2023 IEEE International Systems Conference (SysCon)最新文献

{"title":"Dependability Issues on an Internet Service Provider and availability study of autonomous systems","authors":"Arthur Sérvio, Felipe Oliveira, J. Dantas, D. Silva, Danilo Clemente","doi":"10.1109/SysCon53073.2023.10131183","DOIUrl":"https://doi.org/10.1109/SysCon53073.2023.10131183","url":null,"abstract":"The Internet is arguably the most important means of communication, as there is no business strategy without the Internet. The Internet Service Provider’s challenge is to ensure the high availability of services to meet customers’ expectations, guaranteeing that they will be available and ready for whatever may be the user’s interests may be. Every time the user tries to access the service or product, and it is unavailable, we have the characterization of the service as unavailability. In this article, we evaluate the ISP’s core availability, identify availability issues in the router component, and study CTMC and RBD models by performing a model validation experiment, executing a steady-state availability, and performing a sensitivity analysis. Hierarchical modeling strategies, (availability models combining reliability block diagrams (RBD) and continuous time Markov chain (CTMC)) were used, indicating the availability of the infrastructure. The critical component of the system was indicated through sensitivity analysis. We performed a model validation technique to demonstrate that the models represent the behavior of the real system. The results showed that the system availability is 0.99941, and the sensitive analysis indicated that if the system administrator optimized the ISP infrastructure in 50%, it would yield a yearly downtime reduction of 3.4 hours.","PeriodicalId":169296,"journal":{"name":"2023 IEEE International Systems Conference (SysCon)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130717958","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":"Monkeypox Detection and Classification Using Deep Learning Based Features Selection and Fusion Approach","authors":"Sarmad Maqsood, R. Damaševičius","doi":"10.1109/SysCon53073.2023.10131067","DOIUrl":"https://doi.org/10.1109/SysCon53073.2023.10131067","url":null,"abstract":"In today’s healthcare system, clinical diagnosis has taken on a crucial role. As the COVID-19 virus’s global infection declines, the monkeypox virus is steadily developing. Because of this, it’s critical to identify them early, before they spread to the larger population. Early detection can be aided by AI-based detection. In this study, a fusion based contrast enhancement approach is used to preprocess the source images. Two pre-trained DCNN models (Inception-ResNet-V2 and NASNet-Large) are modified and trained using transfer learning. From each DCNN model, deep feature vectors are extracted and the entropy-based controlled algorithm is used for the best features selection. The convolutional sparse image decomposition fusion approach is utilized to fused the feature for classification. Finally, the selected features are forwarded to a multi-class support vector machine (M-SVM) for final classification. After performing experiments on public datasets, the proposed approach obtained an accuracy of 98.59%, sensitivity of 92.78%, specificity of 95.47%, and AUC of 0.987. Simulation studies show that the proposed approach outperforms other methods both visually and quantitatively.","PeriodicalId":169296,"journal":{"name":"2023 IEEE International Systems Conference (SysCon)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132733425","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":"A method with criteria for using modeling and simulation to achieve space systems Integration Readiness Levels","authors":"Gabriel T. Jesus, M. F. C. Júnior","doi":"10.1109/SysCon53073.2023.10131058","DOIUrl":"https://doi.org/10.1109/SysCon53073.2023.10131058","url":null,"abstract":"Knowledge concerning the integration process throughout a system life cycle is critical for introducing new technologies. Advances in digital technologies and high-fidelity digital models may lessen investments in physical models to fulfill programmatic requirements when verifying space systems. Digital engineering, model-based systems engineering, and digital twins literature link to this topic. The Integration Readiness Levels (IRL) scale is an emerging good practice that complements the Technology Readiness Levels (TRL) scale in supporting the integration of technologies into a system. IRL has been evolving over the past fifteen years. However, IRL still provides few specific directions on the use of modeling and simulation to achieve its levels. The research objective is to propose a method that suggests whether and under what conditions modeling and simulation could comply with Integration Readiness Levels for space systems. Results show the proposed theory and how it was developed through the design science research method. The proposed method addressed model-based capabilities, system lifecycle processes, and information items in a set of suggested criteria for each IRL and additional considerations. This paper could support practitioners in making decisions about using modeling and simulation to meet Integration Readiness Levels and could support organizations in planning their model-based capabilities.","PeriodicalId":169296,"journal":{"name":"2023 IEEE International Systems Conference (SysCon)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131742590","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":"An Ensemble Voting Method of Pre-Trained Deep Learning Models for Orchid Recognition","authors":"Chia-Ho Ou, Yi-Nuo Hu, Dong-Jie Jiang, Po-Yen Liao","doi":"10.1109/SysCon53073.2023.10131263","DOIUrl":"https://doi.org/10.1109/SysCon53073.2023.10131263","url":null,"abstract":"Orchids are a diverse group of angiosperms, many of which share similar physical characteristics such as color, pattern, and inflorescence. As a result, identifying orchid species can be a time-consuming task that requires expert knowledge. This paper proposes a solution that utilizes Convolutional Neural Networks (CNNs) for accurate and efficient image classification. Specifically, three pre-trained models, ResNet50, EfficientNet, and Big Transfer (BiT), were employed and fine-tuned using transfer learning. Ensemble learning was then employed to combine the predicted probabilities of the three models, weighted by their respective performance, to determine the orchid species through soft voting. The proposed approach was validated using the Orchid Flowers Dataset, selecting 84 varieties, and achieved a maximum accuracy of 84.67%, improving upon the best single model by 2.8%. The Orchid-52 dataset also demonstrated a 3.1% improvement, reaching 95.13% accuracy.","PeriodicalId":169296,"journal":{"name":"2023 IEEE International Systems Conference (SysCon)","volume":"140 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127523080","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":"A Gradient Descent Multi-Algorithm Grid Search Optimization of Deep Learning for Sensor Fusion","authors":"T. M. Booth, Sudipto Ghosh","doi":"10.1109/SysCon53073.2023.10131077","DOIUrl":"https://doi.org/10.1109/SysCon53073.2023.10131077","url":null,"abstract":"Sensor fusion approaches combine data from a suite of sensors into an integrated solution that represents the target environment more accurately than that produced by an individual sensor. Deep learning (DL) based approaches can address challenges with sensor fusion more accurately than classical approaches. However, the accuracy of the selected approach can change when sensors are modified, upgraded or swapped out within the system of sensors. Historically, this can require an expensive manual refactor of the sensor fusion solution.This paper develops 12 DL-based sensor fusion approaches and proposes a systematic and iterative methodology for selecting an optimal DL approach and hyperparameter settings simultaneously. The Gradient Descent Multi-Algorithm Grid Search (GD-MAGS) methodology is an iterative grid search technique enhanced by gradient descent predictions and expanded to exchange performance measure information across concurrently running DL-based approaches. Additionally, at each iteration, the worst two performing DL approaches are pruned to reduce the resource usage as computational expense increases from hyperparameter tuning. We evaluate this methodology using an open source, time-series aircraft data set trained on the aircraft’s altitude using multi-modal sensors that measure variables such as velocities, accelerations, pressures, temperatures, and aircraft orientation and position. We demonstrate the selection of an optimal DL model and an increase of 88% in model accuracy compared to the other 11 DL approaches analyzed. Verification of the model selected shows that it outperforms pruned models on data from other aircraft with the same system of sensors.","PeriodicalId":169296,"journal":{"name":"2023 IEEE International Systems Conference (SysCon)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125419005","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":"Considerations for Cyber-Physical Design Teams Tasked with Engineering Safe and Secure Systems for a Notional Electrified Aircraft Concept","authors":"M. Span, L. Mailloux, J. Daily","doi":"10.1109/SysCon53073.2023.10131264","DOIUrl":"https://doi.org/10.1109/SysCon53073.2023.10131264","url":null,"abstract":"This work uses a systems thinking approach to investigate challenges associated with designing safe and secure Cyber-Physical Systems (CPS). First, a brief review the CPS security problem space is presented and the classic systems thinking Iceberg Model is used to perform root cause analysis exploring shortfalls in traditional CPS design teams. Next, the CPS design team construct is explored using a notional electrified aircraft vehicle concept to achieve ’Security by Design’ early in the concept analysis phase. This work uniquely offers recommendations to assist organizations, teams, and individuals preforming early conceptual analysis activities for CPSs. Issues such as team composition, prioritization of effort, and necessary knowledge, skills, and abilities (KSAs) are explored using the notional electrified aircraft concept.","PeriodicalId":169296,"journal":{"name":"2023 IEEE International Systems Conference (SysCon)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125771216","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":"Framework for Target Classification and Strategy Derivation during Production Ramp-up","authors":"Julian Haller, Sebastian Beckschulte, Marcos Padrón, Quoc Hao Ngo, R. Schmitt","doi":"10.1109/SysCon53073.2023.10131053","DOIUrl":"https://doi.org/10.1109/SysCon53073.2023.10131053","url":null,"abstract":"Production ramp-up is an integral part of a product's life cycle and a crucial phase for a product's successful launch in the market. A stable production system is required to predict behaviour of a production system with respect to achieving ramp-up targets. The aim of this work is to develop a qualitative framework for classifying ramp-up targets at a more granular level beyond the target framework of quality, cost, and time. Stability analysis is approached at a local level by reducing ramp-up's complexity through discretisation into time intervals. Each interval can be analysed for stability with respect to a set of targets and disturbance factors. The envisioned objective is to combine, operationalise, and prioritise competing targets and corresponding disturbance factors for evaluating and adapting stabilising ramp-up strategies. The framework is further developed for building description models of ramp-up stability in context of a research project.","PeriodicalId":169296,"journal":{"name":"2023 IEEE International Systems Conference (SysCon)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122136014","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":"Collaborative Edge-Cloud AI for IoT Driven Secure Healthcare System","authors":"Lav Gupta","doi":"10.1109/SysCon53073.2023.10131082","DOIUrl":"https://doi.org/10.1109/SysCon53073.2023.10131082","url":null,"abstract":"In healthcare applications like monitoring patients in ICUs and performing precision robotic surgeries, IoT and sensor networks have become indispensable. These sensors generate a large amount of data that, when processed and visually presented to a medical professional, assists in the more accurate diagnosis and treatment of ailments. For some time now, hospital administrations have been taking advantage of public cloud(referred to as main clouds in this paper) resources to store and process patient data using the advanced AI analytical tools that these clouds provide. However, taking all the medical sensor data to the main cloud encounters network congestion and latencies that may negatively impact the outcomes. In this situation the power of edge-AI may appear appealing, but the state-of-the-art does not allow all the tasks of training complex AI models and drawing inference from them to take place at the edge. Techniques of complexity reduction like pruning and quantization have been applied to reduce storage and processing burden, but they compromise accuracy of the models. Researchers now agree on the necessity of collaborative edge-main cloud AI for demanding workloads.It is, however, necessary to realize that the multi-layer IoT-Edge-Main Cloud arrangement has an expanded attack surface. Any malicious attack on the dataflows among various layers may threaten patients’ quality of life or even their lives. Although AI can be used to secure these dataflows, using large neural network models centrally on the main cloud results in long training and inference dispersion times. We propose a collaborative, hierarchically merged technique to help train large neural network models in real-time. This is achieved by synthesizing the main cloud model using the trained layers of the edge models, resulting in a dramatic reduction in the training times of the model in the main cloud while achieving high detection accuracy. As we shall see in the description, this method removes some of the problems faced with other collaborative methods, like federated learning, which works by disaggregating models for sharing training load.","PeriodicalId":169296,"journal":{"name":"2023 IEEE International Systems Conference (SysCon)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128210027","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":"Sleep Apnea Detection System Using Machine Learning on Resource-Constrained Devices","authors":"Sayani Mallick, Shubhangi K. Gawali, Clement Onime, Neena Goveas","doi":"10.1109/SysCon53073.2023.10131117","DOIUrl":"https://doi.org/10.1109/SysCon53073.2023.10131117","url":null,"abstract":"Sleep Apnea is a condition in which a person has pauses in breathing or very low breathing episodes during sleep. It is a condition that could prove life-threatening if not monitored and treated. A medical diagnosis of Sleep Apnea involves overnight recording of body signals, monitoring by a medical professional, use of hospital based equipment and data analysis for detection of anomalies. During the past decade, the measurement and analysis of human body signals using machine learning techniques on embedded devices have started to transform healthcare applications. The use of cost effective micro-controllers can ensure that health monitoring is available and accessible to all. In this paper, we show that machine learning models deployed on microcontrollers can successfully analyze ECG signals in real-time for Sleep Apnea detection. We have created TinyML models using TensorFlow Lite which we have deployed on cost effective and resource constrained devices like the Raspberry Pi Pico and ESP32. Our setup has given results comparable to more advanced and expensive devices for the detection of Sleep Apnea using ECG signals.","PeriodicalId":169296,"journal":{"name":"2023 IEEE International Systems Conference (SysCon)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127834334","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":"System for Continuous Multi-Dimensional Mobile Network KPI Tracking and Prediction in Drifting Environments","authors":"Hendrik Schippers, S. Böcker, C. Wietfeld","doi":"10.1109/SysCon53073.2023.10131079","DOIUrl":"https://doi.org/10.1109/SysCon53073.2023.10131079","url":null,"abstract":"The usage of public mobile radio networks is steadily increasing. At the same time, the number of new and future smart city applications that rely on reliable and fast mobile data connections based on public mobile networks is rising. In particular, mission-critical smart city applications require continuous and reliable mobile network connectivity. However, the fulfillment of KPIs is not given at all locations and varies over time. Thus, use-cases like tele-operated driving profit from and, in some cases, even depend on spatiotemporal connectivity data. Indirectly, connectivity data can also be utilized to calibrate and improve network planning approaches for future network technologies, such as classical ray tracing or innovative datadriven channel modeling approaches.Massive data acquisition is needed to cover vast city-wide areas like the city of Dortmund. Therefore, this paper discusses a system that enables a dedicated, continuous and systematic measurement campaign to solve this challenge. These measurements are realized by a fully automated open-source monitoring application deployed in multiple vehicles of the local waste disposal company, enabling continuous and city-wide data collection. The initial results of this measurement campaign indicate that up-to-date data is crucial for reliable data-driven services.","PeriodicalId":169296,"journal":{"name":"2023 IEEE International Systems Conference (SysCon)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117290531","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}