{"title":"Sensors at the Edge: Towards Micromechanical in-Memory Computing","authors":"P. Schmitt, M. Hoffmann","doi":"10.1109/COINS57856.2023.10189322","DOIUrl":"https://doi.org/10.1109/COINS57856.2023.10189322","url":null,"abstract":"In this paper, we present a series of mechanical components that can be interconnected to form mechanical integrated sensor circuit. Functions within the measurement chain that are typically implemented by electronic components, can be realized here by mechanical components. We demonstrate how these components enable initial data preprocessing at the sensor level, such as applying defined transfer functions on a measurement signal. The proposed mechanical sensors operate in the analog domain and store only pre-defined values of interest instead of generating measurement results at a given sampling rate. Our approach offers a novel alternative to electronic circuits for implementing sensors and measurement chains aiming on a reduction of data generation and energy consumption within condition monitoring applications","PeriodicalId":328385,"journal":{"name":"2023 IEEE International Conference on Omni-layer Intelligent Systems (COINS)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125446534","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}
{"title":"CiTe: A Testbed for Smart City Applications and Architectures","authors":"Dominic Büch, M. Esch","doi":"10.1109/COINS57856.2023.10189229","DOIUrl":"https://doi.org/10.1109/COINS57856.2023.10189229","url":null,"abstract":"With the continuous development of smart city systems and architectures and their real-world implementation arises the need for a reliable way of verifying their integrity. Most smart city set-ups consist of subsystems derived from the IoT sector, focussing on building sensor networks and powering heterogenous devices of all shapes and sizes. The IoT industry and research sector have long known the benefits of testing new systems in a controllable, minimal environment. These testbeds have become an integral part of hardware evaluation and embedded-systems development. Testbeds for the Smart City application scenario have to meet their own specific requirements. This paper presents a testbed tailored to smart city research. The testbed is based on a model city with integrated sensors and actuators interconnected by a cloud native backend architecture. By this means the testbed allows studying modern smart city software architectures and the interplay of real hardware and software. The testbed is fully implemented and in daily use for research projects and university teaching.","PeriodicalId":328385,"journal":{"name":"2023 IEEE International Conference on Omni-layer Intelligent Systems (COINS)","volume":"50 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120908038","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}
{"title":"Mitigate the Negative TL using Adaptive Thresholding for Fault Diagnosis","authors":"M. PavanKumar, Kun-Chih Jimmy Chen","doi":"10.1109/COINS57856.2023.10189313","DOIUrl":"https://doi.org/10.1109/COINS57856.2023.10189313","url":null,"abstract":"The fourth industrial revolution has created a data-centric ecosystem where the implementation of Prognostics and Health Management (PHM) technology is crucial to support contemporary industrial systems. To enhance performance in fault diagnosis and health assessment of mechanical equipment, Deep Learning (DL) has been integrated into PHM. However, DL models encounter several challenges in PHM, such as the requirement for large amounts of labeled data and a lack of generalizability. TL (TL) has emerged as a promising technique to overcome these limitations. Fine-tuning, a commonly used approach to the inductive transfer of deep models, assumes that the source and target tasks are related and that pre-trained parameters from the source task are likely to be close to the optimal parameters for the target task. Nevertheless, when the amount of training data on the target domain is limited, fine-tuning can lead to negative transfer and catastrophic forgetting. To overcome these issues, we propose a novel regularization approach to selectively modulate the features of normalized inputs based on their distance from the mini-batch mean during fine-tuning. Our approach aims to prevent the negative transfer of pre-trained knowledge that is irrelevant to the target task and mitigate catastrophic forgetting. Furthermore, our approach yields a 0.9-5% increase in accuracy under the same environment and 2.8-6.2% under different environmental conditions, compared to other state-of-the-art regularization-based methods.","PeriodicalId":328385,"journal":{"name":"2023 IEEE International Conference on Omni-layer Intelligent Systems (COINS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123436266","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}
Joe Lorentz, Thomas Hartmann, Assaad Moawad, Djamila Aouada
{"title":"Industrial defect detection on the edge with deep learning over scarcely labeled and extremely imbalanced data","authors":"Joe Lorentz, Thomas Hartmann, Assaad Moawad, Djamila Aouada","doi":"10.1109/COINS57856.2023.10189246","DOIUrl":"https://doi.org/10.1109/COINS57856.2023.10189246","url":null,"abstract":"Reliable automated defect detection is an integral part of modern manufacturing and improved performance can provide a competitive advantage. Despite the proven capabilities of convolutional neural networks (CNNs) for image classification, application on real world tasks remains challenging due to the high demand for labeled and well balanced data of the common supervised learning scheme. Semi-supervised learning (SSL) promises to achieve comparable accuracy while only requiring a small fraction of the training samples to be labeled. However, SSL methods struggle with data imbalance and existing benchmarks do not reflect the challenges of real world applications. In this work we present a CNN-based defect detection unit for thermal sensors. We describe how to collect data from a running process and release our dataset of 1k labeled and 293k unlabeled samples. Furthermore, we investigate the use of SSL under this challenging real world task.","PeriodicalId":328385,"journal":{"name":"2023 IEEE International Conference on Omni-layer Intelligent Systems (COINS)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128618720","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}
{"title":"Brain Age Estimation Using Structural MRI: A Clustered Federated Learning Approach","authors":"Seyyed Saeid Cheshmi, Abtin Mahyar, Anita Soroush, Z. Rezvani, Bahar Farahani","doi":"10.1109/COINS57856.2023.10189329","DOIUrl":"https://doi.org/10.1109/COINS57856.2023.10189329","url":null,"abstract":"Estimating brain age based on structural Magnetic Resonance Imaging (MRI) is one of the most challenging and prominent areas of research in recent medical imaging and neuroscience studies. The significance of brain age prediction in the early diagnosis of neurological disorders has fueled a resurgence of interest in this field. Various studies have addressed this issue using a spectrum of techniques, from traditional machine learning to deep neural networks. The majority of these techniques employ centralized paradigms, which do not adequately preserve privacy. To tackle this problem, a handful of studies have utilized a federated approach. In this study, we propose a novel hierarchical clustered federated learning approach that carefully captures and considers the similarities of the clients’ predictions on a certain benchmark dataset. This method enhances performance in Non-Independent and Identically Distributed (Non-IID) environments while preserving privacy. We use a multi-site dataset that provides a broad variety of MRI scans, characterizing a proper Non-IID environment. Our method achieves a Mean Absolute Error (MAE) of 3.86, while the non-clustered FedAvg federated approach attains a 4.14 MAE on the test set.11Code is available at https://github.com/Abtinmy/Clustered-FL-BrainAGE.","PeriodicalId":328385,"journal":{"name":"2023 IEEE International Conference on Omni-layer Intelligent Systems (COINS)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126871973","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}
Jayandren Moodley, G. A. M. Meiring, Njabulo S. Mtetwa, Obakeng Motuba, Ovi Mphephu, M. Maluleke, Reevana Balmahoon
{"title":"Beyond Reality: An Application of Extended Reality and Blockchain in the Metaverse","authors":"Jayandren Moodley, G. A. M. Meiring, Njabulo S. Mtetwa, Obakeng Motuba, Ovi Mphephu, M. Maluleke, Reevana Balmahoon","doi":"10.1109/COINS57856.2023.10189285","DOIUrl":"https://doi.org/10.1109/COINS57856.2023.10189285","url":null,"abstract":"The convergence of Fourth Industrial Revolution (4IR) technologies and Web2 to Web3 transformation, presents significant benefits and opportunities for industry. This study explores the integrated benefits of Extended Reality (XR) and Distributed Ledger Technology (DLT) in a Metaverse application for virtual consulting. Since XR enhances collaboration using visualization, and DLT ensures transactional security and privacy, an overview of XR and DLT technology is provided, highlighting their specific benefits and challenges concerning Remote Health and Wellness consulting. The paper proposes a Metaverse solution to leverage these benefits, enabling more affordable and accessible healthcare consulting in developing economies. A key outcome of the research is to develop a metaverse prototype that bridges the gap between Web 2.0 and Web 3.0 technologies. By doing so, it aims to improve usability for end-users, drive the adoption of XR and Blockchain, generate new business models, and unlock new revenue streams for industry and underserved communities.","PeriodicalId":328385,"journal":{"name":"2023 IEEE International Conference on Omni-layer Intelligent Systems (COINS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134159283","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}
L. Ortenzi, S. Figorilli, S. Violino, F. Pallottino, C. Costa
{"title":"Artificial Intelligence approaches for fast and portable traceability assessment of EVOO","authors":"L. Ortenzi, S. Figorilli, S. Violino, F. Pallottino, C. Costa","doi":"10.1109/COINS57856.2023.10189267","DOIUrl":"https://doi.org/10.1109/COINS57856.2023.10189267","url":null,"abstract":"Extra virgin olive oil (EVOO) represents one of the first-choice products made in Italy for its high quality and use in the Mediterranean diet. The aim of this study was to evaluate the effectiveness of a portable VIS-NIR open-source spectroscopic system coupled with an artificial intelligence model for the rapid determination of EVOOs traceability. Reported results for EVOO traceability, with respect to different degrees of aggregation (EU and extra-EU, Italian and foreign and Italian areas of membership), show excellent performances of artificial intelligence models and indicate a valid rapid and low-cost method of analysis for combating EVOO counterfeiting.","PeriodicalId":328385,"journal":{"name":"2023 IEEE International Conference on Omni-layer Intelligent Systems (COINS)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132896913","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}
Yoshihisa Kondo, H. Yomo, Shogo Nishimura, Akira Utsumi, T. Miyashita
{"title":"A Practical Implementation of Multi-Radio Wi-Fi for Teleoperated Mobile Robots","authors":"Yoshihisa Kondo, H. Yomo, Shogo Nishimura, Akira Utsumi, T. Miyashita","doi":"10.1109/COINS57856.2023.10189247","DOIUrl":"https://doi.org/10.1109/COINS57856.2023.10189247","url":null,"abstract":"We propose a multi-radio Wi-Fi communication system that can be easily integrated into a mobile robot and provide stable communication using multiple Wi-Fi devices. In the proposed system, Multi-Radio Controller (MRC) and Multi-Link Manager (MLM) hide multi-radio communication from the computer units of a mobile robot in such a way that each computer unit does not need to be aware of multi-radio communication. We implement the proposed system in a real teleoperation system using mobile robots and confirm that our proposed system works stably through a two-day demonstration at a real event site. We also confirm that our proposed system has lower latency communication than a single radio Wi-Fi based system through field tests.","PeriodicalId":328385,"journal":{"name":"2023 IEEE International Conference on Omni-layer Intelligent Systems (COINS)","volume":"154 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133272100","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}
Umuralp Kaytaz, Saba Ahmadian, Fabian Hofmann, F. Sivrikaya, S. Albayrak
{"title":"Online Monte Carlo Planning with QoS Subgoals for Data Caching in ITS MEC Networks","authors":"Umuralp Kaytaz, Saba Ahmadian, Fabian Hofmann, F. Sivrikaya, S. Albayrak","doi":"10.1109/COINS57856.2023.10189272","DOIUrl":"https://doi.org/10.1109/COINS57856.2023.10189272","url":null,"abstract":"Multi-access Edge Computing (MEC) is an imperative for next-generation Machine-Type Communications (MTC) to alleviate the shortcomings of Cloud Computing (CC) infrastructures in terms of service delays and network loads. Intelligent Transportation System (ITS) is an application area of MTC that utilizes edge network nodes and Vehicle-to-Everything (V2X) communication technologies to leverage the benefits of MEC resources such as caching popular content data in nearby edge devices and eliminating redundant data fetching operations. This paper tackles the optimal data caching problem in geographically distributed edge networks and proposes Online Monte CArlo planning based data caching (OMCA) scheme for vehicular environments. Considering multi-dimensional Quality-of-Service (QoS) requirements in the ITS domain, OMCA uses Monte Carlo Tree Search (MCTS) al-gorithm with subgoal based temporal abstractions for au-tomatically discovering and optimizing data caching actions. Employing the BeIntelli smart mobility platform of TU Berlin, we compare the performance of our approach with traditional as well as Reinforcement Learning (RL) based methods in terms of cache hit ratio for varying network sizes and cache capacities. Our results show that OMCA utilizes edge network cache resources more effectively compared to other techniques and outperforms MCTS, Deep Q-Learning (DQL) as well as recency based popular caching policies.","PeriodicalId":328385,"journal":{"name":"2023 IEEE International Conference on Omni-layer Intelligent Systems (COINS)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133494231","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}
{"title":"Predicting the Risk of Death of Cryptocurrencies","authors":"Bedirhan Sakinoğlu, Altay Güvenir","doi":"10.1109/COINS57856.2023.10189205","DOIUrl":"https://doi.org/10.1109/COINS57856.2023.10189205","url":null,"abstract":"In recent years, the attention drawn by cryptocurrencies has increased as their popularity grows rapidly. This situation attracts investors, entrepreneurs, regulators, and the general public. However, these coins may die and become dead coins. A coin is declared dead if no activity is recorded for more than one year. Numerous coins die without completing their one-year timeframe and this issue causes investors to lose a significant amount of money. In this study, we develop a deep neural network architecture based on long short-term memory (LSTM) to predict the death risk of a coin in a specified timeframe. In order to do this, time-series data consisting of the closing price and volume values of 4733 dead coins are utilized. The goal of our model is to inform investors about the death risk of the coin and improve their overall portfolio performance.","PeriodicalId":328385,"journal":{"name":"2023 IEEE International Conference on Omni-layer Intelligent Systems (COINS)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133505434","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}