Artificial intelligence and big-data capacity might help logistics companies withstand supply-chain disruptions by making them more agile and resilient, according to research in the International Journal of Business Performance and Supply Chain Modelling. The results are based on an analysis of responses from almost 300 logistics professionals in Indonesia.

The researchers surveyed employees of logistics service providers and analysed their responses using partial least squares structural equation modelling. This statistical technique can be used to test relationships between multiple factors. The findings indicate that digital capabilities help companies detect disruptions, improve forecasting and decision-making, optimise routing, and respond more rapidly to changing conditions.

Supply chains face persistent uncertainty from geopolitical tensions, natural disasters, trade restrictions and labour disputes, regulatory changes, and energy insecurity. This study suggests that technology alone is insufficient to help companies cope, as its value depends on organisations being able to turn information and automated analysis into faster adaptation and resource reconfiguration.

The research is grounded in dynamic capabilities theory, which says that organisations need to continually identify changes, exploit opportunities, and rearrange resources as circumstances change. The survey captures one point in time and focuses on Indonesia but may well be applicable to other regions. The researchers suggest that longitudinal and cross-country studies are now needed to determine whether this is true.

Sudrajat, D., Nagari, A.L. and Apriyanto, D. (2026) 'Investigating the impact of AI and big data capabilities on supply chain performance: the mediating role of agility and resilience', Int. J. Business Performance and Supply Chain Modelling, Vol. 16, No. 5, pp.1–26.
DOI: 10.1504/IJBPSCM.2026.156049

Research in the International Journal of Sensor Networks has demonstrated a visible-light communication system that uses the inherent randomness of quantum noise to make transmitted data harder for eavesdropping hackers to intercept.

The experimental system was able to transmit data at 100 megabits per second (100 mbps) and applies encryption directly at the optical, or "physical", layer of the communication system. 100 mbps is a modest data transfer speed when compared to modern broadband networks, equivalent to mid-90s Fast Ethernet speeds. Nevertheless, this is a valid initial baseline for a research demonstration, and fast enough for a wide variety of applications.

Moreover, optical wireless of this kind is emerging as a specialised complement to Wi-Fi and fibre connections, for situations with confined coverage and abundant optical spectrum where immunity to radio interference is essential. It could thus be attractive for settings such as hospitals, aircraft, and industrial facilities.

Visible-light communication (VLC) uses rapidly modulated light, typically from LEDs, to carry digital information through an open wireless channel. The researchers can convert data into a signal with many possible light-intensity levels and use a shared secret key to determine how the data is represented. Quantum noise, the random fluctuations arising from the fundamental properties of light, is then superimposed on to the signal. When the noise is at a sufficiently high level, a third party lacking the key cannot reliably distinguish between the signal and the noise. The current approach is based on the Y-00 quantum stream cipher, a technique previously demonstrated in fibre-optic communications and extends the approach to visible-light transmission.

The work could address a particular vulnerability in VLC, that unlike data protected only by higher-level network encryption, the optical signal itself remains exposed while in transit. This kind of physical-layer protection could therefore provide an additional security mechanism for optical wireless links in environments where interception is possible.

Xiao, N., Chen, S., Chen, F. and Shi, S. (2026) 'Experimental demonstrations of visible light communication using quantum noise for high security', Int. J. Sensor Networks, Vol. 52, No. 1, pp.1–6.
DOI: 10.1504/IJSNET.2026.156057

A digital scheduling framework combining machine learning, optimisation and blockchain technology could allow carbon emissions to be reduced at lower cost in regional energy systems, according to research in the International Journal of Environment and Pollution. The system cut the marginal emission-reduction cost, the additional expense of removing one more tonne of carbon, by about 12 per cent when the carbon quota was restricted to half the system's baseline emissions.

The new framework addresses a problem facing those managing increasingly complex regional energy networks, where electricity, heat and other sources must be coordinated while emissions are controlled. The problem being that the differences in data quality can make it difficult to assign emissions to specific sources and to then respond to rapidly changing demand.

The researchers used a machine-learning algorithm known as extreme gradient boosting, XGBoost, to identify complex relationships in the data and so forecast daily energy loads using historical consumption, electricity prices, weather, and industrial activity. The forecasts continuously update a mixed-integer linear programming (MILP) model, an optimisation method that selects decisions subject to constraints such as energy balances and carbon limits.

In addition, the framework records encrypted emissions data using a blockchain platform. Blockchain technology is perhaps more familiar as a cryptocurrency system, but it is essentially an immutable digital ledger that can be used to record data and information exchanges of all kinds. The blockchain thus provides a traceable record of emissions and assigns responsibility across the energy network.

The researchers suggest that integrating forecasting, scheduling, and verification into a single system could provide regional energy systems with a more responsive mechanism for managing emissions as carbon constraints tighten.

Liu, W. and Ma, W. (2026) 'Marginal emission reduction costs of regional energy system transformation enabled by digital economy from the perspective of supply chain', Int. J. Environment and Pollution, Vol. 76, No. 8, pp.1–26.
DOI: 10.1504/IJEP.2026.156117

Research in the International Journal of Pluralism and Economics Education argues that "The Jungle Book" can serve as an unconventional teaching tool for undergraduate economics, using the original stories by Rudyard Kipling as well as the Disney film adaptations to introduce concepts ranging from scarcity and sustainability to happiness and development.

The researchers used qualitative content analysis, a technique that looks beyond the literal content of texts to identify underlying themes and patterns. They thus examined passages from the literary work and the 1967 animated film, as well as its 2016 live-action adaptation. They focused on the theme of the "bare necessities", the basic goods and conditions required for a decent quality of life. The concept was made punningly famous by the lyric sung by Phil Harris voicing the friendly bear of the story, Baloo.

The material is used to illustrate concepts including opportunity cost, the idea that choosing one option means giving up another; barter and monetary economies; sustainable production and consumption; and the relationship between income and happiness. The team suggests that the same material might allow teachers to develop more advanced lessons that even connect the stories to the United Nations Sustainable Development Goals and the "tragedy of the commons", in which an individual's pursuit of their own interests can deplete the resources the benefits of which everyone might otherwise share.

Laha, A. and Maji, S.K. (2026) 'Bare necessities: understanding economics from The Jungle Book', Int. J. Pluralism and Economics Education, Vol. 16, No. 2, pp.200–223.
DOI: 10.1504/IJPEE.2026.156013

A machine-learning model has been designed to predict emerging computer-network security threats with greater reported accuracy than support-vector-machine systems, according to research in the International Journal of Intelligent Information and Database Systems.

The approach described uses a radial basis function neural network (RBFNN). This is an AI, artificial intelligence, model designed to identify complex, non-linear relationships in data. The researchers trained the RBFNN on processed network-security information, including data that can be generated by intrusion-detection systems, firewalls and network traffic. The system ultimately makes network defence more proactive rather than relying on the predominantly reactive technology of firewalls and after-the-fact intrusion-detection systems. Instead of relying on predefined rules to recognise known threats, it can analyse incoming data and use its training to spot similar patterns and so act as an early-warning system.

In tests, the RBFNN correctly classified more than 95% of normal network activity and Heartbleed attacks and achieved 97% accuracy in identifying denial of service (DoS) attacks. Its accuracy for brute-force attacks was somewhat lower, at up to 93%. However, it had an overall misclassification rate of less than 5%.

The researchers envisage a real-time service capable of automatically analysing data, detecting anomalies and generating alerts. Such systems could become increasingly important as attacks and advanced persistent threats become more varied and difficult to identify using fixed rules.

Liu, Y. (2026) 'Prediction of computer network security situation based on machine learning', Int. J. Intelligent Information and Database Systems, Vol. 18, No. 7, pp.1–18.
DOI: 10.1504/IJIIDS.2026.155882

A new AI model for predicting energy consumption could help managers plan ahead as well as open up opportunities for cutting carbon emissions, according to research in the International Journal of Information and Communication Technology.

The system uses a transformer-based generative adversarial network (GAN) to learn complex patterns in energy use. GANs are machine-learning systems in which two neural networks work against each other to produce realistic data. By adding Bayesian statistical optimisation, the team could set the system for best performance.

They tested the model on 2000 hourly energy and emissions records drawn from smart meters, building management systems, and industrial grids. They removed references to missing data and deleted outliers to normalise the input. The model made predictions that closely matched the observed energy data while taking only a few seconds to train and run.

The researchers explain that their computer-generated scenarios will allow operators to test demand-shifting measures, integrate renewable generation, and identify inefficiencies ahead of actual power generation and emission formation.

The approach addresses several weaknesses in conventional predictive models, which are known to struggle with non-linear consumption patterns, sudden spikes and troughs, and multiple external factors. This carbon-aware energy optimisation could be used across sites with internal power generation, such as industrial sites and in wider energy systems.

Liu, Y. and Li, B. (2026) 'Modelling and predicting energy consumption patterns using generative adversarial networks for effective carbon management', Int. J. Information and Communication Technology, Vol. 27, No. 92, pp.79–110.
DOI: 10.1504/IJICT.2026.155939

Local action may offer a model for waste management in rural tourism, according to research in the International Journal of Tourism Anthropology.

A study of waste problems in Kampung Nipah, a coastal tourism hamlet in North Sumatra, Indonesia, argues that rural communities with limited public services may need locally governed waste systems rather than relying solely on municipal provision. The researchers found that fly-tipping and littering in Kampung Nipah is linked to inadequate infrastructure. However, it also occurs because of established cultural practices, weak collective responsibility, and an absence of an institution responsible for managing waste across the wider village. The team explains that government waste-collection services do not reach the area, while rubbish from residents, tourists and rivers can accumulate along the coast.

The study involved ethnographic methods, a close, but extended, study of people and their everyday practices. It was able to show how social behaviour and institutional arrangements contribute to the problem of local waste in such a place. To overcome this problem, the team proposes a community-based model centred on local champions, residents who take an active leadership role, who work alongside tourism managers and other stakeholders to change the waste culture.

While the work focuses on only one location, it may well prove to have wider implications for rural coastal tourism elsewhere.

Zuska, F. and Zulkifli, Z. (2026) 'Developing community-based waste management for public spaces in coastal tourism villages: establishing institutions with local champions', Int. J. Tourism Anthropology, Vol. 10, No. 5, pp.1–22.
DOI: 10.1504/IJTA.2026.155914

Research in the International Journal of Critical Infrastructures describes a digital-twin system that could make safety monitoring on construction sites for high-rise buildings more effective. The system could allow accident risks to be identified as they appear rather than the site simply responding to hazards after the fact.

The team combined three techniques to build their system. First, they used an improved form of grey relational analysis, a statistical approach that works with incomplete data. Secondly, the incorporated local linear embedding reduces data complexity without compromising the relationships. Finally, they embedded a digital twin, a virtual representation of the physical construction site, linked to live measurements from the real environment.

Tests across 90 cases produced recall rates of around 96 to 99 per cent in under a second of processing time. The accuracy of risk factor identification was up to almost 98 per cent.

Fundamentally, accounting for interactions between hazards could help address risks that conventional systems overlook, including falls, struck-by incidents, collapses, mechanical injuries, and electric shocks. The short processing time will allow interventions to be made on-site in a more timely manner when conditions can change rapidly.

Deng, R. and Zhou, L. (2026) 'Safety risk perception of high-rise building construction process based on digital twin technology', Int. J. Critical Infrastructures, Vol. 22, No. 12, pp.1–23.
DOI: 10.1504/IJCIS.2026.155961

On hearing the first cuckoo of spring, the poet's heart might sing, and while one swallow does not a summer make, the annual migrations of bird species across continents have fascinated us for centuries. Today, however, technology is giving ornithologists the means to follow these incredible journeys in ways that would have been unimaginable to earlier generations of naturalists.

Research in the International Journal of Global Environmental Issues shows that artificial intelligence (AI) is being used by conservationists to help predict bird migration timings and patterns. The technology might allow them to identify how climate change and habitat loss are affecting the journeys of many migratory bird species.

The team looked at research into machine learning and deep learning models used to analyse migration, habitat preferences, and bird populations. They explain that machine learning refers to computer systems that identify patterns in data, while deep learning is a form of machine learning that uses layered neural networks to detect more complex patterns. Increasingly, automated sound recording devices that pick up bird calls and songs as they migrate overhead are providing useful data where visual monitoring is simply not possible.

These remote monitoring systems can operate for long periods with relatively little human intervention, building up a picture of migration activity over many nights, seasons, and even years. They offer researchers a way to monitor birds at a scale that would be extremely difficult to achieve with conventional field observations. This technology could thus strengthen monitoring, as habitats and migration routes respond to rising temperatures, changing rainfall, and land development. More accurate forecasts will help determine which habitats require greater protection and inform policy to ensure migratory bird conservation remains central to climate adaptation strategies.

Musale, P.P. and Sonawani, S.S. (2026) 'Advancements and challenges in bird migration models: a comprehensive survey', Int. J. Global Environmental Issues, Vol. 25, No. 1, pp.1–26.
DOI: 10.1504/IJGENVI.2026.155260

A face-recognition system that can see who you are even if you're wearing a face mask covering nose and mouth is discussed in the International Journal of Computational Vision and Robotics. The new system uses biometrics from around the eyes and forehead.

The research addresses a weakness in face recognition as a technology that was exposed during the pandemic. During that period when masks were often compulsory, their use caused conventional face-recognition systems to reject some authorised users. Unlike iris recognition, which can require specialised near-infrared imaging and controlled conditions, periocular recognition can operate with ordinary visible-light cameras.

The team has combined several types of visual information. First, a deep-learning model extracts features from around the eyes. Secondly, two image-processing techniques, local binary patterns and histograms of orientated gradients, analyse the person's forehead. The approach then combines the data to identify or verify an individual with an accuracy up to about 96 per cent in tests on one database but rather less on other testbeds.

Given that, the approach might be used as an initial screening step rather than as definitive proof of identity. A facial match could prompt further authentication with a second factor such as a password, PIN or security token. However, the team explains that they should be able to add other feature recognition into the same system, ears, face shape or profile, and those should improve performance significantly.

Agarwal, D. and Bansal, A. (2026) 'Fusion of periocular and forehead features for masked face recognition', Int. J. Computational Vision and Robotics, Vol. 17, No. 2, pp.133–158.
DOI: 10.1504/IJCVR.2026.155532