Search Results (9)

Currently, the recommendation system is a challenging task in the 21st centuries.The three main reasons and these are: the need for real-time user behavior analysis, the inability to explain why recommendations are made, and the difficulty handling new users/items. In this article, our objective is to develop a hybrid recommendation system that solves the challenges of traditional approaches. Our framework combined real-time learning and agentic rules, as well as sensor compatibility, in a dynamic environment. We developed a novel framework called SAFIRE (Sensor-Aware Framework for Intelligent Recommendations and Explainable Hybrid Techniques), where the eight traditional algorithms (User-Based CF, Item-Based CF, KNNWithMeans, KNNBaseline, SVD, SVD++, NMF, and BaselineOnly), a hybrid ensemble, and Explainable AI are used to recommend it. Our experimental work reveals that the model of BaselineOnly (Baseline Estimation Algorithm) whose accuracy under 5-fold obtained is 0.5156, MAE of 0.34055. Similarly, under 10-fold cross-validation, the models’ performance reached to 0.51558,0.34069, respectively. It has been observed that the lowest MAE obtained in the 5 CV setting is 0.29913. The model NMF(Non-Negative Matrix Factorisation) achieved an MAE of 0.30144 under 10-fold CV. Apart from this, Memory-Based Collaborative Filtering models perform marginally better with 10-fold CV as compared to the 5-fold CV. Overall, the model-based methods—BaselineOnly, NMF, and SVD—show little variance between folds (mean difference < 0.003), suggesting that they hold steady across various cross-validation setups. Full article

Background: Supplier evaluation and selection are pivotal processes in supply chain management, profoundly influencing organisational efficiency and sustainability. This study addresses the limitations of traditional multi-criteria decision-making approaches, particularly the Technique for Order Preference by Similarity to an Ideal Solution, which often lacks dimensional reduction capability and assumes uniform weight distribution across criteria. Methods: To overcome these challenges, a hybrid model integrating non-negative matrix factorisation, random forest, and the Technique for Order Preference by Similarity to an Ideal Solution is developed for supplier evaluation in the pharmaceutical sector. The method first applies non-negative matrix factorisation to condense twenty-four evaluation criteria into eight core dimensions, enhancing analytical efficiency and reducing complexity. Random forest is then employed to derive data-driven weights for each criterion, ensuring accurate prioritisation. Finally, the Technique for Order Preference by Similarity to an Ideal Solution ranks suppliers and provides actionable insights for decision-makers. Results: Results from real-world pharmaceutical data validate the model’s effectiveness and demonstrate superior performance over conventional evaluation methods. Conclusions: The findings confirm that integrating machine learning techniques with established decision-making frameworks enhances precision, interpretability, and sustainability in supplier selection while requiring adequate data quality and computational resources for implementation. Full article

Background: Anthropogenic activities have clearly affected the environment, with irreversible and destructive consequences. Mining activities have a significant negative impact, primarily on soil, and then on human health. The negative impact of the first mining activities is represented even today in the soils of those localities. Research shows that, for different types of mines, the concentrations of potentially toxic elements (PTEs) are high, especially in antimony, multi-metal and lead–zinc mines, which have adverse effects on the environment and then on human health and the economy. A large flood in 2014 in Western Serbia resulted in the breaking of the dam of the processed antimony ore dump of the former antimony mine, causing toxic tailings to spill and pollute the downstream area. Due to this accident, tailings material flooded the area downstream of the dump, and severely affected the local agriculture and population. Methods: Potentially toxic elements content, pollution indices and health indices were determined in soil samples from the flooded area, using referenced methodologies. The sources and routes of pollutants and risks were determined and quantified using statistical principal component analysis, positive matrix factorisation, and a Monte Carlo simulation. Results: The main source of As, Cd, Hg, Pb, Sb and Zn in the upper part of the study area was the tailing material. Based on the pollution indices, about 72% of the studied samples show a high risk of contamination and are mainly distributed immediately downstream of the tailings dump that was spilled due to heavy rainfall. Conclusions: Although the content of the PTEs is high, there is no non-carcinogenic risk for any PTEs except As, for which a threshold risk was determined. There is no carcinogenic risk in the study area. Full article

Zooplankton identification has been the subject of many studies. They are mainly based on the analysis of photographs (computer vision). However, spectroscopic techniques can be a good alternative due to the valuable additional information that they provide. We tested the performance of several chemometric techniques (principal component analysis (PCA), non-negative matrix factorisation (NMF), and common dimensions and specific weights analysis (CCSWA of ComDim)) for the unsupervised classification of zooplankton species based on their spectra. The spectra were obtained using laser-induced breakdown spectroscopy (LIBS) and Raman spectroscopy. It was convenient to assess the discriminative power in terms of silhouette metrics (Sil). The LIBS data were substantially more useful for the task than the Raman spectra, although the best results were achieved for the combined LIBS + Raman dataset (best Sil = 0.67). Although NMF (Sil = 0.63) and ComDim (Sil = 0.39) gave interesting information in the loadings, PCA was generally enough for the discrimination based on the score graphs. The distinguishing between Calanoida and Euphausiacea crustaceans and Limacina helicina sea snails has proved possible, probably because of their different mineral compositions. Conversely, arrow worms (Parasagitta elegans) usually fell into the same class with Calanoida despite the differences in their Raman spectra. Full article

Plastic pollution is one of the most significant environmental issues in the world. The rapid increase of the cumulative amount of plastic waste has caused alarm, and the public have called for actions to mitigate its impacts on the environment. Numerous governments and social activists from various non-profit organisations have set up policies and actively promoted awareness and have engaged the public in discussions on this issue. Nevertheless, social responsibility is the key to a sustainable environment, and individuals are accountable for performing their civic duty and commit to behavioural changes that can reduce the use of plastics. This paper explores a set of topic modelling techniques to assist policymakers and environment communities in understanding public opinions about the issues related to plastic pollution by analysing social media data. We report on an experiment in which a total of 274,404 tweets were collected from Twitter that are related to plastic pollution, and five topic modelling techniques, including (a) Latent Dirichlet Allocation (LDA), (b) Hierarchical Dirichlet Process (HDP), (c) Latent Semantic Indexing (LSI), (d) Non-Negative Matrix Factorisation (NMF), and (e) extension of LDA—Structural Topic Model (STM), were applied to the data to identify popular topics of online conversations, considering topic coherence, topic prevalence, and topic correlation. Our experimental results show that some of these topic modelling techniques are effective in detecting and identifying important topics surrounding plastic pollution, and potentially different techniques can be combined to develop an efficient system for mining important environment-related topics from social media data on a large scale. Full article

The goal of the work was to investigate the possible application of factor analysis methods for processing X-ray Fluorescence (XRF) data acquired with a full-field XRF spectrometer employing a position-sensitive and energy-dispersive Gas Electron Multiplier (GEM) detector, which provides only limited energy resolution at a level of 18% Full Width at Half Maximum (FWHM) at 5.9 keV. In this article, we present the design and performance of the full-field imaging spectrometer and the results of case studies performed using the developed instrument. The XRF imaging data collected for two historical paintings are presented along with the procedures applied to data calibration and analysis. The maps of elemental distributions were built using three different analysis methods: Region of Interest (ROI), Non-Negative Matrix Factorisation (NMF), and Principal Component Analysis (PCA). The results obtained for these paintings show that the factor analysis methods NMF and PCA provide significant enhancement of selectivity of the elemental analysis in case of limited energy resolution of the spectrometer. Full article

Wind turbines are typically organised as a fleet in a wind park, subject to similar, but varying, environmental conditions. This makes it possible to assess and benchmark a turbine’s output performance by comparing it to the other assets in the fleet. However, such a comparison cannot be performed straightforwardly on time series production data since the performance of a wind turbine is affected by a diverse set of factors (e.g., weather conditions). All these factors also produce a continuous stream of data, which, if discretised in an appropriate fashion, might allow us to uncover relevant insights into the turbine’s operations and behaviour. In this paper, we exploit the outcome of two inherently different discretisation approaches by statistical and visual analytics. As the first discretisation method, a complex layered integration approach is used. The DNA-like outcome allows us to apply advanced visual analytics, facilitating insightful operating mode monitoring. The second discretisation approach is applying a novel circular binning approach, capitalising on the circular nature of the angular variables. The resulting bins are then used to construct circular power maps and extract prototypical profiles via non-negative matrix factorisation, enabling us to detect anomalies and perform production forecasts. Full article

Using pan-cancer data from The Cancer Genome Atlas (TCGA), we investigated how patterns in copy number alterations in cancer cells vary both by tissue type and as a function of genetic alteration. We find that patterns in both chromosomal ploidy and individual arm copy number are dependent on tumour type. We highlight for example, the significant losses in chromosome arm 3p and the gain of ploidy in 5q in kidney clear cell renal cell carcinoma tissue samples. We find that specific gene mutations are associated with genome-wide copy number changes. Using signatures derived from non-negative factorisation, we also find gene mutations that are associated with particular patterns of ploidy change. Finally, utilising a set of machine learning classifiers, we successfully predicted the presence of mutated genes in a sample using arm-wise copy number patterns as features. This demonstrates that mutations in specific genes are correlated and may lead to specific patterns of ploidy loss and gain across chromosome arms. Using these same classifiers, we highlight which arms are most predictive of commonly mutated genes in kidney renal clear cell carcinoma (KIRC). Full article

Blind source separation is a common processing tool to analyse the constitution of pixels of hyperspectral images. Such methods usually suppose that pure pixel spectra (endmembers) are the same in all the image for each class of materials. In the framework of remote sensing, such an assumption is no longer valid in the presence of intra-class variability due to illumination conditions, weathering, slight variations of the pure materials, etc. In this paper, we first describe the results of investigations highlighting intra-class variability measured in real images. Considering these results, a new formulation of the linear mixing model is presented leading to two new methods. Unconstrained pixel-by-pixel NMF (UP-NMF) is a new blind source separation method based on the assumption of a linear mixing model, which can deal with intra-class variability. To overcome the limitations of UP-NMF, an extended method is also proposed, named Inertia-constrained Pixel-by-pixel NMF (IP-NMF). For each sensed spectrum, these extended versions of NMF extract a corresponding set of source spectra. A constraint is set to limit the spreading of each source’s estimates in IP-NMF. The proposed methods are first tested on a semi-synthetic data set built with spectra extracted from a real hyperspectral image and then numerically mixed. We thus demonstrate the interest of our methods for realistic source variabilities. Finally, IP-NMF is tested on a real data set and it is shown to yield better performance than state of the art methods. Full article