Air pollution is becoming a rising and serious environmental problem, especially in urban areas affected by an increasing migration rate. The large availability of sensor data enables the adoption of analytical tools to provide decision support capabilities. Employing sensors facilitates air pollution monitoring, but the lack of predictive capability limits such systems’ potential in practical scenarios. On the other hand, forecasting methods offer the opportunity to predict the future pollution in specific areas, potentially suggesting useful preventive measures. To date, many works tackled the problem of air pollution forecasting, most of which are based on sequence models. These models are trained with raw pollution data and are subsequently utilized to make predictions. This paper proposes a novel approach evaluating four different architectures that utilize camera images to estimate the air pollution in those areas. These images are further enhanced with weather data to boost the classification accuracy. The proposed approach exploits generative adversarial networks combined with data augmentation techniques to mitigate the class imbalance problem. The experiments show that the proposed method achieves robust accuracy of up to 0.88, which is comparable to sequence models and conventional models that utilize air pollution data. This is a remarkable result considering that the historic air pollution data is directly related to the output—future air pollution data, whereas the proposed architecture uses camera images to recognize the air pollution—which is an inherently much more difficult problem.

Forecasting air pollution is crucial for understanding the phenomenological and contextual variety of mechanisms underlying pollution in a particular area or region. Analyzing high-dimensional data with spatial and temporal dependencies is pointed out as a major challenge for traditional machine learning approaches for air pollution forecasting. The unprecedented advances in deep learning employed on massive quantities of IoT sensor data raise high hopes for the future of air pollution forecasting. Drawing on past and current experiences and solutions advanced in a growing body of research on the topic, we proposed and evaluated four encoder-decoder architectures with attention for forecasting particulate matter (PM) levels, with a general applicability that is both location- and season-independent. The attention mechanism was employed to better learn representation of time series data. By selectively focusing the attention on elements that contribute the most, superior performance gains have been obtained by the proposed models. Sensor measurements obtained in the past 7 or 14 days as well a set of external factors known to affect the pollutant levels, such as weather conditions, location and time frame (e.g., season, time of day) were taken into account. In this research, we carried out a case study on PM _2.5 forecasting for the city of Skopje, allowing us to discuss the relevance of the results obtained by the proposed solutions. The ability to draw valid inferences from data has critical importance when forecasting air pollution. In this respect, any air pollution forecasting model based on deep learning would require a component for generation of realistic data samples to augment the time series dataset. We address the challenges in missing data by proposing and evaluating two adversarial networks for data augmentation. We have conducted a number of experiments to investigate the performance of the predictive models with and without augmenting the training datasets and obtain superior performance gains by the proposed adversarial models for data augmentation. The deep neural architectures advanced in this research are general enough to be used for predictive and generative tasks for other pollutants; moreover, they could be adopted for related tasks handling time series data in other domains.

Data science and machine-learning techniques help banks to optimize enterprise operations, enhance risk analyses and gain competitive advantage. There is a vast amount of research in credit risk, but to our knowledge, none of them uses credit registry as a data source to model the probability of default for individual clients. The goal of this paper is to evaluate different machine-learning models to create accurate model for credit risk assessment using the data from the real credit registry dataset of the Central Bank of Republic of North Macedonia. We strongly believe that the model developed in this research will be an additional source of valuable information to commercial banks, by leveraging historical data for all the population of the country in all the commercial banks. Thus, in this research, we compare five machine-learning models to classify credit risk data, i.e., logistic regression, decision tree, random forest, support vector machines (SVM) and neural network. We evaluate the five models using different machine-learning metrics, and we propose a model based on credit registry data from the central bank with detailed methodology that can predict the credit risk based on credit history of the population in the country. Our results show that the best accuracy is achieved by using decision tree performing on imbalanced data with and without scaling, followed by random forest and linear regression.

Applied machine learning in bioinformatics is growing as computer science slowly invades all research spheres. With the arrival of modern next-generation DNA sequencing algorithms, metagenomics is becoming an increasingly interesting research field as it finds countless practical applications exploiting the vast amounts of generated data. This study aims to scope the scientific literature in the field of metagenomic classification in the time interval 2008–2019 and provide an evolutionary timeline of data processing and machine learning in this field. This study follows the scoping review methodology and PRISMA guidelines to identify and process the available literature. Natural Language Processing (NLP) is deployed to ensure efficient and exhaustive search of the literary corpus of three large digital libraries: IEEE, PubMed, and Springer. The search is based on keywords and properties looked up using the digital libraries’ search engines. The scoping review results reveal an increasing number of research papers related to metagenomic classification over the past decade. The research is mainly focused on metagenomic classifiers, identifying scope specific metrics for model evaluation, data set sanitization, and dimensionality reduction. Out of all of these subproblems, data preprocessing is the least researched with considerable potential for improvement.

Network-based representations have introduced a revolution in neuroscience, expanding the understanding of the brain from the activity of individual regions to the interactions between them. This augmented network view comes at the cost of high dimensionality, which hinders both our capacity of deciphering the main mechanisms behind pathologies, and the significance of any statistical and/or machine learning task used in processing this data. A link selection method, allowing to remove irrelevant connections in a given scenario, is an obvious solution that provides improved utilization of these network representations. In this contribution we review a large set of statistical and machine learning link selection methods and evaluate them on real brain functional networks. Results indicate that most methods perform in a qualitatively similar way, with NBS (Network Based Statistics) winning in terms of quantity of retained information, AnovaNet in terms of stability and ExT (Extra Trees) in terms of lower computational cost. While machine learning methods are conceptually more complex than statistical ones, they do not yield a clear advantage. At the same time, the high heterogeneity in the set of links retained by each method suggests that they are offering complementary views to the data. The implications of these results in neuroscience tasks are finally discussed.

Accurate, timely, and resource-efficient decision-making is critical for sustainable precision agriculture. This paper proposes an agentic AI-based Internet of Things (IoT) framework that enables coordinated, closed-loop perception–decision–action processes across heterogeneous sensing and actuation components. The framework models agricultural systems as distributed collections of goal-driven agents responsible for multimodal sensing, uncertainty-aware reasoning, and adaptive decision-making. To provide a structured foundation, the proposed architecture is formalized within a Multi-Agent Partially Observable Markov Decision Process (MPOMDP) perspective, enabling systematic treatment of coordination, uncertainty, and decision policies. The framework integrates multimodal information sources, including vision-based perception and environmental sensing, and defines mechanisms for their fusion and use in system-level decision-making. A proof-of-concept instantiation is presented using publicly available datasets, combining visual perception models and tabular reasoning models within the proposed agentic workflow. The experiments are designed to demonstrate the feasibility, modularity, and coordination capabilities of the framework, rather than to benchmark predictive performance or provide field-validated evaluation. The results illustrate how multimodal information can be integrated to support adaptive and resource-aware decision processes. Finally, the paper discusses key challenges and outlines directions for future work, including real-world deployment, integration with physical actuation systems, and validation under operational conditions.