Research conducted at a Chinese university and reported in the International Journal of Computational Systems Engineering has looked at how machine learning and big data techniques might be used to identify the most influential factors in English language learning for non-English majors. The researchers analysed the academic progress of 1,805 students using a refined machine learning model and found that student motivation was the single most important driver of improvement, outweighing even the teaching methods or mode of instruction.

The findings emerged from an analysis using an advanced decision tree algorithm, an enhanced CHAID (Chi-squared Automatic Interaction Detector) decision tree coupled with a genetic algorithm that filters out irrelevant data and has improved predictive accuracy.

A decision tree is a machine learning model that maps the relationships between variables in a branching format. The CHAID variant is particularly suited to education research, as it handles categorical variables well, including learning environments and teaching styles. By enhancing the CHAID algorithm with genetic programming, the researchers were able to evolve the decision model iteratively, improving its ability to identify key patterns in the student data.

The primary metric analysed was the percentage of students making notable progress. Just under 20 percent of students in the sample, 352 individuals, met this threshold. The model was then tasked with identifying what differentiated these students from the majority.

The answer, the researchers found, lay first and foremost in student motivation. Whether driven by career ambitions, academic goals, or personal interest, a student's reason for studying English had the strongest correlation with measurable improvement. Teaching methods, ranging from interactive approaches to more traditional lecture formats, ranked second in influence, followed by the mode of instruction, whether face-to-face or online learning.

English continues to serve as a bridge language in academia, commerce, and international dialogue, so effective English instruction is a priority in educational institutions around the world. The study provides a new insight into how teaching might be improved, specifically in China, but perhaps elsewhere too.

Cai, H. (2025) 'A study on the optimisation of university English teaching based on an enhanced decision tree model in the context of big data', Int. J. Computational Systems Engineering, Vol. 9, No. 12, pp.1–11.
DOI: 10.1504/IJCSYSE.2025.147788

Research in the International Journal of Continuing Engineering Education and Life-Long Learning has looked at why some students persist with Massive Open Online Courses (MOOCs) while many others quietly drop out. It is an issue that has long dogged the promise of online education.

MOOCs have been with us since the late 2000s. Initially, they were touted as the means to democratize education by making high-quality university-level content available globally, often for free. They have to some extent fulfilled that early promise and countless MOOCs have since given access to millions of learners, often in remote, underserved, or economically constrained contexts. Fundamentally, MOOCs allow students to learn at their own pace and on their own terms. Yet despite the obvious putative reach and their appeal, MOOCs continue to suffer from notably low retention and completion rates. There is a gap between the initial enthusiasm of new students and their ongoing engagement or otherwise.

In the current work, the team has turned to a statistical technique known as Fuzzy Set Qualitative Comparative Analysis (FSQCA) to look for multiple causes of MOOC dropouts. FSQCA can be used to examine how combinations of conditions work to produce a given outcome. In the case of MOOCs, the approach has looked at how different complex and context-dependent factors lead to students persisting or failing to complete a course.

Five interrelated factors are thought to affect outcomes. First, the quality of the online system, its reliability and usability. Second, the content quality of the course itself, the learner's engagement, referred to as learning presence. Third, the influence of other students or mentors. Fifth, self-efficacy, the students' belief in their ability to succeed. No single factor could be used to reliably predict whether a student would stick with a course or drop out.

The FSQCA approach found three distinct configurations, or "recipes" in the jargon of the system, that affected outcomes. For example, one recipe recognised combined strong content quality, high self-efficacy, and positive social influence. Another emphasized system usability and learner engagement. Each recipe suggests that course retention depends on various factors, either in or out of balance.

The findings have implications for how MOOCs are developed and improved. Platform providers, universities, and instructional designers must think more holistically about their potential students. Improving technical infrastructure or offering well-produced video lectures alone will not lead to better retention. Instead, interventions must be multifaceted, they must build technically user-friendly platforms, but also foster support communities, enhance instructional design, and assist students in building confidence over time.

Chen, J. and Chen, G. (2025) 'College students' willingness to continue using MOOC platform: configuration analysis based on FSQCA method', Int. J. Continuing Engineering Education and Life-Long Learning, Vol. 35, No. 7, pp.1–18.
DOI: 10.1504/IJCEELL.2025.147807

A new approach to sniffing out user behaviour on social networks could improve how service providers understand and respond to their users' needs. The work discussed in the International Journal of Computational Systems Engineering offers a more accurate way to track "browsing trajectories", the path a user takes through a sequence of pages and content. Critically, the approach cleans up this data by filtering out the digital noise that has always been the bane of such analyses.

Social networks generate huge amounts of data, much of it ambiguous, inconsistent or irrelevant. For researchers and developers trying to spot patterns in this activity, for example, those running content-recommendation systems or monitoring user wellbeing, this is a significant problem. Current systems struggle to distinguish between signal and noise, which means any analysis leads to less effective personalisation and an increased risk of information overload for users.

The new approach integrates several computational tools, including "fuzzy logic", which can handle uncertainty in a way that binary logic cannot. Fuzzy logic can thus model ambiguity in human behaviour online. A second tool is the use of a "random forest learning algorithm", which can handle large and complex datasets and offer several decision trees by combining outputs to improve how well the system predicts behaviour. The third tool is "matched filtering", a technique borrowed from signal processing, that detects patterns within noisy data.

When combined, these tools allowed the researchers to isolate meaningful user behaviour among irrelevant or redundant data and so boost the signal-to-noise ratio. In subsequent simulations, the team was able to achieve up to 93 percent behaviour-prediction accuracy. Such precise analysis of browsing trajectories might help social platforms serve content that more closely matches what users are actually looking for, increasing satisfaction while reducing exposure to irrelevant or disruptive material.

Cai, Q. (2025) 'Social network user browsing trajectory detection based on soft computing to promote a healthy environment', Int. J. Computational Systems Engineering, Vol. 9, No. 12, pp.12–21.
DOI: 10.1504/IJCSYSE.2025.147790

As international companies face increasingly volatile conditions around the world especially in the face of rapid technological change, a study in the European Journal of International Management has looked at how they might systematically understand the way in which digital technologies are reshaping business strategies.

The research introduces the concept of Digital International Value Creation, a model that explains how businesses can use their digital capabilities to create added value in their international operations. Far beyond improving back-end efficiency, digitalisation, defined here as the transformation of an organisation's products, services, and processes into internet-compatible formats, is now an integral component of corporate activity.

Information and communication technology has, of course, supported international firms for many years by enabling more coordinated and efficient global operations. However, the current study argues that recent digital advances represent a structural shift. The new tools are creating new modes of international expansion, particularly for firms that were once limited by their geographic or organisational constraints.

The researchers outline three pathways already being taken by companies. The first involves enhancing existing operations with digital tools. The second considers how digital-native firms have been expanding globally from the outset. This involves historically parochial firms now using digital platforms to enter global markets for the first time. The research shows that whichever path is being taken, digital adoption alone is insufficient for ongoing global success. Rather, success depends heavily on how well firms align their technological strategies with their internal structures and the external environments in which they operate. The researchers add that political stability, legal frameworks, and cultural compatibility can all affect how well digital tools perform in different regions.

The team suggests that companies need to re-imagine digitalisation not as a supporting function but as a central component of their international strategy. This perspective is especially pertinent for small and medium-sized enterprises (SMEs), which often face significant barriers to digital adoption but also stand to benefit from the agility and reach these technologies offer.

Halpern, C. and Fernández-Méndez, L. (2025) 'The role of digitalisation in firms' international value creation: an integrative conceptual framework and a research agenda', European J. International Management, Vol. 27, No. 5, pp.1–42.
DOI: 10.1504/EJIM.2025.147769

Research in the International Journal of Value Chain Management sheds light on a blind spot in how society is tackling complex problems such as climate change, inequality, and food insecurity. There is, the work found, an underrepresentation of small and medium-sized enterprises (SMEs) in public innovation strategies. The researchers focused on the Uppsala region of Sweden and investigated why SMEs, which are often key sources of innovation and adaptability, struggle to engage with the kind of mission-orientated innovation that could help us address the big challenges we face.

Such challenges are large-scale, interlinked societal issues that cannot be solved by a single actor or sector. So, mission-oriented innovation, a framework being used increasingly by governments and institutions worldwide, breaks up the big challenges into smaller measurable missions. Rather than pursuing incremental technological development or narrowly defined market goals, mission-oriented innovation brings together public authorities, the private sector, and civil society in pursuit of transformative objectives. Such missions might include achieving carbon neutrality in city transport or eliminating food waste in national supply chains.

This research suggests that SMEs have all but been forgotten in defining mission-oriented innovation and yet the participation of SMEs, because of their size and flexibility, could be massively beneficial. Through interviews with the owners of SMEs and public sector representatives, the researchers found that there are three structural barriers to the inclusion of SMEs in mission-oriented innovation.

The first is a lack of awareness among many SMEs. This could be address through more effective communication from government bodies and coordinating agencies. Secondly, SMEs face constraints related to resource allocation. With a smaller workforce and tight budgets, these businesses often cannot afford the time nor the investment to participate in longer-term innovation missions. Public actors could solve this by prioritizing appropriate funding mechanisms or institutional support. Thirdly, there are domain differences. These are cultural and operational mismatches between the public and private sectors. Public institutions and SMEs often approach problems with different timelines, risk tolerances, and definitions of success, making sustained cooperation difficult.

As such, there is an urgent need to put in place mechanisms to bridge the gap between SMEs and public missions so that governments can bring a part of the economy into plans for the systemic change needed to address big issues.

Strömqvist, J., Hilletofth, P., Muhos, M., Saarela, M. and Virkkala, P. (2025) 'Barriers of SME engagement in mission-oriented innovation', Int. J. Value Chain Management, Vol. 15, No. 5, pp.1–23.
DOI: 10.1504/IJVCM.2025.147750

As digital technologies continue to transform the logistics industry, research in the International Journal of Logistics Systems and Management has looked at their impact on the wellbeing of professional drivers, namely truckers. The researchers conducted in-depth interviews and drew in survey data in Germany to look at his digital tools are reshaping the technical aspects of the job but also the lived experience of those behind the wheel.

Drivers report that digitalisation, ranging from GPS tracking to automated route planning, can reduce physical demands, streamline communications, and even contribute to improved safety. Systems designed to optimise routes and schedules, for example, reduce stress by minimising delays and helping drivers make more informed decisions in real time. In some cases, these innovations enhance the driver's sense of control, contributing to greater overall job satisfaction.

However, the research also shows that there are some drawbacks. Many drivers express unease about the level of surveillance enabled by digital tools. There is constant monitoring, whether through location tracking, in-cab cameras, or real-time performance metrics, and they often feel this to be intrusive and to erode their sense of independence. Given that independence is often central to the identity of professional drivers, this is not a positive outcome of the adoption of digital technologies. Indeed, some interviewees suggested that it was akin to being "micromanaged by a machine" and this was detrimental to their job satisfaction and psychological wellbeing.

The study identifies driver perceptions as a crucial determinant of how digitalisation is experienced. Those who see digital tools as supportive tend to report greater benefits, such as feeling safer or more efficient. In contrast, drivers who are more sceptical of these technologies are likely to experience them as a source of pressure or even alienation. This divide underscores the importance of the human factor in digital transitions: technological change is not experienced uniformly, and its impact depends heavily on individual attitudes and workplace culture.

For logistics companies, the implications are particularly will be difficult to navigate. Their drivers play a critical role in keeping supply chains functioning, yet their voices are often underrepresented in discussions about innovation. The research argues for a more inclusive approach to digital transformation, one that takes into account not just productivity and profit, but also encompasses driver wellbeing.

Straub, S.M. and Ruiner, C. (2025) 'For better or for worse? How the use of digital technologies affects truck drivers' wellbeing', Int. J. Logistics Systems and Management, Vol. 51, No. 3, pp.420–449.
DOI: 10.1504/IJLSM.2025.147556

As carbon neutrality become an increasingly urgent issue, the challenge of managing increasingly complex and renewable-heavy power systems remains. Work in the International Journal of Reasoning-based Intelligent Systems looks at power system optimization and presents a new approach to reducing both emissions and operating costs using artificial intelligence, AI.

The context for this innovation is the dual carbon goal, a policy framework adopted by many countries aiming to reach carbon neutrality sooner, rather than later. As electricity grids evolve from centralized, fossil-fuel-based structures to more decentralized systems dominated by intermittent renewable sources like wind and solar, they become harder to control in real-time. Grid operators must now balance not only power supply and demand, but also the economic cost of power generation and its environmental impact.

The researchers have used a refined version of a computational technique known as Particle Swarm Optimization (PSO). Originally inspired by the coordinated movement of animals, PSO seeks out optimal solutions from complex systems by simulating swarming behaviour. The researchers have extended PSO with a more advanced variant called Multi-Strategy Adaptive PSO (MAPSO), which incorporates a dynamic "reward mechanism" to improve how the AI searches for optimal outcomes. The researchers have then taken this yet another step forward, with MOMAPSO (Multi-Objective MAPSO). It operates within a dual-objective framework that simultaneously minimizes fuel costs and pollutant emissions, while respecting essential operational constraints such as power balance and generation limits.

Traditional mathematical optimization methods, while theoretically accurate, often struggle under the weight of modern grid complexity. They tend to be computationally demanding and less effective at navigating trade-offs between competing objectives. Heuristic algorithms like PSO and the extended version MAPSO, by contrast, offer a more flexible and efficient alternative.

Yao, L. (2025) 'Optimisation of operation algorithms based on artificial intelligence in power system control', Int. J. Reasoning-based Intelligent Systems, Vol. 17, No. 9, pp.34–43.
DOI: 10.1504/IJRIS.2025.147656

In an obvious departure from conventional wisdom regarding tourism, research in the International Journal of Business Innovation and Research shows that domestic travellers in Indonesia are prioritising safety over traditional markers of quality, such as service excellence. The study, based on data from 300 tourists across Jakarta, Banten, and West Java, suggests that the post-pandemic traveller is guided less by indulgence and more by psychological comfort and trust in a destination.

The researchers draw on the Theory of Planned Behaviour, a social psychology model commonly used to explain how individuals form intentions based on attitudes, social norms, and perceived control. They then examined how a tourist's perception of a destination and the risks associated with a visit to that place are now shaping travel decisions. The findings indicate a fundamental shift in the Indonesian tourism landscape: travellers are no longer primarily attracted by high-end service offerings. Instead, they favourable a strong destination image that encompasses traveller safety, emotional appeal, cultural assets, and perceived value.

Where such positives might encourage travel to a particular tourist spot. Any perceived risk to personal safety and wellbeing acts as a strong deterrent. Fears regarding health and safety risks, as well as concerns about financial loss or the reliability of infrastructure and local services feed into this deterrent, the research shows. Even destinations with traditionally high service standards are seeing waning interest if they cannot address these apparently new psychological barriers.

One of the most notable demographic findings from the study is the emergence of middle-class women aged 30 to 40 as the most influential segment of the domestic market. For this group, affordability, consistency, and emotional well-being rank higher than novelty or luxury. Their preferences are shaping a broader trend toward more cautious, purpose-driven travel.

Ultimately, the research has implications beyond Indonesia if the same personal risks assessments are being applied to other destinations in South East Asia. For tourism operators and policymakers across the globe, these insights suggest the industry needs to recalibrate its marketing and operational strategies to take into account changes in the attitudes of today's tourists.

Ambarwati, M.F.L., So, I.G., Abdinagoro, S.B. and Pradipto, Y.D. (2025) 'Recalibrating the compass: what truly matters to travellers after uncertainty', Int. J. Business Innovation and Research, Vol. 37, No. 6, pp.1–21.
DOI: 10.1504/IJBIR.2025.147657

Research in the International Journal of Vehicle Performance discusses a new integrated sensing and positioning system that can improve how autonomous locomotives navigate underground mining tunnels. This is one of the most challenging environments for vehicle automation, given the potential for hazards. The team has combined advanced laser-based mapping with wireless positioning and demonstrates that their system promises safer and more reliable navigation in settings where traditional sensing technologies often fail.

Underground mining poses distinct problems for autonomous vehicles. Tunnels are narrow, poorly lit, and often filled with dust and smoke, conditions that render conventional cameras almost useless and reduce the effectiveness of radar. This study addresses these challenges with a hybrid approach that pairs Light Detection and Ranging (LiDAR) sensors with Ultra Wide Band (UWB) wireless positioning.

LiDAR works by emitting laser pulses and measuring the time it takes for the light to return after bouncing off nearby objects. Unlike cameras, LiDAR does not depend on ambient light and can generate detailed 3D maps even in visually obscured environments. But the raw data it produces is often noisy and difficult to interpret, especially in cluttered or uneven spaces like those found in mining tunnels.

To refine this data, the researchers employed a technique known as multi-iteration plane fitting, which systematically isolates the ground surface from the rest of the environment. This step is essential for identifying true obstacles rather than confusing irregularities in the terrain for actual hazards. Once the ground is mapped, remaining data points, representing non-ground objects, are grouped into clusters.

Clustering in irregular environments presents its own difficulties. Traditional algorithms can misinterpret the scene, either by merging separate objects into one or splitting a single object into several false positives. The research team addressed this by analysing the scan line distribution from the LiDAR sensors, that is, the geometric pattern in which the laser sweeps across the environment. This allowed them to group points that belong to the same physical object more effectively. This approach not only improves obstacle recognition accuracy but also speeds up data processing by more than a fifth, which is important for systems operating in real time.

Wang, H., Wang, Y. and Shen, Y. (2025) 'Identification of intrusion obstacles for underground locomotives based on the fusion of LiDAR and wireless positioning technology', Int. J. Vehicle Performance, Vol. 11, No. 3, pp.253–277.
DOI: 10.1504/IJVP.2025.147693

As artificial intelligence (AI) continues to transform how images and video are created, concerns about the manipulation of digital content have grown. Research in the International Journal of Forensic Engineering discusses how AI can be used to fight back and find the fakes.

Deepfakes, videos or images that have been manipulated using AI to depict events that never occurred and words that were never uttered, pose a growing threat to public discourse, politics, criminal investigations, and scientific integrity. These convincing forgeries are typically generated by a form of AI known as Generative Adversarial Networks (GANs). In a GAN, two neural networks compete: one creates realistic fake images, while the other attempts to identify the deception. As they evolve, so the system becomes adept at producing forgeries that are difficult even for experts to distinguish from authentic content.

Such technologies have not only led to blurred lines between real and artificial but also raised critical questions for journalism, law enforcement, and scientific publishing, where the authenticity of visual evidence can have serious consequences. As the manipulation of media becomes more sophisticated, traditional detection methods, such as spotting anomalies in shadows or unnatural features, have proven inadequate.

The work in IJFE has repurposed a relatively simple machine-learning model to detect deepfakes with high accuracy. The researchers tested three convolutional neural network (CNN) architectures, ResNet-50, AlexNet, and LeNet-5, to determine which was most effective in distinguishing genuine images from AI-generated fakes.

CNNs are particularly good at analysing visual data. They function by identifying patterns, textures, and other features that may not be visible to the human eye. Although newer models like ResNet-50 are often assumed to be more powerful due to their increased sophistication, the researchers found that LeNet-5, a comparatively basic model developed in the 1990s, initially performed best.

The team was able to enhance this CNN through architectural fine-tuning and parameter optimisation, so that their modified version of the LeNet-5 model could reach almost 96 percent accuracy. It also had a demonstrable Area Under Curve (AUC) score of almost 99 percent, meaning that statistically it performed well across a range of test scenarios. It is worth noting that this system does not rely on prior knowledge about an image's content nor the embedded metadata.

Of course, as researchers are developing the tools to detect the fakes, so those who develop the tools to create them in the first place will respond with increasing sophistication to outwit the detectors.

Pawade, V.S. and Mathur, S. (2025) 'Comparative study of CNN models for detecting altered and manipulated images', Int. J. Forensic Engineering, Vol. 5, No. 3, pp.216–227.
DOI: 10.1504/IJFE.2025.147560