2021 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT)最新文献

Fruits classification by using machine learning - An experiment using popular approaches on local data 利用机器学习进行水果分类——在本地数据上使用流行方法的实验

2021 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT) Pub Date : 2021-12-16 DOI: 10.1109/ICMLANT53170.2021.9690537

Nguyen Vuong Thinh, A. N. T. Y. Nhi, Trinh Gia Huy, Nghi Hoang Khoa, N. Cam

引用次数: 1

Wearable Prototype Module for the Measurement of Explosive Gases in Underground Mining 井下爆炸性气体测量的可穿戴原型模块

2021 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT) Pub Date : 2021-12-16 DOI: 10.1109/ICMLANT53170.2021.9690533

F. Medina, Luis Patarroyo, Bryann Gutierrez, Jorge E. Espindola, Eduardo Avendaño Fernández

{"title":"Wearable Prototype Module for the Measurement of Explosive Gases in Underground Mining","authors":"F. Medina, Luis Patarroyo, Bryann Gutierrez, Jorge E. Espindola, Eduardo Avendaño Fernández","doi":"10.1109/ICMLANT53170.2021.9690533","DOIUrl":"https://doi.org/10.1109/ICMLANT53170.2021.9690533","url":null,"abstract":"Gas explosions including are one of the main causes of accidents in underground mining. Dangerous mixture of methane gas, coal dust, and, to a lesser extent, carbon dioxide are the gases that can cause explosions in underground mining environments. The worldwide regulations for underground work require for continuous monitoring of these gases to identify variations and alert miners inside tunnels. In recent years, wearable technology has become an option for monitoring, control, tracking, and safety of mining operations. This paper proposes a design of a wearable prototype module for the measurement of explosive gases in mining and alert the miners to take preventive actions. The module allows the measurement of methane gas and carbon dioxide and the generation of visual alerts in case of levels above those defined in the regulations. The prototype is designed under the premise of a compact device in their form factor, which results in comfort for the miner, and enables the possibility to record the levels of the gases in a real-time web service outside the mine.","PeriodicalId":127769,"journal":{"name":"2021 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129127866","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

Neural Transfer Learning For Vietnamese Sentiment Analysis Using Pre-trained Contextual Language Models 基于预训练语境语言模型的越南语情感分析神经迁移学习

2021 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT) Pub Date : 2021-12-16 DOI: 10.1109/ICMLANT53170.2021.9690554

An Pha Le, Tran Vu Pham, T. Le, Duy V. Huynh

引用次数: 2

Implementation of MPC and PID Control Algorithms to the Artificial Pancreas for Diabetes Mellitus Type 1 MPC和PID控制算法在1型糖尿病人工胰腺中的实现

2021 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT) Pub Date : 2021-12-16 DOI: 10.1109/ICMLANT53170.2021.9690529

Esther Matamoros-Alcivar, Tanya Ascencio-Lino, Rigoberto Fonseca, G. Villalba-Meneses, Andrés Tirado-Espín, Lorena Barona, D. Almeida-Galárraga

{"title":"Implementation of MPC and PID Control Algorithms to the Artificial Pancreas for Diabetes Mellitus Type 1","authors":"Esther Matamoros-Alcivar, Tanya Ascencio-Lino, Rigoberto Fonseca, G. Villalba-Meneses, Andrés Tirado-Espín, Lorena Barona, D. Almeida-Galárraga","doi":"10.1109/ICMLANT53170.2021.9690529","DOIUrl":"https://doi.org/10.1109/ICMLANT53170.2021.9690529","url":null,"abstract":"Type 1 Diabetes Mellitus (T1DM) patients live with the need for insulin replacement for life. Closed-loop therapies or Artificial Pancreas consist of a continuous subcutaneous insulin infusion pump, a continuous glucose monitoring sensor, and a control algorithm. It automatically adjusts insulin infusion in real time, functioning as a healthy pancreas would regulate glucose levels through the administration of hormones with little or no user input. The control algorithms widely used for artificial pancreas development are Model Predictive Control (MPC) and Proportional-Integral-Derivative (PID) and these are adapted to help TD1M patients to regulate their blood glucose levels.The development of the artificial pancreas has to consider disturbances such as meal intake and physical activity. These disturbances can be unannounced which can bring blood glucose levels down and cause hypoglycemia. Therefore, in this work, two control algorithms are compared facing meal intake and exercise to compensate for the effects of exercise and food and avoid hypoglycemia.","PeriodicalId":127769,"journal":{"name":"2021 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132719242","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: 4

Mathetamical Model Using Denavit-Hartenberg Algorithm For Kinematic Control of 12DOF Zoomorphic Robot 基于Denavit-Hartenberg算法的12DOF兽形机器人运动控制数学模型

2021 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT) Pub Date : 2021-12-16 DOI: 10.1109/ICMLANT53170.2021.9690549

Dennys Fernando Cantarero Urbina, Alicia María Reyes Duke

{"title":"Mathetamical Model Using Denavit-Hartenberg Algorithm For Kinematic Control of 12DOF Zoomorphic Robot","authors":"Dennys Fernando Cantarero Urbina, Alicia María Reyes Duke","doi":"10.1109/ICMLANT53170.2021.9690549","DOIUrl":"https://doi.org/10.1109/ICMLANT53170.2021.9690549","url":null,"abstract":"Walking zoomorphic robots have a great advantage compared to other types of mobile robots thanks to their structure and high adaptability in many areas, and it is thanks to this adaptability that it generates many possibilities of implementation but, due to their locomotion system they tend to be complex to develop since the use of various actuators for their movement and control is taken into account, so to solve these problems, the implementation of algorithms and mathematical models are used because that define the characteristics of the structure and of the various actions that must be taken into account to carry out a movement in a simplified and understandable way. The present research was carried out through the implementation of the spiral methodology for the development of a mathematical model that defines the kinematic control for this type of robot where, through both inverse and forward kinematic analysis, the position and orientation of the robot were described by applying the Denavit-Hartenberg algorithm, as well as the use of polynomial interpolators for the tracking of trajectories, which was verified by using Matlab and Robotics Toolbox software simulating movement that the robot will perform with the different extremities, determining said movement with the establishment of speeds and times in the joints.","PeriodicalId":127769,"journal":{"name":"2021 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124852653","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: 4

Computer vision neural network using YOLOv4 for underwater fish video detection In Roatan, Honduras 在洪都拉斯罗阿坦，使用YOLOv4的计算机视觉神经网络进行水下鱼类视频检测

2021 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT) Pub Date : 2021-12-16 DOI: 10.1109/ICMLANT53170.2021.9690561

Delond Angelo Jimenez Nixon

{"title":"Computer vision neural network using YOLOv4 for underwater fish video detection In Roatan, Honduras","authors":"Delond Angelo Jimenez Nixon","doi":"10.1109/ICMLANT53170.2021.9690561","DOIUrl":"https://doi.org/10.1109/ICMLANT53170.2021.9690561","url":null,"abstract":"Fish spawning aggregations (FSA) are groups of individuals of a specie that group for reproduction purposes. Studies show that globally fish species of commercial importance and their reproduction sites are decreasing at an alarming rate. In Honduras there is little information on these reproduction sites, marine biology analysts have determined that it is of crucial importance to monitor these sites.Obtaining video recordings of the FSA’s is vital to study and monitoring efforts, however it turns out to be very time consuming. This study proposes a neural network capable of the detection, classification, and counting of 11 fish species indicatives of reproductive activity at FSA. With this implementation it will be possible to dedicate more time to communication and socialization of the knowledge obtain to local authorities and fishermen, reduce personnel cost, and allow for the inclusion of innovative and technological solutions.Using the Incremental methodology, the Caribbean Fish database of 387 images is created for the training process of the neural network using YOLOv4 and Darknet as infrastructure and architecture respectively with an experimental approach. After 3 stages of training and testing, the object detector and classifier obtained a mAP of 88.1% and average retention of 80%. The network shows that is very capable of complying with the requirements of the monitoring process of fish reproduction sites through video recordings.","PeriodicalId":127769,"journal":{"name":"2021 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128990243","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: 9

Realtime Pipeline Fire & Smoke Detection Using a Lightweight CNN Model 使用轻量级CNN模型的实时管道火灾和烟雾检测

2021 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT) Pub Date : 2021-12-16 DOI: 10.1109/ICMLANT53170.2021.9690545

V. Kumar, Praveen Sankarasubramanian

引用次数: 2

Assessment of Machine Learning Models in Detecting DGA Botnet in Characteristics by TF-IDF 基于TF-IDF的机器学习模型在DGA僵尸网络特征检测中的评价

2021 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT) Pub Date : 2021-12-16 DOI: 10.1109/ICMLANT53170.2021.9690546

Tong Anh Tuan, Nguyen Viet Anh, Hoang Viet Long

引用次数: 1

A Load Power Distribution Optimization based on Improving Biogeography-Based Optimization 基于改进生物地理学优化的负荷分配优化

2021 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT) Pub Date : 2021-12-16 DOI: 10.1109/ICMLANT53170.2021.9690539

Trong-The Nguyen, Trinh-Dong Nguyen, Truong-Giang Ngo, Thi-Kien Dao

引用次数: 0

Generative Adversarial Network Design for Data Augmentation for Copro-parasite Images 共生寄生虫图像数据增强的生成对抗网络设计

2021 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT) Pub Date : 2021-12-16 DOI: 10.1109/ICMLANT53170.2021.9690544

Miguel Gutierrez-Velazquez, M. I. Chacon-Murguia, J. Ramirez-Quintana, C. Arzate-Quintana, Alma D Corral-Saenz

引用次数: 0