Criminal emotion detector

Crime is an age-old and never-ending problem for societies worldwide and crime detection and crime fighting have always chased after the criminals who often stay one step ahead. Research in the International Journal of Knowledge-Based Development has turned to emotional data alongside machine learning (ML) and deep learning (DL) techniques to develop technology that might one day help us better understand the criminal mind and perhaps even predict criminal activity so that it might be prevented.

A. Kalai Selvan and N. Sivakumaran of the Department of Instrumentation and Control Engineering & Head at the National Institute of Technology,in Tiruchirappalli, Tamil Nadu, India had two main objectives: the prediction of crime using ML models based on emotional data and the identification of future crime hotspots using DL methods applied to crime incident data.

By analysing voice-based emotional cues using ML algorithms, the team has achieved a detection accuracy of 97.2% for various crimes. Additionally, DL techniques, particularly convolutional stacked bidirectional long short-term memory (LSTM), allowed them to detect crime hotspots with an accuracy of 95.64%.

The researchers point out how the significance of emotional states in speech patterns allowed them to explore speech-based emotion detection. They took into account linguistic origin, paralinguistic cues, and the characteristics of the speaker. This allowed them to integrate the emotional data they obtained with other factors such as location and the type of crime that takes place in a hotspot. While, the notion sounds rather futuristic, the rapid advances in algorithms that can extract and identify patterns in data is in no way a matter only for science fiction. The team says that their approach could monitor activity in crime hotspots, detect crimes, and forecast future criminal activities.

Future work might allow similar machine learning techniques to be used for emergency response systems, rather than only in crime fighting. By analysing the emotional content of a person calling the emergency services, the system might be able to distinguish between genuine emergencies and non-emergency or even fraudulent calls, which could reduce the burden on the services considerably. It is only a matter of time before the research takes the prediction accuracy closer and closer to the ideal 100 percent of the ultimate crime-fighting AI emotion detector.

Kalai Selvan, A. and Sivakumaran, N. (2024) ‘Crime detection and crime hot spot prediction using the BI-LSTM deep learning model’, Int. J. Knowledge-Based Development, Vol. 14, No. 1, pp.57–86.

Research pick: Charging up a review of lithium-ion batteries - "Lithium-ion battery: a review"

A comprehensive review of lithium-ion batteries in electric vehicles and energy-storage systems offers a valuable resource for researchers in this area, according to the authors writing in the International Journal of Vehicle Information and Communication Systems.

Electric vehicles (EVs) are an important part of sustainable personal transport as we try to move from a world drive on fossil fuels to one powered by solar, wind, and other renewables. Lithium-ion batteries continue to play a vital role in the ongoing success of EVs, and will do so until an even better alternative storage technology is developed.

Mandar Maruti Bidwe and Swanand Gajanan Kulkarni of the SKN Sinhgad College of Engineering in Korti, Pandharpur, Maharashtra, India, conducted a detailed review of the research literature covering the period 2010 to 2022. They hope that their work will shine headlights on the lithium-ion battery roadmap and help researchers navigate the terrain towards future sustainable of electric transportation and energy storage.

The team’s review looked at various aspects of lithium-ion battery technology and shows that it is important to understanding the diverse materials used in different types of battery and the impact these material choices have on performance, lifetime, and sustainability. The team explains that materials such as lithium cobalt oxide offer high energy density but are hindered by limited availability and lower thermal stability. By contrast, materials such as lithium iron phosphate are much safer and longer-lasting, but do not necessarily have the energy density some applications demand.

There is an ongoing need to model the behaviour of different types of battery in order to develop technology that optimises battery performance and management systems without too much compromise in terms of sustainability and resource safety and ethics. The review points to various papers that have focused on such models and assesses which might be used to best effect by researchers. This is critical given that challenges exist, not least in terms of the recycling and sustainability. The team points to several research gaps in these areas that could help focus efforts.

Research into lithium-ion batteries is multidisciplinary and given its central role in the electrification of transport it will be a focus for several years yet. This review offers waymarkers on the roadmap for research and development.

Bidwe, M.M. and Kulkarni, S.G. (2024) ‘Lithium-ion battery: a review’, Int. J. Vehicle Information and Communication Systems, Vol. 9, No. 2, pp.135–163.

Free sample articles newly available from International Journal of Powertrains

The following sample articles from the International Journal of Powertrains are now available here for free:

• Energy consumption analysis of extended-range electric vehicles with different driving cycle and different modes
• Design and implementation of novel variants of multi-level inverters for traction and heavy vehicle applications
• Deep-Q-network-based energy management of multi-resources in limited power micro-grid
• Transmission energy consumption analysis using ridge regression in wireless sensor nodes
• Performance analysis of precise energy consumption algorithm for smart home using hybrid renewable energy

Research pick: Clocking the influencer effect on TikTok - "Enhance the effectiveness of affiliate marketing on Tiktok for young people"

TikTok is a social media platform known for its short-form videos. Content creators, who have built a significant following on the site, often work with corporate brands to promote products to their audience, often through affiliate marketing. This involves a so-called influencer sharing products in their videos with affiliate links and then earning a commission from the company for purchases made through those links. It might be said that success lies in creating authentic content that attracts users and takes advantage of the current trends. However, for an influencer to be successful, they need to be transparent about their affiliate relationships in order to build and maintain the trust of their audience.

Writing in the International Journal of Technology Marketing, Minh T.H. Le of the College of Business at the University of Economics in Ho Chi Minh City (UEH), Vietnam, discusses how the effectiveness of affiliate marketing might be improved by users hoping to influence young people. Le’s study was based on a standardized questionnaire distributed across internet platforms. The results were analysed using Partial Least Squares Structural Equation Modelling (PLS-SEM). Her research identified some of the factors affecting consumer trust and buying decisions, including the opinions of other followers.

She found that the perceived expertise of content creators and feedback from their followers is important to consumer trust. Le explains that a marketing campaign can pivot on this point. However, the entertainment value of an influencer video, is perhaps the most important factor leading to better user engagement and whether that user buys the products touted by the influencers they follow.

The detailed findings discussed in IJTMKT offer practical guidance for marketers and businesses who are attempting to make the most of digital marketing. The advice suggests that companies need to understand how Key Opinion Leaders, Key Opinion Consumers, and influencers operate and the effect they have on everyday users. Given that TikTok appeals to a wide audience seeking amusement as well as product recommendations, it is worth exploring in detail its potential as a marketing channel.

Le, M.T.H. (2024) ‘Enhance the effectiveness of affiliate marketing on Tiktok for young people’, Int. J. Technology Marketing, Vol. 18, No. 2, pp.162–184.

Special issue published: "Synthesis and Characterisation of Nanomaterials: Latest Advances and Prospects Part 2"

International Journal of Microstructure and Materials Properties 17(2/3) 2024

• Life prediction of vehicle carbon fibre ceramic brake pads based on wavelet packet energy entropy
• Thermal runaway detection method of SiO2 aerogel battery pack based on mixed Gaussian hidden Markov model
• Analysis of stress corrosion behaviour of TC4 titanium alloy in simulated seawater environment
• Surface wear detection of automotive cermet composite brake pads based on machine vision
• Analysis of the influence of XYPEX admixture on the frost resistance of nanometer CaCO3 concrete
• Experimental study on the effect of composite nano-SiO2 on the durability of concrete
• Strength prediction method of nano ceramic composites based on nonlinear regression analysis
• Analysis of pressure damage characteristics of carbon fibre recycled concrete based on acoustic emission technology
• Experimental study on the microstructure of nano TiO2 concrete under carbonisation freeze-thaw conditions
• Study on the dynamic fracture toughness of laminated fine ceramic composites based on fatigue damage accumulation theory
• Fabrication of aluminium metal matrix composites with Al 6063 reinforced with Al2O3 by two step stir casting method for investigation of mechanical properties
• Study on durability analysis method of concrete mixed with nanometre calcium carbonate in acid environment
• The effect of nano-SiO2 strengthening the performance of recycled concrete under ion erosion environment

Research pick: Deep learning in the digital library - "Development of a unified digital library system: integration of image processing, big data, and deep learning"

The digital library is a searchable store of text, audio and visual materials, and more. However, as the amount of data that must be stored and made searchable increases, efficient management and retrieval can be a major headache for the digital library. Research in the International Journal of Information and Communication Technology could lead to a new solution to the problem by integrating image processing, big data analytics, and deep learning techniques.

Xiaoyan Wang and Meimei Jia of Nanyang Normal University, Nanyang, Henan, China, like others, recognise the complexities of enhanced multimedia search and retrieval and have turned to the modern tool of deep learning to help. The team has developed a cross-media semantic search framework. This finds and uses the correlations between different types of media to assist in search and retrieval. Their deep learning algorithm can analyse and organize multimedia resources to improve search accuracy and system performance. Indeed, the use of this cross-modal correlation analysis and hierarchical knowledge inference in refining search results gave the team an almost 12 percent boost in search performance when compared with conventional approaches.

The approach will be useful for generic digital libraries and could be extended to personal devices such as smartphones, enabling greater access to useful information silos for the lay public. In more specialist applications, the same approach might be used in medical and scientific information systems. This could allow complex medical imagery, such as MRI scans and diagnostic test data and chemical databases, to be more readily searchable. In enterprise knowledge management systems, with such a system, companies could better handle their ever-accumulating data and information. Moreover, in any field where vast amounts of multimedia data accumulate every day and need efficient search and retrieval methods to make the most of the information they hold, an improved system will benefit users.

Wang, X. and Jia, M. (2024) ‘Development of a unified digital library system: integration of image processing, big data, and deep learning’, Int. J. Information and Communication Technology, Vol. 24, No. 3, pp.378–391.

Free sample articles newly available from International Journal of Economic Policy in Emerging Economies

The following sample articles from the International Journal of Economic Policy in Emerging Economies are now available here for free:

• Design-proposal of a conceptual model of intellectual property management and technology transfer in the context of higher education in Latin America
• Behaviour of financial consumers in banking market: a central and eastern European perspective regarding gender gap
• A study of macroeconomic effects on the growth of BRICS: a systematic review
• The effect of accounting conservatism on the cost of equity capital: evidence from Indonesia
• Integrated perspective of corporate social responsibility on ASEAN Capital Market Forum members corporate governance code
• Economic uncertainty and working capital management: evidence from Turkey

Free open access article available: "Development of a unified digital library system: integration of image processing, big data, and deep learning"

The following paper, "Development of a unified digital library system: integration of image processing, big data, and deep learning" (International Journal of Information and Communication Technology 24(3) 2024), is freely available for download as an open access article.

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

Research pick: The CALL of the word - "Research on scoring mechanism of spoken English self-study system taking into account artificial intelligence technology and speech knowledge recognition algorithm"

Technology is changing all areas of education not least language learning. Research in the International Journal of Information and Communication Technology has looked at the potential of Computer-assisted Language Learning (CALL).

Learning a new language has usually relied on the traditional classroom setting and a native speaker of the language to teach students the vocabulary and grammar. However, there have for many years language learning systems that use voice recordings and books. In recent years, these systems have migrated to smartphones. The number of learners answering the CALL has risen because of the accessibility and convenience. Such systems now use artificial intelligence and algorithmic processing to help learners get to grips with their language second, or third, or more, language of choice. Indeed, the new tools offer an immersive and interactive language-learning experience.

Ning Li of the Public Teaching Department at Henan Vocational College of Tuina in Luoyang, Henan, China, explains that one aspect of language learning by app is the potential of the software to provide learners with an assessment of their progress and oral proficiency. If the system can analyse the words spoken by the learner in their non-native tongue, then they can be guided to the next level in their education appropriately or given advice on checking and rechecking their understanding and ability.

CALL systems can offer tailored teaching and thus have the potential to address individual learning needs, accelerating language acquisition for those learners who can cope and slowing the teaching process for those who need more time. Of course, variability in accent and dialect represent a challenge for the assessment algorithms and new innovations and refinements are still needed to make CALL as effective as traditional teaching and learning methods.

CALL could open up linguistic opportunities far and wide. With improvements in AI such systems will be able to assess learners before they are released into the wilds of international conversation.

Li, N. (2024) ‘Research on scoring mechanism of spoken English self-study system taking into account artificial intelligence technology and speech knowledge recognition algorithm’, Int. J. Information and Communication Technology, Vol. 24, No. 3, pp.350–365.

Free open access article available: "Quality optimised design of English multimedia courseware combined with 4C comprehensive design model"

The following paper, "Quality optimised design of English multimedia courseware combined with 4C comprehensive design model" (International Journal of Information and Communication Technology 24(3) 2024), is freely available for download as an open access article.

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

Free open access article available: "Research on scoring mechanism of spoken English self-study system taking into account artificial intelligence technology and speech knowledge recognition algorithm"

The following paper, "Research on scoring mechanism of spoken English self-study system taking into account artificial intelligence technology and speech knowledge recognition algorithm" (International Journal of Information and Communication Technology 24(3) 2024), is freely available for download as an open access article.

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

Research pick: Cutting content in a crisis - "Supporting digital key workers: addressing the challenges faced by content moderators during and after the COVID-19 pandemic"

The responsibility for maintaining online safety relies on content moderators particularly in times of crisis. However, not all platforms even have moderation systems in place and so disinformation, misinformation, propaganda, and fake news often circulate freely. The time of the COVID-19 pandemic was a case in point, but the propagation of fake news occurs during times of political change and in the wake of other kinds of crises and socioeconomic upheaval. However, there is much content online that is illegal rather than simply being fake and that must be removed summarily.

Some social media platforms and websites do have individuals and even teams who are tasked with checking user-generated content to ensure it does not contravene the law. Elena Martellozzo, Paula Bradbury, Ruth Spence, and Jeffrey DeMarco of Middlesex University, London, UK, and Paul Bleakley of the University of New Haven, West Haven, USA, point out that during and after the COVID-19 pandemic there was a surge in the volume of illegal content. They report details of their findings and the implications in the International Journal of Technology, Policy and Management.

The researchers have looked at the experience of content moderators during this period and their findings offer new insights into how this important online role can affect the moderators’ mental well-being. Indeed, the upward trend in illegal material being shared online, exacerbated by lockdown measures during the pandemic, put the content moderators under immense pressure. There was a heightened risk of personal burnout, mental health problems, and even trauma when it came to particular kinds of illegal content that required moderation. The new findings suggest that there is an urgent need to improve the working conditions and personnel backup for such moderators.

Lessons drawn from the pandemic era should provide service providers and their staff, including their content moderators, useful guidance for the improvement of working conditions. Employers must prioritize mental health support, fair compensation, and comprehensive training, the research suggests. This is especially important given the role played by content moderators in helping to remove illegal content from the internet.

The researchers add that clear communication, professional development opportunities, and tailored support mechanisms, particularly for those working remotely or in a hybrid work environment, are important considerations for employers and service providers.

Martellozzo, E., Bleakley, P., Bradbury, P., Spence, R. and DeMarco, J. (2024) ‘Supporting digital key workers: addressing the challenges faced by content moderators during and after the COVID-19 pandemic’, Int. J. Technology, Policy and Management, Vol. 24, No. 2, pp.212–228.

Special issue published: "Health Economics and Econometrics"

International Journal of Computational Economics and Econometric 2024 Vol.14 No.2

• Procuring medical devices: evidence from Italian public tenders
• Technical efficiency in Irish public hospitals: a multi-output distance function SFA approach
• The role of home healthcare in reducing hospital readmissions and costs in patients with acute myocardial infarction
• Is the European refugee crisis a potential threat to public health? Evidence from Italy
• Might low-protein diet for chronic kidney disease patients be successful? A case study with the application of a random effects ordered probit model
• Financial problems and self-reported health status: an analysis for selected European countries

Free open access article available: "Critical success factors of strategic alliance in the shipping industry"

The following paper, "Critical success factors of strategic alliance in the shipping industry" (International Journal of Shipping and Transport Logistics 18(2) 2024), is freely available for download as an open access article.

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

Special issue published: "Interdisciplinary Applications and Technologies of Computer Vision"

International Journal of Computational Intelligence Studies 12(3/4) 2023

• Performance prediction analysis of college aerobics course based on back propagation neural network
• Research on the optimal charging method of parallel power batteries for smart electric vehicles
• Research on spiking neural network in art visual image classification
• Application of binocular image reconstruction method in the construction of 3D model of wooden arch corridor bridge structure
• New media interaction in art design based on deep learning binocular stereo vision
• Research on intelligent access control technology of face recognition model based on parameter sharing and dense connection
• Nonlinear modelling and analysis of stable behaviour of robot gait control system based on image processing technology

Research pick: Crowdfunding success - "Does first impression count? A look at Indiegogo campaigns on the ‘Explore All Projects’ page"

The advent of crowdfunding, whereby innovative ideas find financial backing from the collective support of online communities, such as Indiegogo and Kickstarter, has allowed countless projects to become viable in recent years. Many of those projects, while attractive and ultimately successful, may never have garnered support from conventional investors and backers. Of course, not all crowdfunding enterprises are successful, and a study in the International Journal of Electronic Business has looked at how much effect first impressions has on what a campaign might ultimately achieve.

Mathupayas Thongmak of the Thammasat Business School at Thammasat University in Bangkok, Thailand, has focused on Indiegogo as a well-known crowdfunding platform. She points out that to date, the rate of success among crowdfunding campaigns remains relatively low. The present study offers insights that might help putative campaigners develop a more effective strategy for success.

Presentation is almost all when it comes to a successful campaign. Potential backers wading through many project options commonly rely on first impressions to decide whether to investigate a given campaign further. In other words, an attractive thumbnail image, text introduction, and category choice, are vital. Without them, most backers scanning for opportunities will simply swipe left, to use the parlance of dating apps, where such a swipe amounts to a rejection.

Earlier work has looked at the factors that coincide with a successful crowdfunding campaign, but Thongmak has used descriptive statistics, word clouds, tree maps, and hierarchical regression analysis to analyse data from more than 300 campaigns to look at what characterises successful outcomes. It seems that timing is almost everything, but appropriate category choice can affect success rate for campaigners significantly. Moreover, the most likely to succeed are campaigns in the technology and innovation sectors, with health and fitness products featuring prominently, followed by home, travel, and outdoor equipment. It is worth noting that text on a thumbnail image did not affect success rate. As such, Thongmak suggests that campaigners should use their thumbnail image to make their project stand out more from the other images through the choice of a more creative design and colour scheme.

Thongmak, M. (2024) ‘Does first impression count? A look at Indiegogo campaigns on the ‘Explore All Projects’ page’, Int. J. Electronic Business, Vol. 19, No. 2, pp.181–208.

Free open access article available: "Impact of surface choking on gas-lift stability and flow behaviour in oil producing wells"

 The following paper, "Impact of surface choking on gas-lift stability and flow behaviour in oil producing wells" (International Journal of Oil, Gas and Coal Technology 35(3) 2024), is freely available for download as an open access article.

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

Special issue published: "AI/Machine Learning Techniques as a Tool for Process Modelling and Product Design"

International Journal of Product Development 28(1/2) 2024

• Colour offset compensation method of product packaging image based on colour difference interpolation
• The deep mining of consumer behaviour data on product network marketing platform
• Study on evaluation method of human-computer interface quality of intelligent products based on Bayesian classification
• Colour matching method of product interactive interface based on user experience
• Fuzzy edge detection method of product packaging image based on Kalman filter
• Prediction method of product market demand based on Prophet random forest

Additional papers

• Review of models and frameworks for set-based design
• A formal consideration of user tactics during product evaluation in early-stage product development