2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)最新文献_第10页

Conformal Wearable for Quantification of Dorsiflexion for a Hemiplegic Ankle Pair with Distinction by Machine Learning 基于机器学习区分的适形可穿戴设备对偏瘫踝关节的背屈量进行量化

2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA) Pub Date : 2021-12-01 DOI: 10.1109/ICMLA52953.2021.00212

R. LeMoyne, Timothy Mastroianni

{"title":"Conformal Wearable for Quantification of Dorsiflexion for a Hemiplegic Ankle Pair with Distinction by Machine Learning","authors":"R. LeMoyne, Timothy Mastroianni","doi":"10.1109/ICMLA52953.2021.00212","DOIUrl":"https://doi.org/10.1109/ICMLA52953.2021.00212","url":null,"abstract":"Dorsiflexion of the ankle serves a critical role for the functionality of gait with regards to both the swing phase and stance phase. Hemiparesis can adversely influence the ability to conduct dorsiflexion of the ankle. Inertial sensor systems have been successfully demonstrated for objectively quantifying the disparity of a hemiplegic limb pair, which can be readily visualized. The gyroscope signal provides a kinematic representation that is clinically recognizable. These achievements to visualize through inertial sensors and distinguish by machine learning classification constitute an advance for the progressive rehabilitation for the ability to dorsiflex a hemiplegic affected ankle relative to the unaffected ankle. Conformal wearable and wireless inertial sensor systems that are inherently flexible can be readily be mounted about the dorsum of the ankle for quantifying dorsiflexion of the ankle based on the gyroscope signal. Wireless access to Cloud computing enables a convenient and remote means for signal data storage. The signal data can be consolidated to a feature set for machine learning classification to distinguish between a hemiplegic affected ankle and unaffected ankle pair. Using a multilayer perceptron neural network considerable machine learning classification accuracy is attained for distinguishing between dorsiflexion for a hemiplegic affected ankle and unaffected ankle. The amalgamation of conformal wearables, Cloud computing access, and machine learning imply the opportunity to conduct at home therapy with highly augmented clinical acuity for an optimal rehabilitation experience.","PeriodicalId":6750,"journal":{"name":"2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"47 1","pages":"1307-1310"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91202934","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

Federated Fuzzy Learning with Imbalanced Data 不平衡数据下的联邦模糊学习

2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA) Pub Date : 2021-12-01 DOI: 10.1109/ICMLA52953.2021.00185

Lukas Johannes Dust, Marina López Murcia, Andreas Mäkilä, Petter Nordin, N. Xiong, Francisco Herrera

引用次数: 3

Kernel Factorisation Machines 核分解机

2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA) Pub Date : 2021-12-01 DOI: 10.1109/ICMLA52953.2021.00278

Francois Buet-Golfouse, Islam Utyagulov

{"title":"Kernel Factorisation Machines","authors":"Francois Buet-Golfouse, Islam Utyagulov","doi":"10.1109/ICMLA52953.2021.00278","DOIUrl":"https://doi.org/10.1109/ICMLA52953.2021.00278","url":null,"abstract":"This paper explores a generalisation of factorisation machines via kernels, which we call Kernel Factorisation Machines (“KFM”). It is well-known that functions in reproducing kernel Hilbert spaces can be understood as a linear combination of features in very high-dimensional (or infinite-dimensional) spaces while being computed in a finite-dimensional space, thanks to the representer theorem. Simultaneously, it has been shown recently that the dot product operation was a key component behind the success of a number of recommender systems, while the recent literature has been preoccupied with enriching factorisation machines. There is thus a need for a framework able to interpolate between factorisation machines that tend to outperform other techniques on sparse datasets and more advanced models that perform well on large and dense datasets. One of the drawbacks of kernel methods is their high dimensionality when the number of observations is large, which is typical of recommender systems. It is thus extremely important to be able to reduce the dimensionality, which we do in two different ways: first, we find a representation of the input features in a lower-dimensional space, and, second, we consider inducing points, i.e., surrogate inputs that are optimised upon training to avoid building (kernel) interactions between each pair of observations in the dataset. In short, we propose a method that adapts kernels to the set up of high-dimensional and potentially sparse datasets. To illustrate our approach, we test it on four well-known datasets and benchmark its results against most available models. While comparisons are difficult and should be interpreted carefully, KFM is able to perform well and obtains the best performance overall. Our methodology is not limited to recommender systems and can be applied to other settings, which we illustrate on a heart disease classification task.","PeriodicalId":6750,"journal":{"name":"2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"91 1","pages":"1755-1760"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83966726","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

Mood detection ontology integration with teacher context 情绪检测本体与教师语境的集成

2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA) Pub Date : 2021-12-01 DOI: 10.1109/ICMLA52953.2021.00272

Nader N. Nashed, Christine Lahoud, Marie-Hélène Abel, F. Andrès, Bernard Blancan

{"title":"Mood detection ontology integration with teacher context","authors":"Nader N. Nashed, Christine Lahoud, Marie-Hélène Abel, F. Andrès, Bernard Blancan","doi":"10.1109/ICMLA52953.2021.00272","DOIUrl":"https://doi.org/10.1109/ICMLA52953.2021.00272","url":null,"abstract":"Recommender systems in education improve the teacher’s working process by providing relevant resources to aid his course design in addition to learning new teaching methodologies. However, these systems have limited adaptability according to a global evaluation of teacher’s activities. This approach of user profiling is convenient, but not adequate for teacher’s context description. In our approach, it is assumed that the utilization of teacher’s emotions has an inevitable role to accomplish a full contextual description for teacher. Teacher context ontology (TCO) provides a representation for the teacher’s living and working contexts along with the main educational concepts. In this paper, we introduce a conceptual integration approach between Moodflow@doubleYou emotional data as a concept and TCO ontology. Furthermore, we intend to prove the importance of integrating such concept for sufficient teacher’s context description. The impact of utilization emotional data in educational recommender systems is discussed. Finally, this paper represents the conducted experiments’ results which show the advantage of such integration.","PeriodicalId":6750,"journal":{"name":"2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"11 1","pages":"1710-1715"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88324988","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

A Machine Learning Approach for Predicting Deterioration in Alzheimer’s Disease 预测阿尔茨海默病恶化的机器学习方法

2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA) Pub Date : 2021-12-01 DOI: 10.1109/ICMLA52953.2021.00232

H. Musto, D. Stamate, Ida M. Pu, Daniel Stahl

引用次数: 4

Catch Weight Prediction for Multi-Species Fishing using Artificial Neural Networks 基于人工神经网络的多物种捕捞重量预测

2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA) Pub Date : 2021-12-01 DOI: 10.1109/ICMLA52953.2021.00248

Tianbai Chen, Li Zhong, Naweiluo Zhou, Dennis Hoppe

{"title":"Catch Weight Prediction for Multi-Species Fishing using Artificial Neural Networks","authors":"Tianbai Chen, Li Zhong, Naweiluo Zhou, Dennis Hoppe","doi":"10.1109/ICMLA52953.2021.00248","DOIUrl":"https://doi.org/10.1109/ICMLA52953.2021.00248","url":null,"abstract":"Due to the increasing demand for fish consumption, sustainable fishery become more and more challenging. To prevent from overfishing, massive data in open sea fishing have been collected and analyzed to achieve efficient management of fishery. Still, it is extremely difficult for fishers and fishery managers to exploit available data for accurate prediction, because of their limited data processing capacities, and the overall lack of adequate database systems [1].The goal of this work is therefore to analyze the relationship between data collected from all sensors installed on-board fishing vessels and catch weight, to better support generating a map showing likely fishing effort allocation. To do so, we train neural networks to predict catch weight using all available data from sensors on fishing vessels. The raw data are pre-processed using random sampling techniques to be fed into a neural network for training. A multi-layer perceptron (MLP) neural network is proposed as the baseline. We propose a data augmentation method and a training strategy in order to optimize the prediction accuracy of the model. Our data augmentation method conducts random sampling of the original data multiple times, which reduces the root mean square error (RMSE) by 15.8%, as compared with the results obtained by the model trained without data augmentation. Our training strategy works well to further optimize the prediction accuracy of the model trained with an augmented dataset, which significantly decreased the RMSE by 11. 2%. To the best of our knowledge, this is the first study on the catch weight prediction using neural networks.","PeriodicalId":6750,"journal":{"name":"2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"38 1","pages":"1545-1552"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77116984","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

A Physics-Informed Graph Attention-based Approach for Power Flow Analysis 一种基于物理信息图的潮流分析方法

2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA) Pub Date : 2021-12-01 DOI: 10.1109/ICMLA52953.2021.00261

Ashkan B. Jeddi, A. Shafieezadeh

{"title":"A Physics-Informed Graph Attention-based Approach for Power Flow Analysis","authors":"Ashkan B. Jeddi, A. Shafieezadeh","doi":"10.1109/ICMLA52953.2021.00261","DOIUrl":"https://doi.org/10.1109/ICMLA52953.2021.00261","url":null,"abstract":"Risk-informed management of power grids requires accurate and computationally efficient power flow analysis. However, existing methods for solving power flow problems are computationally inefficient considering the many simulations needed to quantify uncertainties in system performance. This work presents a novel physics-informed graph attention-based method for power flow analysis in power transmission systems. We employ a graph attention network (GAT) based architecture which leverages the self-attention mechanism. As a result, structural information of a graph is learned and utilized to implicitly consider the importance of nodes in the graph. Through the integration of the GAT model, the power flow analysis is efficient and applicable to inductive learning problems where the model has to generalize to a priori unseen power grids. Furthermore, the physics-based knowledge of the power flow analysis is directly implemented by enforcing minimization of the violation of Kirchhoff’s law at each bus during training. To illustrate the performance of the proposed model, well-known IEEE power grid testbeds, namely, case9, case14, case30, and case118 are selected and the graph attention-based model is tested and compared with state-of-the-art methods. The result of these analyses indicates the efficacy of the physics-informed graph attention-based approach in achieving a superior accuracy and less computational cost. Furthermore, the robustness of the proposed model to the variations in power grid topology is demonstrated. Therefore, it shows a reliable performance in inductive learning problems.","PeriodicalId":6750,"journal":{"name":"2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"48 1","pages":"1634-1640"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80299928","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: 7

Improved Deep Representation Learning for Human Activity Recognition using IMU Sensors 基于IMU传感器的人类活动识别改进深度表示学习

2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA) Pub Date : 2021-12-01 DOI: 10.1109/ICMLA52953.2021.00057

Niall Lyons, Avik Santra, Ashutosh Pandey

引用次数: 5

Character-level Adversarial Examples in Arabic 阿拉伯语字符级对抗示例

2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA) Pub Date : 2021-12-01 DOI: 10.1109/ICMLA52953.2021.00010

Basemah Alshemali, J. Kalita

引用次数: 0

Threshold-free Anomaly Detection for Streaming Time Series through Deep Learning 基于深度学习的流时间序列无阈值异常检测

2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA) Pub Date : 2021-12-01 DOI: 10.1109/ICMLA52953.2021.00285

Jing Zhang, Chao Wang, Zezhou Li, Xianbo Zhang

引用次数: 0