<abstract xmlns="http://www.w3.org/1999/xhtml">

<italic>Context</italic>: Machine Learning (ML) is a disruptive concept that has given rise to and generated interest in different applications in many fields of study. The purpose of Machine Learning is to solve real-life problems by automatically learning and improving from experience without being explicitly programmed for a specific problem, but for a generic type of problem. This article approaches the different applications of ML in a series of econometric methods.
<italic>Objective</italic>: The objective of this research is to identify the latest applications and do a comparative study of the performance of econometric and ML models. The study aimed to find empirical evidence for the performance of ML algorithms being superior to traditional econometric models. The Methodology of systematic mapping of literature has been followed to carry out this research, according to the guidelines established by [39], and [58] that facilitate the identification of studies published about this subject.
<italic>Results</italic>: The results show, that in most cases ML outperforms econometric models, while in other cases the best performance has been achieved by combining traditional methods and ML applications.
<italic>Conclusion</italic>: inclusion and exclusions criteria have been applied and 52 articles closely related articles have been reviewed. The conclusion drawn from this research is that it is a field that is growing, which is something that is well known nowadays and that there is no certainty as to the performance of ML being always superior to that of econometric models.
</abstract>

University of Granada Colegio Máximo de Cartuja

Department of Electronics, Information and Communication, Faculty of Engineering

Machine Learning and Traditional Econometric Models: A Systematic Mapping Study

<abstract xmlns="http://www.w3.org/1999/xhtml">

There has been an amplified focus on and benefit from the adoption of artificial intelligence (AI) in medical imaging applications. However, deep learning approaches involve training with massive amounts of annotated data in order to guarantee generalization and achieve high accuracies. Gathering and annotating large sets of training images require expertise which is both expensive and time-consuming, especially in the medical field. Furthermore, in health care systems where mistakes can have catastrophic consequences, there is a general mistrust in the black-box aspect of AI models. In this work, we focus on improving the performance of medical imaging applications when limited data is available while focusing on the interpretability aspect of the proposed AI model. This is achieved by employing a novel transfer learning framework, <italic>progressive transfer learning</italic>, an automated annotation technique and a correlation analysis experiment on the learned representations.
<italic>Progressive transfer learning</italic> helps jump-start the training of deep neural networks while improving the performance by gradually transferring knowledge from two source tasks into the target task. It is empirically tested on the wrist fracture detection application by first training a general radiology network <italic>RadiNet</italic> and using its weights to initialize <italic>RadiNetwrist</italic>, that is trained on wrist images to detect fractures. Experiments show that <italic>RadiNetwrist</italic> achieves an accuracy of 87% and an AUC ROC of 94% as opposed to 83% and 92% when it is pre-trained on the ImageNet dataset.
This improvement in performance is investigated within an <italic>explainable AI</italic> framework. More concretely, the learned deep representations of <italic>RadiNetwrist</italic> are compared to those learned by the baseline model by conducting a correlation analysis experiment. The results show that, when transfer learning is <italic>gradually</italic> applied, some features are learned earlier in the network. Moreover, the deep layers in the <italic>progressive transfer learning</italic> framework are shown to encode features that are not encountered when traditional transfer learning techniques are applied.
In addition to the empirical results, a clinical study is conducted and the performance of <italic>RadiNetwrist</italic> is compared to that of an expert radiologist. We found that <italic>RadiNetwrist</italic> exhibited similar performance to that of radiologists with more than 20 years of experience.
This motivates follow-up research to train on more data to feasibly surpass radiologists’ performance, and investigate the interpretability of AI models in the healthcare domain where the decision-making process needs to be credible and transparent.
</abstract>

Department of Electrical and Computer Engineering

Department of Health Professions, Medical Imaging Sciences, Faculty of Health Sciences

Department of Radiology, Faculty of Medicine

A Progressive and Cross-Domain Deep Transfer Learning Framework for Wrist Fracture Detection

<abstract xmlns="http://www.w3.org/1999/xhtml">

Text-based CAPTCHA is a convenient and effective safety mechanism that has been widely deployed across websites. The efficient end-to-end models of scene text recognition consisting of CNN and attention-based RNN show limited performance in solving text-based CAPTCHAs. In contrast with the street view image and document, the character sequence in CAPTCHA is non-semantic. The RNN loses its ability to learn the semantic context and only implicitly encodes the relative position of extracted features. Meanwhile, the security features, which prevent characters from segmentation and recognition, extensively increase the complexity of CAPTCHAs. The performance of this model is sensitive to different CAPTCHA schemes. In this paper, we analyze the properties of the text-based CAPTCHA and accordingly consider solving it as a highly position-relative character sequence recognition task. We propose a network named PosConv to leverage the position information in the character sequence without RNN. PosConv uses a novel padding strategy and modified convolution, explicitly encoding the relative position into the local features of characters. This mechanism of PosConv makes the extracted features from CAPTCHAs more informative and robust. We validate PosConv on six text-based CAPTCHA schemes, and it achieves state-of-the-art or competitive recognition accuracy with significantly fewer parameters and faster convergence speed.
</abstract>

Position-Encoding Convolutional Network to Solving Connected Text Captcha

<abstract xmlns="http://www.w3.org/1999/xhtml">

1Most reinforcement learning benchmarks – especially in multi-agent tasks – do not go beyond observations with simple noise; nonetheless, real scenarios induce more elaborate vision pipeline failures: false sightings, misclassifications or occlusion. In this work, we propose a lightweight, 2D environment for robot soccer and autonomous driving that can emulate the above discrepancies. Besides establishing a benchmark for accessible multi-agent reinforcement learning research, our work addresses the challenges the simulator imposes. For handling realistic noise, we use self-supervised learning to enhance scene reconstruction and extend curiosity-driven learning to model longer horizons. Our extensive experiments show that the proposed methods achieve state-of-the-art performance, compared against actor-critic methods, ICM, and PPO.
</abstract>

Handling Realistic Noise in Multi-Agent Systems with Self-Supervised Learning and Curiosity

<abstract xmlns="http://www.w3.org/1999/xhtml">

Security threats, among other intrusions affecting the availability, confidentiality and integrity of IT resources and services, are spreading fast and can cause serious harm to organizations. Intrusion detection has a key role in capturing intrusions. In particular, the application of machine learning methods in this area can enrich the intrusion detection efficiency. Various methods, such as pattern recognition from event logs, can be applied in intrusion detection. The main goal of our research is to present a possible intrusion detection approach using recent machine learning techniques. In this paper, we suggest and evaluate the usage of stacked ensembles consisting of neural network (SNN) and autoen-coder (AE) models augmented with a tree-structured Parzen estimator hyperparameter optimization approach for intrusion detection. The main contribution of our work is the application of advanced hyperparameter optimization and stacked ensembles together.
We conducted several experiments to check the effectiveness of our approach. We used the NSL-KDD dataset, a common benchmark dataset in intrusion detection, to train our models. The comparative results demonstrate that our proposed models can compete with and, in some cases, outperform existing models.
</abstract>

An Autoencoder-Enhanced Stacking Neural Network Model for Increasing the Performance of Intrusion Detection

AHEAD OF PRINT

Volume 14 (2024): Issue 2 (March 2024)

Volume 14 (2024): Issue 1 (January 2024)

Volume 13 (2023): Issue 4 (October 2023)

Volume 13 (2023): Issue 3 (June 2023)

Volume 13 (2023): Issue 2 (March 2023)

Volume 13 (2023): Issue 1 (January 2023)

Volume 12 (2022): Issue 4 (October 2022)

Volume 12 (2022): Issue 3 (July 2022)

Volume 12 (2022): Issue 2 (April 2022)

Volume 12 (2022): Issue 1 (January 2022)

Volume 11 (2021): Issue 4 (October 2021)

Volume 11 (2021): Issue 3 (July 2021)

Volume 11 (2021): Issue 2 (April 2021)

Volume 11 (2021): Issue 1 (January 2021)

Volume 10 (2020): Issue 4 (October 2020)

Volume 10 (2020): Issue 3 (July 2020)

Volume 10 (2020): Issue 2 (April 2020)

Volume 10 (2020): Issue 1 (January 2020)

Volume 9 (2019): Issue 4 (October 2019)

Volume 9 (2019): Issue 3 (July 2019)

Volume 9 (2019): Issue 2 (April 2019)

Volume 9 (2019): Issue 1 (January 2019)

Volume 8 (2018): Issue 4 (October 2018)

Volume 8 (2018): Issue 3 (July 2018)

Volume 8 (2018): Issue 2 (April 2018)

Volume 8 (2018): Issue 1 (January 2018)

Volume 7 (2017): Issue 4 (October 2017)

Volume 7 (2017): Issue 3 (July 2017)

Volume 7 (2017): Issue 2 (April 2017)

Volume 7 (2017): Issue 1 (January 2017)

Volume 6 (2016): Issue 4 (October 2016)

Volume 6 (2016): Issue 3 (July 2016)

Volume 6 (2016): Issue 2 (April 2016)

Volume 6 (2016): Issue 1 (January 2016)

Volume 5 (2015): Issue 4 (October 2015)

Volume 5 (2015): Issue 3 (July 2015)

Volume 5 (2015): Issue 2 (April 2015)

Volume 5 (2015): Issue 1 (January 2015)

Volume 4 (2014): Issue 4 (October 2014)

Volume 4 (2014): Issue 3 (July 2014)

Volume 4 (2014): Issue 2 (April 2014)

Volume 4 (2014): Issue 1 (January 2014)

Volume 3 (2013): Issue 4 (October 2013)

Volume 3 (2013): Issue 3 (July 2013)

Volume 3 (2013): Issue 2 (April 2013)

Volume 3 (2013): Issue 1 (January 2013)

Journal of Artificial Intelligence and Soft Computing Research

 Print version published by: The Journal of the Polish Neural Network Society and the University of Social Sciences in Lodz  Editor-in-Chief: Prof. Leszek Rutkowski, IEEE FellowFrequency of publishing: quarterlyMonths of publication: January, April, July, October  ISSN (print): 2083-2567ISSN (on-line): 2449-6499  Journal of Artificial Intelligence and Soft Computing Research is a dynamically developing international journal focused on the latest scientific results and methods constituting traditional artificial intelligence methods and soft computing techniques. Our goal is to bring together scientists representing both approaches and various research communities.  Why JAISCR?   Premier source of high quality research,  We have practice in publishing innovative articles dealing with various aspects of artificial intelligence methods and soft computing,  Extensive scope,  We are focused on permanent development of our journal.   JAISCR research areas  JAISCR publishes high quality, innovative research results in various areas of artificial intelligence and soft computing. These areas include, but are not limited to:   AI in Modelling and Simulation,  AI in Scheduling and Optimization,  Automated Reasoning and Inference,  Bioinformatics,  Cognitive Aspects of AI,  Computer Vision and Speech Understanding,  Data Mining,  Distributed Intelligent Processing,  Evolutionary Design,  Expert Systems,  Fuzzy Modelling and Control,  Hardware Implementations,  Heuristic Search,  Hybrid Models,  Information Retrieval,  Intelligent Database Systems,  Knowledge Engineering,  Mechatronics,  Multi-agent Systems,  Natural Language Processing,  Neural Network Theory and Architectures,  Neuro-informatics and Bio-inspired Models,  Pattern Recognition,  Robotics and Related Fields,  Rough Sets Theory: Foundations and Applications,  Supervised and Unsupervised Learning,  Swarm Intelligence and Systems,  Web Intelligence Applications &amp; Search,  Various Applications.   Submitting to JAISCR - a great advantage for the authorsWhy?   Fair and thorough peer review (at least three referees are required for the acceptance of each article),  Fast and efficient publication process,  Polishing the structure and technical format of each submission,  Open access (all articles published in JAISCR are open access - freely available on Sciendo platform),  Permanence (because of the open access form, permanent accessibility is assured),  High visibility within the field (the author's work is freely accessible to a global audience. In addition, articles are available through Sciendo),  Promotion of the published papers in the scientific community.   Archiving  Sciendo archives the contents of this journal in Portico - digital long-term preservation service of scholarly books, journals and collections.  Plagiarism Policy  The editorial board is participating in a growing community of Similarity Check System's users in order to ensure that the content published is original and trustworthy. Similarity Check is a medium that allows for comprehensive manuscripts screening, aimed to eliminate plagiarism and provide a high standard and quality peer-review process. 