The following International Journal of Medical Engineering and Informatics article, "Endoscopic ultrasonography in differential diagnostics of benign and malignant pathology of the common bile ducts utilising fuzzy mathematical technologies", is freely available for download as an open access article.
It can be downloaded via the full-text link available here.
A study of advertising embedded in Indian reality television examines how stealth, or subliminal, advertising, affects brand recall in a media environment saturated with promotional messages. The work, published in the International Journal of Indian Culture and Business Management, looks at how audiences exposed to thousands of brand impressions daily are affected by this approach to advertising. The findings have implications for marketing departments, which are increasingly using subtle product placement to familiarise potential and known customers with brands.
The research used within-subject experiments where participants viewed 12-minute clips from five Indian reality programmes containing embedded brand appearances. Recall was measured using standardised questionnaires assessing brand memory after exposure. Across 20 brands, most achieved moderate recall through this form of advertising.
The team found that two factors most influenced brand recall: whether the placement was spoken or visual and whether it meshed with the premise or arc of the segment. The results showed that verbal references were more effective than visual placements, but higher congruity between brand and the storyline of the segment improved recall.
Perhaps paradoxically, visual prominence of a product did not affect brand recall significantly. This challenges the marketing assumption that visibility drives effectiveness. The researchers concluded that embedded advertising depends largely on more subtle cues than straightforward visibility in the segment. Product placement is on the rise across TV, streaming platforms, and in digital content. Marketing departments hoping to familiarise consumers with their products need to understand these findings to benefit the most.
Dua, G.G., Vaidya, R.D. and Bapat, G.S. (2026) ‘Unveiling the recall power of covert advertising: a study on stealth advertising in Indian reality shows’, Int. J. Indian Culture and Business Management, Vol. 38, No. 1, pp.68–93.
The following International Journal of Business Innovation and Research article, "Fuelling the customer experience: an exploration of service quality in fuel stations through importance-performance analysis", is freely available for download as an open access article.
It can be downloaded via the full-text link available here.
Researchers have developed an artificial intelligence model that predicts crime more accurately than several existing approaches by combining information about where crimes occur, when they happen, and wider social patterns. They report details of the approach in the International Journal of Innovative Computing and Applications.
The model combines a graph convolutional network, which identifies relationships between locations, with a transformer, an AI architecture designed to detect patterns over time. Together, the techniques allow the system to capture both spatial and temporal trends in criminal activity. The researchers also incorporated a generative adversarial network (GAN), a system in which two AI models compete to improve performance. The GAN was enhanced using a variational autoencoder, a method that helps generate more representative data while reducing common training problems such as biased outputs and vanishing gradients, where learning slows or stops.
The system integrates several machine-learning techniques to analyse complex datasets that traditional methods often struggle to process. In tests on historical data from several US cities, including Los Angeles and Seattle, the model achieved an accuracy rate of 86.3 per cent when predicting robberies. The strongest competing systems had an accuracy of 83.2 per cent. The new system also gave strong results across other crime categories.
The researchers suggest that accurate forecasting could help law enforcement allocate resources more effectively and identify areas at higher risk of crime. However, there are limitations. The system was less accurate in areas with sparse crime data and struggled to make predictions in locations with little or no historical information. Future work will focus on adapting the model to such environments through transfer learning, which will allow knowledge gained in one setting to be applied to another.
Xie, M. (2026) ‘Multidimensional crime prediction technique optimisation combining feature extraction and GAN’, Int. J. Innovative Computing and Applications, Vol. 15, No. 5, pp.289–299.
The following Progress in Computational Fluid Dynamics, An International Journal article, "Quantifying wall effects on spherical particle settling with the Lattice Boltzmann method", is freely available for download as an open access article.
It can be downloaded via the full-text link available here.
The following International Journal of Continuing Engineering Education and Life-Long Learning article, "Classroom student emotion recognition using an improved segmentation clustering and multi-feature fusion emotion recognition algorithm", is freely available for download as an open access article.
It can be downloaded via the full-text link available here.
The following International Journal of Power and Energy Conversion article, "Change detection framework for power facilities in disaster scenarios", is freely available for download as an open access article.
It can be downloaded via the full-text link available here.
Researchers have developed an artificial intelligence-based patient monitoring system they say can identify signs of clinical deterioration earlier and more accurately than existing approaches. The system could help hospital staff intervene before a patient’s condition becomes critical. Details are discussed in the International Journal of Ad Hoc and Ubiquitous Computing.
Traditional monitoring systems rely largely on fixed thresholds for individual measurements such as heart rate, blood pressure or oxygen levels. However, these approaches often fail to account for differences between patients and may overlook how physiological changes interact across the body.
The new approach combines three machine-learning techniques. An adaptive attention mechanism continuously adjusts the importance assigned to different physiological signals. A spatiotemporal graph neural network analyses how vital signs influence one another and evolve. The system also incorporates reinforcement learning, a method in which algorithms learn decision-making strategies through feedback, enabling it to provide active clinical decision support rather than simply issuing alarms.
Tests were carried out to see how well the system performed in predicting historical outcomes recorded in two major intensive care unit (ICU) databases, MIMIC-III and eICU. The system achieved 96.3 per cent anomaly detection accuracy, generated warnings almost 40 minutes before critical events occurred, and reduced false alarms to 6.4 per cent.
Cheng, S., Zhu, J., Guan, S., Cheng, J. and Dou, T. (2026) ‘Intelligent monitoring of patient vital signs based on adaptive attention fusion spatiotemporal graph neural network’, Int. J. Ad Hoc and Ubiquitous Computing, Vol. 52, No. 5, pp.48–62.
The following International Journal of Systems, Control and Communications article, "Automation measures and power quality optimisation of power line carrier control based on electric spring and wavelet transform", is freely available for download as an open access article.
It can be downloaded via the full-text link available here.
The following International Journal of Technology Enhanced Learning article, "Unlocking computational thinking: immersive technologies for solving complex problems", is freely available for download as an open access article.
It can be downloaded via the full-text link available here.
A machine-learning model based on Transformer architecture, a form of artificial intelligence originally developed for language processing, can be used to detect heart disease from electrocardiogram (ECG), according to research in the International Journal of Medical Engineering and Informatics. Tests show it works well with data from several well-known medical datasets.
Heart disease is a major healthcare problem, with almost 18 million dying prematurely each year because of it. The challenge if finding ways to detect cardiovascular disease early enough to make treatment effective. An ECG is the standard way to record the heart’s electrical activity and is thus a common diagnostic tool. Interpretation of the trace needs significant expertise, is time-consuming and is not without the risk of misinterpretation.
The researchers discusses a one-dimensional (1D) Transformer model that can analyse ECG signals and in parallel with other clinical data. In tests, it was up to 94.2 per cent accurate in spotting the early stages of heart disease. Such precision coupled with expert clinical assessment can suffice to give the healthcare team more reliable options in taking a patient on to the next step in diagnosis and potential treatment.
The researchers suggest that their approach needs further development and validation with independent clinical datasets before it can be tested in a live clinical setting.
Miloud Aouidate, A. (2026) ‘Heart disease detection using 1D transformer network: case of ECG signals and clinical data’, Int. J. Medical Engineering and Informatics, Vol. 18, No. 5, pp.1–18.
A comparative modelling study of two Brazilian rain catchments suggests that climate change will have contrasting effects on future soil erosion in the Amazon and Cerrado. The findings have implications for land management in both biomes in the coming decades.
The research, published in the International Journal of Hydrology Science and Technology, used rainfall records and projections from NASA’s Earth Exchange Global Daily Downscaled Projections (NEX-GDDP). This allowed the team to estimate soil loss under different scenarios.
Soil loss, the amount of soil removed by erosion, was calculated using the Universal Soil Loss Equation (USLE), which estimates erosion driven by rainfall, land cover, topography, and soil properties. Rainfall erosivity refers to rain’s capacity to detach and transport soil particles.
The team explains that the Cerrado is a biodiverse savanna, while the Amazon regulates rainfall through evapotranspiration, the transfer of water from land to the atmosphere. Differences in rainfall, elevation and land use affect soil erosion patterns. The global circulation models (GCMs) of climate simulations suggest that shifting rainfall intensity will change erosion rates with heavier rainfall increasing soil loss risk.
In the Amazon catchment, soil loss historically ranges from just a few dozen kilograms per hectare each year to almost 20 tonnes per hectare per year. Soil erosion is predicted to increase by several per cent through the remainder of this century.
By contrast, soil loss in the Cerrado’s Piranhas River catchment has been from a hundred kilograms or so to almost 250 tonnes per hectare per year. The models predict that soil erosion will actually become less of a problem in the coming years despite the effects of climate change.
As such, there is a need to respond to the changes of the future in different ways in the two very different regions. In the Amazon catchment, rising erosion risk supports conservation measures such as terracing, no-till farming and crop rotation. While in the Cerrado catchment, simply maintaining current agricultural practices may help sustain reduced soil loss.
Sobral, R.V.S., Lobato, A.K.R., Soares, A.d.C.L., de Mendonça, L.M., Cruz, J.d.S. and Blanco, C. (2026) ‘Impact of climate change on soil loss in small catchments in the Amazon and Cerrado biomes’, Int. J. Hydrology Science and Technology, Vol. 21, No. 4, pp.417–436.
A new AI system can convert social media discussion about a product into a new design that takes into account user needs more accurately than earlier approaches, according to research in the International Journal of Information and Communication Technology.
The work addresses the problem of complexity in attempting to extract useful information from social network data for product development. Comments and reviews are typically unstructured, meaning they do not follow a fixed format, and also have many variables, such as sentiment, context, and usage scenarios, which makes it difficult to translate into insights about how people feel about products.
A deep-learning framework is at the heart of the system and combines various AI components. Firstly, it uses a multi-scale attention network to identify emotional needs in user comments. Attention in machine learning refers to a mechanism that prioritises the most relevant information in a dataset. The idea of multi-scale processing means it captures both detailed and broad patterns in language. The second component is a generative adversarial network (GAN). This uses two models working against each other, with one generating images and the other evaluating them. In addition, a spatial cross-reconstruction module refines image features, while a semantic correlation module links textual emotion signals to visual attributes. All of this works to improve the link between what the users say about the original product and the new design.
In tests, the model achieved more than 90 per cent accuracy in identifying the users’ emotional needs. This improves on existing methods and suggests that AI might help with data-driven product design informed by user sentiment and social media behaviour.
Wang, C. (2026) ‘Deep learning-based innovative product design driven by social network data’, Int. J. Information and Communication Technology, Vol. 27, No. 49, pp.59–78.
The following World Review of Entrepreneurship, Management and Sustainable Development article, "Assessing environmentally sustainable practices in boutique hotels: frontline staff perspectives", is freely available for download as an open access article.
It can be downloaded via the full-text link available here.
A study in the Global Business and Economics Review suggests that the failure of small and medium-sized enterprises (SMEs) can be predicted as much as three years before insolvency. The work could offer lenders, investors, and business owners an early warning of financial problems years in advance.
The researchers analysed data from more than 24500 European companies over an eight-year period. From this data, they developed a forecasting model that has an overall accuracy of about 82 per cent. It could identify more than 70 per cent of insolvencies three years in advance on test data with known outcomes. The final model relies on seven financial indicators: cash ratio, contribution per interest paid ratio, solvency ratio, short-term financing, leverage, debt-assets ratio, and return on assets. These measures capture a company’s liquidity, debt burden, financial resilience, and profitability. However, the model could yet be improved if there were greater disclosure from SMEs. That said, this is highly unlikely given the nature of smaller businesses.
The researchers say the work addresses a big gap in the corporate finance literature. Traditionally, this has focused on large publicly listed companies. However, SMEs account for most businesses in OECD economies and roughly two-thirds of employment, making their stability an important economic issue.
Silva, S. (2026) ‘Corporate failure prediction model for European SMEs’, Global Business and Economics Review, Vol. 34, No. 4, pp.395–419.
The following International Journal of Electronic Security and Digital Forensics article, "Judgement stage in electronic administrative proceedings and evidentiary authority", is freely available for download as an open access article.
It can be downloaded via the full-text link available here.
The following International Journal of Entrepreneurship and Small Business article, "Roots of innovative knowledge in small commercial enterprises in Ecuador", is freely available for download as an open access article.
It can be downloaded via the full-text link available here.
