Category: publication

A4.6: Publication “Designing a Competency-Focused Course on Applied AI Based on Advanced System Research on Business Requirements”

A4.6: Publication “Designing a Competency-Focused Course on Applied AI Based on Advanced System Research on Business Requirements”

The publication disseminating WP4 has been published in Applied Sciences.

Below is the link

https://www.mdpi.com/2076-3417/14/10/4107

Abstract

The consortium of “The Future is in Applied Artificial Intelligence” Project designed the first competency-based applied artificial intelligence curriculum at the higher-education institution level. The development was based on advanced system research on existing artificial intelligence-related resources and surveying target groups of teachers, information technology students, and employers, which should enhance the performance of implementing artificial intelligence education. A review of applied artificial intelligence was prepared in the form of keyword clustering. The initial data were collected with the help of surveying by identifying job offers, existing artificial intelligence training courses, scientific projects, and real cases. A synthetic analysis of the textual information from the studies was conducted using the word clouds technique. A tensor-based approach was used for the presentation of the competency-based course. The specific numerical requirements for the course in the form of priorities followed from the solution to decision-making problems using the analytic hierarchy process technique. Based on a comprehensive study of surveys, educational experience, scientific projects, and business requirements, and a meta-analysis of the recent references, we specified the criteria for a training course in the form of a tensor-based representation of competencies in relation to content and educational modules.

 

A5.6: Publication on advanced neural network models

A5.6: Publication on advanced neural network models

The work has been published in a top-ranked journal “IEEE Transactions on Neural Networks and Learning Systems”

The link is below

https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10479223

 

The title: On Model of Recurrent Neural Network on a Time Scale: Exponential Convergence and Stability Research

Abstract:

The majority of the results on modeling recurrent neural networks (RNNs) are obtained using delayed differential equations, which imply continuous time representation. On the other hand, these models must be discrete in time, given their practical implementation in computer systems, requiring their versatile utilization across arbitrary time scales. Hence, the goal of this research is to model and investigate the architecture design of a delayed RNN using delayed differential equations on a time scale. Internal memory can be utilized to describe the calculation of the future states using discrete and distributed delays, which is a representation of the deep learning architecture for artificial RNNs. We focus on qualitative behavior and stability study of the system. Special attention is paid to taking into account the effect of the time-scale parameters on neural network dynamics. Here, we delve into the exploration of exponential stability in RNN models on a time scale that incorporates multiple discrete and distributed delays. Two approaches for constructing exponential estimates, including the Hilger and the usual exponential functions, are considered and compared. The Lyapunov–Krasovskii (L–K) functional method is employed to study stability on a time scale in both cases. The established stability criteria, resulting in an exponential-like estimate, utilizes a tuple of positive definite matrices, decay rate, and graininess of the time scale. The models of RNNs for the two-neuron network with four discrete and distributed delays, as well as the ring lattice delayed network of seven identical neurons, are numerically investigated. The results indicate how the time scale (graininess) and model characteristics (weights) influence the qualitative behavior, leading to a transition from stable focus to quasiperiodic limit cycles.

This work was supported in part by the Erasmus + Program for Education of the European Union through the Key Action 2 Grant (the Future Is in Applied Artificial Intelligence) under Grant 2022-1-PL01-KA220-HED000088359 (work package 5: “Piloting,” activity A5.6 “Project deliverables”)

Article of UCM Team on Motion Recognition Using a Transformer Model and LIDAR Sensor

Article of UCM Team on Motion Recognition Using a Transformer Model and LIDAR Sensor

Within framework of WP4, the UCM team of the project FAAI has published the paper “Playing Flappy Bird Based on Motion Recognition Using a Transformer Model and LIDAR Sensor” in Sensors MDPI.  The authors study a good practice using a transformer neural network which is employed in order to predict Q-values in a simulated environment using reinforcement learning techniques. The goal is to teach an agent to navigate and excel in the Flappy Bird game, which became a popular model for control in machine learning approaches. Unlike most top existing approaches that use the game’s rendered image as input, our main contribution lies in using sensory input from LIDAR, which is represented by the ray casting method.
Going forward, the authors aim to apply this approach in real-world scenarios.

The link to the paper is https://doi.org/10.3390/s24061905

Iva Kostadinova,Georgi Dimitrov,Paulina Tsvetkova,Katia Rasheva-Yordanova,Pepa Petrova, Research and Analysis of IT Specifications of Good Practices in the Area of Artificial Intelligence, 2023, 2023 International Conference on Advanced Technologies, Systems and Services in Telecommunications, TELSIKS 2023Pages 284 – 2902016 16th International Conference on Advanced Technologies, Systems and Services in Telecommunications, TELSIKS 2023Nis25 October 2023through 27 October 2023. ISBN 979-835034702-9, DOI 10.1109/TELSIKS57806.2023.10316145

Iva Kostadinova,Georgi Dimitrov,Paulina Tsvetkova,Katia Rasheva-Yordanova,Pepa Petrova, Research and Analysis of IT Specifications of Good Practices in the Area of Artificial Intelligence, 2023, 2023 International Conference on Advanced Technologies, Systems and Services in Telecommunications, TELSIKS 2023Pages 284 – 2902016 16th International Conference on Advanced Technologies, Systems and Services in Telecommunications, TELSIKS 2023Nis25 October 2023through 27 October 2023. ISBN 979-835034702-9, DOI 10.1109/TELSIKS57806.2023.10316145

This article is a contribution within the Erasmus+ project titled “The Future Lies in Applied Artificial Intelligence” (FAAI) and examines research of collected IT specifications of good practices in Area of Artificial Intelligence (AAI). The article describes research conducted, the purpose of which is to find IT specifications of good practices in AI and describe their characteristics, like an area of implementation of the AI solution, the result of processing the data, the source of data, Data processing, and quality, what tools are used for processing data, and others. AAI application cases and the technologies used for implementation are reviewed. The specifics of the data and the applications used are described. The examination of these technologies will provide insight into which ones are favored and provide an overview of what is commonly referred to as “best practices” in this particular domain.

Best practices in applied artificial intelligence, 2023 – Research and Analysis of IT Specifications of Good Practices in the Area of Artificial Intelligence

Best practices in applied artificial intelligence, 2023 – Research and Analysis of IT Specifications of Good Practices in the Area of Artificial Intelligence

This article is a contribution within the Erasmus+ project titled “The Future is in Applied Artificial Intelligence” (FAAI) and examines research of collected IT specifications of good practices in Area of Artificial Intelligence (AAI). The article describes research conducted, the purpose of which is to find IT specifications of good practices in AI and describe their characteristics, like an area of implementation of the AI solution, the result of processing the data, the source of data, Data processing, and quality, what tools are used for processing data, and others. AAI application cases and the technologies used for implementation are reviewed. The specifics of the data and the applications used are described. The examination of these technologies will provide insight into which ones are favored and provide an overview of what is commonly referred to as “best practices” in this particular domain.

Article: On Manufacturing Network Design as an Applied AI Problem

Article: On Manufacturing Network Design as an Applied AI Problem

The work is devoted to designing a manufacturing network incorporating logistic-production sites that are located at the nodes of the squared lattice with the help of the AI technique. We focused on qualitative analysis of the dynamic behavior of the dynamic lattice model. The model includes rate constants and initial conditions affecting the trajectories of the model which can be classified either as a stable node, limit cycle, or chaotic attractor. We aim to solve the problem of the model qualitative behavior as an AI classification problem. The training dataset is constructed with the help of Monte-Carlo simulation with high-performance computing in Julia. The AI model is built as a C5.0 decision tree. The work was fulfilled with the framework of Erasmus+ Project No. 2022-1-PL01- KA220-HED000088359 entitled “The Future is in Applied Artificial Intelligence” (FAAI) and offers a use case to be studied during the applied AI training course.

Full paper can be found at:https://ieeexplore.ieee.org/document/10316176

Audio version is available:

Article: On Predicting Financial Time Series of Various Granularity as an Applied AI Problem

Article: On Predicting Financial Time Series of Various Granularity as an Applied AI Problem

We comprehensively examine the efficacy of LSTM models in predicting financial time series. We evaluate the performance of LSTM networks based on various numbers of units determined by temporal granularity, considering aspects such as prediction accuracy. This study contributes to the ongoing discourse on the role of AI in financial markets, offeringa nuanced perspective on the practicality and limitations of LSTM models in this critical domain.

Full paper can be found at: https://ieeexplore.ieee.org/document/10316038

Audio version is available:

Article: Research and Analysis on the Labor Market in the Field of Applied AI

Article: Research and Analysis on the Labor Market in the Field of Applied AI

This article is fulfilled within the framework of Erasmus+ project “The Future is in Applied Artificial Intelligence (FAAI). It gives overview of current job market related to the field of Applied Artificial Intelligence. The data is obtained from online survey, and it gives highlights of severalaspects of labor market divided into research and analysis of the market, and specific requirements necessary. Regarding research and analysis, the data provided deals with:

– positions offered in the market.

– machine learning problems occurring.

– models being developed while resolving the realworld problem.

– machine learning tasks to be solved.

The collected data in the domain of job market requirements gives highlight about:

– required programming languages.

– educational requirements.

– required competencies.

Results given can serve as a guide to which competencies are necessary in the field of AAI and provide information for both professionals and curriculum creators.

Full paper can be found at: https://ieeexplore.ieee.org/document/10316155

Audio version is available:

Article: Employer Requirements for Graduate Competencies in Applied Artificial Intelligence

Article: Employer Requirements for Graduate Competencies in Applied Artificial Intelligence

ERASMUS+ project The Future is in Applied Artificial Intelligence (FAAI) aims to increase the quality and relevance of students’ and graduates’ knowledge and skills in AI/ML-specific topics based on skills needed in the labor market. This paper presents the results of the survey that was conducted in the context of the FAAI project to assess the needs of employers in project participants’ countries in graduates’ competencies in Artificial Intelligence, Machine Learning, and Data Science in general for the purpose of training specialists in the field of Applied AI. The survey was filled in by 38 companies and consisted of 31 questions related to general required competencies, type of machine learning problems solved, AI libraries used in companies, required soft skills, employers’ satisfaction with the level of preparedness of master’s degree graduates in the field of AI.

Full paper can be found at: https://ieeexplore.ieee.org/document/10315726

Audio version is available:

Article: Research and Analysis of Different Real Cases, with use AAI

Article: Research and Analysis of Different Real Cases, with use AAI

This article is fulfilled within the framework of Erasmus+ project “The Future is in Applied Artificial Intelligence” (FAAI) and examines the study of practical solutions implemented using applied artificial intelligence. The research was done by preparing an online survey containing a total of 7 questions, open and closed. The purpose of the study is to find real working applications of applied artificial intelligence projects, describe their application in what field, and record the name of the projects found to describe their activity. The study was done by looking at cases all over the world. The analysis of the data provides insight in several directions: – in which countries are more real cases of artificial intelligence solutions used – what is the distribution of realized cases – depending on whether the country is a member of the EU or not EU. – In what category is the real case developed. – whether the country of the real case works in collaboration with other countries or implements the real case only the country. The research and analysis done provide a clear picture of the developed projects using artificial intelligence. The obtained results will guide in what areas to organize the practical training. Also, the research would help future AI application developers.

The full paper can be found at: https://ieeexplore.ieee.org/document/10316177

Audio version is available: