Search

Globally, fire incidents cause significant social, economic, and environmental destruction, making early detection and rapid response essential for minimizing such devastation. While various traditional machine learning and deep learning techniques have been proposed, their detection performances remain poor, particularly due to low-resolution data and ineffective feature selection methods. Therefore, this study develops a novel framework for accurate fire detection, especially in challenging environments, focusing on two distinct phases: preprocessing and model initializing. In the preprocessing phase, super-resolution is applied to input data using LapSRN to effectively enhance the data quality, aiming to achieve optimal performance. In the subsequent phase, the proposed network utilizes an attention-based deep neural network (DNN) named Xception for detailed feature selection while reducing the computational cost, followed by adaptive spatial attention (ASA) to further enhance the model's focus on a relevant spatial feature in the training data. Additionally, we contribute a medium-scale custom fire dataset, comprising high-resolution, imbalanced, and visually similar fire/non-fire images. Moreover, this study conducts an extensive experiment by exploring various pretrained DNN networks with attention modules and compares the proposed network with several state-of-the-art techniques using both a custom dataset and a standard benchmark. The experimental results demonstrate that our network achieved optimal performance in terms of precision, recall, F1-score, and accuracy among different competitive techniques, proving its suitability for real-time deployment compared to edge devices. [ABSTRACT FROM AUTHOR]

With the widespread deployment of video surveillance devices, a large number of indoor and outdoor places are under the coverage of cameras, which plays a significant role in enhancing regional safety management and hazard detection. However, a vast number of cameras lead to high installation, maintenance, and analysis costs. At the same time, low-quality images and potential blind spots in key areas prevent the full utilization of the video system's effectiveness. This paper proposes an optimization method for video surveillance system deployment based on space syntax analysis and deep reinforcement learning. First, space syntax is used to calculate the connectivity value, control value, depth value, and integration of the surveillance area. Combined with visibility and axial analysis results, a weighted index grid map of the area's surveillance importance is constructed. This index describes the importance of video coverage at a given point in the area. Based on this index map, a deep reinforcement learning network based on DQN (Deep Q-Network) is proposed to optimize the best placement positions and angles for a given number of cameras in the area. Experiments show that the proposed framework, integrating space syntax and deep reinforcement learning, effectively improves video system coverage efficiency and allows for quick adjustment and refinement of camera placement by manually setting parameters for specific areas. Compared to existing coverage-first or experience-based optimization, the proposed method demonstrates significant performance and efficiency advantages. [ABSTRACT FROM AUTHOR]

Person re-identification (Re-ID) includes matching people across multiple cameras plays an essential role in security, and surveillance, tracking people. People’s identification with multiple cameras presents significant challenges, particularly when behavior changes due to factors such as clothing variations, lighting conditions, and other people that affect multiple camera identification. A robust deep learning approach is proposed that aims to enhance the reliability of the re-identification model and novel technique for detecting suspicious activity using a combination of Euclidean Distance (ED) and Lookup Table(LUT). This model is trained on a publicly available VIPER dataset. We have also created our dataset to verify the validation through multiple cameras. The proposed model detects people by fine-tuning the YOLOv8 model, for trimming out objects along with individuals and afterward performing feature extraction and attribute evaluation. The feature extraction is performed in two steps: firstly, hand-crafted features used such as LOMO, which employs the HSV color space, and secondly, deep features retrieved from pre-trained neural networks models such as VGG16 and ResNet-50. The triplet loss and clustering methods are implemented to re-identify people and enable efficient interaction across multiple cameras or locations. The proposed Lookup Table (LUT) is developed through generated triplet loss features and a provided attribute matrix. It assists in the detection of suspicious activities based on information provided by identified individuals. In this research, a novel technique for activity detection is developed that combination of Euclidean Distance (ED) and Lookup Table(LUT) can accurately identify suspicious and non-suspicious actions. People have been detected using a re-identification model and used five camera configurations. The model achieves 90% accuracy in identifying suspicious and non-suspicious actions. [ABSTRACT FROM AUTHOR]

Background: Healthcare-associated bloodstream infections (BSI) threaten patient safety and are the third most common healthcare-associated infection (HAI) in low- and middle-income countries. An intensive-care-unit (ICU) based HAI surveillance network recording BSIs was started in India in 2017. We evaluated this surveillance network’s ability to detect BSI to identify best practices, challenges, and opportunities in its implementation. Methods: We conducted a mixed-methods descriptive study from January to May 2022 using the CDC guidelines for evaluation. We focused on hospitals reporting BSI surveillance data to the HAI network from May 2017 to December 2021, and collected data through interviews, surveys, record reviews, and site visits. We integrated quantitative and qualitative results and present mixed methods interpretation. Results: The HAI surveillance network included 39 hospitals across 22 states of India. We conducted 13 interviews, four site visits, and one focus-group discussion and collected 50 survey responses. Respondents included network coordinators, surveillance staff, data entry operators, and ICU physicians. Among surveyed staff, 83% rated the case definitions simple to use. Case definitions were correctly applied in 280/284 (98%) case reports. Among 21 site records reviewed, 24% reported using paper-based forms for laboratory reporting. Interviewees reported challenges, including funding, limited human resources, lack of digitalization, variable blood culture practices, and inconsistent information sharing. Conclusion: Implementing a standardized HAI surveillance network reporting BSIs in India has been successful, and the case definitions developed were simple. Allocating personnel, digitalizing medical records, improving culturing practices, establishing feedback mechanisms, and funding commitment are crucial for its sustainability. [ABSTRACT FROM AUTHOR]

The pertussis resurgence has currently become a global public health concern. The widespread vaccination of pertussis vaccine will inevitably lead to changes in the transmission pattern, epidemiological characteristics, and clinical manifestations of pertussis while reducing the overall incidence level. At present, there is no unified pertussis surveillance program across countries, and different surveillance and monitoring approaches are used in different regions, and the reported incidence levels and epidemiological characteristics vary greatly. The integration of emergency management and epidemiological research is essential in the combating of pertussis. Emergency management provides the rapid response necessary to mitigate the impact of an outbreak, while epidemiological research provides the knowledge and understanding to guide effective control strategies. Researchers should take a consideration and discussion about the role of traditional Chinese medicine in this epidemic, as well as the treatment and prevention in the whole course of the disease. Besides, a model of emergency management and epidemiological surveillance system should be established and continuously improved in clinical to combat the pertussis outbreak. This paper aims to provide an epidemic control model of the emergency management procedure in hospital for references, so that the clinical practitioners and healthcare workers may be better prepared and well-respond to a next epidemic. [ABSTRACT FROM AUTHOR]

Fire is a severe catastrophe that harms consequences for humans, the environment, materials, and the economy. A practical solution to fighting fires involves using early warning systems that enable timely detection, thereby reducing their spread and mitigating possible risks. With technological development, surveillance cameras are available in most places, encouraging researchers to develop fire detection systems using convolutional neural networks (CNN). However, most researchers use very deep CNNs, which are computationally expensive, requiring large memory resources and robust hardware for training. To bridge these gaps, four new simple and lightweight CNN networks to classify fires and detect them in their initial stage are proposed in this paper, CNN_A, CNN_B, CNN_C and CNN_D. Furthermore, to improve the algorithm's performance and reduce the error rate, a new assembly approach that combines the predictions of the four networks is applied to single models. A comparison of the proposed algorithms with the recent works on fires shows the efficiency of the approach. Above all, the CNN_BC ensemble model that reached an excellent accuracy of 99.69% and 96.01% on two challenging testsets, achieving a reduced number of floating-point operations and a smaller size. Therefore, the CNN_BC model has an excellent robustness and can easily classify fire at the early stages. [ABSTRACT FROM AUTHOR]

Abstract Background The COVID-19 pandemic highlights the importance of strong surveillance systems in detecting and responding to public health threats. We sought to evaluate attributes of Keur Massar district's existing COVID-19 surveillance system. Method A descriptive, cross-sectional study was conducted in June 2022; desk review covered data collected from March 03, 2020 to May 31, 2022 in 18 health posts. Data were collected using a standardized questionnaire completed during a face-to-face interview and a desk review of surveillance data gathered from different notification platforms (Excel, ODK, DHIS2 aggregated, and tracker). Study was conducted in Keur Massar department, in the Dakar region. We conducted face-to-face interviews with 18 nurses in June 2022. We utilized a standardized, semi-structured questionnaire adapted from CDC guidelines for surveillance evaluation. Results All 18 head nurses targeted, responded to the questionnaire, with an average age of 41.5 years and 63% aged between 30 and 44. The sex ratio (M/F) was 0.6, and respondents had an average of 15.1 years of experience. All nurses were involved in COVID-19 surveillance and had notified at least one suspected case. While 39% conducted COVID-19 data analysis, 55.6% received feedback from the national level. The usefulness score for the surveillance system was 77.7, with the lowest score (72.9) related to describing the pandemic’s magnitude. Simplicity scored 63.3, with low scores for the availability of guidelines (0) but high scores for training and equipment (94.4). Acceptability scored 76.6, with strong support for COVID-19 surveillance but weak community involvement (48.6). While no cases were reported through the DHIS2 aggregated platform, 1327 PCR-positive SARS-CoV-2 cases were reported through the national Excel sheet and 278 PCR-positive cases were reported through the COVID-19 DHIS2 tracker during the same period. Timeliness varied, averaging 3 days using ODK and 7 days with the national Excel sheet, with a combined average of 5 days across both systems. Conclusion The study highlights challenges in COVID-19 surveillance due to limited human resources, multiple data systems, and delays in notification. While most nurses were trained and equipped, gaps in data quality, timeliness, and community support emphasize the need for streamlined processes and increased workforce capacity.

Background: Brucellosis, as a zoonotic disease, is widespread among humans and animal andcontinues to be a major public health problem. The present study aimed to analyze the trends and epidemiological characteristics of human brucellosis in Ain Témouchent (Western Algeria).Methods: In this registry-based longitudinal study, data on the reported new cases of brucellosis for five years (2014 to 2019) were obtained from the provincial notifiable diseases surveillance system of Ain Temouchent. Using official population data, we calculated the incidence rate per 100,000 inhabitants.Results: From 2014 to 2019, 599 cases of brucellosis cases were notified in Ain Temouchent province (mean annual incidence: 26.37 cases/100,000 inhabitants). The yearly notification peaked in 2014 (n=170 cases). The highest incidence was reported for males (56%) compared to females (44%) with a sex ratio of 1.29. Regarding age, the highest incidence of notified cases for brucellosis was in the group aged 25-44 years and over, accounting for 37,73% of all notified cases. The lowest incidence was found in the age group between 0-14 years with 11.52%. The disease peaked in May with 139 cases. The geographical distribution indicated that the highest risk area of human brucellosis was Hammam Bou Hadjar and Ain Larabaa region.Conclusion: Our findings showed a high prevalence of human brucellosis in Ain Témouchent, with gender, age, and seasonal changes as the main risk factors for human brucellosis.

Abstract Background Formal assessment of a surveillance system’s features and its ability to achieve objectives is crucial for disease control and prevention. Since the implementation of the mpox surveillance system in Cameroon, no evaluation has been conducted. Methods In a cross-sectional study, we assessed the performance of the mpox surveillance system in accordance with the Centers for Disease Control and Prevention (CDC) and World Health Organization (WHO) guidelines. We collected mpox surveillance data from 2018 to 2022 and conducted a survey with key stakeholders of the surveillance program. The survey results were summarized. The rates of complete reporting and mpox detection, as well as the time lag between the different stages of surveillance were analyzed using R version 4.1. Results The mpox detection rate was 21.6% (29/134) over the five years under review. Surveillance indicators revealed that a combination of sample types, including vesicles, crust, and blood, was associated with higher case confirmation. Overall, the mpox surveillance system was effective. Weaknesses in terms of simplicity were identified. Most components of the assessed system failed to meet the timeliness and data quality goals, except for the laboratory component, which was commendable. The lack of a computerized shared database and the system’s non-sustainability were a course of concern. Conclusions Despite all identified bottlenecks in the mpox surveillance system in Cameroon, it was found to meet it stipulated goals. Recommendations are made for training on surveillance system features, particularly at the facility/field level. Therefore, there is a crucial need to globally improve the mpox surveillance system in Cameroon for better disease control.

Background: The COVID-19 pandemic highlights the importance of strong surveillance systems in detecting and responding to public health threats. We sought to evaluate attributes of Keur Massar district's existing COVID-19 surveillance system. Method: A descriptive, cross-sectional study was conducted in June 2022; desk review covered data collected from March 03, 2020 to May 31, 2022 in 18 health posts. Data were collected using a standardized questionnaire completed during a face-to-face interview and a desk review of surveillance data gathered from different notification platforms (Excel, ODK, DHIS2 aggregated, and tracker). Study was conducted in Keur Massar department, in the Dakar region. We conducted face-to-face interviews with 18 nurses in June 2022. We utilized a standardized, semi-structured questionnaire adapted from CDC guidelines for surveillance evaluation. Results: All 18 head nurses targeted, responded to the questionnaire, with an average age of 41.5 years and 63% aged between 30 and 44. The sex ratio (M/F) was 0.6, and respondents had an average of 15.1 years of experience. All nurses were involved in COVID-19 surveillance and had notified at least one suspected case. While 39% conducted COVID-19 data analysis, 55.6% received feedback from the national level. The usefulness score for the surveillance system was 77.7, with the lowest score (72.9) related to describing the pandemic's magnitude. Simplicity scored 63.3, with low scores for the availability of guidelines (0) but high scores for training and equipment (94.4). Acceptability scored 76.6, with strong support for COVID-19 surveillance but weak community involvement (48.6). While no cases were reported through the DHIS2 aggregated platform, 1327 PCR-positive SARS-CoV-2 cases were reported through the national Excel sheet and 278 PCR-positive cases were reported through the COVID-19 DHIS2 tracker during the same period. Timeliness varied, averaging 3 days using ODK and 7 days with the national Excel sheet, with a combined average of 5 days across both systems. Conclusion: The study highlights challenges in COVID-19 surveillance due to limited human resources, multiple data systems, and delays in notification. While most nurses were trained and equipped, gaps in data quality, timeliness, and community support emphasize the need for streamlined processes and increased workforce capacity. [ABSTRACT FROM AUTHOR]

There are few studies utilizing only IR cameras for long-distance gender recognition, and they have shown low recognition performance due to their lack of color and texture information in IR images with a complex background. Therefore, a rough body segmentation-based gender recognition network (RBSG-Net) is proposed, with enhanced gender recognition performance achieved by emphasizing the silhouette of a person through a body segmentation network. Anthropometric loss for the segmentation network and an adaptive body attention module are also proposed, which effectively integrate the segmentation and classification networks. To enhance the analytic capabilities of the proposed framework, fractal dimension estimation was introduced into the system to gain insights into the complexity and irregularity of the body region, thereby predicting the accuracy of body segmentation. For experiments, near-infrared images from the Sun Yat-sen University multiple modality re-identification version 1 (SYSU-MM01) dataset and thermal images from the Dongguk body-based gender version 2 (DBGender-DB2) database were used. The equal error rates of gender recognition by the proposed model were 4.320% and 8.303% for these two databases, respectively, surpassing state-of-the-art methods. [ABSTRACT FROM AUTHOR]

This developmental research aims to enhancing and extend the implementation of an integrated injury surveillance system for all age groups in areas where responsibilities have been transferred to local authorities in Ubon Ratchathani Province. The study period is from February to April 2024. The target groups include 208 individuals from government agencies, community leaders, and public health volunteers, as well as 200 individuals from all age groups at risk. The tools used in this research include the surveillance forms created and developed by the researchers in the model areas, communication and public relations strategies for injury warnings, health literacy assessments for at-risk groups, random helmet use surveys, and participation and satisfaction assessments. Data analysis involves qualitative methods using content analysis and quantitative methods using descriptive statistics, including percentages, medians, and paired t-tests. The study results indicate that after expanding the model, there was an integration of networks participating in the surveillance system. The use of surveillance tools for risk assessment facilitated communication and risk management at the individual, causative agent, and environmental levels. Consequently, participants' health literacy significantly increased, with a p-value < 0.01. Helmet use rose from 32.00% to 82.00%. Additionally, the management of risk points increased to 5 from the initial target of 4. Network participation post-implementation reached its highest level at 86.06%, and satisfaction was at 81.73%. The injury rate from major causes across all age groups decreased compared to the median rate of the past five years during the same period. Therefore, the surveillance system should focus on proactive measures to provide warnings before incidents occur. It should also encourage public participation, with local administrative organizations playing a central role in driving and coordinating efforts. This approach ensures continuous and sustainable integration of network operations. [ABSTRACT FROM AUTHOR]

Background: Formal assessment of a surveillance system's features and its ability to achieve objectives is crucial for disease control and prevention. Since the implementation of the mpox surveillance system in Cameroon, no evaluation has been conducted. Methods: In a cross-sectional study, we assessed the performance of the mpox surveillance system in accordance with the Centers for Disease Control and Prevention (CDC) and World Health Organization (WHO) guidelines. We collected mpox surveillance data from 2018 to 2022 and conducted a survey with key stakeholders of the surveillance program. The survey results were summarized. The rates of complete reporting and mpox detection, as well as the time lag between the different stages of surveillance were analyzed using R version 4.1. Results: The mpox detection rate was 21.6% (29/134) over the five years under review. Surveillance indicators revealed that a combination of sample types, including vesicles, crust, and blood, was associated with higher case confirmation. Overall, the mpox surveillance system was effective. Weaknesses in terms of simplicity were identified. Most components of the assessed system failed to meet the timeliness and data quality goals, except for the laboratory component, which was commendable. The lack of a computerized shared database and the system's non-sustainability were a course of concern. Conclusions: Despite all identified bottlenecks in the mpox surveillance system in Cameroon, it was found to meet it stipulated goals. Recommendations are made for training on surveillance system features, particularly at the facility/field level. Therefore, there is a crucial need to globally improve the mpox surveillance system in Cameroon for better disease control. [ABSTRACT FROM AUTHOR]

Object monitoring in video analysis is a crucial component of smart surveillance systems, enabling the observation and analysis of customer behavior and interactions with various items. This research aims to present a vision-based approach to object monitoring specifically tailored for surveillance systems in smart shops, utilizing an intelligent Internet of Things device. The focus of this study revolves around monitoring jewelry objects within jewelry shops. To accomplish the object monitoring task, an object detector based on Yolo architecture is employed, allowing for the detection and localization of objects. The Yolo network is trained and validated using a customized dataset that encompasses two distinct classes of jewelry objects: rings and earrings. The experimental findings show that the suggested object monitoring approach fulfills the real-time requirements for monitoring objects within smart shops' surveillance systems. [ABSTRACT FROM AUTHOR]

ABSTRACTRubella is a major cause of congenital defects, and the presence of rubella infection in a pregnant woman may lead to fetal death or congenital defects known as congenital rubella syndrome(CRS). Since China has not yet established a national CRS surveillance system, the true incidence cannot be determined. To understand the disease burden and epidemiological characteristics of CRS cases in China, the article reports the first case of CRS in Quzhou, China, and conducts a retrospective analysis of related cases that have been reported in China over the past decade. Because the availability of rubella-containing vaccines (RCV) was not widespread in China before 2008, women of childbearing age born before 2008 are generally unvaccinated against RCV. Due to the lack of routine CRS monitoring and screening, CRS is underreported in China. Vaccination of nonimmune women of childbearing age with RCV and establishing a sensitive and timely case-based CRS surveillance system can accelerate the elimination of rubella and CRS.

Abstract Background EU workers exposed to hand-arm vibration should be offered health surveillance to detect early symptoms, and findings, of Hand-Arm Vibration Syndrome (HAVS). To execute the mandatory vocational rehabilitation, the employer needs to be aware of injuries found in the medical check-up. We aimed to analyse: 1) How physicians graded the neurosensory component of HAVS on the Stockholm Workshop Scale (SWS), compared to semi-objective findings. 2) What vocational rehabilitative decisions (VRD) were taken by physicians after examinations. 3) Whether the VRDs differed in relation to the SWS-grading. Methods Data came from 660 medical records - all examinations performed during twelve consecutive months in one large Swedish occupational healthcare company. 572 individuals had data on the SWS from the physician. For the qualitative analysis, we used the inductive-iterative immersion-crystallization method. Results 60% of the examined workers had symptoms and 32% had semi-objective findings consistent with HAVS. The physicians’ SWS gradings were underestimated in 59% of the cases with semi-objective findings. The VRDs were classified, relative to communication with the employer, as: “Adequate” (57%), when no injury was present, communication had already taken place, was planned, or was no longer needed in the absence of further exposure, “Semi-adequate” (18%), if no plan for communication was yet established or only communicated through a document with a shorter time until next check-up, and “Inadequate”(25%), when patients refused (20%), or physicians failed to communicate with the employer, despite findings (80%). Underestimated SWS-gradings of HAVS were significantly associated with more “Inadequate” VRDs in the group with semi-objective findings. Conclusions Occupational physicians underestimate the number of individuals with SWS 2–3 compared with semi-objective findings and regularly fail to communicate to the employer despite findings of HAVS. The underestimation of SWS-grading, followed by inadequate VRDs, excludes many workers from the employer’s mandatory protective measures which may lead to aggravation of an untreatable injury in the affected individual and development of HAVS in their similarly exposed colleagues.

Abstract Background Uganda has a sentinel surveillance system in seven high-risk sites to monitor yellow fever (YF) patterns and detect outbreaks. We evaluated the performance of this system from 2017 to 2022. Methods We evaluated selected attributes, including timeliness (lags between different critical time points), external completeness (proportion of expected sentinel sites reporting ≥ 1 suspect case in the system annually), and internal completeness (proportion of reports with the minimum required data elements filled), using secondary data in the YF surveillance database from January 2017–July 2022. We conducted key informant interviews with stakeholders at health facility and national level to assess usefulness, flexibility, simplicity, and acceptability of the surveillance system. Results In total, 3,073 suspected and 15 confirmed YF cases were reported. The median time lag from sample collection to laboratory shipment was 37 days (IQR:21–54). External completeness was 76%; internal completeness was 65%. Stakeholders felt that the surveillance system was simple and acceptable, but were uncertain about flexibility. Most (71%) YF cases in previous outbreaks were detected through the sentinel surveillance system; data were used to inform interventions such as intensified YF vaccination. Conclusion The YF sentinel surveillance system was useful in detecting outbreaks and informing public health action. Delays in case confirmation and incomplete data compromised its overall effectiveness and efficiency.

Background: EU workers exposed to hand-arm vibration should be offered health surveillance to detect early symptoms, and findings, of Hand-Arm Vibration Syndrome (HAVS). To execute the mandatory vocational rehabilitation, the employer needs to be aware of injuries found in the medical check-up. We aimed to analyse: 1) How physicians graded the neurosensory component of HAVS on the Stockholm Workshop Scale (SWS), compared to semi-objective findings. 2) What vocational rehabilitative decisions (VRD) were taken by physicians after examinations. 3) Whether the VRDs differed in relation to the SWS-grading. Methods: Data came from 660 medical records - all examinations performed during twelve consecutive months in one large Swedish occupational healthcare company. 572 individuals had data on the SWS from the physician. For the qualitative analysis, we used the inductive-iterative immersion-crystallization method. Results: 60% of the examined workers had symptoms and 32% had semi-objective findings consistent with HAVS. The physicians' SWS gradings were underestimated in 59% of the cases with semi-objective findings. The VRDs were classified, relative to communication with the employer, as: "Adequate" (57%), when no injury was present, communication had already taken place, was planned, or was no longer needed in the absence of further exposure, "Semi-adequate" (18%), if no plan for communication was yet established or only communicated through a document with a shorter time until next check-up, and "Inadequate"(25%), when patients refused (20%), or physicians failed to communicate with the employer, despite findings (80%). Underestimated SWS-gradings of HAVS were significantly associated with more "Inadequate" VRDs in the group with semi-objective findings. Conclusions: Occupational physicians underestimate the number of individuals with SWS 2–3 compared with semi-objective findings and regularly fail to communicate to the employer despite findings of HAVS. The underestimation of SWS-grading, followed by inadequate VRDs, excludes many workers from the employer's mandatory protective measures which may lead to aggravation of an untreatable injury in the affected individual and development of HAVS in their similarly exposed colleagues. [ABSTRACT FROM AUTHOR]

Hajj is an annual Islamic event attended by millions of pilgrims every year from around the globe. It is considered to be the biggest religious event that includes large human crowds in the world. Managing such crowds and detecting abnormal behaviors is one of the most significant challenges for the host country, particularly the crowds of pilgrims. Most of the current solutions can only handle small-scale crowd management issues, that involve simple and clear abnormal behaviors. Therefore, there is a need to have a human abnormal behavior detection approach that can deal with large-scale crowd situations. This study aims to propose a computer vision-based framework that automatically analyzes video sequences and detects human abnormal behaviors. The Convolutional LSTM Autoencoder is used for analyzing video scenes and extracting valuable spatial and temporal features. The proposed approach has achieved a good loss reduction of 0.176587 in detecting abnormal pilgrims' behavior. The results demonstrate a promising picture of the effectiveness of computer vision technologies to detect abnormal behavior in large-scale crowds. [ABSTRACT FROM AUTHOR]

Background: Uganda has a sentinel surveillance system in seven high-risk sites to monitor yellow fever (YF) patterns and detect outbreaks. We evaluated the performance of this system from 2017 to 2022. Methods: We evaluated selected attributes, including timeliness (lags between different critical time points), external completeness (proportion of expected sentinel sites reporting ≥ 1 suspect case in the system annually), and internal completeness (proportion of reports with the minimum required data elements filled), using secondary data in the YF surveillance database from January 2017–July 2022. We conducted key informant interviews with stakeholders at health facility and national level to assess usefulness, flexibility, simplicity, and acceptability of the surveillance system. Results: In total, 3,073 suspected and 15 confirmed YF cases were reported. The median time lag from sample collection to laboratory shipment was 37 days (IQR:21–54). External completeness was 76%; internal completeness was 65%. Stakeholders felt that the surveillance system was simple and acceptable, but were uncertain about flexibility. Most (71%) YF cases in previous outbreaks were detected through the sentinel surveillance system; data were used to inform interventions such as intensified YF vaccination. Conclusion: The YF sentinel surveillance system was useful in detecting outbreaks and informing public health action. Delays in case confirmation and incomplete data compromised its overall effectiveness and efficiency. [ABSTRACT FROM AUTHOR]

A smart and practical method of keeping an eye on and preventing theft in homes and offices is what Theft Detection using Telegram seeks to achieve. The Telegram bot serves as a conduit for user communication, providing alerts and notifications in the event of any questionable activity. A third-party program called a bot is able to send and receive messages, commands, and requests within the Telegram platform. The bot is created and run by a Bot Father. Moreover, this study investigates the possibility of combining PIR sensors and the wellknown microcontroller ESP32 to efficiently detect motion in smart home applications. Utilizing the ESP32's features, such as its low power consumption and Wi-Fi connectivity, the suggested system is appropriate for Internet of Things implementations. We concentrate on assessing the precision and effectiveness of motion detection with this straightforward but effective configuration. We examine the system's functionality responsiveness, and energy usage through real-world smart home experimentation. The outcomes show the viability and efficacy of the ESP32-PIR integration for motion detection, offering insightful information for improving energy efficiency and smart home security. This study lays the groundwork for the creation of affordable, energy-efficient smart home solutions that make use of off-the-shelf component. [ABSTRACT FROM AUTHOR]

Copyright of World Nuclear Geoscience is the property of World Nuclear Geoscience Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

SEL, a State-based Language for Video Surveillance Modeling, is a formal language designed to represent and identify activities in surveillance systems through scenario semantics and the creation of motion primitives structured in programs. Motion primitives represent the temporal evolution of motion evidence. They are the most basic motion structures detected as motion evidence, including operators such as sequence, parallel, and concurrency, which indicate trajectory evolution, simultaneity, and synchronization. SEL is a very expressive language that characterizes interactions by describing the relationships between motion primitives. These interactions determine the scenario's activity and meaning. An experimental model is constructed to demonstrate the value of SEL, incorporating challenging activities in surveillance systems. This approach assesses the language's suitability for describing complicated tasks. [ABSTRACT FROM AUTHOR]

Introduction: In infectious diseases, there are essential indices used to describe the disease state. In this study, we estimated the basic reproduction number, R0, peak level, doubling time, and daily growth rate of COVID-19. Methods: This ecological study was conducted in 5 provinces of Iran. The daily numbers of new COVID-19 cases from January 17 to February 8, 2020 were used to determine the basic reproduction number (R0), peak date, doubling time, and daily growth rates in all five provinces. A sensitivity analysis was conducted to estimate epidemiological parameters. Result: The highest and lowest number of deaths were observed in Hamedan (657 deaths) and Chaharmahal and Bakhtiari (54 deaths) provinces, respectively. The doubling time of confirmed cases in Kermanshah and Hamedan ranged widely from 18.59 days (95% confidence interval (CI): 17.38, 20) to 76.66 days (95% CI: 56.36, 119.78). In addition, the highest daily growth rates of confirmed cases were observed in Kermanshah (0.037, 95% CI: 0.034, 0.039) and Sistan and Baluchestan (0.032, 95% CI: 0.030, 0.034) provinces. Conclusion: In light of our findings, it is imperative to tailor containment strategies to the unique epidemiological profiles of each region in order to effectively mitigate the spread and impact of COVID-19. The wide variation in doubling times underscores the importance of flexibility in public health responses. By adapting measures to local conditions, we can better address the evolving dynamics of the pandemic and safeguard the well-being of communities.

Introduction: The WHO targets Southeast Asia to eliminate measles and rubella by 2023. Measles-Contain Vaccination (MCV) coverage in Indonesia has dropped 6 %, and vaccine-preventable disease (VPD) reporting has fallen 30 % due to the pandemic. Bantul's MR positive rate rose 16 % in 2022. Measles outbreak with 71 cases in March 2023. We evaluated the system to identify program implementation gaps. Methods: Following system surveillance evaluation guidelines 2006, we conducted a descriptive cross-sectional study. We evaluate the structure and attribute components. We chose eighteen public health facilities for sub-districts, with 52 health workers as representatives of all areas in the Bantul district. We interviewed with a semi-structured questionnaire. We calculated the frequencies and proportions of each component, categorized as good, fair, and weak. Results: The average service time was almost ten years. No Public Health Center (PHC) used the system to make decisions. Since the private health facilities and community involvement was minimal, the surveillance system contains structural weaknesses in networks and partnerships. Timeliness completeness coupled with the weak evidence for variables of accessibility and flexibility is also vulnerable. Conclusions: The Bantul measles-rubella disease surveillance system lacked networking, partnerships, and community involvement. The health office is expected to boost private health facility participation, monitoring and assessment, and vaccine coverage by at least 95 %, especially in vulnerable areas.

SEL, a State-based Language for Video Surveillance Modeling, is a formal language designed to represent and identify activities in surveillance systems through scenario semantics and the creation of motion primitives structured in programs. Motion primitives represent the temporal evolution of motion evidence. They are the most basic motion structures detected as motion evidence, including operators such as sequence, parallel, and concurrency, which indicate trajectory evolution, simultaneity, and synchronization. SEL is a very expressive language that characterizes interactions by describing the relationships between motion primitives. These interactions determine the scenario’s activity and meaning. An experimental model is constructed to demonstrate the value of SEL, incorporating challenging activities in surveillance systems. This approach assesses the language’s suitability for describing complicated tasks.

ObjectiveTo construct an evaluation index system for foodborne disease surveillance system in Beijing， and to provide reference foodborne disease system evaluation in Beijing.MethodsBased on the actual situation of foodborne disease surveillance in Beijing， the evaluation index framework was established through literature search， and the Delphi method was applied to the index system for two rounds of expert consultation， and finally the three-level evaluation index system of foodborne disease surveillance system was established.ResultsThe evaluation index system of foodborne disease surveillance system was divided into three levels， including 3 primary indexes， 24 secondary indexes and 94 tertiary indexes. The indexes are sorted by weight， and the primary indexes are the monitoring system structure and function （0.402 3）， the monitoring system operation guarantee （0.321 5）， and the monitoring system performance （0.276 2）. The top 3 secondary indexes were monitoring definition （0.065 0）， monitoring purpose （0.063 1） and monitoring content （0.059 3）. The top 3 third-level indexes were food-borne disease case definition （0.032 7）， food-borne cluster case definition （0.032 3） and active surveillance case definition （0.031 0）. The average score of importance of each index was 7.68 （5.62-9.18）， and the average coefficient of variation was 0.21 （0.11-0.39）.ConclusionThe index system established in this study covers the structure and function of the surveillance system， monitoring performance and operation guarantee， etc. The research method is appropriate and the results are reliable， which has reference significance for the evaluation of foodborne disease surveillance system in other regions in the future.

Nowadays, for controlling crime, surveillance cameras are typically installed in all public places to ensure urban safety and security. However, automating Human Activity Recognition (HAR) using computer vision techniques faces several challenges such as lowlighting, complex spatiotemporal features, clutter backgrounds, and inefficient utilization of surveillance system resources. Existing attempts in HAR designed straightforward networks by analyzing either spatial or motion patterns resulting in limited performance while the dual streams methods are entirely based on Convolutional Neural Networks (CNN) that are inadequate to learning the long-range temporal information for HAR. To overcome the above-mentioned challenges, this paper proposes an optimized dual stream framework for HAR which mainly consists of three steps. First, a shots segmentation module is introduced in the proposed framework to efficiently utilize the surveillance system resources by enhancing the lowlight video stream and then it detects salient video frames that consist of human. This module is trained on our own challenging Lowlight Human Surveillance Dataset (LHSD) which consists of both normal and different levels of lowlighting data to recognize humans in complex uncertain environments. Next, to learn HAR from both contextual and motion information, a dual stream approach is used in the feature extraction. In the first stream, it freezes the learned weights of the backbone Vision Transformer (ViT) B-16 model to select the discriminative contextual information. In the second stream, ViT features are then fused with the intermediate encoder layers of FlowNet2 model for optical flow to extract a robust motion feature vector. Finally, a two stream Parallel Bidirectional Long Short-Term Memory (PBiLSTM) is proposed for sequence learning to capture the global semantics of activities, followed by Dual Stream Multi-Head Attention (DSMHA) with a late fusion strategy to optimize the huge features vector for accurate HAR. To assess the strength of the proposed framework, extensive empirical results are conducted on real-world surveillance scenarios and various benchmark HAR datasets that achieve 78.6285%, 96.0151%, and 98.875% accuracies on HMDB51, UCF101, and YouTube Action, respectively. Our results show that the proposed strategy outperforms State-of-the-Art (SOTA) methods. The proposed framework gives superior performance in HAR, providing accurate and reliable recognition of human activities in surveillance systems.

This research paper highlights the significance of vehicle detection in aerial images for surveillance systems, focusing on deep learning methods that outperform traditional approaches. However, the challenge of high computation complexity due to diverse vehicle appearances persists. The motivation behind this study is to highlight the crucial role of vehicle detection in aerial images for surveillance systems, emphasizing the superior performance of deep learning methods compared to traditional approaches. To address this, a lightweight deep neural network-based model is developed, striking a balance between accuracy and efficiency enabling real-time operation. The model is trained and evaluated on a standardized dataset, with extensive experiments demonstrating its ability to achieve accurate vehicle detection with significantly reduced computation costs, offering a practical solution for real-world aerial surveillance scenarios. [ABSTRACT FROM AUTHOR]

Wastewater-based epidemiology (WBE) has emerged as a key method for the continuous monitoring of COVID-19 prevalence including circulating SARS-CoV-2 lineages. WBE addresses the limitations of traditional clinical COVID-19 surveillance such as clinical test availability, fluctuating testing rates, and increased reliance on rapid antigen tests. Our study in Perth, Western Australia found a significant positive correlation between SARS-CoV-2 concentrations in wastewater and clinical PCR positivity rates (rs = 0.772; p < 0.001) over an 18-month period that included four successive COVID-19 waves. A strong positive correlation was apparent between the proportions of SARS-CoV-2 lineages in wastewater and clinical cases within the same region (rs = 0.728, p < 0.001), including earlier detection of Omicron and recombinant lineages in wastewater before clinical case confirmation. The successful integration of WBE with healthcare data underscores its critical role in enhancing public health decision-making and pandemic management. This approach not only demonstrates the value of WBE in current global health surveillance efforts but also highlights the potential of WBE to address future public health challenges, as a comprehensive disease monitoring and response approach. [ABSTRACT FROM AUTHOR]

Background and Aims: No recovery related surveillance system exists but given the evidence of effectiveness and growing supply, a house‐ and resident‐ level recovery house (RH) surveillance system could be beneficial for data collection on recovery support service (RSS) engagement, and retention; for improved standardization of RH programs and services; and for identification of outcomes associated with long‐term recovery. Methods: This study aimed to explore current data collection practices at the resident‐ and house‐ level through qualitative focus interviews of RH representatives. The 13 RH interviews were scheduled with 16 RH representative respondents. Results: The most frequently collected resident data was at entry (92%) and departure (85%) and included demographics (n = 5), substance use history (n = 6), treatment and recovery history (n = 5), legal and correctional history (n = 6) and mental health information (n = 7). Recovery support data was collected by 85% of houses. Post‐stay data was only collected by four RHs (31%). Conclusion: These results indicate that there is a lack of standardized systematic collection, analysis, and reporting of recovery related data in the RH field. A recovery related surveillance system has the potential to fill this gap and inform and improve standard of resident care to support long‐term recovery from substance use disorder. [ABSTRACT FROM AUTHOR]

Nowadays, for controlling crime, surveillance cameras are typically installed in all public places to ensure urban safety and security. However, automating Human Activity Recognition (HAR) using computer vision techniques faces several challenges such as lowlighting, complex spatiotemporal features, clutter backgrounds, and inefficient utilization of surveillance system resources. Existing attempts in HAR designed straightforward networks by analyzing either spatial or motion patterns resulting in limited performance while the dual streams methods are entirely based on Convolutional Neural Networks (CNN) that are inadequate to learning the long-range temporal information for HAR. To overcome the above-mentioned challenges, this paper proposes an optimized dual stream framework for HAR which mainly consists of three steps. First, a shots segmentation module is introduced in the proposed framework to efficiently utilize the surveillance system resources by enhancing the lowlight video stream and then it detects salient video frames that consist of human. This module is trained on our own challenging Lowlight Human Surveillance Dataset (LHSD) which consists of both normal and different levels of lowlighting data to recognize humans in complex uncertain environments. Next, to learn HAR from both contextual and motion information, a dual stream approach is used in the feature extraction. In the first stream, it freezes the learned weights of the backbone Vision Transformer (ViT) B-16 model to select the discriminative contextual information. In the second stream, ViT features are then fused with the intermediate encoder layers of FlowNet2 model for optical flow to extract a robust motion feature vector. Finally, a two stream Parallel Bidirectional Long Short-Term Memory (PBiLSTM) is proposed for sequence learning to capture the global semantics of activities, followed by Dual Stream Multi-Head Attention (DSMHA) with a late fusion strategy to optimize the huge features vector for accurate HAR. To assess the strength of the proposed framework, extensive empirical results are conducted on real-world surveillance scenarios and various benchmark HAR datasets that achieve 78.6285%, 96.0151%, and 98.875% accuracies on HMDB51, UCF101, and YouTube Action, respectively. Our results show that the proposed strategy outperforms State-of-the-Art (SOTA) methods. The proposed framework gives superior performance in HAR, providing accurate and reliable recognition of human activities in surveillance systems. [ABSTRACT FROM AUTHOR]

Objectives: Evaluating communicable diseases surveillance system Process at Mosul City. Methodology: A descriptive study using an evaluation approach is conducted to evaluate the Communicable Diseases Surveillance System Process in Mosul City from April 20th, 2022, to May 21st 2023. A non-probability multistage sample was adopted of the study, as twenty-three (23) health institutions are chosen and interview is conducted with health staff works in the communicable diseases Surveillance System. The validity of the instrument determined by a group of experts and the stability of Internal consistency reliability of the questionnaire is (r= 0.86), it is determined by using split-half technique and the computation of Cronbach alpha correlation coefficient. Data are gathered from the samples by using the questionnaire and application of the interview technique. The descriptive statistical data analysis approach is used to analysis the data by using SPSS program, version (26). Results: The study results indicate that the most of system's Process component are effective, available and sufficient in addition to good level of evaluation for all health institutions to implement such system for the benefit of communicable diseases services’ consumers in relation to case detection and registration, case information, data reporting and sending, data analysis, epidemic preparation, response to epidemic, feedback and supervision. Conclusion: The study concluded that all health facilities in Mosul city like family medicine and main primary health care centers that they are providing adequate surveillance system services to the community in regard to Communicable Diseases Surveillance System Process. Recommendations: The study recommended that Surveillance System Process for Communicable Diseases at hospitals in Mosul city, can be enhanced with all measures to continue and keep its perfect performance; with implement Regular and periodic monitoring and follow-up to benefits to the Communicable Diseases Surveillance. [ABSTRACT FROM AUTHOR]

This article presents the design and validation of a novel visual servoing scheme for a surveillance system. In this system, a two-axis gimbal mechanism operates the rotation of a camera which is able to provide visual information on the tracked target for the control system. The control objective is to bring the target's projection to the center of the image plane with the smallest steady-state error and a smooth transient response, even with the unpredictable motion of the target and the influence of external disturbances. To fulfill these tasks, the proposed control scheme is designed consisting of two parts: (1) an observer estimates simultaneously the matched and unmatched disturbances; and (2) a motion control law guarantees the finite-time stability and visual servoing performance. Finally, experiments are conducted for validation and evaluation. The proposed control system shows its consistency and ought to perform better than previous approaches. [ABSTRACT FROM AUTHOR]

With the growth of the global economy, changes in climate and ecological environments, and increased mobility of humans and animals, the transmission risk of vector-borne tropical diseases continues to rise. To address this challenge, strengthening surveillance of vector-borne tropical diseases is urgent. This consensus brought together 29 renowned experts in related professional fields from 26 institutions in China, who, through analyzing the epidemic trend and hazard situation of vector-borne tropical diseases and summarizing the working experiences of experts, have firstly reached following consensus: the burden of vector-borne tropical diseases is heavy with great threats to human health; China has achieved remarkable results in prevention and control of vector-borne tropical diseases, but still needs to strengthen the surveillance and response actively. Secondly, a unanimous consensus has been reached on the aspects of surveillance definition, objectives, contents, and methods of vector-borne tropical diseases. Thirdly, detail requirements have been agreed including: strengthening the concept of early surveillance and forecast, standarding the function, evaluation steps, and construction requirements of surveillance system for vector-borne tropical diseases. Fourthly, key tasks were put forward that need to be investigated and strengthened in the future. This expert consensus provides a standardized reference for the construction of the surveillance pathway and surveillance system for vector-borne tropical diseases in China. [ABSTRACT FROM AUTHOR]