation system. Also, for the solution of the problem, a metaheuristic algorithm, based on the linear approximant of the magnetic levitation system, is proposed. The performance of the proposed control scheme, for the resulting nonlinear closed loop system, is illustrated through a series of computational experiments.
{"title":"Model Following through a Metaheuristic PD Controller for a Magnetic Levitation System","authors":"N. Kouvakas, F. Koumboulis, Katerina Xydi","doi":"10.1109/INDIN51773.2022.9976156","DOIUrl":"https://doi.org/10.1109/INDIN51773.2022.9976156","url":null,"abstract":"The problem of controlling the position of a magnetically levitated ball is studied through a PD state feedback linear controller and the simultaneous satisfaction of a set of individual miscellaneous design requirements including stability, command following, model following and appropriately bounded input. The requirements are defined over the linear approximant of the magnetic levitation system. Also, for the solution of the problem, a metaheuristic algorithm, based on the linear approximant of the magnetic levitation system, is proposed. The performance of the proposed control scheme, for the resulting nonlinear closed loop system, is illustrated through a series of computational experiments.","PeriodicalId":359190,"journal":{"name":"2022 IEEE 20th International Conference on Industrial Informatics (INDIN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126193467","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 : 2022-07-25DOI: 10.1109/INDIN51773.2022.9976094
Mohammed Sharafath Abdul Hameed, Venkata Harshit Koneru, Johannes Poeppelbaum, Andreas Schwung
This paper presents a novel approach to train a Reinforcement Learning (RL) agent faster for transportation of parcels in a Peristaltic Sortation Machine (PSM) using curriculum learning (CL). The PSM was developed as a means to transport parcels using an actuator and a flexible film where a RL agent is trained to control the actuator. In a previous paper, training of the actuator was done on a Discrete Element Method (DEM) simulation environment of the PSM developed using an open-source DEM library called LIGGGHTS, which reduced the training time of the transportation task compared to the real machine. But it still took days to train the agent. The objective of this paper is to reduce the training time to hours. To overcome this problem, we developed a faster but lower fidelity python simulation environment (PSE) capable of simulating the transportation task of PSM. And we used it with a curriculum learning approach to accelerate training the agent in the transportation process. The RL agent is trained in two steps in the PSE: 1. with a fixed set of goal positions, 2. with randomized goal positions. Additionally, we also use Gradient Monitoring (GM), a gradient regularization method, which provides additional trust region constraints in the policy updates of the RL agent when switching between tasks. The agent so trained is then deployed and tested in the DEM environment where the agent has not been trained before. The results obtained show that the RL agent trained using CL and PSE successfully completes the tasks in the DEM environment without any loss in performance, while using only a fraction of the training time (1.87%) per episode. This will allow for faster prototyping of algorithms to be tested on the PSM in future.
{"title":"Curriculum Learning in Peristaltic Sortation Machine","authors":"Mohammed Sharafath Abdul Hameed, Venkata Harshit Koneru, Johannes Poeppelbaum, Andreas Schwung","doi":"10.1109/INDIN51773.2022.9976094","DOIUrl":"https://doi.org/10.1109/INDIN51773.2022.9976094","url":null,"abstract":"This paper presents a novel approach to train a Reinforcement Learning (RL) agent faster for transportation of parcels in a Peristaltic Sortation Machine (PSM) using curriculum learning (CL). The PSM was developed as a means to transport parcels using an actuator and a flexible film where a RL agent is trained to control the actuator. In a previous paper, training of the actuator was done on a Discrete Element Method (DEM) simulation environment of the PSM developed using an open-source DEM library called LIGGGHTS, which reduced the training time of the transportation task compared to the real machine. But it still took days to train the agent. The objective of this paper is to reduce the training time to hours. To overcome this problem, we developed a faster but lower fidelity python simulation environment (PSE) capable of simulating the transportation task of PSM. And we used it with a curriculum learning approach to accelerate training the agent in the transportation process. The RL agent is trained in two steps in the PSE: 1. with a fixed set of goal positions, 2. with randomized goal positions. Additionally, we also use Gradient Monitoring (GM), a gradient regularization method, which provides additional trust region constraints in the policy updates of the RL agent when switching between tasks. The agent so trained is then deployed and tested in the DEM environment where the agent has not been trained before. The results obtained show that the RL agent trained using CL and PSE successfully completes the tasks in the DEM environment without any loss in performance, while using only a fraction of the training time (1.87%) per episode. This will allow for faster prototyping of algorithms to be tested on the PSM in future.","PeriodicalId":359190,"journal":{"name":"2022 IEEE 20th International Conference on Industrial Informatics (INDIN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129264880","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 : 2022-07-25DOI: 10.1109/INDIN51773.2022.9976078
J. Kuschan, H. Filaretov, J. Krüger
Motion datasets in industrial environments are essential for the research on human-robot interaction and new exoskeleton control. Currently, a lot of Activities of Daily Living (ADL) datasets are available for researchers, but only a few target an industrial context. This paper presents a dataset for a semi-industrial Overhead Car Assembly (OCA) task consisting of synchronized video and 9-Degrees of Freedom (DOF) Inertial Measurement Unit (IMU) data. The dataset was recorded with a soft-robotic exoskeleton equipped with 4 IMUs covering the upper body. It has a minimum sampling rate of 20 Hz, lasts approximately 360 minutes and comprises of 282 cycles of a realistic industrial assembly task. The annotations consist of 6 mid-level actions and an additional Null class. Five different test subjects performed the task without specific instructions on how to assemble the used car shielding. In this paper, we describe the dataset, set guidelines for using the data in supervised learning approaches, and analyze the labeling error caused by the labeler onto the dataset. We also compare different state-of-the-art neural networks to set the first benchmark and achieve a weighted F1 score of 0.717.
{"title":"Inertial Measurement Unit based Human Action Recognition Dataset for Cyclic Overhead Car Assembly and Disassembly","authors":"J. Kuschan, H. Filaretov, J. Krüger","doi":"10.1109/INDIN51773.2022.9976078","DOIUrl":"https://doi.org/10.1109/INDIN51773.2022.9976078","url":null,"abstract":"Motion datasets in industrial environments are essential for the research on human-robot interaction and new exoskeleton control. Currently, a lot of Activities of Daily Living (ADL) datasets are available for researchers, but only a few target an industrial context. This paper presents a dataset for a semi-industrial Overhead Car Assembly (OCA) task consisting of synchronized video and 9-Degrees of Freedom (DOF) Inertial Measurement Unit (IMU) data. The dataset was recorded with a soft-robotic exoskeleton equipped with 4 IMUs covering the upper body. It has a minimum sampling rate of 20 Hz, lasts approximately 360 minutes and comprises of 282 cycles of a realistic industrial assembly task. The annotations consist of 6 mid-level actions and an additional Null class. Five different test subjects performed the task without specific instructions on how to assemble the used car shielding. In this paper, we describe the dataset, set guidelines for using the data in supervised learning approaches, and analyze the labeling error caused by the labeler onto the dataset. We also compare different state-of-the-art neural networks to set the first benchmark and achieve a weighted F1 score of 0.717.","PeriodicalId":359190,"journal":{"name":"2022 IEEE 20th International Conference on Industrial Informatics (INDIN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124640720","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 : 2022-07-25DOI: 10.1109/INDIN51773.2022.9976092
Yuanzhen Liu, Dutliff Boshoff, G. Hancke
In the past few years, smart healthcare has become a popular topic. Many users wear smart devices to monitor their health conditions. To provide information for health analysis, many sensors are installed in smart wearable devices to collect personal health data. Due to the limitation of space and computational power, private health data is not processed locally. Instead, it is usually sent to a mobile phone for further analysis, which required wireless data exchange between the mobile phone and smart wearable devices. To protect a user’s privacy, it is important to guarantee the connection security of the devices’ network as well as prevent information leakage. A possible method to secure the data exchange process is symmetric encryption. In this paper, we investigate the feasibility of symmetric key generation for communication between a mobile phone and smart wearable device using angular velocity data collected by gyroscopes as data source. We collected over 1000 samples of gait data, totally more than 20000 seconds of movements, using two industrial products including a smart watch and mobile phone placed on wrist and in pocket respectively. We successfully generated the same random number for mobile phone and smart wearable device in 78% samples.
{"title":"Feasibility of using Gyroscope to Derive Keys for Mobile Phone and Smart Wearable","authors":"Yuanzhen Liu, Dutliff Boshoff, G. Hancke","doi":"10.1109/INDIN51773.2022.9976092","DOIUrl":"https://doi.org/10.1109/INDIN51773.2022.9976092","url":null,"abstract":"In the past few years, smart healthcare has become a popular topic. Many users wear smart devices to monitor their health conditions. To provide information for health analysis, many sensors are installed in smart wearable devices to collect personal health data. Due to the limitation of space and computational power, private health data is not processed locally. Instead, it is usually sent to a mobile phone for further analysis, which required wireless data exchange between the mobile phone and smart wearable devices. To protect a user’s privacy, it is important to guarantee the connection security of the devices’ network as well as prevent information leakage. A possible method to secure the data exchange process is symmetric encryption. In this paper, we investigate the feasibility of symmetric key generation for communication between a mobile phone and smart wearable device using angular velocity data collected by gyroscopes as data source. We collected over 1000 samples of gait data, totally more than 20000 seconds of movements, using two industrial products including a smart watch and mobile phone placed on wrist and in pocket respectively. We successfully generated the same random number for mobile phone and smart wearable device in 78% samples.","PeriodicalId":359190,"journal":{"name":"2022 IEEE 20th International Conference on Industrial Informatics (INDIN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129659187","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 : 2022-07-25DOI: 10.1109/INDIN51773.2022.9976079
A. O. Júnior, G. Funchal, J. Queiroz, Jorge Loureiro, T. Pedrosa, Javier Parra, Paulo Leitão
The Internet of Things (IoT) is one of the main foundations of Industry 4.0, providing widespread connectivity of systems and devices, which promotes significant benefits, such as improved performance, responsiveness, and reconfigurability. However, it also brings some security problems, which make these devices and systems vulnerable to cyberattacks, consequently demanding efficient learning and training initiatives to address the challenges regarding the qualification of undergraduate students and active professionals to design more secure systems, as well as to be more aware of cyberthreats during the management and use of them. With this in mind, this paper describes a Capture the Flag competition based on IoT cybersecurity. The participants’ feedback and performance evaluation show that this type of hands-on competition strongly contributes to learning the importance of cybersecurity in IoT-based applications.
{"title":"Learning Cybersecurity in IoT-based Applications through a Capture the Flag Competition","authors":"A. O. Júnior, G. Funchal, J. Queiroz, Jorge Loureiro, T. Pedrosa, Javier Parra, Paulo Leitão","doi":"10.1109/INDIN51773.2022.9976079","DOIUrl":"https://doi.org/10.1109/INDIN51773.2022.9976079","url":null,"abstract":"The Internet of Things (IoT) is one of the main foundations of Industry 4.0, providing widespread connectivity of systems and devices, which promotes significant benefits, such as improved performance, responsiveness, and reconfigurability. However, it also brings some security problems, which make these devices and systems vulnerable to cyberattacks, consequently demanding efficient learning and training initiatives to address the challenges regarding the qualification of undergraduate students and active professionals to design more secure systems, as well as to be more aware of cyberthreats during the management and use of them. With this in mind, this paper describes a Capture the Flag competition based on IoT cybersecurity. The participants’ feedback and performance evaluation show that this type of hands-on competition strongly contributes to learning the importance of cybersecurity in IoT-based applications.","PeriodicalId":359190,"journal":{"name":"2022 IEEE 20th International Conference on Industrial Informatics (INDIN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131629678","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 : 2022-07-25DOI: 10.1109/INDIN51773.2022.9976070
T. Heikkilä, E. Halbach, J. Koskinen, Janne Saukkoriipi
Maintenance tasks represent a potential area for applying multi-purpose Autonomous Mobile Robots (AMRs). Intelligent control and coordination of such a system is challenging and optimization methods are feasible only for small fleets. Decentralized control can provide flexibility and robustness, which are better applicable also for large fleets, though with less guaranteed performance. Our focus is on flexibility and robustness in task scheduling and task assignments and we use entropy as an indirect performance criterion for coordination, both at the system level (maximize entropy) and at the AMR level (minimize entropy). As a distributed coordination scheme, we use a modified contract negotiation protocol. We show preliminarily the feasibility of our approach with simulation results.
{"title":"Entropy-based coordination for maintenance tasks of an autonomous mobile robot system","authors":"T. Heikkilä, E. Halbach, J. Koskinen, Janne Saukkoriipi","doi":"10.1109/INDIN51773.2022.9976070","DOIUrl":"https://doi.org/10.1109/INDIN51773.2022.9976070","url":null,"abstract":"Maintenance tasks represent a potential area for applying multi-purpose Autonomous Mobile Robots (AMRs). Intelligent control and coordination of such a system is challenging and optimization methods are feasible only for small fleets. Decentralized control can provide flexibility and robustness, which are better applicable also for large fleets, though with less guaranteed performance. Our focus is on flexibility and robustness in task scheduling and task assignments and we use entropy as an indirect performance criterion for coordination, both at the system level (maximize entropy) and at the AMR level (minimize entropy). As a distributed coordination scheme, we use a modified contract negotiation protocol. We show preliminarily the feasibility of our approach with simulation results.","PeriodicalId":359190,"journal":{"name":"2022 IEEE 20th International Conference on Industrial Informatics (INDIN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123470429","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 : 2022-07-25DOI: 10.1109/INDIN51773.2022.9976155
Yifan Wang, Lin Yang, Hong Chen, Aamir Hussain, Congcong Ma, Malek Al-gabri
In agriculture 4.0, internet of things is pushing the boundary of smart agricultural applications to assist farmers from production to sale of crops. Mushroom is one of the most economically valuable crops in agriculture production, and widely cultivated all over the world, from China to the United States. Growing shiitake mushrooms requires real-time adjustment of the indoor environment, and statistics on the yield and types of shiitake mushrooms. The traditional planting method is labor-intensive and inefficient. Moreover, the traditional image processing methods have strict requirements on crop background, which also increases the cost of planting. To address this issue, in this paper, a deep learning algorithm for mushroom growth recognition based on improved YOLOv5 is proposed and named Mushroom-YOLO for small targets detection such as mushrooms, and the mean average precision is up to 99.24% and this performance is much better than the original YOLOv5. In addition, a prototype system for the flower shiitake mushroom yield recognition used iMushroom is presented. The prototype and real shiitake mushroom planting case study show the effectiveness, and provide a potential way to control the quality of shiitake mushroom growth without human in indoor farming.
{"title":"Mushroom-YOLO: A deep learning algorithm for mushroom growth recognition based on improved YOLOv5 in agriculture 4.0","authors":"Yifan Wang, Lin Yang, Hong Chen, Aamir Hussain, Congcong Ma, Malek Al-gabri","doi":"10.1109/INDIN51773.2022.9976155","DOIUrl":"https://doi.org/10.1109/INDIN51773.2022.9976155","url":null,"abstract":"In agriculture 4.0, internet of things is pushing the boundary of smart agricultural applications to assist farmers from production to sale of crops. Mushroom is one of the most economically valuable crops in agriculture production, and widely cultivated all over the world, from China to the United States. Growing shiitake mushrooms requires real-time adjustment of the indoor environment, and statistics on the yield and types of shiitake mushrooms. The traditional planting method is labor-intensive and inefficient. Moreover, the traditional image processing methods have strict requirements on crop background, which also increases the cost of planting. To address this issue, in this paper, a deep learning algorithm for mushroom growth recognition based on improved YOLOv5 is proposed and named Mushroom-YOLO for small targets detection such as mushrooms, and the mean average precision is up to 99.24% and this performance is much better than the original YOLOv5. In addition, a prototype system for the flower shiitake mushroom yield recognition used iMushroom is presented. The prototype and real shiitake mushroom planting case study show the effectiveness, and provide a potential way to control the quality of shiitake mushroom growth without human in indoor farming.","PeriodicalId":359190,"journal":{"name":"2022 IEEE 20th International Conference on Industrial Informatics (INDIN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123505593","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 : 2022-07-25DOI: 10.1109/INDIN51773.2022.9976081
M. Müller, Janina Knorr, D. Behnke, Christian Arendt, S. Böcker, Caner Bektas, C. Wietfeld
The ongoing process of shop floor digitalization makes production processes more transparent and helps technical staff and managers at their day-to-day work in modern factories. The digitalization is enabled by a wide variety of applications which run on different device types and demand support for different network characteristics.
{"title":"Enhancing Reliability by Combining Manufacturing Processes and Private 5G Networks","authors":"M. Müller, Janina Knorr, D. Behnke, Christian Arendt, S. Böcker, Caner Bektas, C. Wietfeld","doi":"10.1109/INDIN51773.2022.9976081","DOIUrl":"https://doi.org/10.1109/INDIN51773.2022.9976081","url":null,"abstract":"The ongoing process of shop floor digitalization makes production processes more transparent and helps technical staff and managers at their day-to-day work in modern factories. The digitalization is enabled by a wide variety of applications which run on different device types and demand support for different network characteristics.","PeriodicalId":359190,"journal":{"name":"2022 IEEE 20th International Conference on Industrial Informatics (INDIN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129730657","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：