Systematic Mapping Research Articles

Modelling the quantification of requirements technical debt

AbstractRequirements Technical Debt (RTD) applies the Technical Debt (TD) metaphor to capture the consequences of sub-optimal decisions made concerning Requirements. Understanding the quantification of RTD is key to its management. To facilitate this understanding, we developed a conceptual model, the Requirements Technical Debt Quantification Model (RTDQM). Our work is grounded in the literature found via a systematic mapping study and informed by prior work modeling the quantification of software code-related TD types. The key finding is that although RTD is similar to code-related TD in many aspects, it also has its own components. RTD can be incurred regardless of the presence of code-related TD. Unlike code-related TD, RTD has a feedback loop involving the user. RTD can have a cascading impact on other development activities, such as design and implementation, apart from the extra costs and efforts incurred during requirements engineering activities; this is modeled by the RTD Interest constituents in our model. The model was used to compare and analyze existing quantification approaches. It helped identify what RTD quantification concepts are discussed in the existing approaches and what concepts are supported by metrics for their quantification. The model serves as a reference for practitioners to select existing or to develop new quantification approaches to support informed decision-making for RTD management.

Systematic Mapping Study of Sales Forecasting: Methods, Trends, and Future Directions

In a dynamic business environment, the accuracy of sales forecasts plays a pivotal role in strategic decision making and resource allocation. This article offers a systematic review of the existing literature on techniques and methodologies used in forecasting, especially in sales forecasting across various domains, aiming to provide a nuanced understanding of the field. Our study examines the literature from 2013 to 2023, identifying key techniques and their evolution over time. The methodology involves a detailed analysis of 516 articles, categorized into classical qualitative approaches, traditional statistical methods, machine learning models, deep learning techniques, and hybrid approaches. The results highlight a significant shift towards advanced methods, with machine learning and deep learning techniques experiencing an explosive increase in adoption. The popularity of these models has surged, as evidenced by a rise from 10 articles in 2013 to over 110 by 2023. This growth underscores their growing prominence and effectiveness in handling complex time series data. Additionally, we explore the challenges and limitations that influence forecasting accuracy, focusing on complex market structures and the benefits of extensive data availability.

Trends and challenges in research into the human aspects of ransomware: a systematic mapping study

Purpose The purpose of this paper is to provide an overview of the trends and challenges relating to research into the human aspects of ransomware. Design/methodology/approach A systematic mapping study was carried out to investigate the trends in studies into the human aspects of ransomware, identify challenges encountered by researchers and propose directions for future research. For each of the identified papers from this study, the authors mapped the year of publication, the type of paper, research strategy and data generation method, types of participants included, theories incorporated and lastly, the authors mapped the challenges encountered by the researchers. Findings Fifty-nine papers published between 2006 and 2022 are included in the study. The findings indicate that literature on the human aspects of ransomware was scarce prior to 2016. The most-used participant groups in this area are students and cybersecurity professionals, and most studies rely on a survey strategy using the questionnaire to collect data. In addition, many papers did not use theories for their research, but from those that did, game theory was used most often. Furthermore, the most reported challenge is that being hit with ransomware is a sensitive topic, which results in individuals and organisations being reluctant to share their experiences. Research limitations/implications This mapping study reveals that the body of literature in the area of human aspects of ransomware has increased over the past couple of years. The findings highlight that being transparent about ransomware attacks, when possible, can help others. Moreover, senior management plays an important role in shaping the information security culture of an organisation, whether to have a culture of transparency or of secrecy. Originality/value This study is the first of its kind of systematic mapping studies contributing to the body of knowledge on the human aspects of ransomware.

A Systematic Mapping Study Exploring Quantification Approaches to Code, Design, and Architecture Technical Debt

To effectively manage Technical Debt (TD), we need reliable means to quantify it. We conducted a Systematic Mapping Study (SMS) where we identified 39 quantification approaches for Code, Design, and Architecture TD. We analyzed concepts and metrics discussed in these quantification approaches by classifying the quantification approaches based on a set of abstract TD Quantification (TDQ) concepts and their high-level themes, process/time, cost, benefit, probability, and priority, which we developed during our SMS. This helped identify gaps in the literature and to propose future research directions. Among the abstract TDQ concepts discussed in the different quantification approaches, TD item, TD remediation cost, TD interest, and Benefit of remediating TD were the most frequently discussed concepts. They were also supported by some form of measurement. However, some TDQ concepts were poorly examined, for example, the benefit of taking TD. It was evident that cost concepts were more frequently quantified among the approaches, while benefit concepts were not. Most of the approaches focused on remediating TD in retrospect rather than quantifying TD to strategically use it during software development. This raises the question of whether existing approaches reliably quantify TD and suggests the need to further explore TD quantification.

Collaboration and term usage dynamics in agricultural buffer strip research: Research weaving

Abstract Systematic maps are used to comprehensively gather and describe the literature on a topic, which is often defined by policy and practice relevance and stakeholder input, identifying trends and gaps in research. Bibliometric methods elucidate the connections between publications, for example, providing information about collaboration in research communities. Research weaving combines these approaches to produce a comprehensive view of research activity on a well‐defined research area. In this paper, we conduct and describe a bibliometric analysis on a previously published systematic map on the functional roles of buffer strips in agricultural fields. Among other findings, the original systematic map found a paucity of studies addressing multiple functional roles and a huge variation in terminology related to buffer strips. We used research weaving to deepen our understanding of these findings and shed light on collaboration within and among the research communities contributing knowledge to this field. Of the 1019 papers originally included in the systematic map, 930 were identified in Lens.org and used for subsequent analyses. Co‐authorship and bibliographic coupling networks identified distinct research communities, defined by geography, subdiscipline and characteristic usage of buffer strip terminology. Topic modelling provided further information about these subcommunities and aligned with manually extracted information about the studies' focus on functional roles, indicating potential utility for screening of records in large systematic maps. Practical Implication: We demonstrate that research weaving methods add insights in support of and in addition to the original systematic map. We provide a methodological approach and discuss limitations related to applying bibliometric analyses to a previously published systematic map. We demonstrate the feasibility of this approach and its ability to enhance and enrich the findings gained from conventional systematic mapping techniques.

Statistical relationships between surface form and sensory meanings of English words influence lexical processing.

Across spoken languages, there are some words whose acoustic features resemble the meanings of their referents by evoking perceptual imagery, i.e., they are iconic (e.g., in English, "splash" imitates the sound of an object hitting water). While these sound symbolic form-meaning relationships are well-studied, relatively little work has explored whether the sensory properties of English words also involve systematic (i.e., statistical) form-meaning mappings. We first test the prediction that surface form properties can predict sensory experience ratings for over 5,000 monosyllabic and disyllabic words (Juhasz & Yap, 2013), confirming they explain a significant proportion of variance. Next, we show that iconicity and sensory form typicality, a statistical measure of how well a word's form aligns with its sensory experience rating, are only weakly related to each other, indicating they are likely to be distinct constructs. To determine whether form typicality influences processing of sensory words, we conducted regression analyses using lexical decision, word recognition, naming and semantic decision tasks from behavioral megastudy data sets. Across the data sets, sensory form typicality was able to predict more variance in performance than sensory experience or iconicity ratings. Further, the effects of typicality were consistently inhibitory in comprehension (i.e., more typical forms were responded to more slowly and less accurately), whereas for production the effect was facilitatory. These findings are the first evidence that systematic form-meaning mappings in English sensory words influence their processing. We discuss how language processing models incorporating Bayesian prediction mechanisms might be able to account for form typicality in the lexicon. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Impacts of polycultural cropping on crop yields and biodiversity: A systematic map protocol

Abstract Agriculture is currently the largest driver of biodiversity‐loss worldwide. There is a critical need to develop agricultural systems that protect and promote biodiversity, while also meeting local and global food needs. Ecological theory suggests that cultivating crops in diverse mixtures both maximises niche occupancy and generates additional niches, generating both higher yields and higher biodiversity than cultivation in monocultures. A large and growing body of agronomic research provides strong evidence for the potential productivity and biodiversity benefits of in‐field crop‐diversification strategies. This protocol sets out a methodology for a systematic map of evidence on yield‐ and biodiversity‐outcomes in ‘polycultures’—systems of cultivation where multiple food crop species are grown together simultaneously at field‐scale. Systematic searches with a global scope will be conducted in Web of Science Core Collection, Scopus, and CAB Abstracts to yield a comprehensive sample of relevant published, peer‐reviewed literature. The articles returned by searches will be subject to eligibility screening according to pre‐defined inclusion criteria, at successive stages (title and abstract, and full text). Following this, we will extract data from eligible studies on study designs, survey and sampling protocols, experimental treatments and comparators, and outcomes measured. A narrative synthesis, illustrated by tables, figures and maps, will describe the quantity and characteristics of the available evidence on the impacts of polycultural cropping on (i) crop yields, and (ii) agroecosystem biodiversity. We will also identify the research that examines these two outcomes in parallel. The synthesis will be accompanied by a published database containing bibliographic information as well as data (see ‘2’) on study characteristics and outcomes. Practical implications. The anticipated systematic map will provide a synthesis of current evidence regarding the potential yield‐ and biodiversity‐impacts of polycultural cropping. We will identify key knowledge gaps, and ‘clusters’ of related evidence that could lend themselves to further quantitative synthesis via subsequent systematic reviews and/or meta‐analyses. As such, the work will facilitate future appraisal of the potential of polyculture as a tool to bridge the currently conflicting priorities of food production on the one hand and biodiversity conservation on the other.

Software maintenance practices using agile methods towards cloud environment: A systematic mapping

AbstractAgile methods have emerged to overcome the obstacles of structured methodologies, such as the waterfall, prototype, spiral, and so on. There are studies showing the usefulness of agile approaches in software development. However, studies on Agile maintenance are very limited in number. Regardless of the chosen methodology, software maintenance can be carried out in either a local (on‐the‐premise) or global (distributed) environment. In a local environment, the software maintenance team is co‐located on the same premises, while in a global environment, the team is geographically dispersed from the customer. The main objective of this Systematic Mapping (SM) study is to identify the practices useful for software maintenance using the Agile approaches in the Cloud environment. We have conducted a comprehensive search in well‐known digital databases and examined the articles that map to the pre‐defined inclusion criteria. The study selected and analyzed 48 articles out of 320 published between 2000 and 2022. The findings of the mapping study reveal that Agile can resolve the major issues faced in traditional software maintenance, making the role of this approach significant in global/distributed software maintenance. Cloud computing plays a vital role in software maintenance. Most of the studies highlight the application of XP‐ and Scrum‐based Agile maintenance models. The study found a need for more Agile maintenance solutions in the cloud, highlighting the importance of agile in software maintenance, both locally and globally. Irrespective of the environment, Cloud computing provides a centralized platform for collaboration and communication, while also offering scalability and flexibility to adapt to diverse infrastructure needs. This allows agile maintenance practices to be implemented across both local and global environments, leveraging the cloud's capabilities to overcome geographical and infrastructural challenges.

Obituary: Surendra Abaji Pandhare (1940 – 2023)

Shri Surendra Abaji Pandhare, Retired Director, Geological Survey of India (GSI), did his schooling from Chandrapur. He completed his post graduation in Applied Geology from the University Department of Geology, Nagpur University, in 1965, topping the merit list. He worked with the Directorate of Geology and Mining (DGM), Maharashtra, for two years thereafter, and joined GSI as Assistant Geologist in February 1968. Shri Pandhare was promoted as Geologist in 1972 and as Senior Geologist in 1981. Posted at Raipur and Bhopal, he was engaged in systematic mapping. Thereafter, he was engaged in magnesite exploration in Bastar dist, bauxite in Amarkantak and East Coast, base metals in Sidhi district and iron ore in Raoghat area, all in the then undivided M.P. state. During 1968, he compiled technical information on the till then, all the GSI Engineering Geology projects in Central India and prepared a reference map. Shri Pandhare was transferred to the then Planning and Coordination Division (now Policy Support System Division), Central Region, GSI, Nagpur, in 1982, where he continued to be posted till 1998. Here, he handled matters related to technical coordination of field items in the Central Region, material management (stores) and was also inquiry officer for many vigilance cases . He was elected as President of the GSI Scientific Officers Association (GSISOA) for the 1993- 95 term. His keen administrative acumen helped him navigate through as a popular leader, during the turbulent years of career progression of GSI geoscientists. He was liked by a vast majority in the geoscientific fraternity of the GSI.

A mapping review of challenges in existing technology-based occupational safety training in the tourism and hospitality industry: Research potential in commercial kitchens

Introduction: An effective response to a safe and healthy work environment relies on advanced preparedness such as occupational safety training. The main objectives of this study are to describe and classify the most critical challenges and identify knowledge gaps in the literature that could inform future research. Methods: A systematic mapping review gathers information from six search engines; Francis and Taylor, Scopus, Science Direct, Emerald Insight, and SpringerLink, which yielded journal publications between 1948 and 2022. The data were analyzed using meta-analysis from 135,310 article search results, whereby 20 articles met the inclusion criteria. The studies varied in terms of aim, study design, and reporting detail. Results: The results showed that Canada and the United States are countries that study safety training in the tourism or hospitality industry, mainly in food management and food safety. The results also show that studies on occupational safety training in commercial kitchens are not common in the existing literature. The findings revealed that the highest number of articles involving safety training focused on food safety and food management in the tourism industry but less on kitchen workers' safety. Conclusions: This mapping review demonstrates hospitality workers' struggles, especially commercial kitchen workers. This review presents the types of technologies used for occupational safety training and provides an overview of different strategies that address the challenges. Among the most significant obstacles in occupational safety and health training are a lack of knowledge, high financial costs for implementation, and outdated policies from authorities.

A Systematic Mapping Review of COVID 19 Data Feature for Infection Detection

The coronavirus disease (COVID-19) has become widespread. It has caused outbreaks in more than 213 nations leading to many fatalities. It is still going around in all its forms. The diagnosis, prognosis, and treatment of disease include a variety of novel approaches, including machine learning, artificial intelligence, and the Internet of Things (IoT). Numerous studies on the detection of COVID-19 using various techniques have been conducted. Numerous strategies are used and suggested in the literature. This study aims to pinpoint the data features of COVID-19 that have been employed for disease detection by IoT devices using machine learning techniques. This research project offers a comprehensive mapping and evaluation of current studies on COVID-19. The focus is on IoT gadgets employing machine learning for detection. The study is conducted using a systematic mapping review. For the mapping study review, five electronic databases were searched. Studies published until April 2022 were considered. There are 50 studies selected that address COVID-19, IoT devices, and machine-learning approaches. This research concludes the investigation of data features that are usually used for effective, and efficient detection. This research will be useful for a future COVID-19 variant pandemic, as it provides a comprehensive review of the best data features for disease detection. Also, the data features identified in this research can aid in the early and precise exposure of COVID-19 in existing circumstances.

Photoactivated Chromophore for Keratitis-Corneal Cross-linking (PACK-CXL)-A Scoping Review Based on Preclinical Studies.

Photoactivated chromophore for keratitis-corneal cross-linking (PACK-CXL) stabilizes the corneal stroma and eliminates microorganisms. Numerous PACK-CXL protocols, using different energy sources and chromophores, have been applied in preclinical studies, including live animal studies, with various experimental designs and endpoints. So far, a systematic mapping of the applied protocols and consistency across studies seems lacking but is essential to guide future research. The scoping review protocol was in line with the JBI Manual for Evidence Synthesis. Electronic databases were searched (Embase, MEDLINE, Scopus, Web of Science) to identify eligible records, followed by a two-step selection process (title and abstract screening, full text screening) for record inclusion. We extracted information on (1) different PACK-CXL protocol characteristics; (2) infectious pathogens tested; (3) study designs and experimental settings; and (4) endpoints used to determine antimicrobial and tissue stabilizing effects. The information was charted in frequency maps. The searches yielded 3654 unique records, 233 of which met the inclusion criteria. With 103 heterogeneous endpoints, the researchers investigated a wide range of PACK-CXL protocols. The tested microorganisms reflected pathogens commonly associated with infectious keratitis. Bacterial solutions and infectious keratitis rabbit models were the most widely used models to study the antimicrobial effects of PACK-CXL. If preclinical PACK-CXL studies are to guide future translational research, further cross-disciplinary efforts are needed to establish, promote, and facilitate acceptance of common endpoints relevant to PACK-CXL. Systematic mapping of PACK-CXL protocols in preclinical studies guides future translational research.

Identification of Shallow Groundwater Facies and Flow Patterns in Batang Regency, Central Java, Indonesia

Abstract Population growth as a result of a subsequent increase in the economic center and industrial complex construction has also proven to influence the shallow groundwater occurrence in Batang Regency, Central Java, Indonesia. The region per se, had a minimum amount of observation and literature, especially regarding the issue namely groundwater flow pattern and facies distribution. This research discussed hydrogeological assessment through systematic mapping to investigate shallow groundwater occurrence, including 90 observation & measurement points consisting of 89 dug well and one water spring. Based on purposive random sampling with upstream-downstream consideration, 73 of 90 samples were analyzed in the laboratory to determine groundwater hydrochemistry. The results indicated that the shallow groundwater pattern in Batang Regency generally flows from south to north with a dominant southwest-northeast pattern. Based on the trilinear piper diagram, shallow groundwater facies in the study area are characterized by calcium bicarbonate, alkaline chloride, alkaline bicarbonate, and mixed types. The distribution of calcium bicarbonate facies is widely spread in the southern part of the study area. In contrast, alkaline bicarbonate is mainly found between the coastline and hilly in the south. On the other hand, alkaline chloride is distributed evenly along the coastal area. Intermixing of different groundwater facies is expected due to its positive correlation between TDI and major ions plot in the composition diagram.

A research synthesis of humans, animals, and environmental compartments exposed to PFAS: A systematic evidence map and bibliometric analysis of secondary literature

BackgroundPer- and polyfluoroalkyl substances (PFAS) are a class of widely used anthropogenic chemicals. Concerns regarding their persistence and potential adverse effects have led to multiple secondary research publications. Here, we aim to assess the resulting evidence base in the systematic secondary literature by examining research gaps, evaluating the quality of reviews, and exploring interdisciplinary connections. MethodsThis study employed a systematic evidence-mapping approach to assess the secondary literature on the biological, environmental, and medical aspects of exposure to 35 fluorinated compounds. The inclusion criteria encompassed systematic reviews published in peer-reviewed journals, pre-prints, and theses. Comprehensive searches across electronic databases and grey literature identified relevant reviews. Data extraction and synthesis involved mapping literature content and narrative descriptions. We employed a modified version of the AMSTAR2 checklist to evaluate the methodological rigour of the reviews. A bibliometric data analysis uncovered patterns and trends in the academic literature. A research protocol for this study was previously pre-registered (osf.io/2tpn8) and published (Vendl et al., Environment International 158 (2022) 106973). The database is freely accessible through the interactive and user-friendly web application of this systematic evidence map at https://hi-this-is-lorenzo.shinyapps.io/PFAS_SEM_Shiny_App/. ResultsOur map includes a total of 175 systematic reviews. Over the years, there has been a steady increase in the annual number of publications, with a notable surge in 2021. Most reviews focused on human exposure, whereas environmental and animal-related reviews were fewer and often lacked a rigorous systematic approach to literature search and screening. Review outcomes were predominantly associated with human health, particularly with reproductive and children’s developmental health. Animal reviews primarily focused on studies conducted in controlled laboratory settings, and wildlife reviews were characterised by an over-representation of birds and fish species. Recent reviews increasingly incorporated quantitative synthesis methodologies. The methodological strengths of the reviews included detailed descriptions of study selection processes and disclosure of potential conflicts of interest. However, weaknesses were observed in the critical lack of detail in reporting methods. A bibliometric analysis revealed that the most productive authors collaborate within their own country, leading to limited and clustered international collaborations. ConclusionsIn this overview of the available systematic secondary literature, we map literature content, assess reviews’ methodological quality, highlight data gaps, and draw research network clusters. We aim to facilitate literature reviews, guide future research initiatives, and enhance opportunities for cross-country collaboration. Furthermore, we discuss how this systematic evidence map and its publicly available database benefit scientists, regulatory agencies, and other stakeholders by providing access to current systematic secondary literature on PFAS exposure.

Key-Plain Mapping Algorithm: A Symmetric Key Cryptographic Technique for Secure Communication

Abstract:- In the realm of cryptography, ensuring secure communication is paramount. Symmetric key cryptographic techniques offer a robust means of encryption and decryption. The Key-Plain Mapping Algorithm presents a novel approach to symmetric key cryptography, utilizing a fixed keyword and systematic mapping between plaintext and ciphertext alphabets. This thesis delves into the principles, operations, and security aspects of the Key-Plain Mapping Algorithm, demonstrating its efficacy in securing digital communication. Keywords:- plain text; cipher text or encrypted message; encryption; decryption; symmetric key cryptography; decrypted message; keyword

Improved assessments of subsurface projects: Systematic mapping of geosystem services and a review of their economic values

Awareness of the subsurface and its multitude of resources is generally low and decisions on access to subsurface resources are often guided by a ‘first come, first served principle’. Although not yet fully developed, the concept of geosystem services has been put forward to make subsurface resources more visible and acknowledged in decision-making. This study (1) illustrates a systematic mapping of effects on geosystem services using a process-oriented perspective in two conceptual case studies; (2) translates the mapped effects into costs and benefits items in a qualitative cost-benefit analysis (CBA) context; and (3) presents a systematic review of economic valuation studies of geosystem services to investigate the available support for a quantitative CBA. The findings suggest that systematic mapping of effects on multiple geosystem services can inform different types of assessment methods and decision-makers on trade-offs and provide a basis for well-informed and responsible decisions on subsurface use. Combining such mapping with a CBA can further strengthen decision support through indications of the net effects on human well-being. However, although economic valuation of non-market geosystem services is possible using established valuation methods, such studies are scarce in scientific literature. Thus, although a CBA can provide a basis for supporting decisions on subsurface use from a consequentialist perspective, full quantification of all effects may require great efforts, and it needs to be complemented with other methods to capture the full range of values the subsurface can provide. This study also highlights that depending on the context, supporting and regulating geosystem services can be either intermediate or final services. Therefore, if geosystem services are to be included in the abiotic extension of CICES, in which supporting services by definition are excluded, reclassification of the supporting geosystem services should be considered not to risk being overlooked in economic valuation and CBA.

A indexação da informação jurídica: mapeamento sistemático na área de Ciência da Informação

This paper addresses the information processing, more precisely, the theme of the indexing of legal information. Its objective is to analyze the scientific production on the theme in the area of Information Science, aiming at the elaboration of a systematic mapping of literature and identification of an overview of these publications. This is a theoretical, exploratory and descriptive research, with a qualitative and quantitative approach. The bibliographic databases searched were BRAPCI, LISTA, Redalyc, SciELO, Scopus and CAPES Periodicals Portal. The works analyzed point to the librarian’s need for specialized knowledge about the indexing of legal information. All articles dealt with the scarcity of works and discussions about the theme, and the need for further research in order to minimize noise at the time of searching. The conclusion is that the production of scientific knowledge disseminated by scientific journals on the theme, in the period from 2002 to 2022, includes ten articles by Brazilian authors associated mainly with universities. The articles bring important contributions to the research and practice of indexing legal information, but the problem of scarcity of works persists.

Applying Generative Machine Learning to Intrusion Detection: A Systematic Mapping Study and Review

Intrusion Detection Systems (IDSs) are an essential element of modern cyber defense, alerting users to when and where cyber-attacks occur. Machine learning can enable IDSs to further distinguish between benign and malicious behaviors, but it comes with several challenges, including lack of quality training data and high false-positive rates. Generative Machine Learning Models (GMLMs) can help overcome these challenges. This article offers an in-depth exploration of GMLMs’ application to intrusion detection. It gives (1) a systematic mapping study of research at the intersection of GMLMs and IDSs, and (2) a detailed review providing insights and directions for future research.

Systematic mapping of organism-scale gene-regulatory networks in aging using population asynchrony

In aging, physiologic networks decline in function at rates that differ between individuals, producing a wide distribution of lifespan. Though 70% of human lifespan variance remains unexplained by heritable factors, little is known about the intrinsic sources of physiologic heterogeneity in aging. To understand how complex physiologic networks generate lifespan variation, new methods are needed. Here, we present Asynch-seq, an approach that uses gene-expression heterogeneity within isogenic populations to study the processes generating lifespan variation. By collecting thousands of single-individual transcriptomes, we capture the Caenorhabditis elegans "pan-transcriptome"-a highly resolved atlas of non-genetic variation. We use our atlas to guide a large-scale perturbation screen that identifies the decoupling of total mRNA content between germline and soma as the largest source of physiologic heterogeneity in aging, driven by pleiotropic genes whose knockdown dramatically reduces lifespan variance. Our work demonstrates how systematic mapping of physiologic heterogeneity can be applied to reduce inter-individual disparities in aging.

Literature Review of Deep-Learning-Based Detection of Violence in Video.

Physical aggression is a serious and widespread problem in society, affecting people worldwide. It impacts nearly every aspect of life. While some studies explore the root causes of violent behavior, others focus on urban planning in high-crime areas. Real-time violence detection, powered by artificial intelligence, offers a direct and efficient solution, reducing the need for extensive human supervision and saving lives. This paper is a continuation of a systematic mapping study and its objective is to provide a comprehensive and up-to-date review of AI-based video violence detection, specifically in physical assaults. Regarding violence detection, the following have been grouped and categorized from the review of the selected papers: 21 challenges that remain to be solved, 28 datasets that have been created in recent years, 21 keyframe extraction methods, 16 types of algorithm inputs, as well as a wide variety of algorithm combinations and their corresponding accuracy results. Given the lack of recent reviews dealing with the detection of violence in video, this study is considered necessary and relevant.