2021 6th International Conference on Smart and Sustainable Technologies (SpliTech)最新文献_第4页

The use of Bluetooth Mesh Networking in IoT-aware Applications 蓝牙Mesh网络在物联网感知应用中的使用

2021 6th International Conference on Smart and Sustainable Technologies (SpliTech) Pub Date : 2021-09-08 DOI: 10.23919/SpliTech52315.2021.9566430

Ilaria Sergi, Teodoro Montanaro, Maria Carla Gammariello, L. Patrono

引用次数: 3

Deterministic Theory of Aerosol Displacement Before Dehydration as Vehicle of Virus in Outdoor Infections 室外感染中脱水前气溶胶置换作为病毒载体的确定性理论

2021 6th International Conference on Smart and Sustainable Technologies (SpliTech) Pub Date : 2021-09-08 DOI: 10.23919/splitech52315.2021.9566452

H. Nieto-Chaupis

{"title":"Deterministic Theory of Aerosol Displacement Before Dehydration as Vehicle of Virus in Outdoor Infections","authors":"H. Nieto-Chaupis","doi":"10.23919/splitech52315.2021.9566452","DOIUrl":"https://doi.org/10.23919/splitech52315.2021.9566452","url":null,"abstract":"As it is well-known aerosol is an important vehicle to transport strain of virus and produce an chain of infection among humans. Thus outdoor aerosol in conjunction to the lack of face protection is a first cause of infection by convid-19 at the ongoing pandemic. In this paper, a theory developed from deterministic grounds that might to model the dynamics of aerosol previous to its dehydration is presented. For this end some realistic assumptions that associates a concrete scenario of wind velocity and the potential events that would be cause of public infection are emphasized. The central point of this analysis is the assumption that the path that aerosol would opt at outdoor spaces is of deterministic character. Some distributions are assumed that model the trajectory of aerosol. The present analysis is done under a macroscopic view that discards physics effects in details at the aerosol aerodynamics. Essentially, attention is paid on that cases that wind velocity drives the trajectory and composition of aerosol. In this manner, results are derived entirely under a deterministic view. The obtained computational simulations derived from the designed model are in accordance with a previous work done entirely in a probabilistic framework.","PeriodicalId":119005,"journal":{"name":"2021 6th International Conference on Smart and Sustainable Technologies (SpliTech)","volume":"415 2-3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131536868","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

Deep Learning based Eye gaze estimation and prediction 基于深度学习的人眼注视估计与预测

2021 6th International Conference on Smart and Sustainable Technologies (SpliTech) Pub Date : 2021-09-08 DOI: 10.23919/SpliTech52315.2021.9566413

P. Mazzeo, Dilan D'Amico, P. Spagnolo, C. Distante

{"title":"Deep Learning based Eye gaze estimation and prediction","authors":"P. Mazzeo, Dilan D'Amico, P. Spagnolo, C. Distante","doi":"10.23919/SpliTech52315.2021.9566413","DOIUrl":"https://doi.org/10.23919/SpliTech52315.2021.9566413","url":null,"abstract":"Eye gaze understanding plays a crucial role in human social interactions. The gaze has emerged as a powerful tool for many applications including health assessment, disease diagnosis, human behavior, communication analysis. Eye gaze estimation and prediction has become a very hot topic in the field of computer vision during the last decades, with a surprising and continuously growing number of application fields. In the last decade deep neural networks have revolutionized the whole machine learning area, and gaze tracking. Appearance-based models use deep convolutional networks (CNNs) to directly estimate the direction of gaze in the camera's frame of reference. This paper focuses on analyzing and investigating different CNN architectures for gaze estimation and prediction. Two tasks have been developed in this work: the gaze estimation and the gaze prediction based on previously estimated gaze-points. In the first task, several CNNs were used for finding the most accurate gaze estimation. In the second task, we predict gaze locations basing on the previously estimated gaze vectors while leveraging spatio-temporal information encoded in a previously recorded eye-images sequences. We used a Long Short Term Memory (LSTM) and Transformers based on self-attention approach and use of positional encoding, in order to predict next gaze locations. Different architectures has been trained on the OPENEDS2020 public dataset which has been revisited in order to improve overall performance. We, also, propose a novel architecture composed by ResNext50 and two fully connected layer. We demonstrate that proposed architectures obtain results that in terms of angular error outperforms the state of art.","PeriodicalId":119005,"journal":{"name":"2021 6th International Conference on Smart and Sustainable Technologies (SpliTech)","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131550352","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: 5

Unit Cube Test for Double Surface Integrals in Frequency Domain Integral Equation Formulations 频域积分方程中二重曲面积分的单位立方检验

2021 6th International Conference on Smart and Sustainable Technologies (SpliTech) Pub Date : 2021-09-08 DOI: 10.23919/SpliTech52315.2021.9566347

M. Cvetković, D. Poljak, A. Kapetanović, Hrvoje Dodig

引用次数: 1

Machine Learning as Tag Estimation Method for ALOHA-based RFID system 基于aloha的RFID系统标签估计的机器学习方法

2021 6th International Conference on Smart and Sustainable Technologies (SpliTech) Pub Date : 2021-09-08 DOI: 10.23919/splitech52315.2021.9566455

Lea Dujić Rodić, I. Stančić, Kristina Zovko, P. Šolić

引用次数: 0

Effect of Steam Activation on Oil Shale Semi-coke Surface Properties 蒸汽活化对油页岩半焦表面性质的影响

2021 6th International Conference on Smart and Sustainable Technologies (SpliTech) Pub Date : 2021-09-08 DOI: 10.23919/SpliTech52315.2021.9566397

H. Pikkor, A. Konist, B. Maaten, Oliver Jörvik, H. Lees

引用次数: 0

The indicators of agricultural crops based on the remote sensing of the Earth (ERS) 基于地球遥感的农作物指标研究

2021 6th International Conference on Smart and Sustainable Technologies (SpliTech) Pub Date : 2021-09-08 DOI: 10.23919/splitech52315.2021.9566469

M. Sadenova, M. Rakhymberdina, N. Kulenova, A. Mamysheva, Z. Assylkhanova, J. Klemeš

引用次数: 0

Sustainable Platform for Environmental Changes in Smart City 智慧城市环境变化的可持续平台

2021 6th International Conference on Smart and Sustainable Technologies (SpliTech) Pub Date : 2021-09-08 DOI: 10.23919/SpliTech52315.2021.9566381

T. Ueda, T. Ogishi

{"title":"Sustainable Platform for Environmental Changes in Smart City","authors":"T. Ueda, T. Ogishi","doi":"10.23919/SpliTech52315.2021.9566381","DOIUrl":"https://doi.org/10.23919/SpliTech52315.2021.9566381","url":null,"abstract":"In the world of human evolution, species with excellent physical and brain abilities do not survive, but only species with attributes that can adapt to the environment at each specific trend can survive. Therefore, in this paper, we propose the future smart city concept and structure, based on mechanism in human evolution. Our proposed platform consists of, 1) “the large archive which consists of many different AI models”, and 2) “various trials and update of AI models”. Then, we deploy these two functions into three hierarchy, i.e. cloud stratum, MEC (Multi-access Edge Computing) stratum and Fog stratum. And these stratums should be nationwide common open platform. Consensus buildings are performed among the tracking and learning of Cloud stratum (wider & long-term in space-time zone), MEC (medium-term in space-time zone) and Fog (narrow & short-term in space-time zone) stratums. At the same time, according to the update of the currently used model, in cloud stratum, various trials are continuously operated in parallel, as background process. New AI models and modules are created, using the gathered historical data, the existing AI models and just finished AI modules. In addition, for this creation of new models, federated learning is carried out through AI, human control/knowledge and the social world. The federation/ensemble/transfer among the followings, bring about another mechanism of Human evolution: a) The large archive which consists of many different models, b) Various trials and update of models, c) Human knowledge/Intervention, and d) Social world (trend, opinion). If the existing models and modules can't cope with the big change, then the new model, which is the federation/ensemble/transfer of AI, human professional knowledge and social under the observed ongoing trend, appear. These federation/ensemble/transfer are effective for not only the adaptation to the new trend, but also the design of future smart city.","PeriodicalId":119005,"journal":{"name":"2021 6th International Conference on Smart and Sustainable Technologies (SpliTech)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127979523","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

Drone Interrogation (and its Low-Cost Alternative) in Backscatter Environmental Sensor Networks 后向散射环境传感器网络中的无人机探测(及其低成本替代方案)

2021 6th International Conference on Smart and Sustainable Technologies (SpliTech) Pub Date : 2021-09-08 DOI: 10.23919/SpliTech52315.2021.9566340

Emmanouil Andrianakis, G. Vougioukas, Evangelos Giannelos, Orestis Giannakopoulos, Georgios Apostolakis, Konstantinos Skyvalakis, A. Bletsas

{"title":"Drone Interrogation (and its Low-Cost Alternative) in Backscatter Environmental Sensor Networks","authors":"Emmanouil Andrianakis, G. Vougioukas, Evangelos Giannelos, Orestis Giannakopoulos, Georgios Apostolakis, Konstantinos Skyvalakis, A. Bletsas","doi":"10.23919/SpliTech52315.2021.9566340","DOIUrl":"https://doi.org/10.23919/SpliTech52315.2021.9566340","url":null,"abstract":"Due to its ultra-low-power and low-complexity character, backscatter radio technology has been recently employed in wireless sensor networks (WSNs). This work puts forth experimental study on drone (UAV)-based interrogation of a backscatter environmental WSN; the latter can measure various environmental attributes (e.g., soil moisture), assisting the farmers towards more productive and greener operation. Three backscatter radio architectures are experimentally compared: a) monostatic, where a single embedded software-defined radio (SDR) is used for illuminating the sensors, receiving and decoding the sensor-backscattered signal, b) bistatic illumination from a drone and c) bistatic illumination from a pedestrian; in the latter two architectures, a remote SDR received and processed the sensor-backscattered signals. For the specific small-scale sensor deployment, it was surprisingly found that the bistatic pedestrian illumination was roughly twice as effective compared to the bistatic drone illumination, which was again twice as effective compared to the mono static drone illumination. Safety issues relevant to low-altitude flights in the monostatic architecture were also raised. Future work will focus on larger-scale backscatter sensor deployments.","PeriodicalId":119005,"journal":{"name":"2021 6th International Conference on Smart and Sustainable Technologies (SpliTech)","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127395767","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

Generation of Non-Isolated Radial Configuration in Distributed Power Systems 分布式电力系统非隔离径向结构的产生

2021 6th International Conference on Smart and Sustainable Technologies (SpliTech) Pub Date : 2021-09-08 DOI: 10.23919/SpliTech52315.2021.9566424

Ê. R. Viana, A. S. Sousa, Ricardo de Andrade Lira Rabêlo

引用次数: 0