Accurate crime prediction is crucial for the proactive allocation of law enforcement resources and ensuring urban safety. A major challenge in achieving accurate predictions lies in identifying generalized patterns of criminal behavior from spatiotemporal features in crime data. Additionally, the inherent randomness and volatility of crime data at the spatiotemporal level introduce noise, which can mislead prediction models. While many effective spatiotemporal crime prediction methods have been proposed, most overlook this issue, reducing their ability to generalize. In this paper, we introduce a novel deep learning-based model, adaptive-GCNLSTM (Ada-GCNLSTM). Specifically, in the spatial feature extraction module, we enhance the model's ability to capture crime spatial distributions by leveraging graph convolutional networks to model spatial dependencies in conjunction with the maximum mean discrepancy to extract the universal features of crime data. We then incorporate a memory network based on long short-term memory network to capture the underlying relationships between temporal features. Through extensive experiments, our model demonstrates an average improvement of 11.7% in mean absolute error and 2.7% in root mean squared error across the three datasets, outperforming the best baseline model. These results underscore the effectiveness of our approach in enhancing crime prediction accuracy.
Marcelo dos Santos Póvoas, Jéssica Freire Moreira, Severino Virgínio Martins Neto
et al.
This study aims to provide a comprehensive overview of the application of artificial intelligence (AI) methods to solve real-world problems in the oil and gas sector. The methodology involved a two-step process for analyzing AI applications. In the first step, an initial exploration of scientific articles in the Scopus database was conducted using keywords related to AI and computational intelligence, resulting in a total of 11,296 articles. The bibliometric analysis conducted using VOS Viewer version 1.6.15 software revealed an average annual growth of approximately 15% in the number of publications related to AI in the sector between 2015 and 2024, indicating the growing importance of this technology. In the second step, the research focused on the OnePetro database, widely used by the oil industry, selecting articles with terms associated with production and drilling, such as “production system”, “hydrate formation”, “machine learning”, “real-time”, and “neural network”. The results highlight the transformative impact of AI on production operations, with key applications including optimizing operations through real-time data analysis, predictive maintenance to anticipate failures, advanced reservoir management through improved modeling, image and video analysis for continuous equipment monitoring, and enhanced safety through immediate risk detection. The bibliometric analysis identified a significant concentration of publications at Society of Petroleum Engineers (SPE) events, which accounted for approximately 40% of the selected articles. Overall, the integration of AI into production operations has driven significant improvements in efficiency and safety, and its continued evolution is expected to advance industry practices further and address emerging challenges.
The digital transformation of business contributes to the growth of productivity in all sectors of the economy, creating additional value for consumers, optimizing the internal business processes of enterprises and reducing costs. In socially significant sectors, digital transformation contributes to solving social problems, improving access to public and social services.
The rapid advancement of technology and the growing complexity of the business environment make effective risk management a critical factor for the strategic success of enterprises in all sectors of the economy. Especially important in this context is the transformation of traditional methods of risk management with the help of digital tools and data analytics. The implementation of digital technologies in the process of risk management can become decisive for achieving competitive advantages and ensuring sustainable development in Ukraine.
The article describes the main principles of digital risk management; methods of risk management are explored through the selection of options with sustainability in mind; modern practice is considered and information management tools are analyzed. In the framework of the conducted research, foreign experience was considered; and also, with the help of the analysis of the "EBIOS RM" method, recommendations were formulated regarding the subject area of the study.
Detailed attention is paid to the current state of the information technology industry in Ukraine and the identification of key problems of information management. Effective information management mechanisms were analyzed and digital risk management tools were systematized.
William V. Mbasa, Wilson A. Nene, Fortunus A. Kapinga
et al.
Abstract Epidemic of Cashew Fusarium wilt disease (CFWD) has been a continuous focal challenge in the cashew farming, in Tanzania. Limited to edaphic conditions as a major factor in its epidemic, the current study aimed to assess the habitat-disease relationship. Purposive surveys involving assessment of disease prevalence and habitat compositions were conducted across four landscapes of southeastern zone from 2019 to 2023. Findings revealed a widespread of CFWD across diversified landscapes possessing varying habitat characteristics, mainly cultivated land with mature cashew, brownish sand loamy soils, grassland or shrub vegetation, seasonal river streamlines and natural water wells. The highest disease incidence and severity were noted at Nachingwea/Masasi plain (99.28:88.34%) followed by Liwale inland plain (98.64:89.3%), Coastal zone (72.72:59.83%) and Tunduru dissected plain (62.13:54.54%). The habitat characteristics were strongly similar within the landscape (0.86-Jaccard index) except between villages of the coastal zone (0.71-Jaccard index). Across landscapes, Nachingwea/Masasi plains and the Coastal zone were strongly similar to Tunduru dissected plain (0.63—1.0-Jaccard index), but strongly dissimilar with the Liwale inland plain (0.67—0.70- Jaccard distance). Furthermore, the presence of greater than 0.5 suitability indices across landscapes were revealed, with Liwale inland plain having strongest suitability index of 0.743 followed by Coastal zone (0.681), Tunduru dissected plain (0.617) and Nachingwea/Masasi plain. Significantly, the habitats had an increase of 0.1 suitability index, and positively correlated with disease prevalence by triggering disease incidence of 13.9% and severity of 31.4%. The study for the first time revealed the presence of an association between disease prevalence and landscape habitat characteristics of southeastern, Tanzania; paving the way to inclusive thinking of habitat as one of the drivers in the prevalence of fusarium wilt disease of cashews. Further research on the genetic coevolution of Fusarium oxysporum across landscapes to strengthen disease risk management in the cashew industry is recommended.
Minhaz Farid Ahmed, Bijay Halder, Liew Juneng
et al.
Flooding is considered a significant natural hazard in Malaysia. climatic conditions and anthropogenic activities are gradually triggering floods in different parts of Malaysia including the study area, i.e. Shah Alam municipality. In the southern region of Shah Alam, where the Klang River runs, November/December and March/April saw the most flooding. To create a mapping of Shah Alam’s flood potential, the Analytic Hierarchy Process (AHP) and Fuzzy-AHP methods were applied with the twelve criteria. The Sentinel 1 Synthetic Aperture Radar (SAR) datasets and the Google Earth Engine (GEE) platform were used to compute the flood inundation area. Based on the twelve criteria, flood potential zones were divided into five categories such as very high potential (11.58 km2 – AHP and 10.35 km2 – F-AHP) to very low potential (6.49 km2 – AHP and 39.21 km2 – F-AHP), respectively. The most affected areas are the southern part (near Klang River), the central part, and some parts of the northern zone in Shah Alam. The near real-time flood mapping used for previous flood-affected area identification in Shah Alam, Malaysia. Local government and relevant stakeholders can benefit from using this flood potential mapping to reduce the flood effects at Shah Alam via appropriate planning.
Overcrowding and stampedes may occur in public places with the gathering of crowds. To mitigate and prevent risk, the accident mechanism and methods for monitoring and evaluating crowd-gathering risk were investigated. Related studies are reviewed and summarized in this paper. The evolution process of crowd-gathering risk and precipitating factors were explained systematically. Risk monitoring methods are classified into three types according to the key technologies adopted. Articles exploring risk evaluation methods for crowd gathering are outlined, and the three main paradigms were formed. Finally, the shortcomings and future research points are summarized to promote more in-depth and comprehensive studies on crowd-gathering risk, develop monitoring technologies, and build an integrated system of risk management.
Tzu-Chia Chen, Marziah Zahar, Olga Yuryevna Voronkova
et al.
The risk management process is a systematic and logical process that should include identification, analysis, measurement, and dealing with risk-taking into account the facilities, conditions, and context of the organization. Today, work-related accidents, as one of the important factors in losing efficient manpower and Waste of capital and time, are considered a threat to the development and progress of any country. Therefore, failure to pay attention and assess the safety risk in the construction industry will cause irreparable problems and impose high costs on the project. Work-related accidents are not entirely accidental, so the most effective measures can be taken to control and reduce them while anticipating. Appropriate hi-tech in the analysis of hazards in industries is an important step in determining effective measures to reduce accidents. This study aims to use the most appropriate techniques available to identify hazards and assess the risk in order to improve safety, reduce accidents and costs and save time. In this research, to identify, evaluate and rank the safety risks of construction projects with fuzzy approach and TOPSIS method, which we have dealt with according to the importance of each risk, appropriate strategies and response programs should be applied according to them. The main finding of this research is that Excavation is the most important risky work in construction projects that needs more attention to reduce total risks.
Ecosystems as new organizational forms of business, whose activity generates changes in the theory and practice of management, have become a significant phenomenon of the modern economy. The article discusses the features of the strategy development of ecosystems based on digital platforms, the typology of strategies and the directions of classical approaches transformation to the strategic development of ecosystem players. The research methodology includes the analysis of scientific approaches within the framework of the emerging ecosystem theory as well as the systematization of the national digital ecosystems’ practice based on the analysis of real situations from various spheres of Russian business. As a result of the analytical study, the multi-vector strategies of Russian ecosystems are described; the dominant directions of development in transaction ecosystems and decision ecosystems are identified and systematized on the basis of the Ansoff matrix. The directions of transformation of traditional methods and tools of strategic management in a broad context are revealed from the standpoint of market and intra-ecosystem interactions. The obtained results contribute to the urgent scientific discussions concerning the prospects and limitations of the digital ecosystems development, changes in the nature and models of competition, as well as the problems of traditional management methods transformation in the digital economy.
The socio-economic effects from the introduction of smart manufacturing technologies are of significant interest in terms of their generalisation and systematisation at the current stage of the digital transformation on industrial enterprises, as well as the objectives in the context of industrial modernization and new business model development. The proposed systematisation is based on the allocation of three groups of socio-economic effects according to the main direction of their action. The first group of effects primarily leads to reduction in the costs of industrial enterprises. The second group of effects leads mainly to an increase in revenues: some effects to a greater extent in the short and medium term, others in the long term, including through the creation of long-term distinctive capabilities, unique competencies, and sustainable competitive advantages for industrial companies. The third group of effects includes social and economic effects that are broader in focus and have a multiplicative effect, as well as the character of positive externalities (external effects).As a result of systematisation, the author identified in three groups, respectively, 12, 8 and 13 effects from the implementation of the complex of smart manufacturing technologies. The author stresses the particular importance of studying the socio-economic effects from the implementation of smart manufacturing technologies, since many improvements at the intersection of production and social transformation are currently insufficiently studied. It contrasts to the core production effects, many of which have been studied in sufficient detail by the scientific and expert communities. Systematisation, classification, differentiation and quantitative assessment of various socio-economic effects of the complex of smart manufacturing technologies can and even in a certain sense should (in the context of the tasks to modernise the economy and industries of the Russian Federation) become a separate subject area at the intersection of performance management and smart production.
This article considers innovative solutions used in sports industry. Taking into account the importance for the consumer in the context of pandemic restrictions, as well as the presence of a large number of modern technological cases, the author focuses on fitness sector. The innovative solutions discussed in the study can be classified as follows: mobile apps; sensors; virtual reality. The analysis allowed the author to highlight the pros and cons of digitalization, determine the development trends of fitness industry, the specifics of its financial model and competitiveness. Despite the importance of automation, the author emphasizes the high role of “living” labor, the importance of which can be studied in further developments.
Abstract Enterprise Risk Management (ERM) focuses on the elevation of risk management to the center of the firm’s strategic activities. Risks are treated both as exposures to be managed and opportunities to be exploited. This study examines the firm performance implications of ERM maturation and more specifically firm characteristics that serve to engender or inhibit these performance implications. We find that in general ERM maturation increases firm value and return on assets and the impact is moderated by stakeholder related factors such as innovation intensity and knowledge focused industry structures. Additionally, we show that a firm’s complexity moderates the effect of ERM valuation over the long term.
Multisectoral partnerships are increasingly cited as a mechanism to deliver and improve disaster risk management. Yet, partnerships are not a panacea and more research is required to understand the role that they can play in disaster risk management and particularly disaster risk reduction. This paper investigates how partnerships can incentivise flood risk reduction by focusing on the UK public-private partnership on flood insurance. Developing the right flood insurance arrangements to incentivise flood risk reduction and adaptation to climate change is a key challenge. In the face of rising flood risks due to climate change and socio-economic development insurance partnerships can no longer afford to focus only on the risk transfer function. However, while expectations of the insurance industry have traditionally been high when it comes to flood risk management, the insurance industry alone will not provide the solution to the challenge of rising risks. The case of flood insurance in the UK illustrates this: even national government and industry together cannot fully address these risks and other actors need to be involved to create strong incentives for risk reduction. Using an agent-based model focused on surface water flood risk in London we analyse how other partners could strengthen the insurance partnership by reducing flood risk and thus helping to maintain affordable insurance premiums. Our findings are relevant for wider discussions on the potential of insurance schemes to incentivise flood risk management and climate adaptation in the UK and also internationally.
Flood is one of the most dangerous environmental hazards that threaten the human lives and properties on a large scale. Identification of flood risk areas with the aim of optimal management of this area is very necessary. In this research, the estimation of Land use/Land cover (LULC) in the Marand basin was modelled on the Sub-basin level using remote sensing and geographic information systems (GIS). The runoff coefficient was determined using the LULC extracted from satellite images, slope map and soil hydrologic groups, and rainfall intensity. Then, peak runoff for each sub-basin was calculated. In the following, by using linear membership function in the fuzzy logic model, the integration of two layers of peak runoffs and the elevation line layers between 0 and 1 were transformed into fuzzy values. Afterward, by applying multiple overlaps of weights to each of these two layers and their results, classes of flood hazard distribution map were produced. By comparing the hazard map with the results of participatory geographic information system (PGIS) and entering this information into the confusing matrix, the collision accuracy of the map was 87.83%. Finally, by comparing this map with the land cover/use map, their flood extent was determined separately.
Ladislav JÁNOŠÍK, Ivana JÁNOŠÍKOVÁ, Pavel POLEDŇÁK
et al.
The paper summarizes results of the study aimed to evaluate the change of firefighters-engineers’ driving skills after attending the one-day training course. The research focused at drivers of firefighting water tenders. These trucks represent the first-response vehicles in case of emergency rides. The water tenders form the majority of firefighting vehicles at units of the Fire Rescue Service of the Czech Republic with the highest mileage per year. They represent the most important fire appliances at each professional fire station. Water tender drivers’ primary task is to transport both firefighters and vehicles safely without any traffic accident to the intervention point.
Industrial safety. Industrial accident prevention, Risk in industry. Risk management
There is increasing empirical evidence that the relocation of the victims of the Tokwe-Mukosi floods in Zimbabwe was marred by a combination of challenges. These challenges are argued in this article to have resulted from the adoption of Eurocentric models by government and non-governmental organisation technocrats and experts while relegating traditional leadership and the lived experiences of the displaced to the shadows. The writer provides a summary and critique of the Elizabeth Colson–Thayer Scudder four-stage model and Michael Cernea’s Impoverishment Risks and Reconstruction Model. This article argues that traditional leadership is the missing link in disaster-induced displacement and its integration can overcome most of the challenges faced by the displaced in Zimbabwe. Traditional leadership in Zimbabwe can be traced to precolonial states and it has survived the colonial and postcolonial epochs. The study was guided by the Afrocentric theoretical framework. The case for the integration of traditional leadership was buttressed by numerous arguments. Among these arguments include proximity of traditional leadership to the displaced, the Zunde raMambo concept and ubuntu, among others.
Mohammad Eskandari, Babak Omidvar, Mahdi Modiri
et al.
Iran, as a seismic country, is situated over the Himalayan-Alpied seismic belt and has faced many destructive earthquakes throughout history. Therefore, it is very important to evaluate the possible damage to the existing infrastructure based on statistical and spatial analysis. In this study, a new model is developed to analyse seismic damages based on seismic hazard assessment and extraction of the vulnerability function for all features of fuel infrastructure. To consider uncertainty analysis in the model, Monte Carlo simulation is used based on 10,000 iterations. The results of hazard analysis indicated that peak ground acceleration is about 0.18 g and there is slight to moderate damages to the desired fuel infrastructure in the study area. Moreover, sensitivity analysis is also performed to determine how median, standard deviation (or beta), grid size, attenuation relationships, liquefaction and landslide susceptibility impact the seismic loss. Last but not least, the effect of input parameters of earthquake scenarios including magnitude, focal depth and focal distance are also analysed in conjunction with regression analysis. The results of the study show that magnitude and focal distance are the most sensitive parameters in which the expected damage to the fuel infrastructure is reduced by about 25% if the epicentre of the earthquake is moved from 10 to 25 km.