Delond Angelo Jimenez-Nixon, María Celeste Paredes-Sánchez, Alicia María Reyes-Duke
{"title":"Design, construction and control of a SCARA robot prototype with 5 DOF","authors":"Delond Angelo Jimenez-Nixon, María Celeste Paredes-Sánchez, Alicia María Reyes-Duke","doi":"10.1109/ICMLANT56191.2022.9996479","DOIUrl":"https://doi.org/10.1109/ICMLANT56191.2022.9996479","url":null,"abstract":"The SCARA robot is one of the most important robots and a standard in industrial robotics worldwide. Scara's are able to move with ease horizontally but have difficulties to move vertically. Given the characteristics of its workspace it's difficult for this robot to grow its range of applications as soon as significant height changes are required. One of the devised ways to overcome the height limitations found in the SCARA, is the addition of a fifth degree of freedom in its base. This research shows the robotic design in different CAD software, construction through additive and subtractive manufacturing, and control by means of mathematical models and programming of a SCARA robot prototype with five degrees of freedom. The experimental results demonstrate that, a fifth degree of freedom implemented in the base of a SCARA is a viable way to increase its vertical workspace. These results also demonstrate new capabilities for performance in new applications, higher versatility, economical installation and ease of adaptation to changes of location or application.","PeriodicalId":224526,"journal":{"name":"2022 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT)","volume":"333 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131459397","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}
{"title":"Analyzing Deficits in Awareness Among Chief Supply Chain Officers Who Have Not Adopted Cybersecurity as a Threat to Supply Chains","authors":"S. Muller","doi":"10.1109/ICMLANT56191.2022.9996456","DOIUrl":"https://doi.org/10.1109/ICMLANT56191.2022.9996456","url":null,"abstract":"This article addresses the lack of cybersecurity awareness addressing critical gaps in the managerial decision-making of Supply Chain Officers (SCO) at the executive level. Research suggests that C-Suite Level SCOs do not address technology integration and have not adopted cybersecurity as a threat to supply chains. This research seeks to understand the related level of alignment and how organizations can deploy a Cyber Supply Chain Risk Management (C-SCRM) strategy that goes beyond single companies' technical and internal functioning and moves beyond the dyad. A better alignment ultimately leads to improved cyber supply chain resilience. Several critical areas that threaten the supply chain are addressed for awareness. Recommendations are offered at the conclusion of the article for adoption and consideration.","PeriodicalId":224526,"journal":{"name":"2022 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131193881","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}
Fábio D. L. Coutinho, Hugerles S. Silva, P. Georgieva, Arnaldo S. R. Oliveira
{"title":"A Flexible CNN Architecture for Real-Time FPGA Implementation","authors":"Fábio D. L. Coutinho, Hugerles S. Silva, P. Georgieva, Arnaldo S. R. Oliveira","doi":"10.1109/ICMLANT56191.2022.9996537","DOIUrl":"https://doi.org/10.1109/ICMLANT56191.2022.9996537","url":null,"abstract":"In this paper, an optimized and flexible architecture for the convolutional neural networks (CNN) algorithms is proposed for real-time implementation in the field-programmable gate array (FPGA) platforms. In these networks, the convolutional layer is responsible for the high resource usage and the computational complexity. With our approach, the resource and complexity overheads are decreased keeping performance. Moreover, a flexible and fast framework is also introduced and described in this work, in which a hardware description language (HDL) tool is adopted to generate HDL code from the proposed behavioral CNN model. To the best of the author's knowledge, this is the first work in which a CNN architecture is implemented with an HDL tool, decreasing the overhead imposed by software and maintaining the clarity of the CNN structure. The obtained results show the feasibility of the proposed architecture in different scenarios considering the global performance measured by the mean-square error (MSE), resource reports, and timing requirements, in which the resources allocated in the FPGA are considerably reduced compared to a fully parallelized implementation.","PeriodicalId":224526,"journal":{"name":"2022 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT)","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124215928","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}
Vikram Puri, Aman Kataria, Vijender Kumar Solanki, Sita Rani
{"title":"AI-based botnet attack classification and detection in IoT devices","authors":"Vikram Puri, Aman Kataria, Vijender Kumar Solanki, Sita Rani","doi":"10.1109/ICMLANT56191.2022.9996464","DOIUrl":"https://doi.org/10.1109/ICMLANT56191.2022.9996464","url":null,"abstract":"End-user Internet of Things (IoT) devices, including security cameras, smart appliances, home monitors, and thermostats, are becoming more prevalent in households. Additionally, the proliferation of devices facilitates the propagation of security concerns like DoS and spoofing. However, it is difficult for conventional rule-based security systems to recognize IoT assaults due to the development of heterogenous devices in the IoT ecosystem. Artificial Intelligence (AI) techniques can be a solution which enables the creation of an effective security model based on actual data from each device. In this work, IoT botnets are detected and classified using machine learning (ML) and deep learning (DL) based algorithms. Six ML models and three DL models are used to assess the system's performance. The best-performing model is also implemented as an API.","PeriodicalId":224526,"journal":{"name":"2022 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123587361","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}
{"title":"Machine learning for telecoms: From churn prediction to customer relationship management","authors":"Farah Alhaqui, Mariam Elkhechafi, A. Elkhadimi","doi":"10.1109/ICMLANT56191.2022.9996496","DOIUrl":"https://doi.org/10.1109/ICMLANT56191.2022.9996496","url":null,"abstract":"The use of machine learning algorithms in churn prediction for telecom customers has shown its effectiveness in the last decades. Thus, uplift modeling, as a prescriptive analytic machine learning technique, may help telcos to reduce churn by setting up effective retention campaigns targeting only customers who are more suitable to be retained. In this paper, we compare three uplift models used in churn prediction contexts in three different sectors having many similarities to telecoms. Results gave some recommendations for building effective uplift models especially in terms of the quantity and quality of data sets. Therefore, the study also gave an empirical proof of uplift modeling being a good decision-making tool for customer relationship management.","PeriodicalId":224526,"journal":{"name":"2022 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122703605","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}
M. E. Perdomo, M. Cardona, Leonardo David Romero, Nayeli Sarahi Barnica
{"title":"State of the Art and Current Perception of Augmented Reality in Honduras","authors":"M. E. Perdomo, M. Cardona, Leonardo David Romero, Nayeli Sarahi Barnica","doi":"10.1109/ICMLANT56191.2022.9996462","DOIUrl":"https://doi.org/10.1109/ICMLANT56191.2022.9996462","url":null,"abstract":"The research was conducted on Augmented Reality (AR), its concept, its precedents, the fields of application in which it is presented, and the advantages it has at the time this technology is implemented. It also analyzes the implementation of AR in the world in various sectors such as education, medicine, and industry. The applications of augmented reality in Honduras were identified. And the factors why Honduras has not implemented AR are analyzed. AR is a human-computer interface design strategy aimed at enhancing a user's visual perception by superimposing computer graphics on the user's view. AR has a series of devices, and software, among other elements that operate as development tools making the experience with this reality more attractive. In the fields of application four areas stand out: Education, Textile, Marketing, and Manufacturing. By evaluating the sectors and fields where AR is applied worldwide, a comparison and analysis are made to define which would be the best option to develop this technology in the best way in Honduras.","PeriodicalId":224526,"journal":{"name":"2022 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123757680","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}
Julio Barzola-Monteses, Wendy Yánez-Pazmiño, Eduardo Flores-Morán, Franklin Parrales-Bravo
{"title":"Comparisons of Deep Learning Models to predict Energy Consumption of an Educational Building","authors":"Julio Barzola-Monteses, Wendy Yánez-Pazmiño, Eduardo Flores-Morán, Franklin Parrales-Bravo","doi":"10.1109/ICMLANT56191.2022.9996517","DOIUrl":"https://doi.org/10.1109/ICMLANT56191.2022.9996517","url":null,"abstract":"According to the latest United Nations Environment Programme report, in 2020, the construction and operation of buildings globally accounted for more than a third (36%) of final energy used and 37% of carbon dioxide emissions. This has given rise to research interest in energy efficiency in buildings in recent years, considering different approaches. In this work, black-box approaches based on bio-inspired techniques to predict the energy consumption of a university building are proposed. Three artificial neural network (ANN) architectures. Feed Forward Neural Network (FFNN) such as multilayer perceptron (MLP) and recurrent neural network (RNN) such as long short-term memory (LSTM), and gated recurrent unit (GRU). Three scenarios with different resolution timesteps and forecast horizons multi-step are tested for each architecture. The results according to the comparison of analyzed metric and computational execution times, the MLP model ranks first. These models can be very useful in predictive control systems considered in buildings to forecast the behavior of buildings' electric load in the short term with very good precision.","PeriodicalId":224526,"journal":{"name":"2022 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120967423","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}
{"title":"Robotics Platforms for Solar Tracking System: A Review","authors":"M. Cardona, Fernando E. Serrano","doi":"10.1109/ICMLANT56191.2022.9996509","DOIUrl":"https://doi.org/10.1109/ICMLANT56191.2022.9996509","url":null,"abstract":"In this paper it is shown basically the most important active solar tracking systems. It is reviewed the different types of solar tracking mechanisms based on robotics platforms which are classified basically in its degrees of freedom. In this paper are evinced first the state of the art regarding the design of novel trajectory tracking system explaining first how they are implemented and the frequency in which these mechanisms are implemented in different countries of the world while showing not only their configurations. Apart, it is explained the kinds of actuator that are commonly implemented in these mechanisms, for example direct current DC motors, permanent magnet motors, etc. Another issues that is mentioned in this study is the trajectory generation based on the solar path and how this variable changes according to the season of the year. Then the main results of this study are found in which it is explained how the dynamics of these mechanisms are obtained focused on four categories of this kind of mechanisms, which are horizontal 1-axis tracker, vertical 1-axis tracker, tip-tilt two axis tracker and azimuth altitude two axis tracker. Finally, as a contribution of this paper, an experimental simulation is performed for trajectory tracking purposes of this kind of mechanism by a proportional derivative controller in order to verify the closed loop system performance by tuning the gains with a gradient descent algorithm.","PeriodicalId":224526,"journal":{"name":"2022 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123506622","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}
M. E. Perdomo, M. Cardona, Denisse Melisa Castro, W. Mejia
{"title":"Literature Review on Artificial Intelligence Implementation in the Honduran Agricultural Sector","authors":"M. E. Perdomo, M. Cardona, Denisse Melisa Castro, W. Mejia","doi":"10.1109/ICMLANT56191.2022.9996484","DOIUrl":"https://doi.org/10.1109/ICMLANT56191.2022.9996484","url":null,"abstract":"Nowadays, many sectors have been faced with the need to achieve technological and automated processes, to keep up with the new trends and remain competitive. This study describes the beginnings of artificial intelligence (AI), its concept, branches, and applications. A general context is given about the different agricultural sectors in which the focus is on, in this case, the coffee, banana, oil palm, and cocoa sectors. The research was done on the diverse applications of AI in different countries and how it helped improve the processes of these sectors. To achieve this, an average of fifteen articles were taken into consideration for each sector investigated, to have a wide variety of information that will be able to validate the veracity of implementations. It was also possible to determine which countries have applied most of these technologies in their processes. As a result, Malaysia, a country in Southeast Asia, is the one that predominates the AI studies applied to agricultural sectors. In addition, the reasons why AI has not been applied to a large extent in the agricultural sectors in Honduras and the main reasons why this process has advanced relatively gradually are also investigated.","PeriodicalId":224526,"journal":{"name":"2022 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT)","volume":"186 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121731129","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}
M. Cardona, J. L. Ordoñez-Ávila, H. Moreno, Douglas Adalberto Aguilar, Marcial Ordoñez
{"title":"Wheels Statistical Analysis for Mobile Robots in Irregular Surface: Spring Stiffness Calculation","authors":"M. Cardona, J. L. Ordoñez-Ávila, H. Moreno, Douglas Adalberto Aguilar, Marcial Ordoñez","doi":"10.1109/ICMLANT56191.2022.9996486","DOIUrl":"https://doi.org/10.1109/ICMLANT56191.2022.9996486","url":null,"abstract":"Obtaining contact models that can optimize wheel design depends on certain variables such as impact velocity, material properties of the colliding bodies and geometric characteristics of the contact surfaces. These models can provide much in terms of stability for mobile robots. The aim of this research is to demonstrate that the wheel shape has significant impacts on the contact force calculating the spring stiffnes for linear hooke model. The method proposed is the obtention of data from simulations and a statistical analysis based on non parametric test to determine the contact force and the level penetration due to the geometry and material properties. As main result the spring stiffnes constant was approximate for different wheels geometry.","PeriodicalId":224526,"journal":{"name":"2022 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121526586","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}