Search Results (46)

Understanding human perceptual strategies in high-stakes environments, such as crime scene investigations, is essential for developing cognitive models that reflect expert decision-making. This study presents an immersive experimental framework that utilizes virtual reality (VR) and eye-tracking technologies to capture and analyze visual attention during simulated forensic tasks. A360° panoramic crime scene, constructed using the Nikon KeyMission 360 camera, was integrated into a VR system with HTC Vive and Tobii Pro eye-tracking components. A total of 46 undergraduate students aged 19 to 24–23, from the National University of Singapore in Singapore and 23 from the Central Police University in Taiwan—participated in the study, generating over 2.6 million gaze samples (IRB No. 23-095-B). The collected eye-tracking data were analyzed using statistical summarization, temporal alignment techniques (Earth Mover’s Distance and Needleman-Wunsch algorithms), and machine learning models, including K-means clustering, random forest regression, and support vector machines (SVMs). Clustering achieved a classification accuracy of 78.26%, revealing distinct visual behavior patterns across participant groups. Proficiency prediction models reached optimal performance with a random forest regression ($R^2$ = 0.7034), highlighting scan-path variability and fixation regularity as key predictive features. These findings demonstrate that eye-tracking metrics—particularly sequence-alignment-based features—can effectively capture differences linked to both experiential training and cultural context. Beyond its immediate forensic relevance, the study contributes a structured methodology for encoding visual attention strategies into analyzable formats, offering valuable insights for cognitive modeling, training systems, and human-centered design in future perceptual intelligence applications. Furthermore, our work advances the development of autonomous vehicles by modeling how humans visually interpret complex and potentially hazardous environments. By examining expert and novice gaze patterns during simulated forensic investigations, we provide insights that can inform the design of autonomous systems required to make rapid, safety-critical decisions in similarly unstructured settings. The extraction of human-like visual attention strategies not only enhances scene understanding, anomaly detection, and risk assessment in autonomous driving scenarios, but also supports accelerated learning of response patterns for rare, dangerous, or otherwise exceptional conditions—enabling autonomous driving systems to better anticipate and manage unexpected real-world challenges. Full article

This study advances crime analysis methodologies in Maryland by leveraging sophisticated machine learning (ML) techniques designed to cater to the state’s varied urban, suburban, and rural contexts. Our research utilized an enhanced combination of machine learning models, including random forest, gradient boosting, XGBoost, extra trees, and advanced ensemble methods like stacking regressors. These models have been meticulously optimized to address the unique dynamics and demographic variations across Maryland, enhancing our capability to capture localized crime trends with high precision. Through the integration of a comprehensive dataset comprising five years of detailed police reports and multiple crime databases, we executed a rigorous spatial and temporal analysis to identify crime hotspots. The novelty of our methodology lies in its technical sophistication and contextual sensitivity, ensuring that the models are not only accurate but also highly adaptable to local variations. Our models’ performance was extensively validated across various train–test split ratios, utilizing R-squared and RMSE metrics to confirm their efficacy and reliability for practical applications. The findings from this study contribute significantly to the field by offering new insights into localized crime patterns and demonstrating how tailored, data-driven strategies can effectively enhance public safety. This research importantly bridges the gap between general analytical techniques and the bespoke solutions required for detailed crime pattern analysis, providing a crucial resource for policymakers and law enforcement agencies dedicated to developing precise, adaptive public safety strategies. Full article

Forest fires, i.e., wildfires, often cause an inevitable strain on society and human living conditions. Incident Commanders (IC) at the Fire and Rescue Services (FRS) are challenged to handle forest fires and at the same time address the forest owners’ needs; this stipulates a need for collaboration, information, and communication. Hence, the aim of this study was to explore and describe the ICs’ experiences and actions in their interactions with forest owners during forest fires on private property. Interviews were conducted and analyzed using Flanagan’s Critical Incident Technique (CIT) to describe the experiences and actions of 22 ICs. The results showed that a firefighting operation needs clarity in information exchange with the forest owner as a stakeholder, not a victim. The trust between forest owner and IC accelerated the operational phase. The ICs demonstrate more care than the law stipulates, and they worry about the forest owners. Therefore, the FRS needs to form a strategic partnership with forest owners and their network on a local level. Also, future forest fire drills should not only include emergency stakeholders (i.e., police, ambulance, etc.) but also forest owners and local volunteer organizations. For a resilient community, FRS and forest owner collaboration is vital. Full article

Research studies on the conservation genetics of endangered plants play a crucial role in establishing management plans for biodiversity conservation. Phoebe chekiangensis is a precious and scarce tree species resource in the East China region. To comprehend the origin, evolutionary history, geographical, and historical factors that has contributed to the current distribution pattern of Phoebe chekiangensis in the East China region, we conducted a phylogeographic analysis that utilized intergenic spacers of chloroplast DNA (cpDNA). We amplified and sequenced three spacer regions of cpDNA (psbC-trnS, trnL-Intro, and Ycf3) intergenic spacer regions of 306 individuals from 11 populations, encompassing the majority of its geographical range in China. Our analysis revealed a total of 11 haplotypes. The research findings show that the spacer regions of the cpDNA genetic diversity of Phoebe chekiangensis was H_d = 0.423, and the nucleotide diversity was P_i × 10⁻³ = 0.400. At the species level, the population differentiation index F_st = 0.25610 (p < 0.05), and the gene flow N_m = 0.73. The genetic variation between populations was 29.14%, while within populations, it was 70.86%, with the inter-population genetic variation much lower than the within-population variation. The divergence time between the genera Phoebe and Machilus was estimated to be approximately 37.87 mya (PP = 1; 95%HPD: 25.63–44.54 mya), and the crown group time of the genus Phoebe was estimated to be 21.30 mya (PP = 1; 95%HPD: 9.76–34.94 mya). The common ancestor of the 11 Phoebe chekiangensis haplotypes was 7.85 mya, while the H7, H8, and H10 haplotypes of Phoebe chekiangensis (northern region) differentiated relatively late, with a divergence time of 1.90 mya. Neutrality tests (NTs) and mismatch distribution analysis (MDA) suggest that the time frame for Phoebe chekiangensis to expand southwestward along Wuyishan was relatively short and its adaptability to the environment was low, thereby limiting the formation of new haplotypes. These results suggest that Phoebe chekiangensis exhibited greater adaptation to the northern subtropics than to the central subtropics, offering valuable insights for the conservation and utilization of germplasm resources. Full article

This paper presents a research program called CP2DIMG conducted at the Federation of Environment and Society Research at the University of Corsica. The goal of CP2DIMG is to better understand the influence of emotions on operational personnel’s decision-making, aiming to test training systems dedicated to individuals facing high stress during their professional activities. This type of training system is intended to enhance emotional and mental resilience, thereby improving decision-making ability in uncertain situations under the influence of emotions related to the event. For implementation, the method will be tailored to the specificities of two categories of operational personnel: firefighters and municipal police officers. The expected results will address significant demands from operational professionals in the Mediterranean region for firefighting safety but also for large-scale or highly complex interventions. This study fully integrates into the challenges of the Mediterranean region: forest management, risk prevention plans, and preparedness of local actors responsible for crisis management. Furthermore, individuals responsible for crisis management, including local government officials and risk management and security personnel, will be able to use the obtained results for effective decision-making. Full article

Understanding the causes of traffic road accidents is crucial; however, as data collection is conducted by traffic police, accident-related environmental information is not available. To fill this gap, we collect information on the built environment within R = 500 m of the accident site; model the factors influencing accident severity in Shenyang, China, from 2018 to 2020 using the Random Forest algorithm; and use the SHapley Additive exPlanation method to interpret the underlying driving forces. We initially integrate five indicators of the built environment with 18 characteristics, including human and vehicle at-fault characters, infrastructure, time, climate, and land use attributes. Our results show that road type, urban/rural, season, and speed limit in the first 10 factors have a significant positive effect on accident severity; density of commercial-POI in the first 10 factors has a significant negative effect. Factors such as urban/rural and road type, commercial and vehicle type, road type, and season have significant effects on accident severity through an interactive mechanism. These findings provide important information for improving road safety. Full article

Forest fires, severe natural disasters causing substantial damage, necessitate accurate predictive modeling to guide preventative measures effectively. This study introduces an enhanced window-based Transformer time series forecasting model aimed at improving the precision of forest fire predictions. Leveraging time series data from 2020 to 2021 in Chongli, a myriad of forest fire influencing factors were ascertained using remote sensing satellite and GIS technologies, with their interrelationships estimated through a multicollinearity test. Given the intricate nature of real-world forest fire prediction tasks, we propose a novel window-based Transformer architecture complemented by a dual time series input strategy premised on 13 influential factors. Subsequently, time series data were incorporated into the model to generate a forest fire risk prediction map in Chongli District. The model’s effectiveness was then evaluated using various metrics, including accuracy (ACC), root mean square error (RMSE), and mean absolute error (MAE), and compared with traditional deep learning methods. Our model demonstrated superior predictive performance (ACC = 91.56%, RMSE = 0.37, MAE = 0.05), harnessing spatial background information efficiently and effectively utilizing the periodicity of forest fire factors. Consequently, the study proves this method to be a novel and potent approach for time series fire prediction. Full article

One of the major responsibilities for forest police is forest fire prevention and forecasting; therefore, accurate and timely fire detection is of great importance and significance. We compared several deep learning networks based on the You Only Look Once (YOLO) framework to detect forest flames with the help of unmanned aerial vehicle (UAV) imagery. We used the open datasets of the Fire Luminosity Airborne-based Machine Learning Evaluation (FLAME) to train the YOLOv5 and its sub-versions, together with YOLOv3 and YOLOv4, under equal conditions. The results show that the YOLOv5n model can achieve a detection speed of 1.4 ms per frame, which is higher than that of all the other models. Furthermore, the algorithm achieves an average accuracy of 91.4%. Although this value is slightly lower than that of YOLOv5s, it achieves a trade-off between high accuracy and real-time. YOLOv5n achieved a good flame detection effect in the different forest scenes we set. It can detect small target flames on the ground, it can detect fires obscured by trees or disturbed by the environment (such as smoke), and it can also accurately distinguish targets that are similar to flames. Our future work will focus on improving the YOLOv5n model so that it can be deployed directly on UAV for truly real-time and high-precision forest flame detection. Our study provides a new solution to the early prevention of forest fires at small scales, helping forest police make timely and correct decisions. Full article

Ormosia hosiei is an endemic plant in China listed as a national grade II key protected wild plant with important scientific, economic, and cultural values. This study was designed to predict the potential suitable distribution areas for O. hosiei under current and future climate change and to provide a reference to enhance the species’ conservation and utilization. Based on the actual geographical locations of O. hosiei in Sichuan, we applied two species distribution models (BIOCLIM and DOMAIN) to predict its current and future potential suitable areas and future change patterns. We also analyzed the major climatic variables limiting its geographical distribution with principal component analysis. The results indicated that O. hosiei was mainly distributed in the eastern region of Sichuan and concentrated in the middle subtropical climate zone at relatively low elevations. The principal component analysis identified two critical factors representing temperature and moisture. The temperature was the most critical factor limiting O. hosiei distribution in Sichuan, especially the effect of extreme low temperatures. Both models’ simulation results of potential suitable areas under the current climate scenario showed that the excellent suitable habitat was consistent with the current actual distribution, remaining in the eastern region of Sichuan. Under the future climate scenario with doubled CO₂ concentration (2100), both models predicted a sharp decrease in the areas of excellent and very high suitable habitats. The findings can inform strategies and guidelines for O. hosiei research, conservation, nursery production, and cultivation in Sichuan. Full article

Pterocarpus santalinus is considered among the finest luxury woods in the world and has potential commercial and medicinal value. Due to its rich hue and high price, Pterocarpus santalinus has often been substituted and mislabeled with other woods of lower economic value. To maintain the order of the timber market and the interests of consumers, it is necessary to establish a fast and reliable method for Pterocarpus species identification. In this study, wood samples of Pterocarpus santalinus and nine other wood samples commonly used for counterfeiting were analyzed by visible light/near-infrared (Vis/NIR) hyperspectral imaging (HSI). The spectral data were preprocessed with different algorithms. Principal component analysis (PCA) was applied in different spectral ranges: 400~2500 nm, 400~800 nm, and 800~2500 nm. Partial least squares discriminant analysis (PLS-DA) and square support vector machine (SVM) modeling methods were performed for effective discrimination. The best classification model was SVM combined with a normalization preprocessing method in whole spectral range (400~2500 nm), with prediction accuracy higher than 99.8%. The results suggest that the use of Vis/NIR-HSI in combination with chemometric approaches can be used as an effective tool for the discrimination of Pterocarpus santalinus. Full article

Road accidents are a worldwide problem, affecting millions of people annually. One way to reduce such accidents is to predict risk areas and alert drivers. Advanced research has been carried out on identifying accident-influencing factors and potential highway risk areas to mitigate the number of road accidents. Machine learning techniques have been used to build prediction models using a supervised classification based on a labeled dataset. In this work, we experimented with many machine learning algorithms to discover the best classifier for the Brazilian federal road hotspots associated with severe or nonsevere accident risk using several features. We tested with SVM, random forest, and a multi-layer perceptron neural network. The dataset contains a ten-year road accident report by the Brazilian Federal Highway Police. The feature set includes spatial footprint, weekday and time when the accident happened, road type, route, orientation, weather conditions, and accident type. The results were promising, and the neural network model provided the best results, achieving an accuracy of 83%, a precision of 84%, a recall of 83%, and an F1-score of 82%. Full article

Large forest fires can cause significant damage to forest ecosystems and threaten human life and property. Heilongjiang Province is a major forested area in China with the highest number and concentration of lightning-caused forest fires in the country. This study examined the spatial and temporal distribution patterns of forest fires in Heilongjiang Province, as well as the ability of satellite remote sensing to detect these fires using VIIRS 375 m fire point data, ground history forest fire point data, and land cover dataset. The study also investigated the occurrence patterns of lightning-caused forest fires and the factors affecting satellite identification of these fires through case studies. Results show that April has the highest annual number of forest fires, with 77.6% of forest fires being caused by lightning. However, less than 30% of forest fires can be effectively detected by satellites, and lightning-caused forest fires account for less than 15% of all fires. There is a significant negative correlation between the two. Lightning-caused forest fires are concentrated in the Daxing’an Mountains between May and July, and are difficult to monitor by satellites due to cloud cover and lack of satellite transit. Overall, the trend observed in the number of forest fire pixels that are monitored by satellite remote sensing systems is generally indicative of the trends in the actual number of forest fires. However, lightning-caused forest fires are the primary cause of forest fires in Heilongjiang Province, and satellite remote sensing is relatively weak in monitoring these fires due to weather conditions and the timing of satellite transit. Full article

Alligator gar Atractosteus spatula originates from North America but has been introduced into China recently. Considered an invasive fish, it may cause losses in the diversity and number of local species and in fish catch due to its predation on numerous aquatic animals in non-native habitats. A comprehensive study of this alien invasive species’ existing spatial patterns in relation to climatic variables is critical to understanding the conditions amenable to its distribution and controlling its further spread into potential range areas. We used MaxEnt and QGIS species distribution modeling to estimate the likely biogeographical range of A. spatula in China based on 36 validated distribution records and seven selected environmental variables. The highly suitable area was found primarily in a series of provinces extending from inland to coastal regions, covering southwest to south, central and east China. The model identified the minimum temperature of the coldest month (Bio6) and mean temperature of the warmest quarter (Bio10) as the strongest predictors of A. spatula distribution. The findings could offer scientific guidance for managing and preventing the spread of this invasive fish and hint at controlling invasive aquatic fauna. Full article

Deforestation is a common threat to the environment that has a substantial impact on the forest’s distribution across territorial boundaries. It is simply defined as the loss of forest cover, which most commonly occurs as a result of deforestation for various reasons. Pakistan is among those countries which have a very high deforestation rate. This paper analyzes the various socioeconomic factors which cause deforestation in northern Pakistan and the existing economic incentive tools for reducing deforestation. Data collected from 602 respondents were analyzed using descriptive statistics and a logistic regression model, while the Likert scale was used to determine the mean socioeconomic factor score encouraging deforestation and the economic incentives used to reduce deforestation. Gender distributions showed that the majority (65.9%) of the respondents were male while 34.1% were female. On family size, the majority of the respondents (66.8%) had a family size of 5–8. On age, between 21–25 years (46.0%) recorded the highest number. The average age of the respondents was 24 years. Educationally, 13.8% had a master’s education, 11.1% a bachelor’s education, 4.3% no formal education, 5.6% a higher education level, meaning master’s or PhD students, 56.1% had a primary education, and 9.0% had a secondary education. On occupation, the majority (50.4%) of the respondents were involved in farming as their main occupation. On income, the major income recorded a mean of 25,000 net, while the minor income recorded a mean of 15,500 net. Setting the forest ablaze, increasing farming activities, low level of literacy, increasing timber mafia, growing population, and poverty were the socioeconomic factors found. The economic incentives listed were for forest crop subsidies, an enhanced system of taxes on exploited forest products, the acquisition of well-monitored hunting licenses, alternative job opportunities, credit provision, and a limited ban on round log exports. The results of the logit regression established that rewarding socioeconomic factors were statistically significant variables at (p < 0.05). Conclusively, if adequately controlled and applied, economic incentives can be an important instrument for reducing deforestation. Therefore, deforestation activities cannot be entirely eradicated but they can be reduced to the barest minimum by properly enforcing forest policies in terms of efficient forest policing. The goals of this study are to help with the implementation of appropriate policies and decision-making in forest management, as well as to provide a foundation for future scenario analysis of deforestation potential or to investigate potential environmental and human implications. Full article

This paper assesses the existing reforestation and forest conservation policies and strategies in Southeast Asia and how they have impacted people’s lives. Southeast Asia contains 11 countries and is home to 20% of the world’s species. Unfortunately, the region has been practising deforestation at an alarming rate. The main cause of deforestation in the region is the creation of land for agriculture, with forest fires and the growing demand for timber also contributing. As a result, the region has lost 376,000 km² of forest in the last 30 years. Parts of the region have been involved in international efforts to protect forests, such as the 2016 Paris Agreement. However, some of these policies have not made much difference because most countries are not willing to support the necessary strategies. From the study findings, the main strength of the existing polices and strategies is that they are being amended to suit different changes in demographics and the practical needs of the sector. The sector has been able to shift from the initial state forestry management to making forests a multi-sectoral economic development agent. On the other hand, there are few polices at the national level that ensure every citizen participates in tree planting and that they understand the need to stop deforestation. In addition, many countries in the region are less willing to join the international communities in fighting climate change; that is, they do not agree with international partnerships like the Pris Climate Change Agreement. Full article