2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI)最新文献_第3页

A Multimodal Deep Learning Approach to Emotion Detection and Identification 情感检测与识别的多模态深度学习方法

2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 2022-05-25 DOI: 10.1109/SACI55618.2022.9919496

Satya Chandrashekhar Ayyalasomayajula, B. Ionescu, Mircea Trifan, D. Ionescu

{"title":"A Multimodal Deep Learning Approach to Emotion Detection and Identification","authors":"Satya Chandrashekhar Ayyalasomayajula, B. Ionescu, Mircea Trifan, D. Ionescu","doi":"10.1109/SACI55618.2022.9919496","DOIUrl":"https://doi.org/10.1109/SACI55618.2022.9919496","url":null,"abstract":"Automated emotion recognition and identification and its subsequent challenges have a long history. More recently, intense scientific research on computer based evaluation of human emotions has arrived at a crossroad. Reputable scientists in the cognitive science domain consider that the system built on Ekman's seven basic emotions is vitiated by generalizations obtained on a reduced number of test cases. In contrast, computer scientists consider that the progress made so far in the theory and application of Neural Networks allows computers to increase the accuracy of emotion detection and identification. A Multimodal Convolutional Neural Network (MMCNN) for emotion detection and identification in near real-time, will be introduced in this paper. The MMCNN detects, identifies and tracks users' emotions, by reasoning on facial micro-expressions, on body motions and on speech. A CNN classifies the emotion into one of the 7 universal classes accepted so far. The deciding classifier then takes the scores generated from both the micro-expression detector and speech synthesizer to predict the emotion. The emotion class is validated using the Berkeley Expressivity Questionnaire. Results on testing the accuracy of the algorithm are given at the end of this paper.","PeriodicalId":105691,"journal":{"name":"2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132301653","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

On cost-effective strategies for opinion diffusion in complex networks 复杂网络中意见传播的成本效益策略研究

2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 2022-05-25 DOI: 10.1109/SACI55618.2022.9919571

Alexandru Topîrceanu, M. Udrescu

{"title":"On cost-effective strategies for opinion diffusion in complex networks","authors":"Alexandru Topîrceanu, M. Udrescu","doi":"10.1109/SACI55618.2022.9919571","DOIUrl":"https://doi.org/10.1109/SACI55618.2022.9919571","url":null,"abstract":"Better understanding of diffusion dynamics in complex networks is of notable scientific and social interest, since it allows predicting, controlling, and delaying information, innovation, or even epidemics. The most effective strategy for fast and impactful opinion dissemination is to use social agents to diffuse and indoctrinate neighboring peers, be it online or offline. Although these agents imply a real-world cost of operation, there is limited literature on the trade-offs between diffusion performance and incurred costs. Our study incorporates a cost awareness model into the classic linear threshold opinion diffusion model and studies the effect of variable network topology, number of spreaders, and spreader active time (i.e., injection strategies). By performing detailed discrete event simulations on several types of network topologies, we uncover a set of general rules for a cost-effective approach in targeting real-world scenarios of influence maximization. Specifically, we determine that a constant opinion injection incurs costs of up to 80% higher than intermittent injection, that increasing the number of spreaders results in a polynomial increase in the cost of operation, and that irregular (random, preferential attachment) topologies imply diffusion costs of up to 3 times higher than regular topologies.","PeriodicalId":105691,"journal":{"name":"2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125777933","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

Parameter estimation from realistic experiment scenario using artificial neural networks 基于人工神经网络的真实实验场景参数估计

2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 2022-05-25 DOI: 10.1109/SACI55618.2022.9919464

Melánia Puskás, Borbála Gergics, Alexander Ládi, D. Drexler

{"title":"Parameter estimation from realistic experiment scenario using artificial neural networks","authors":"Melánia Puskás, Borbála Gergics, Alexander Ládi, D. Drexler","doi":"10.1109/SACI55618.2022.9919464","DOIUrl":"https://doi.org/10.1109/SACI55618.2022.9919464","url":null,"abstract":"One of the promising directions in future medicine is the optimization of therapies based on mathematical and engi-neering methods, with which the treatment can be personalized. In personalization, the key issue is the identification of the model parameters. We carry out the identification using artificial neural networks, which require training. We generate training data that is as realistic as possible, by generating sparse training datasets. We aim to simulate realistic experimental setups that also take the presence of holidays into account, when the drug injection and tumor volume measurement are not possible. We generate several smaller training datasets and their different versions, to determine how many times the parameters can change every week for the proper functioning of neural networks and to examine how the networks can give a proper estimate of the time-varying parameters from sparse measurements. In this research two different types of training datasets will be introduced to train artificial neural network. The training data are generated on known parameter intervals, taking into consideration the experimental setup we use to validate our results. The estimated parameters can be used to track the change of the parameters and personalize the model for optimization algorithms.","PeriodicalId":105691,"journal":{"name":"2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123852953","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: 3

Considerations Regarding The Perturb And Observe Method To Control High-Power Wind Systems Operating At Variable Wind Speeds

2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 2022-05-25 DOI: 10.1109/SACI55618.2022.9919526

C. Șorândaru, S. Musuroi, Mihaela-Codruta Ancuti, R. Ancuti, Alin Marius Stanciu, Meda Alexandra Lazar

{"title":"Considerations Regarding The Perturb And Observe Method To Control High-Power Wind Systems Operating At Variable Wind Speeds","authors":"C. Șorândaru, S. Musuroi, Mihaela-Codruta Ancuti, R. Ancuti, Alin Marius Stanciu, Meda Alexandra Lazar","doi":"10.1109/SACI55618.2022.9919526","DOIUrl":"https://doi.org/10.1109/SACI55618.2022.9919526","url":null,"abstract":"In this study, the situations in which the Perturb and Observe Method (POM) can be used to determine the points in which the wind turbine operates at maximum power were examined. Among them, the points in which there are large fluctuations in wind speed over time were taken into consideration. The performance of management systems in wind power plants operating at variable wind speeds is determined using data received through measurements (wind speed values). The control systems based on the Perturb and Observe Method were analyzed and compared with the ones based PI-type (proportional-integrator) regulators, resulting in that the first ensures the wind turbine operates in the optimal area from the energy point of view. The conditions under which the Perturb and Observe Method can be applied have been determined here. The maximum power point coordinates (MPP) were also estimated. The connection between the optimal mechanical angular velocity and the wind speed was used to assess the quality of the adjustment. In this case, the obtained results were based on experimental data from the wind turbines in the Dobrogea area. The optimum area from the energy point of view is determined by changing the load of the electric generator and therefore, the new coordinates of the maximum power point of the turbine are estimated, e.g. the maximum power value and the optimal mechanical angular velocity.","PeriodicalId":105691,"journal":{"name":"2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124203000","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

The Dependence Between Power of the Electric Generator and Variable Wind Speed 发电机功率与变风速的关系

2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 2022-05-25 DOI: 10.1109/SACI55618.2022.9919592

Antonio-Marius-Flavius Luputi, M. Babescu, H. Ciocarlie

引用次数: 0

Semantic automatization of the data-analytical processes 数据分析过程的语义自动化

2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 2022-05-25 DOI: 10.1109/SACI55618.2022.9919438

P. Bednar, Juliana Ivančáková, M. Sarnovský

引用次数: 1

Monte Carlo Tree Search to Compare Reward Functions for Reinforcement Learning 蒙特卡洛树搜索比较奖励函数的强化学习

2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 2022-05-25 DOI: 10.1109/SACI55618.2022.9919518

Bálint Kövári, Bálint Pelenczei, Tamás Bécsi

引用次数: 0

NoSQL Performance Analysis in Android Apps Android应用中的NoSQL性能分析

2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 2022-05-25 DOI: 10.1109/SACI55618.2022.9919443

Eduard Gumbinger, M. Marcu

引用次数: 0

Load Comparison Between Two Controlling Strategies for Wind Energy Conversion System Power-Boosting 风能转换系统功率增压两种控制策略的负荷比较

2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 2022-05-25 DOI: 10.1109/SACI55618.2022.9919466

D. Bordeasu, O. Proștean, C. Vașar, Ali Debeş

{"title":"Load Comparison Between Two Controlling Strategies for Wind Energy Conversion System Power-Boosting","authors":"D. Bordeasu, O. Proștean, C. Vașar, Ali Debeş","doi":"10.1109/SACI55618.2022.9919466","DOIUrl":"https://doi.org/10.1109/SACI55618.2022.9919466","url":null,"abstract":"This paper explains in detail the development, validation and simulation of a standard PI controller that can boost the WECS (Wind energy conversion system) power through two strategies. In the first strategy, the power is boosted by increasing the generator angular velocity through the direct increase of the angular velocity of the wind turbine rotor by slightly pitching the blades. In the second strategy, the power is boosted by increasing the load torque of the generator, through the direct increase of the load torque of the wind turbine rotor. For achieving this goal, the following tasks have been accomplished: a wind energy conversion system nonlinear mathematical model has been developed, a gain scheduled proportional-integral (PI) controller as the baseline controller, and two gain scheduled proportional-integral (PI) power-boosting controllers for the two power-boosting strategies. For the power-boosting controllers, it is also presented a logic that switches between baseline and power booster controllers when certain wind speeds conditions are met. The response, stability, performance and the increase in the shaft torsion, tower and blades bending moments of the gain scheduled PI power-boosting controllers have been compared with the baseline controller. By comparing the output power response of the controllers, it can be seen that the power booster controllers boost the power when the defined conditions are met. Finally, for boosting the power of a WECS in certain conditions the most efficient way is by increasing the generator load torque, because this strategy increases the least the loading of the main components of a WECS. This power boosting strategy implementation it might require the change (or reinforcement) of the drive train shaft, if it cannot take the extra loading created by power boosting controller.","PeriodicalId":105691,"journal":{"name":"2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117018727","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

New Ways of Exploring Connections Between Cultural Heritage Objects 探索文物之间联系的新途径

2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 2022-05-25 DOI: 10.1109/SACI55618.2022.9919495

Peter Smatana, T. Sabol, J. Hreno, P. Bednar, M. Smatanova

{"title":"New Ways of Exploring Connections Between Cultural Heritage Objects","authors":"Peter Smatana, T. Sabol, J. Hreno, P. Bednar, M. Smatanova","doi":"10.1109/SACI55618.2022.9919495","DOIUrl":"https://doi.org/10.1109/SACI55618.2022.9919495","url":null,"abstract":"This paper describes PLUGGY platform which is the first European social platform for cultural heritage and its extension the Smart Discovery tool. These tools were developed to bring culture closer to a wider public audience. After decades of digitization of cultural heritage objects there are several initiatives to present all these data in a meaningful, engaging and educational way. Most of the time these digital libraries present content only in searchable list format without meaningful interpretation. PLUGGY platform tries to fill this gap with a set of authoring and presentation tools. These tools allow creation of a wide variety of virtual exhibitions and narrative stories linked to the content from the digital libraries or user's uploaded content. We are extending PLUGGY with the Smart Discovery tool for the simplification of the curatorial process. It is a visualization, modelling and recommendation tool for the elimination of a cognitive load of art curators. The tool allows to model relationships between cultural heritage objects. During the modelling process the tool recommends related concepts aggregated from multiple external art content libraries. Created models can be transformed to the different types of virtual exhibitions skeletons ready for further PLUGGY curation.","PeriodicalId":105691,"journal":{"name":"2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"26 11","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131491767","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