Researchers have developed a new artificial intelligence-based system designed to improve cyberattack detection in software-defined networks (SDNs), a networking architecture widely used in data centres and enterprise systems.

The system combines a deep quantum neural network with a novel optimisation technique inspired by the behaviour of wild geese and dwarf mongooses. Its aim is to identify abnormal network traffic, including distributed denial-of-service (dDoS) attacks, while preventing network controllers from becoming overloaded.

SDNs differ from traditional networks by separating the control plane, which makes routing decisions, from the data plane, which forwards traffic. While this design improves flexibility and centralises management, it also creates potential targets for attackers seeking to disrupt communications between controllers and network devices.

In the new approach outlined in the International Journal of Heavy Vehicle Systems, network traffic is analysed using a deep quantum neural network, a machine-learning model designed to recognise complex patterns. When suspicious traffic is detected, the system assesses controller workloads and automatically transfers network switches from overloaded controllers to those with spare capacity.

In simulations, the researchers demonstrated a detection accuracy of 93.7%. They obtained a true positive rate of 91.6% and a true negative rate of 87.5%. The researchers argue that combining traffic anomaly detection with automated load balancing could strengthen increasingly centralised network infrastructures.

Ahsan Shariff, M. and Nelson Kennedy Babu, C. (2026) 'Traffic anomaly detection with wild geese dwarf mongoose optimisation_DQNN', Int. J. Heavy Vehicle Systems, Vol. 33, No. 2, pp.147–172.
DOI: 10.1504/IJHVS.2026.153659

Researchers have developed an enhanced wearable motion-tracking system that could improve the accuracy of fitness trackers used to monitor exercise and training. The team provides details in the International Journal of Data Mining and Bioinformatics.

Current wearable devices often show inconsistencies in heart-rate monitoring and can miscalculate calories burnt, speed, and distance travelled. Such inaccuracies limit their usefulness for health-conscious consumers, but particularly for athletes and their coaches who need precision

The new work hopes to improve both data collection and sensor calibration. Researchers used fuzzy algorithms, computational methods designed to handle uncertain or variable information, to analyse real-time exercise data. They also applied filtering techniques to remove noise and improve data quality before calibrating the device's sensors.

In their tests, they found that measurements of heart rate, calorie expenditure, movement speed, and distance closely matched those obtained through standard laboratory procedures. The researchers suggest that their main advance lies in combining improved sensor calibration with more sophisticated data processing. This allows the device to generate a more reliable picture of an athlete's training performance in real time.

The findings could be used beyond competitive sport to help users develop personalised fitness programmes for health monitoring and injury prevention by giving them more dependable information about their physical activity.

An artificial intelligence (AI) system that combines breast cancer tissue images with molecular marker data achieves high accuracy in diagnosis, tumour classification, and survival prediction. Details are reported in the International Journal of Data Mining and Bioinformatics.

A common limitation of breast cancer care is that medical imaging and molecular markers as well as hormone receptor status are usually analysed separately. The researchers suggest that this can reduce the effectiveness of early detection, subtype classification, and personalised treatment planning. Their new addresses this issue.

In testing, the system achieved an accuracy of 96.3 per cent and an F1 score of 0.95, a measure that balances precision and recall. The system could also successfully classify eight breast cancer subtypes, with accuracy remaining above 90 per cent across all categories.

The approach combines two forms of AI. A Vision Transformer (ViT), a deep-learning model that identifies patterns across entire images, extracts features from biopsy slides. A fully connected neural network (FCNN) analyses molecular marker data. The resulting information is combined to give a clearer diagnosis.

The team says the method improves on many existing AI systems, which usually focus on image analysis and overlook molecular information that influences tumour behaviour and treatment response. The model also incorporates clinical data regarding survival trends and so can help support treatment decisions.

A study in the International Journal of Computer Applications in Technology has developed an improved way to determine the underlying beat, or tempo, in recorded music. It addresses persistent issues in analysing modern popular music where vocals, multiple instruments, and background noise overlap. A beat is the regular pulse that structures rhythm and guides how music is perceived and organised in time. While humans detect it naturally, machines struggle when audio is complex or when tempo changes during a track.

Existing beat detection systems often perform well only under simplified conditions. Many rely on limited audio features or assume relatively clean recordings, making them less effective in real-world music. Even advanced machine learning approaches can be unstable when audio conditions vary and may require high computational power, limiting their use in real-time applications, where latency can be a serious problem in music production and recording.

The researchers have used a multifeature fusion approach, which combines multiple types of audio information instead of relying on a single signal. The system first pre-processes the audio by segmenting it, reducing noise, and normalising volume levels to ensure consistent input. It then tracks changes over time and the frequencies present.

Features such as short-term energy and zero-crossing rate help identify rhythmic changes, while additional analysis separates rhythmic structure from melody and harmony. These signals are combined into a unified model that detects repeating patterns corresponding to beats and adapts when tempo changes occur.

Tests show reduced missed beats and false detections compared with traditional methods. The approach could be used to improve music recommendation systems, automated accompaniment tools, performance synchronisation, and music education software.

A new machine learning framework designed to detect malicious interference in unmanned aerial vehicles (UAVs), commonly known as drones, has shown strong performance in identifying both sudden and slow-developing sensor attacks, according to research in the International Journal of Automation and Control. The system, called GTF-MAD (Graph Time-Frequency Mixed Anomaly Detection), achieved a peak F1-score of 99.71% in detecting bias in tests on a quadrotor drone.

UAVs depend on sensors such as GPS (which provides satellite-based location data) and gyroscopes (which measure rotation and orientation). These act as the drone's navigational senses. However, they are vulnerable to manipulation. GPS spoofing can feed false location signals to a drone, while gyroscope bias injection introduces small but persistent errors into motion readings. Both can accumulate into major navigation failures if undetected.

Traditional detection systems rely on fixed rules, physical flight models, or machine learning patterns in sensor data. However, they struggle with changing sensor relationships during flight, lack of frequency-based signal analysis, and difficulty detecting slow-burn attacks that evolve over time.

GTF-MAD addresses these issues through three components. An adaptive graph attention network models sensors as a dynamic system of relationships that change during flight. A dual time-frequency architecture analyses signals both as time sequences and as frequency patterns, capturing vibrations and periodic disturbances. A trend detection module combines statistical methods to identify slow, stealthy deviations.

A study covering 76 countries has found that people who are more trusting, patient, altruistic and cooperative tend to report higher levels of happiness and life satisfaction, suggesting that wellbeing depends on more than material prosperity alone. The work was published in the International Journal of Happiness and Development.

The research looked at behavioural preferences, stable patterns in how people make decisions and interact with others, and how these relate to subjective wellbeing. Subjective wellbeing is a metric that embodies both life satisfaction and emotional experiences such as happiness, enjoyment, and worry.

The researchers used data from the Global Preferences Survey and the Gallup World Poll They looked at five personality traits in the data: patience, risk-taking, reciprocity, altruism, and trust. The study combined survey responses with experimentally validated behavioural measures designed to reflect real-world behaviour, something that earlier studies had not generally done.

Across most countries and measures, stronger behavioural preferences were associated with higher wellbeing, the team found. People who were more trusting, altruistic, reciprocal and willing to take risks generally reported greater happiness and lower levels of worry.

What was particularly interesting about the findings is that there was consistency across different regions. Previous research on wellbeing has often focused on income, employment and health, mainly in wealthier countries. The new study suggests behavioural and social dispositions play an important role across cultures and economic systems in different parts of the world.

The team found that trust and reciprocity were especially important. They suggest that this is because cooperative societies foster stronger social bonds, and that reduces personal stress. Altruism may also improve wellbeing by increasing social connectedness and meaning. Patience may support healthier and more stable long-term choices, the team suggests.

It is worth adding that the findings are correlational rather than causal. The team cannot say whether the behavioural traits studied improve wellbeing or whether it is that happier people tend to become more trusting and altruistic.

Artificial intelligence might now be used to address a less visible problem associated with renewable electricity production: the carbon footprint of the grid infrastructure itself. Details of how an AI-based forecasting system can predict the full lifecycle emissions of zero-carbon substations are provided in the International Journal of Business Intelligence and Data Mining. The approach is faster and more accurate than previous methods.

Substations convert high-voltage electricity into forms suitable for transmission and local distribution. Although often overlooked in climate debates, they generate emissions throughout construction, manufacturing, transport, maintenance, operation, and their decommissioning.

The study examines zero carbon substations, designed to minimise emissions through energy-efficient technologies, renewable integration, and offset measures such as carbon sinks. The researchers argue that only a full lifecycle perspective can properly assess their environmental impact, since supply chains and construction materials can account for substantial hidden emissions. Existing forecasting models, including deep reinforcement learning, recurrent neural networks, and random forest regression, usually cannot cope fully with the most important variables while maintaining speed and accuracy.

The new hybrid system, called Lasso-GRNN, combines statistical filtering with a neural network designed to model complex nonlinear relationships. Clustering techniques are also used to improve data quality before analysis.

The model achieves 98.51 per cent prediction accuracy with processing times of just 0.68 seconds. This could allow utility providers to make more timely and more informed infrastructure, maintenance, and investment decisions as electricity grids become increasingly decentralised and renewable focused.

Zeng, T., Chen, Y., Wang, L., Yuan, M., Lv, Z. and Wang, D. (2026) 'Prediction of carbon emissions throughout the lifecycle of zero carbon substations based on Lasso-GRNN neural network model', Int. J. Business Intelligence and Data Mining, Vol. 28, No. 8, pp.1–19.
DOI: 10.1504/IJBIDM.2026.153567

Research in the International Journal of Information and Communication Technology suggests that so-called knowledge graphs, a form of AI-based data organisation, could improve the reliability and maintenance of power communication systems that help keep the lights on and modern electricity grids running smoothly.

The researchers report that such a system works better than a conventional database in query efficiency, fault diagnosis, and operational decision-making. They explain that this technology could be used to help utility operators anticipate equipment failures earlier and manage increasingly complex power networks more effectively.

Power communication equipment functions as the information backbone of electricity grids, enabling substations, sensors and control centres to exchange data in real-time. However, as grids are becoming more digitalised through smart sensors, distributed energy systems and private 5G networks, operators are generating far larger volumes of interconnected data that somehow has to be managed.

The researchers argue that conventional relational databases struggle with this level of complex data. Relational databases organise information into rigid tables linked by predefined relationships. While suitable for simpler systems, the researchers say they create information silos in large infrastructure networks, where maintenance records, fault reports, environmental conditions, and operational data are fragmented across separate systems.

The proposed AI framework instead uses a knowledge graph, which represents devices, faults, maintenance activities, and communication links as interconnected nodes. By explicitly mapping relationships between all these different pieces of information, the system can identify dependencies and hidden correlations more effectively. In order to integrate this information from different sources, the researchers used natural language processing (NLP), an AI technique that extracts meaning from human language.

NLP enables the system to analyse unstructured materials such as maintenance reports and technical documents alongside structured operational data. The resulting information is stored in the graph database designed specifically for highly connected data. This approach allows the utility operator to have in place predictive infrastructure management. Now, instead of relying mainly on manual inspections and operator experience when faults occur, they can predict failures in advance and carry out preventative maintenance.

Research in the International Journal of Collaborative Engineering has found that universities that bring together environmental engineering and landscape architecture students in joint projects produce stronger design outcomes and better-prepared graduates for the world of work. These students can face real-world infrastructure challenges more effectively, the research into interdisciplinary teaching in sustainability-focused disciplines found.

The researchers focused on a persistent mismatch between professional practice and higher education. In the workplace, environmental engineers and landscape architects frequently collaborate on projects such as urban drainage systems, flood mitigation schemes, and climate adaptation plans. However, most university courses teach these two subjects separately, with few connections made between the disciplines to allow students to learn about each other's methods, terminology, and priorities.

Environmental engineering is a discipline concerned with designing systems that protect environmental quality, including water treatment, stormwater infrastructure, and flood control. Landscape architecture focuses on shaping outdoor and urban spaces with ecological processes, human use, and aesthetics in mind. These two disciplines overlap often in practice but those working in each field will commonly have followed separate educational paths.

To test their hypothesis of whether structured collaboration might address this silo effect, the researchers embedded joint learning activities into two existing courses: an environmental engineering watershed engineering module and a landscape architecture urban design studio. Students were put into small interdisciplinary groups and given the task of developing climate-adaptive stormwater and flood management strategies for a real city. External partners introduced practical constraints, such as budgeting, planning regulations, and community requirements. This meant the students had to move beyond abstract design exercises and engage with realistic decision-making and work together to do so.

Feedback from students and instructors and an assessment of the design outcomes of the project showed that the collaboration led to a higher standard of outcome than previous iterations completed within a single discipline. Avoiding professional siloing in these two fields and other related areas is increasingly important in the context of climate change, rapid urbanisation, and growing flood risk. The challenges are inherently complex, involving environmental systems, built infrastructure and social behaviour simultaneously, and so interdisciplinary approaches to problem-solving are increasingly needed in the real world.

Financial inclusion has emerged as a driver of development rather than a secondary outcome, according to research in the International Journal of Intelligent Enterprise. Financial inclusion defines the extent to which individuals and firms have fair, affordable, and reliable access to financial services such as banking, credit, insurance, and equity markets.

The IJIE paper reviewed the research literature in this area and found that a clearer understanding of impact can be drawn if a distinction is made between financial development and financial inclusion. Financial development refers to the size, depth, and efficiency of a country's financial system, in other words, how effectively it mobilises savings and allocates capital to productive uses. Financial inclusion, by contrast, focuses on who is able to participate in that system. A financial sector can be highly sophisticated while still excluding large parts of the population due to income, geography, gender, and social status.

Various studies show that the effects of inclusion are identified at multiple levels. At the household level, access to formal financial services allows people to save securely, borrow for emergencies or investment, and finance a family member's education or assist with the startup of a small business. This reduces dependence on informal lending networks, which are often expensive, unstable, and unregulated in the developing world. At the company level, limited access to credit constrains expansion. Businesses without formal finance tend to rely on retained earnings or potentially risky informal borrowing, which restricts productivity growth and innovation.

The research also found a link between financial inclusion and broader distributional outcomes. By widening access to financial tools, groups that were once excluded can build assets and smooth income over time. Ultimately, this reduces inequality and poverty. Numerous papers reviewed also showed that gender inclusion increases female participation in economic activity and leadership roles, which then has an effect on institutional performance and policy design.