2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI)最新文献_第7页

Improving Students’ Performance by Interpretable Explanations using Ensemble Tree-Based Approaches 使用基于集成树的方法通过可解释的解释来提高学生的表现

2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 2021-05-19 DOI: 10.1109/SACI51354.2021.9465558

Alexandra Vultureanu-Albisi, C. Bǎdicǎ

{"title":"Improving Students’ Performance by Interpretable Explanations using Ensemble Tree-Based Approaches","authors":"Alexandra Vultureanu-Albisi, C. Bǎdicǎ","doi":"10.1109/SACI51354.2021.9465558","DOIUrl":"https://doi.org/10.1109/SACI51354.2021.9465558","url":null,"abstract":"The careful analysis and evaluation of students’ results are an important part of the educational activity, with a potentially strong impact on the students’ future development. Seven classification algorithms, which are Decision Tree, Bagging, Random Forest, AdaBoost, Gradient Boosting, XGBoost, and LightGBM, were used in this research. In this paper, for our experiments we used two datasets, the first refers to classify and predict Portuguese language performance and the second for students’ level at courses. In this paper, we propose to identify the most appropriate classification technique to improve the prediction of students’ performance, interpreting it using the LIME algorithm. The obtained results using both datasets show that the model built using Decision Tree, outperforms the other constructed models. Our methodology consists of four major steps: i) analyzing and preprocessing the dataset; ii) optimizing the models using cross-validation and hyperparameter tuning; iii) comparing the performance of different ensemble tree-based models, and iv) interpreting the model by providing explanations. The development of explainable models can lead to important advantages: the model can be trusted, the transparency of the model helps to understand the underlying mechanisms that make the model work and opaque models can be interpreted without sacrificing their predictive performance.","PeriodicalId":321907,"journal":{"name":"2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127333946","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: 6

Human Computer Interaction Feedback Based-On Data Visualization Using MVAR and NN 基于MVAR和NN数据可视化的人机交互反馈

2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 2021-05-19 DOI: 10.1109/SACI51354.2021.9465564

J. Olszewska

引用次数: 1

Performance Comparison between S3, HDFS and RDS storage technologies for real-time big-data applications S3、HDFS和RDS存储技术在实时大数据应用中的性能比较

2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 2021-05-19 DOI: 10.1109/SACI51354.2021.9465594

Alaa Jamal, Rita Fleiner, E. Kail

引用次数: 1

An Emotional Topic Recommendation Chat Assistant 一个情感话题推荐聊天助手

2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 2021-05-19 DOI: 10.1109/SACI51354.2021.9465626

Xiao zhuhanling

引用次数: 1

Analysis of Monetary Policy Decisions of the National Bank of Romania with Text Mining Techniques 用文本挖掘技术分析罗马尼亚国家银行的货币政策决策

2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 2021-05-19 DOI: 10.1109/SACI51354.2021.9465639

Cristian Pop, R. Precup, Liviu Ioan Cadariu-Brailoiu

引用次数: 0

Multi-Constrained Voronoi-Based Task Allocator for Smart-Warehouses 基于多约束voronoi的智能仓库任务分配器

2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 2021-05-19 DOI: 10.1109/SACI51354.2021.9465629

George S. Oliveira, P. Plentz, J. T. Carvalho

{"title":"Multi-Constrained Voronoi-Based Task Allocator for Smart-Warehouses","authors":"George S. Oliveira, P. Plentz, J. T. Carvalho","doi":"10.1109/SACI51354.2021.9465629","DOIUrl":"https://doi.org/10.1109/SACI51354.2021.9465629","url":null,"abstract":"Multi-robot systems consist of a set of robots working together to achieve a common goal. In these systems, two types of problems are widely addressed: the multi-robot path planning (MPP) and the multi-robot task allocation (MRTA). While the first one consists of finding the best path between two points in the space, the second one consists of allocating tasks to the robots, meeting restrictions, and completing one or more general objectives. The objectives are usually related to time optimization and energy consumption. The constraints require attention because they impact the complexity of the problem and reduce the system’s performance. Smart warehouses are an important example of application in which these problems are relevant. In such applications, the picking and shipping products control happens in an automated way, and mobile robots completely operate them. The literature shows that few studies explore integrated MPP and MRTA strategies to solve task allocation restrictions in smart warehouses. The main contribution of this paper is to present an integrated MRTA and MPP approach for smart warehouses by using static, seasonal, and dynamic information. Static information is provided by fixed obstacles, battery level, and load capacity of the robots. Seasonal information comes from products’ location and availability of them in a given period. The dynamic information corresponds to battery consumption and dynamic obstacles. In this paper a Multi-Constraints Voronoi-based Task Allocator (MCVB-TA) is presented. Its implementation incorporates a variation of the Voronoi diagram to allocate robots to the nearest tasks according to constraints, robots, and the environment. The simulation results obtained show that the proposed solution considerably reduces the time and energy cost of executing tasks in a smart warehouse scenario compared to a regular scheduler.","PeriodicalId":321907,"journal":{"name":"2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130099978","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 CNN Applied to Speech-to-Text – Comparative Analysis of Different Gradient Based Optimizers CNN在语音转文本中的应用——不同梯度优化器的比较分析

2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 2021-05-19 DOI: 10.1109/SACI51354.2021.9465635

Theodora Gaiceanu, O. Pastravanu

{"title":"On CNN Applied to Speech-to-Text – Comparative Analysis of Different Gradient Based Optimizers","authors":"Theodora Gaiceanu, O. Pastravanu","doi":"10.1109/SACI51354.2021.9465635","DOIUrl":"https://doi.org/10.1109/SACI51354.2021.9465635","url":null,"abstract":"In this paper the authors have developed a Convolutional Neural Network architecture adapted to Speech-to-Text research field. This type of network has been chosen due to its capacity to extract the relevant features and its popularity in classification problems. A particular model for a Speech-to-Text application has been designed. The parameters of the model (i.e. the size of filters and kernels), and the number of the layers have been chosen by conducting appropriate experiments, and the model that ensured the highest accuracy has been selected. The model takes raw waveforms of spoken digits as input, and outputs a text with the predicted digit. The network is capable of providing the right digit no matter the gender or age of the speaker. The overfitting has been avoided by using Dropout layers and early stopping function. In order to select the best model, the authors have taken into account two basic criteria: the accuracy of the model, and the execution time, respectively. Considering the computational time, the first order cost function has been chosen. By testing different gradient descent optimization algorithms, the best optimizer has been selected. The application has been developed using Python programming language.","PeriodicalId":321907,"journal":{"name":"2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125059775","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

AI vs AI (Augmenting [Human] Intellect vs Artificial Intelligence) : Plenary Talk AI vs AI(增强[人类]智力vs人工智能):全体会议演讲

2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 2021-05-19 DOI: 10.1109/SACI51354.2021.9465578

F. Filip

引用次数: 2

Investigation of High-Growth Firms in the SME sector via the Perspective of Owners and CEOs using Wordclouds 基于业主和ceo视角的中小企业高成长企业研究

2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 2021-05-19 DOI: 10.1109/SACI51354.2021.9465560

Ferenc Tolner, G. Eigner, Balázs Barta, M. Takács

引用次数: 1

A CNN Approach to Micro-Expressions Detection 基于CNN的微表情检测方法

2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 2021-05-19 DOI: 10.1109/SACI51354.2021.9465542

Satya Chandrashekhar Ayyalasomayajula, B. Ionescu, D. Ionescu

{"title":"A CNN Approach to Micro-Expressions Detection","authors":"Satya Chandrashekhar Ayyalasomayajula, B. Ionescu, D. Ionescu","doi":"10.1109/SACI51354.2021.9465542","DOIUrl":"https://doi.org/10.1109/SACI51354.2021.9465542","url":null,"abstract":"Machine Learning and Convolutional Neural Networks (CNN) have significantly increased the performance in image recognition and are being widely adopted to analyze faces based on availability of very large databases of Figure and postures. A hot research interest of the the Face Recognition community is the recognition of different types of facial expressions. Among these, Facial Micro-Expressions (ME’s) are of big interest due to subtle movements which can show deep or suppressed emotions of an individual. These micro-expressions are quite prominently being used in security, psychotherapy, neuroscience and other related disciplines. The major challenge encountered while detecting these expressions are their low intensity and short duration. Previous works have used Eulerian Video Magnification (EVM) in conjunction with haar-cascades for face detection which gave misleading results. In this paper, we have proposed a special Convolutional Neural Network (CNN) model for face detection on which EVM is applied for amplifying the micro-expressions to a calculated threshold. Following that, a separately trained CNN is used to classify the formerly detected micro-expression into one of the seven universal micro expressions. Results obtained during the test experiment are presented at the end of the paper.","PeriodicalId":321907,"journal":{"name":"2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"135 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124603330","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: 2