Proceedings of the 14th IEEE/ACM International Conference on Utility and Cloud Computing Companion最新文献

{"title":"Multi-path selection access algorithm and design of intelligent perception network model for blockchain-enabled CPSs","authors":"Qijie Qian, Yu'ao Wang, Hao She, Yongan Guo, Hongbo Sun","doi":"10.1145/3492323.3495575","DOIUrl":"https://doi.org/10.1145/3492323.3495575","url":null,"abstract":"Blockchain-enabled cyber-physical systems (CPSs) are developed to provide the mass of Intelligent Object Terminal Equipment (IOTE). However, they cannot deal with the real-time control problem of perception. Hence, this paper studies the multi-type access methods and multi-path selective access algorithm of intelligent end devices in the local area network. The algorithm is proposed based on the multi-terminal collaboration technology. This network model provides a basis for realizing real-time awareness and optimal resource scheduling of IOTE. The model effectively alleviates the problem of state loss of IOTEs in the current local area. The experimental results show that the network model can effectively control the location and state of the IOTE in real time.","PeriodicalId":440884,"journal":{"name":"Proceedings of the 14th IEEE/ACM International Conference on Utility and Cloud Computing Companion","volume":"35 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133796892","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 integrated approach for cloud computing service selection and cost estimation","authors":"Christian Plewnia","doi":"10.1145/3492323.3503505","DOIUrl":"https://doi.org/10.1145/3492323.3503505","url":null,"abstract":"Selecting suitable cloud services and estimating future cloud costs for organizations with a large set of software services is a challenging task. To achieve this, one needs to understand all software applications' cloud service configuration requirements. Further, one needs to estimate how the applications' requirements change over time, e.g., due to scaling with a growing number of application users. Then, one needs to compare for different cloud providers the costs over time of setups matching the requirements. This task, if done manually, is laborious, error prone, and has to be repeated when the organization's business or application requirements change. In my PhD project, I will research an integrated approach that assists users in, on the one hand, finding a cost-optimal selection of cloud services for given requirements and, on the other hand, estimating future costs. I want to achieve this with the support of a software tool integrating existing research on the individual topics and, thereby, allowing to apply and study existing cloud service selection and cost estimation approaches.","PeriodicalId":440884,"journal":{"name":"Proceedings of the 14th IEEE/ACM International Conference on Utility and Cloud Computing Companion","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122511375","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 urban sensing architecture as essential infrastructure for future cities","authors":"Vijay Kumar, G. Oikonomou, T. Tryfonas","doi":"10.1145/3492323.3503507","DOIUrl":"https://doi.org/10.1145/3492323.3503507","url":null,"abstract":"Climate change and migration have become one of the most challenging problems for our civilization. In this context, city councils work hard to manage essential services for citizens such as waste collection, street lamp lighting, and water supply. Increasingly, digitalization and the Internet of Things (IoT) help cities improve services, increase productivity and reduce costs. However, to understand how this may happen, we explore the urban sensing capabilities from citizen- to city-scale, how sensing at different levels is interlinked, and the challenges of managing innovations based on IoT data and devices. Local authorities collaborate with researchers and deploy testbeds as a part of demonstration and research projects to perform the above data collection, improve city services, and support innovation. The data gathered is about indoor and outdoor environmental conditions, energy usage, built environment, structural health monitoring. Such monitoring requires IT infrastructure at three different tiers: at the endpoint, edge, and cloud. Managing infrastructure at all tiers with provisioning, connectivity, security updates of devices, user data privacy controls, visualization of data, multi-tenancy of applications, and network resilience, is challenging. So, in turn, we focus on performing a systematic study of the technical and non-technical challenges faced during the implementation, management, and deployment of devices into citizens' homes and public spaces. Our third piece of work explores IoT edge applications' resiliency and reliability requirements that vary from non-critical (best delivery efforts) to safety-critical with time-bounded guarantees. We investigate how to meet IoT application mixed-criticality QoS requirements in multi-communication networks. Finally, to demonstrate the principles of our framework in the real world, we implement an open-source air quality platform Open City Air Quality Platform (OpenCAQP), that merges a wide range of data sources and air pollution parameters into a single platform. The OpenCAQP allows citizens, environmentalists, data analysts, and developers to access and visualize that data.","PeriodicalId":440884,"journal":{"name":"Proceedings of the 14th IEEE/ACM International Conference on Utility and Cloud Computing Companion","volume":"16 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120821782","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 privacy-preserving distributed platform for COVID-19 vaccine passports","authors":"M. Barati, W. Buchanan, O. Lo, O. Rana","doi":"10.1145/3492323.3495626","DOIUrl":"https://doi.org/10.1145/3492323.3495626","url":null,"abstract":"Digital vaccination passports are being proposed by various governments internationally. Trust, scalability and security are all key challenges in implementing an online vaccine passport. Initial approaches attempt to solve this problem by using centralised systems with trusted authorities. However, sharing vaccine passport data between different organisations, regions and countries has become a major challenge. A platform for creating, storing and verifying digital COVID-19 vaccine certifications is presented, making use of InterPlanetary File System (IPFS) to guarantee that there is no single point of failure and to allow data to be securely distributed globally. Blockchain and smart contracts are also integrated into the platform to explicitly determine policies and log access rights to the passport data while ensuring all actions are audited and verifiably immutable. Our proposed platform realises General Data Protection Regulation (GDPR) requirements in terms of user consent, data encryption, data erasure and accountability obligations. We assess the scalability and performance of the platform using IPFS and Blockchain test networks.","PeriodicalId":440884,"journal":{"name":"Proceedings of the 14th IEEE/ACM International Conference on Utility and Cloud Computing Companion","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129078259","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":"Session details: 2nd Workshop on Big Biomedical Data in Deep Learning Models (B2D2LM)","authors":"","doi":"10.1145/3517182","DOIUrl":"https://doi.org/10.1145/3517182","url":null,"abstract":"","PeriodicalId":440884,"journal":{"name":"Proceedings of the 14th IEEE/ACM International Conference on Utility and Cloud Computing Companion","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121349824","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":"Alcoholism detection via GLCM and particle swarm optimization","authors":"Jian Wang, Mackenzie Brown","doi":"10.1145/3492323.3495567","DOIUrl":"https://doi.org/10.1145/3492323.3495567","url":null,"abstract":"Alcoholism refers to the addiction to alcohol abuse from which lots of patients around the world suffer. Most of the patients with alcoholism cannot control themselves from consuming too much alcohol. Therefore, alcoholism could damage human bodies, including important organs like livers, eyes, especially brains. Scientists have observed through magnetic resonance imaging (MRI) on brains that the gray matter and white matter of alcoholism patients tend to decrease compared to normal healthy people. Based on this foundation, methods of alcoholism detection using computer-aided diagnosis techniques have been proposed in recent years. Unlike those methods like support vector machine (SVM) or convolutional neural networks (CNN), in this paper, we proposed a novel structure for alcoholism detection. Our structure applied gray level co-occurrence matrix (GLCM) as the feature extractor and adopted particle swarm optimization (PSO) training single-hidden-layer neural network as the classifier. It attained a sensitivity of 92.82±1.93%, a specificity of 91.31±1.71%, a precision of 91.35±1.47%, an accuracy of 92.06±0.87%, a F1 score of 92.06±0.89%, a MCC of 84.17±1.71%, and a FMI of 92.07±0.88%. Our proposed structure not only showed convincing performance via experiment datasets but also presented superiority of speed and simpleness to other strategies. It beat selected six state-of-the-art algorithms in almost every measure except for specificity and precision. From our perspective, our proposed structure for brain image classification is potential for similar fields and tasks.","PeriodicalId":440884,"journal":{"name":"Proceedings of the 14th IEEE/ACM International Conference on Utility and Cloud Computing Companion","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116171560","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 continuous blood glucose level using deep learning","authors":"Safiullah Shahid, Shujaat Hussain, W. A. Khan","doi":"10.1145/3492323.3495598","DOIUrl":"https://doi.org/10.1145/3492323.3495598","url":null,"abstract":"Diabetes is among the most common chronic diseases nowadays; in diabetes management control of blood glucose is essential. Significant attention has been paid to get the accurate prediction of diabetes. Various deep learning techniques are already proposed, such as multiple types of Neural Networks, SVR, LVX, ARX, LSTM models, and many more. The error rate of existing predicting models are very high. Error rate in prediction can cause several false positive notifications, which results in a decreasing the accuracy if the model. This study presented a hybrid model for predicting blood glucose levels based on two different kinds of neural networks CNN and GRU. The proposed model can predict blood glucose levels with leading accuracy of (MSE = 26.88 ± 17.87 [mg/dl] for 15 mins, MSE = 39.82 ± 22.19 [mg/dl] for 30 mins, MSE = , 66.33 ± 25.2 [mg/dl] for 60 mins) and (RMSE = 4.84 ± 1.83 [mg/dl] for 15 mins, RMSE = 6.04 ± 1.84 [mg/dl] for 30 mins, RMSE = 8.12 ± 1.46 [mg/dl] for 60 mins) on simulated T1D patient. The proposed model used CGM data and used extra features as input, like carbohydrates and insulin. The proposed model is then evaluated on 10 simulated patients of different ages generated using the UVA/Padova simulator.","PeriodicalId":440884,"journal":{"name":"Proceedings of the 14th IEEE/ACM International Conference on Utility and Cloud Computing Companion","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124294550","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":"Session details: 10th International Workshop on Cloud and Edge Computing, and Applications Management (CloudAM)","authors":"","doi":"10.1145/3517185","DOIUrl":"https://doi.org/10.1145/3517185","url":null,"abstract":"","PeriodicalId":440884,"journal":{"name":"Proceedings of the 14th IEEE/ACM International Conference on Utility and Cloud Computing Companion","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128299302","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":"Session details: International Workshop on Machine Learning and Health Informatics (MLHI)","authors":"","doi":"10.1145/3517187","DOIUrl":"https://doi.org/10.1145/3517187","url":null,"abstract":"","PeriodicalId":440884,"journal":{"name":"Proceedings of the 14th IEEE/ACM International Conference on Utility and Cloud Computing Companion","volume":"275 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115119438","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":"Scheduling ML training on unreliable spot instances","authors":"Sheng Yang, S. Khuller, Sunav Choudhary, S. Mitra, K. Mahadik","doi":"10.1145/3492323.3495594","DOIUrl":"https://doi.org/10.1145/3492323.3495594","url":null,"abstract":"Cloud providers rent out surplus computational resources as spot instances at a deep discount. However, these cheap spot instances are revocable. When demand surges for higher priced on-demand instances, cloud providers can interrupt these spot instances after a brief alert. Such unreliability makes it challenging to utilize spot instances for many long-running jobs. However, with checkpoints and restoration, machine-learning (ML) training jobs are a good candidate to overcome this difficulty. In this paper, we formalize the problem of scheduling ML-training jobs on transient spot instances, especially from an ML researcher's view, who may have some grant/credit for renting cloud computing services for several ML training tasks. Such a researcher would need to partition the computational resources wisely to maximize outcome (or total expected utility of all jobs) while maintaining some fairness between jobs. We investigate the trade-off between low-cost/interruptible and high-cost/uninterruptible computation, by proposing a linear-programming (LP) rounding based polynomial time algorithm. Based on the LP solution, we also give an LP-based heuristic that performs well in practice. We implement and evaluate these algorithms, and are able to achieve the same utility with 23% to 48% of the budget needed with on-demand instances. Moreover, the total utility we get is close to the theoretical upper bound under various settings, indicating close to optimal performance.","PeriodicalId":440884,"journal":{"name":"Proceedings of the 14th IEEE/ACM International Conference on Utility and Cloud Computing Companion","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133588751","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}