2023 IEEE International Conference on Omni-layer Intelligent Systems (COINS)最新文献

筛选
英文 中文
Optimal Fractional Order PID Control of Sensorless BLDC Motor 无传感器无刷直流电机的最优分数阶PID控制
2023 IEEE International Conference on Omni-layer Intelligent Systems (COINS) Pub Date : 2023-07-23 DOI: 10.1109/COINS57856.2023.10189249
Amir Atef F. H, Roba Abdelfatah, A. Madbouly, M. Samy, BAHAA-ALDEEN M. ABO-ALNAGA, R. Shalaby
{"title":"Optimal Fractional Order PID Control of Sensorless BLDC Motor","authors":"Amir Atef F. H, Roba Abdelfatah, A. Madbouly, M. Samy, BAHAA-ALDEEN M. ABO-ALNAGA, R. Shalaby","doi":"10.1109/COINS57856.2023.10189249","DOIUrl":"https://doi.org/10.1109/COINS57856.2023.10189249","url":null,"abstract":"This paper presents the implementation of a Fractional Order PID (FOPID) controller for regulating the angular speed of a Brushless DC (BLDC) sensorless motor. The controller is optimized using the Flower Pollination Algorithm and Genetic Algorithm (GA) to determine the optimal values for the fractional order system parameters and PID parameters of the controller. A comparison between the results obtained from FOPID and PID controllers is conducted, focusing on the strengths of FOPID in terms of rising time, overshoot, and settling time when controlling the angular speed of the BLDC motor. The simulation results unequivocally demonstrate that FOPID is the optimal choice for angular speed control, yielding a satisfactory transient response, particularly with regards to the critical rising time aspect, which holds significance across a wide range of applications involving BLDC motors.","PeriodicalId":328385,"journal":{"name":"2023 IEEE International Conference on Omni-layer Intelligent Systems (COINS)","volume":"111 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":"124112988","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}
引用次数: 0
Suitability of Forward-Forward and PEPITA Learning to MLCommons-Tiny benchmarks 前向和PEPITA学习对mlcommons的适用性-微小基准
2023 IEEE International Conference on Omni-layer Intelligent Systems (COINS) Pub Date : 2023-07-23 DOI: 10.1109/COINS57856.2023.10189239
D. Pau, F. M. Aymone
{"title":"Suitability of Forward-Forward and PEPITA Learning to MLCommons-Tiny benchmarks","authors":"D. Pau, F. M. Aymone","doi":"10.1109/COINS57856.2023.10189239","DOIUrl":"https://doi.org/10.1109/COINS57856.2023.10189239","url":null,"abstract":"On-device learning challenges the restricted memory and computation requirements imposed by its deployment on tiny devices. Current training algorithms are based on backpropagation which requires storing intermediate activations to compute the backward pass and to update the weights into the memory. Recently “Forward-only algorithms” have been proposed as biologically plausible alternatives to backpropagation. At the same time, they remove the need to store the intermediate activations which potentially lower the power consumption due to memory read and write operations, thus, opening to new opportunities for further savings. This paper investigates quantitatively the improvements in terms of complexity and memory usage brought by PEPITA and Forward-Forward computing approaches with respect to backpropagation on the MLCommons-Tiny benchmarks set as case studies. It was observed that the reduction in activations' memory provided by “Forward-only algorithms” does not affect total RAM in Fully-connected networks. On the other hand, Convolutional neural networks benefit the most from such reduction due to lower parameters-activations ratio. In the context of the latter, a memory-efficient version of PEPITA reduces, on average, one third of the total RAM with respect to backpropagation, introducing only a third more complexity. Forward-Forward brings average memory reduction to 40%, and it involves additional computation at inference that, depending on the benchmarks studied, can be costly on micro-controllers.","PeriodicalId":328385,"journal":{"name":"2023 IEEE International Conference on Omni-layer Intelligent Systems (COINS)","volume":"16 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":"128990264","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}
引用次数: 1
Decentralized Machine Learning on a Blockchain: Case Studies 区块链上的分散机器学习:案例研究
2023 IEEE International Conference on Omni-layer Intelligent Systems (COINS) Pub Date : 2023-07-23 DOI: 10.1109/COINS57856.2023.10189230
Xiaohui Liu
{"title":"Decentralized Machine Learning on a Blockchain: Case Studies","authors":"Xiaohui Liu","doi":"10.1109/COINS57856.2023.10189230","DOIUrl":"https://doi.org/10.1109/COINS57856.2023.10189230","url":null,"abstract":"Our approach involves utilizing smart contracts on a blockchain to enhance transparency and collaboration in machine learning. To achieve this, we integrate machine learning with blockchain technology. We showcase four practical examples of this approach in action through real-world case studies. Furthermore, we offer free and open source implementation of these case studies on the Bitcoin SV blockchain.","PeriodicalId":328385,"journal":{"name":"2023 IEEE International Conference on Omni-layer Intelligent Systems (COINS)","volume":"8 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":"117029213","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}
引用次数: 0
Comparison of 2D and 3D LiDARs Trajectories and AMCL Positioning in ROS-Based move_base Navigation 基于ros的move_base导航中二维和三维lidar轨迹和AMCL定位的比较
2023 IEEE International Conference on Omni-layer Intelligent Systems (COINS) Pub Date : 2023-07-23 DOI: 10.1109/COINS57856.2023.10189271
Shi-Peng Chen, Cheng-Yu Peng, Guo-Shing Huang, Chun C. Lai, Chi-Chun Chen, Meng-Hua Yen
{"title":"Comparison of 2D and 3D LiDARs Trajectories and AMCL Positioning in ROS-Based move_base Navigation","authors":"Shi-Peng Chen, Cheng-Yu Peng, Guo-Shing Huang, Chun C. Lai, Chi-Chun Chen, Meng-Hua Yen","doi":"10.1109/COINS57856.2023.10189271","DOIUrl":"https://doi.org/10.1109/COINS57856.2023.10189271","url":null,"abstract":"This paper compares the performance of 2D and 3D LiDAR in terms of trajectory and AMCL localization using the ROS 1 Kinetic system architecture. First, 2D and 3D LiDAR are used to scan maps, generate COST MAP and TF coordinates, and perform route planning. Then, 2D and 3D LiDAR are used for map scanning and localization, and finally, move_base is used for local and global automatic navigation for path planning, obstacle avoidance, and trajectory. The study also compares the differences between path planning, 2D and 3D trajectories. In the experiment, auto-guidance is performed for 10 positions and its accuracy is discussed, including the RMS error of the actual spatial origin and the RMS error of the AMCL coordinates positioning, and the obstacle avoidance is analyzed for the 1-point position. The results show that the use of 3D LiDAR in the ROS-based move_base navigation system can achieve better performance in positioning and path planning.","PeriodicalId":328385,"journal":{"name":"2023 IEEE International Conference on Omni-layer Intelligent Systems (COINS)","volume":"61 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":"121617593","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}
引用次数: 0
A Holistic Blockchain Architecture for IoT Systems: Design Considerations and Challenges 物联网系统的整体区块链架构:设计考虑和挑战
2023 IEEE International Conference on Omni-layer Intelligent Systems (COINS) Pub Date : 2023-07-23 DOI: 10.1109/COINS57856.2023.10189237
Siddarth Banerjee, N. Ramanathan, Ragul Kumar
{"title":"A Holistic Blockchain Architecture for IoT Systems: Design Considerations and Challenges","authors":"Siddarth Banerjee, N. Ramanathan, Ragul Kumar","doi":"10.1109/COINS57856.2023.10189237","DOIUrl":"https://doi.org/10.1109/COINS57856.2023.10189237","url":null,"abstract":"This paper introduces an IoT Blockchain platform that encompasses a new decentralized consensus protocol named Proof of Real-time Transfer (PoRT) that addresses the challenges of privacy, security, scalability and storage in IoT systems. PoRT protocol preserves privacy by conferring decentralized identities to every entity in its ecosystem, encrypts data at source and preserves data integrity and authenticity using digital signatures. PoRT adopts a novel construct for blockchain storage that places no hard requirements on universal state, rather imparts tamper resistance through cryptographic sortition driven sub-chain replication across the network. Nodes maintains three local chains namely, a main chain, a custody chain and a log chain. While the main chain comprises blocks validated by the node and the log chain saves summary of services rendered, the custody chain comprises random segments of the main chain and the log chain from across the network. The above construct is highly scalable, is leaderless, and yields instant finality and tamper resistance to chains. PoRT combines the powers of cryptographic sortition and Kademlia DHTs in running behavioral audits placing the onus on the platform delivering on its data storage promises. Finally, this paper discusses newer challenges to tackle with formalized solutions in the space","PeriodicalId":328385,"journal":{"name":"2023 IEEE International Conference on Omni-layer Intelligent Systems (COINS)","volume":"80 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":"122285321","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}
引用次数: 0
Predicting Asset Returns with Self-Attentive Networks 用自关注网络预测资产收益
2023 IEEE International Conference on Omni-layer Intelligent Systems (COINS) Pub Date : 2023-07-23 DOI: 10.1109/COINS57856.2023.10189288
Qianru Qi, Zhili Gong
{"title":"Predicting Asset Returns with Self-Attentive Networks","authors":"Qianru Qi, Zhili Gong","doi":"10.1109/COINS57856.2023.10189288","DOIUrl":"https://doi.org/10.1109/COINS57856.2023.10189288","url":null,"abstract":"Predictor interactions play a crucial role in esti-mating risk premiums. However, current methodologies might not effectively and understandably address this. Inspired by the broad success of the self-attention mechanism, we develop an attention-based asset pricing model in this paper, which we'll refer to as AAPM. This model, utilizing several stacked multi-head self-attention blocks, can efficiently capture high-order factor interactions. Empirical evidence suggests that our model surpasses all other machine learning models studied in relevant finance literature in terms of out-of-sample R2. Interestingly, our model, despite having fewer predictors, outperforms its original version that incorporates all predictors as input. We attribute this phe-nomenon to negative factor interactions that detrimentally affect the latter's result. Moreover, we identify critical predictor bundles using our model. Our results demonstrate substantial economic benefits to investors and offer a novel perspective in empirical asset pricing literature.","PeriodicalId":328385,"journal":{"name":"2023 IEEE International Conference on Omni-layer Intelligent Systems (COINS)","volume":"512 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":"131175502","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}
引用次数: 0
Personalized Seizure Detection Using Spiking Neural Networks 使用脉冲神经网络的个性化癫痫检测
2023 IEEE International Conference on Omni-layer Intelligent Systems (COINS) Pub Date : 2023-07-23 DOI: 10.1109/COINS57856.2023.10189269
Xavante Erickson, S. Bastani, A. Aminifar
{"title":"Personalized Seizure Detection Using Spiking Neural Networks","authors":"Xavante Erickson, S. Bastani, A. Aminifar","doi":"10.1109/COINS57856.2023.10189269","DOIUrl":"https://doi.org/10.1109/COINS57856.2023.10189269","url":null,"abstract":"Around 50 million people worldwide suffer from Epilepsy, making it one of the most common neurological diseases. Epilepsy is characterized by sudden intermittent seizures, often imposing profound social and physical limitations. More importantly, the risk of premature death in these patients is up to three times that of the corresponding healthy population. It is estimated that 30% of the population with epilepsy is at risk of severe trauma, or premature death, despite currently available treatments. Smart wearable systems could mitigate many of the risks associated with epilepsy and seizures by providing early warnings for the patients and caretakers to take precautions. However, wearable systems are highly constrained in terms of resources and, therefore, are generally unable to utilize modern machine learning, due to their limited computing power, memory storage, and energy/battery budget. To address this issue, in this paper, we consider personalized seizure detection by adopting spiking neural networks, which are known to be efficient in terms of energy. Our experimental results demonstrate that our personalized spiking neural networks are on par with their artificial neural network counterparts in terms of performance, reaching a sensitivity of 78.8 % and a specificity of 76.9 %.","PeriodicalId":328385,"journal":{"name":"2023 IEEE International Conference on Omni-layer Intelligent Systems (COINS)","volume":"138 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":"132580223","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}
引用次数: 0
Towards Sustainable Energy Communities: Local Optimization of Battery Usage in P2P Energy Trading 迈向可持续能源社区:P2P能源交易中电池使用的局部优化
2023 IEEE International Conference on Omni-layer Intelligent Systems (COINS) Pub Date : 2023-07-23 DOI: 10.1109/COINS57856.2023.10189231
C. Groß, F. Gehring, O. Bringmann
{"title":"Towards Sustainable Energy Communities: Local Optimization of Battery Usage in P2P Energy Trading","authors":"C. Groß, F. Gehring, O. Bringmann","doi":"10.1109/COINS57856.2023.10189231","DOIUrl":"https://doi.org/10.1109/COINS57856.2023.10189231","url":null,"abstract":"As renewable energy resources are integrated into the power grid to address the global energy and climate crisis, local energy markets have emerged as a possible solution. In such markets, peers in a smart grid trade locally generated energy. To reduce the stress on the grid caused by the volatility of renewable energy sources, households use electric batteries to maximize their self-consumption of generated energy. In this paper, we propose a peer-to-peer trading platform that integrates batteries into the distributed energy management trading system. We show that local optimization of single households not only benefits the individual households in terms of increased self-consumption and financial gains but also has an overall positive impact on the energy community compared to a simple battery implementation.","PeriodicalId":328385,"journal":{"name":"2023 IEEE International Conference on Omni-layer Intelligent Systems (COINS)","volume":"22 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":"114903871","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}
引用次数: 0
Emergent Outcomes of the veToken Model veToken模型的紧急结果
2023 IEEE International Conference on Omni-layer Intelligent Systems (COINS) Pub Date : 2023-07-23 DOI: 10.1109/COINS57856.2023.10189201
Thomas Lloyd, Daire O'Broin, Martin Harrigan
{"title":"Emergent Outcomes of the veToken Model","authors":"Thomas Lloyd, Daire O'Broin, Martin Harrigan","doi":"10.1109/COINS57856.2023.10189201","DOIUrl":"https://doi.org/10.1109/COINS57856.2023.10189201","url":null,"abstract":"Decentralised organisations use blockchains as a basis for governance: they use on-chain transactions to allocate voting weight, publish proposals, cast votes, and enact the results. However, blockchain-based governance structures have challenges, mostly notably, the need to align the short-term outlook of pseudononymous voters with the long-term growth and success of the decentralised organisation. The Vote-Escrowed Token (veToken) model attempts to resolve this tension by requiring voters to escrow or lock tokens of value for an extended period in exchange for voting weight. In this paper, we describe the veToken model and analyse its emergent outcomes. We show that voting behaviour follows bribes set by higher-level protocols, and that the cost per vote varies depending on how it is acquired. We describe the implementation of the veToken model by Curve Finance, a popular automated market maker for stablecoins, and the ecosystem of protocols that has arisen on top of this implementation. We show that voting markets such as Votium largely determine the outcome of fortnightly votes held by Convex Finance, and we show that Frax Finance, a stablecoin issuer, plays a central role in the ecosystem even though they directly lock relatively few tokens with Curve. Instead, they indirectly lock tokens through yield aggregators such as Convex Finance and purchase voting weight through voting markets such as Votium. Although the veToken model in isolation is straight-forward and easily explained, it leads to many complex and emergent outcomes. Decentralised organisations should consider these outcomes before adopting the model.","PeriodicalId":328385,"journal":{"name":"2023 IEEE International Conference on Omni-layer Intelligent Systems (COINS)","volume":"46 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":"132048971","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}
引用次数: 0
IEEE COINS 2023 Committee IEEE硬币2023委员会
2023 IEEE International Conference on Omni-layer Intelligent Systems (COINS) Pub Date : 2023-07-23 DOI: 10.1109/coins57856.2023.10189275
{"title":"IEEE COINS 2023 Committee","authors":"","doi":"10.1109/coins57856.2023.10189275","DOIUrl":"https://doi.org/10.1109/coins57856.2023.10189275","url":null,"abstract":"","PeriodicalId":328385,"journal":{"name":"2023 IEEE International Conference on Omni-layer Intelligent Systems (COINS)","volume":"186 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":"132263949","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}
引用次数: 0
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信
小红书