AI pose estimation is in vogue

A lightweight artificial-intelligence (AI) system designed to assess rehabilitation exercises in real time could make computer-assisted therapy more practical on low-powered devices, according to research in the International Journal of Business Intelligence and Data Mining.

The researchers developed RMPE Tiny, a human-pose estimation network tailored to rehabilitation. Pose estimation is a computer-vision technique that identifies key points on the body, such as the shoulders, knees and ankles, from images or video. These points can then be used to measure movement, including range, symmetry, and coordination.

The challenge for such systems is that precise pose estimation usually needs a lot of computing power; this limits them to specialist equipment rather than allowing them to be used on tablets or simple, embedded monitoring systems. RMPE Tiny addresses this through several modifications intended to reduce computational demands without substantially compromising accuracy.

The system uses laser triangulation to improve image acquisition and map 3D coordinates onto a 2D image. In tests, it achieved more than 96 per cent overall pose-estimation accuracy, with most samples approaching or exceeding 98 per cent. The system might ultimately be used to support rehabilitation systems that provide immediate feedback outside clinical settings.

Yang, Q. and Zhang, G. (2026) ‘Design of lightweight human pose estimation network for rehabilitation training’, Int. J. Business Intelligence and Data Mining, Vol. 28, No. 10, pp.85–102.

News media may use this press release as source material, in whole or in part, provided the content is not materially misrepresented. A link back to the original article is appreciated.

Free sample articles newly available from International Journal of Environmental Technology and Management

The following sample articles from the International Journal of Environmental Technology and Management are now available here for free:

• Plastic waste recycling product design based on sustainable concepts: study of improvement, developments, and innovations in Kampala City, Uganda
• Preparation and characterisation of aloe vera/nanocellulose/bentonite biocomposite scaffold to remove arsenic from wastewater
• Combination of activated carbon and thermal energy system for the clarification of surface water at Bousellem
• Treated municipal wastewater for irrigation: a case study from Misurata City, Libya
• Study on comprehensive evaluation of environmental pollution in tourist attractions based on FCM algorithm
• Carbon flow tracking methods for power systems in energy conservation and emission reduction environments
• Teak trees computational modelling to measure environmental contribution using functional-structural plant modelling
• Hydraulic modelling and flood hazard zoning in rivers of the urban basin of Sulaymaniyah using 2D modelling with HEC-RAS and GIS
• Carbon emission calculation and control of agricultural product supply chain under the background of energy conservation and emission reduction
• Peak carbon emission prediction of expressway toll stations using GRA-LSTM under the dual carbon background
• Research on influencing factors of regional tourism carbon emission based on LMDI model
• A positive and negative balance accounting method for carbon emissions in parks based on K-nearest neighbour clustering algorithm
• Evaluation method of landscape ecological quality based on remote sensing ecological index
• Automatic classification method of construction waste based on machine vision
• Short-term load prediction of electric vehicle charging stations based on conditional generative adversarial networks

Research pick: Clean up on the roof - "Intelligent autopilot drone robot for de-mossing ramped roofs"

Drones have many uses in surveillance and surveying, industrial inspection, aerial photography and filmmaking, package delivery, even dynamic light-shows. Their fundamental ability to carry cameras, sensors and other equipment opened up these diverse applications. Now, research in the International Journal of Intelligent Machines and Robotics has explored another: the safe removal of moss and lichen from sloping roofs, an otherwise hazardous job for a worker.

The team used an Arduino-based autopilot system for a quadcopter-type drone capable of operating over horizontal or sloping roofs. It follows a programmed zig-zag, or “staircase”, trajectory designed to cover the roof systematically while avoiding obstacles.

Arduino is a low-cost, programmable electronics platform commonly used to control robots. The proposed system combines it with motors, batteries, electronic speed controllers (ESCs), which regulate motor power, and a flight controller that manages the aircraft’s movement and stability. The researchers point out that this seemingly mundane demonstration opens up possibilities for such machines to be used in other applications that otherwise involve risk to workers.

The prototype remains a development platform. Future work identified by the researchers includes improved obstacle handling and machine learning to better identify patterns from video input to allow the drone to adapt to unexpected situations.

Sanyal, S. (2026) ‘Intelligent autopilot drone robot for de-mossing ramped roofs’, Int. J. Intelligent Machines and Robotics, Vol. 2, No. 1, pp.22–44.

News media may use this press release as source material, in whole or in part, provided the content is not materially misrepresented. A link back to the original article is appreciated.

Free sample articles newly available from International Journal of Human Resources Development and Management

The following sample articles from the International Journal of Human Resources Development and Management are now available here for free:

• The impact of positive organisational behaviour on employee engagement and performance
• The future of recruitment: a mixed-methods scenario analysis in Germany
• Fostering alignment in the hybrid workplace: bridging the gap between employee experience and expectations
• Human resources in the era of the fourth industrial revolution: Competencies 4.0
• Empowering leadership in cognitive processes and behavioural dynamics: a thematic analysis

Free Open Access special issue on "Global Mobility Law: Rethinking the Role of Law In Movement Across Borders" published by International Journal of Migration and Border Studies

The International Journal of Migration and Border Studies has published an Open Access issue. All of the issue’s papers can be downloaded via the full-text links available here.

• Infrastructuring pathways: traversing the legal infrastructure of mobility in South America
• Authoritarian borders? Turning authoritarian international law inside-out
• Reconciling the tensions of the European deportation regime: how the law shapes compulsory mobility across borders
• Freedom of movement, sovereignty, and the Third World in postwar international law (1948-1968)
• Global commerce and global mobility law
• Citizenship as transnational mobility capital
• An international human rights law of migration? Reflections on the place of a right to immigrate

Research pick: Spotting the spoof - "A hybrid deep learning method for URL spoofing in websites"

A machine-learning system can identify fake, or “spoofed”, website addresses, according to research in the International Journal of Electronic Security and Digital Forensics. The work offers a new tool to protect users against phishing attacks, where attackers direct someone to a deceptive website to steal information such as bank logins or personal and private data.

The team combined two deep-learning techniques: a convolutional neural network (CNN), which can identify patterns in data, and a long short-term memory (LSTM) network, which can retain information about sequences in that data. This hybrid CNN-LSTM model achieved accuracy rates of almost 99 per cent on the UCL standard test dataset and almost 97 per cent on the PhishTank dataset.

The findings highlight the potential for automated AI systems in protecting people using online commerce, government services, and other activities. Phishing attacks remain particularly difficult to address as a cybercrime problem because they often simply exploit human behaviour and weaknesses rather than being a technical loophole. If a message is sufficiently convincing and a website realistic, then vulnerable or even simply distracted users might disclose sensitive information without realising they have been duped.

A system to accurately flag spoofed addresses before that happens would be invaluable. For the small percentage that it false-flags, the inconvenience would be negligible compared to what is not lost by blocking spoofed sites.

Santhosh Krishna, B.V., Vidhya, S., Krishnaveni, S. and Ashokkumar, N. (2026) ‘A hybrid deep learning method for URL spoofing in websites’, Int. J. Electronic Security and Digital Forensics, Vol. 18, No. 5, pp.524–537.

News media may use this press release as source material, in whole or in part, provided the content is not materially misrepresented. A link back to the original article is appreciated.

New Open Access article available: "Informal entrepreneurship and entrepreneurial ecosystems: a systematic literature review and future research agenda"

The following International Journal of Entrepreneurship and Small Business article, "Informal entrepreneurship and entrepreneurial ecosystems: a systematic literature review and future research agenda", is freely available for download as an open access article.

It can be downloaded via the full-text link available here.

Research pick: Hoarse? With no blame? Physics might explain! - "Physics-informed modelling of vocal fold fatigue process using acoustic and laryngovibrography data"

A new approach to modelling vocal fold fatigue could improve detection and monitoring of problems as they arise, particularly among people whose jobs depend on sustained voice use. The research, published in the International Journal of Information and Communication Technology, uses a physics-based framework for tracking changes over time.

The vocal folds, colloquially referred to as vocal cords, are the vibrating muscular structures within the larynx at the top of the trachea that allow us to speak, sing, and make various sounds. Vocal fold fatigue involves declining vocal efficiency, poorer voice quality and greater effort when speaking and can arise in anyone at any time but is common among public speakers, teachers, call centre operators, singers, and others who use their voice more than average or at higher volume.

The new approach, called physics-informed joint simulation and identification (PJSF), treats fatigue as a continuously changing process rather than a fixed condition. It models the depletion and recovery of the vocal system using equations that describe how a system changes over time and combines these with acoustic recordings and laryngovibrography, measurements of vocal-fold vibration to give a diagnosis or predict issues that might arise.

In tests on 20 volunteers, the system was shown to balance between correctly identifying fatigue and avoiding false alarms. The work could lead to a system capable of monitoring vocal strain and supporting personalised voice-use guidance for users whose profession involves constant use of the voice.

Zhang, X., Sun, R., Zhao, C. and Zhao, Y. (2026) ‘Physics-informed modelling of vocal fold fatigue process using acoustic and laryngovibrography data’, Int. J. Information and Communication Technology, Vol. 27, No. 97, pp.89–118.

News media may use this press release as source material, in whole or in part, provided the content is not materially misrepresented. A link back to the original article is appreciated.

Free Open Access special issue on "Sustainable Education in the Age of Artificial Intelligence (AI) – Part 1" published by International Journal of Innovation and Sustainable Development

The International Journal of Innovation and Sustainable Development has published an Open Access issue. All of the issue’s papers can be downloaded via the full-text links available here.

• Analysing the innovation game in school-enterprise cooperation for talent cultivation under the concept of industry-education integration
• A fuzzy evaluation of AI-assisted English teaching quality based on random forest regression algorithm
• Research on AI assisted teaching effectiveness evaluation method based on PSO-RBF
• Study on fine-grained classification of MOOC ideological and political teaching resources based on an improved switching ensemble algorithm
• Evaluation of public mathematics teaching quality in universities under the fuzzy matrix assessment model
• A deep semantic matching network-based method for retrieving Q&A data in online vocational education
• An AI-driven approach to quality evaluation for large-scale online teaching
• Dynamic evaluation and intervention mechanism of collaborative effectiveness of university research teams based on multimodal learning analysis

Research pick: Harder, better, safer, stronger - Three-way AI improves cybersecurity - "DNN and BiGRU-based hierarchical attention network for intrusion detection"

A new deep-learning architecture could deflect cyberattacks by combining several methods for analysing network traffic, according to research in the International Journal of Business Intelligence and Data Mining. The approach addresses a weakness in standard intrusion-detection systems, which struggle with the volume and complexity of modern network traffic.

The researchers combined a deep neural network (DNN), which identifies complex patterns in large sets of features, with a bidirectional gated recurrent unit (BiGRU), a type of neural network designed to identify relationships across sequences in both directions. Both components use an attention mechanism, which allows the system to concentrate on the features and points in a sequence that are most relevant to anomaly detection. The outputs are brought together and classified using a multilayer perceptron (MLP), another neural-network architecture used to assign data to categories.

Tests on two well-known benchmark datasets showed that the system could achieve validation accuracies of around 99 per cent. The researchers explain that the system is stable in training and has comparatively strong robustness and generalisation, which means it should be effective on data beyond its training data.

The results suggest that combining static-feature analysis with temporal pattern recognition can harden cybersecurity systems against denial-of-service attacks, network probing, and attempts to gain unauthorised access.

Yan, H., Liu, H., Yu, P., Xu, X., Li, M., Long, Y., Chen, H., Wang, Q. and Long, D. (2026) ‘DNN and BiGRU-based hierarchical attention network for intrusion detection’, Int. J. Business Intelligence and Data Mining, Vol. 28, No. 10, pp.1–24.

News media may use this press release as source material, in whole or in part, provided the content is not materially misrepresented. A link back to the original article is appreciated.

New Open Access article available: "World uncertainty and the marginal value of cash: suggestive nonlinear evidence from six ASEAN technology markets"

The following International Journal of Economics and Business Research article, "World uncertainty and the marginal value of cash: suggestive nonlinear evidence from six ASEAN technology markets", is freely available for download as an open access article.

It can be downloaded via the full-text link available here.

Research pick: Inferred information - "The legal and ethical implications of social media privacy concerns"

There is a modern adage: If you don’t want it on the internet, don’t put it on the internet!

However, a review of research into social media privacy in the International Journal of Management Concepts and Philosophy has found that legal and ethical protections are not keeping pace with the volume of personal information collected and shared online. Moreover, a lot of inferred information that people don’t deliberately share can now be gleaned by interested third parties from one’s social media activity.

Social media refers to online platforms, websites, and “apps” that people use to create, share, and interact with content and communicate with others. People use it to stay connected, share experiences, access information, and build professional or social networks.

The researchers examined privacy breaches, regulatory frameworks, and the responsibilities of social media companies and users. They argue that the central problem is not about what people choose to post but what can subsequently be inferred or indexed by others.

Social media use leaves a “digital trail" of one’s activities, locations, and interactions and can usually be stored, searched, and analysed easily by third parties, or at the very least by the platform providers themselves. The researchers suggest that even seemingly mundane online activities can reveal personality traits, shopping habits, political opinions and allegiance, and religious leanings.

The team argues that individual privacy and confidentiality support personal autonomy, civil liberties and democratic participation, strengthening the case for greater legal accountability and transparency from social media platforms. It also calls for improved digital literacy, so users are better equipped to understand and manage the risks of sharing information online.

Policymakers and other stakeholders sometimes argue that people who have “nothing to hide” have little reason to worry about privacy. But if that principle were applied consistently, there would be little need for frosted glass in bathroom windows. Privacy is not about concealing wrongdoing; it is about having control over who can see into the most personal parts of our lives, a principle that does not disappear simply because those lives have moved online.

Bilgrami, T., Singh, K. and Ahmed, S. (2026) ‘The legal and ethical implications of social media privacy concerns’, Int. J. Management Concepts and Philosophy, Vol. 19, No. 3, pp.306–322.

News media may use this press release as source material, in whole or in part, provided the content is not materially misrepresented. A link back to the original article is appreciated.

New Open Access article available: "English digital transformation algorithm for distributed big data based on Spark"

The following International Journal of Intelligent Information and Database Systems article, "English digital transformation algorithm for distributed big data based on Spark", is freely available for download as an open access article.

It can be downloaded via the full-text link available here.

Research pick: Architecture and virtual reality - "Generation of virtual reality landscape scenes for digital urban architecture based on AI"

Artificial intelligence (AI) combined with virtual reality (VR) could guide us through tomorrow's cities before they are even built, according to research in the International Journal of Environment and Pollution. Such models could be useful for architects, planners, and policymakers.

The team describes a modelling method that uses computer vision, technology that enables computers to interpret images, to scan architectural drawings and buildings. Machine learning (ML), a form of AI that identifies patterns in data, then processes these scans to allow VR technology to construct realistic virtual architectural scenes.

The researchers suggest that greater automation of this process could reduce the labour and resources required by conventional 3D modelling, in which scanned material is often assembled and processed manually. This will be increasingly important as expanding cities place greater demands on infrastructure management and public services. Aside from applications in architecture and construction, the virtual city environments could be used to simulate transport conditions, investigate how tourism might be supported, and also allow responses to emergencies to be rehearsed. Such simulations would allow officials and other professionals to test scenarios in a controlled digital environment before acting in the physical city.

The work points towards digital representations of urban areas becoming increasingly useful in the management of infrastructure and the coordination of complex projects.

Dai, D., Tu, B. and Liu, J. (2026) 'Generation of virtual reality landscape scenes for digital urban architecture based on AI', Int. J. Environment and Pollution, Vol. 76, No. 8, pp.109-122.

News media may use this press release as source material, in whole or in part, provided the content is not materially misrepresented. A link back to the original article is appreciated.

Free Open Access issue published by International Journal of Information and Communication Technology

The International Journal of Information and Communication Technology has published an Open Access issue. All of the issue’s papers can be downloaded via the full-text links available here.

• Optimisation of English speech recognition using contrastive learning and feature reconstruction
• Impact of personalised learning system based on generative AI on students' higher-order thinking ability and reconstruction of teachers' roles
• Predicting athletes' physical condition using multimodal machine learning models
• Risk perception and traceability in higher education quality management using dynamic knowledge graphs and link prediction
• Quantum computing-driven portfolio optimisation framework for the intelligent economy