Search

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]

Concomitant administration refers to the receipt of two or more vaccines during a single healthcare encounter, which is an efficient way to increase vaccination coverage in children. However, the post-marketing safety studies of concomitant administration are scarce. Inactivated hepatitis A vaccine (Healive®) has been used widely in China and other countries for more than a decade. We aimed to explore the safety of Healive® co-administered with other vaccines compared to Healive® alone in children under 16 years old. We retrieved Adverse Events Following Immunization (AEFI) cases and vaccination doses of Healive® during 2020–2021 in Shanghai, China. The AEFI cases were divided into concomitant administration group and Healive® alone group. We used administrative data on vaccine doses as denominators to calculate and compare crude reporting rates between groups. We also compared baseline gender and age distribution, clinical diagnoses, and time interval from vaccination to onset of symptoms between groups. A total 319,247 doses of inactivated hepatitis A vaccine (Healive®) were used and 1,020 AEFI cases (319.50 per million doses) associated with Healive® were reported during 2020–2021 in Shanghai. There were 259,346 doses concomitantly administered with other vaccines and 830 AEFI cases (320.04 per million doses) were reported. There were 59,901 doses of Healive® that vaccinated alone, with 190 AEFI cases (317.19 per million doses). There was only one case with serious AEFI in concomitant administration group, with a rate of 0.39 per million doses. Reported rates of AEFI cases were similar between groups in general (p > 0.05). Concomitant administration of inactivated hepatitis A vaccine (Healive®) with other vaccines has a similar safe profile as Healive® alone. [ABSTRACT FROM AUTHOR]

• Azithromycin-resistant E. coli cross-resistant to other antibiotics (MAR: 56 ± 26.5 %). • Prevalence: mph(A) 100 %, erm(B) 37.5 %, ere(A) 2.5 %. • Predominant phylogenetic groups: D and A among isolates. • Strong correlation: WWTP is representative for AR data. Due to the limited information on azithromycin-resistant E. coli and the difficulty in finding a reliable surveillance source for antibiotic resistance (AR) data, this study aimed to investigate the characteristics of such isolates in clinical samples and their correlation with wastewater isolates. Samples were collected from a hospital in Iran over a six-month period and analysed for resistant E. coli , multiple antibiotic resistance (MAR), azithromycin resistance genes (AzRGs), phylogroups, and molecular types and compared with the corresponding parameters in wastewater isolates. Isolates separated from the clinical setting were resistant to all antibiotics tested, from 5 % to 80 %, of which 95 % had MAR values > 0.2. The mph(A), erm(B) , and ere (A) genes were prominent with a prevalence of 100 %, 69.2 % and 2.5 %, respectively, most of them in groups D (52.5 %) and A (42.5 %). The characteristics of the isolates showed a close correlation with those from municipal wastewater (P values for: Mean resistance prevalence = 0.71, MAR = 0.836, AzRGs = 0.134 and phylogenetic analysis = 0.39). This confirms that measuring AR levels in E. coli from wastewater environments may be representative of the corresponding levels in community. [Display omitted] [ABSTRACT FROM AUTHOR]

Surveillance systems are essential in computer vision, with video anomaly detection (VAD) critical for real-world security. Conventional approaches anticipate abnormal frames using normal patterns learned with normal training data and determine anomalies by comparing the output and input. However, they often incur high computational costs due to pre-trained networks and complex modules. Also, they suffer from the tendency to overlook anomalies due to strong generalizing ability. To address these, we propose two innovations: Anomaly Distance Learning (ADL) and Context-Aware Skip Connection (CONASkip), maximizing the distinction between normal and abnormal samples. ADL increases the feature gap by learning to separate normal and abnormal features, while CONASkip selectively connects layers to preserve normal information and differentiate output quality. These methods operate on self-supervised signals, replacing complex and costly modules. Additionally, ADL is excluded during testing, enabling fast inference. Our model achieves 130 frames per second and superior performance on three benchmarks, addressing real-world efficiency challenges. [Display omitted] • Patch anomaly generation enforces normality learning, in terms of appearance and motion. • Anomaly distance learning enlarges the feature distance of normal and abnormal frames. • Context-aware shortcut widens the quality gap between outputs for normal and abnormal samples. • Our method is fast, accurate, and free from pre-trained networks. [ABSTRACT FROM AUTHOR]

This paper proposes a framework for optimizing the layout of surveillance cameras in general outposts along the mountainous border region of the Republic of Korea. Traditional optimization methods focusing on maximizing detection areas often fall short in this terrain. Our approach incorporates expected infiltration routes to enhance detection success rates. The framework involves four stages: (1) defining the surveillance area, (2) identifying infiltration routes using terrain and vegetation data with the A* algorithm, (3) modeling cameras detection areas and probabilities, and (4) optimizing the camera layout for maximum detection success. The optimized layout is compared to traditional methods and evaluated under various scenarios, including information leakage. Results indicate that the proposed method significantly improves detection effectiveness in challenging mountainous regions. [ABSTRACT FROM AUTHOR]

In the face of urbanization and the widespread use of CCTV cameras, the processing of surveillance videos has gained importance. This study endeavors to create a city-wide monitoring system utilizing human action recognition that can elevate the social sustainability of citizens. The primary goal is to develop an entire framework to detect unusual events within urban environments, with a specific focus on identifying four aberrant actions: "falling," "violence," "loitering," and "intrusion.". The processing of CCTV images is vulnerable to adverse weather conditions, particularly impacting human detection and tracking when obstructions like body parts occlusion, such as during falling events. To address these challenges, the paper proposes tracking compensation techniques that boost the system's ability to detect anomalies without requiring additional training. The proposed approach demonstrates a remarkable 21.21% enhancement in detecting falling events, without compromising its handling of other event types. Overall, the system achieves an impressive average F1 score of 93% across diverse event categories. The system's effectiveness is thoroughly assessed through an extensive subway domain case study, shedding light on its robustness and adaptability for potential real-world deployment. This study also delves into transfer learning dynamics based on sample quantity and pre-training with relevant human-of-interest data. • Developed a CCTV event detection system to enhance social sustainability. • Proposed a method for tracking fallen individuals in adverse weather conditions. • Introduced an filtering method to reduce misclassification of non-human objects. • Conducted an adaptation study of the proposed system in the subway domain. [ABSTRACT FROM AUTHOR]

Fire is considered to be one of the major influencing factors that cause fatalities, property damage, and economic, and ecological disruption. To perform the early detection of fire using data from vision sensors and prevent or reduce the damage that fires cause, deep learning models have been widely adopted to overcome the limitations of conventional methods. However, mainstream convolutional neural network (CNN) models have limited generalisation abilities in unseen scenarios and struggle to obtain a good trade-off among the accuracy, inference speed, and model size. Currently, vision transformers (ViT) outperform conventional CNN models; however, they are computationally expensive and required more data for training. They provide a limited performance for small and medium-sized datasets, which are very common in the fire scene classification domain. In this work, we employ a novel ViT architecture by combining shifted patch tokenisation and local self-attention modules for efficient fire scene classification and enable the model to learn from scratch even on small and medium-sized datasets. Furthermore, to make the model suitable for real-time inferencing, we modify the transformer encoder and eventually achieve a reduced number of floating-point operations and a reduced model size. Additionally, in this work, a medium-scale fire dataset is developed that contains complex real-world scenarios. Our model is assessed on three benchmark and a self-created datasets using several evaluation metrics, including a novel cross-corpse evaluation metric, as well as a robustness evaluation metric. The experimental results indicate that our model achieved an overwhelmingly better performance compared to existing methods in terms of the accuracy and model complexity. • We used a novel tokenization mechanism in ViT for effective fire scene classification. • Employing a locality attention mechanism with a tuned three dense layered-block of multi-head unit in MLP. • Extensive experimental evaluations via three benchmark and a self-created datasets. • The proposed model achieved state-of-the-art performance. [ABSTRACT FROM AUTHOR]

• A multiscale fusion framework is proposed to enhance patient monitoring systems. • The human centric attentional fusion is introduced for contextual features. • Deep multiscale features fusion network is proposed for temporal learning. • Sequential multiheaded attention is used for fusion and feature refinement. • The proposed fusion method is evaluated on five benchmark datasets. Recent advancements in the Internet of Medical Things (IoMT) have revolutionized the healthcare sector, making it an active research area in the academic and industrial sectors. Following these advances, an automatic Human Activity Recognition (HAR) is now integrated into the IoMT, facilitating remote patient monitoring systems for smart healthcare. However, implementing HAR via computer vision is intricate due to complex spatiotemporal patterns, single stream fusion, and clutter backgrounds. Mainstream approaches practice pre-trained CNN model, which extract non-salient features due to their generalized weight optimization and limited discriminative feature fusion. In addition, their sequential models have inadequate performance in complex scenarios due to the vanishing gradients encountered during backpropagation across multiple layers. In response to these challenges, we propose a multiscale feature fusion framework for both indoor and outdoor environments to enhance HAR in healthcare monitoring systems, which is mainly composed of two stages: First, the proposed Human Centric Attentional Fusion (HCAF) network is fused with the intermediate convolutional feature of lightweight MobileNetV3 backbone to enriches spatial learning capabilities for accurate HAR. Next, a Deep Multiscale Features Fusion (DMFF) network is proposed that enhanced the long-range temporal dependencies by redesigning the traditional bidirectional LSTM network into a residual fashion followed by Sequential Multihead Attention (SMA) to eliminate non-relevant information and optimized spatiotemporal feature vectors. The performance of the proposed fusion model is evaluated on benchmark healthcare and general activity datasets. In the healthcare, we used Multiple Camera Fall and UR Fall Detection datasets that achieved 99.941% and 100% accuracy. Despite this, our fusion strategy is rigorously evaluated over three challenging general HAR datasets, including HMDB51,UCF101, and UCF50, demonstrating 74.942%, 97.337%, and 96.156% superior performance compared to State-of-The-Art (SOTA) methods. The run time analysis shows that the proposed method is 2x times faster than the existing methods. [ABSTRACT FROM AUTHOR]

Background: Surveillance systems for surgical site infections (SSIs), as a measure of patient safety, help health institutions devise strategies to reduce or prevent them. No surveillance systems exist to monitor SSIs in Ghana.Aim: To establish a system for monitoring trends and detecting outbreaks in order to create awareness of and control SSIs.Methods: An active 30-day surveillance was undertaken at the general surgical unit of the Korle Bu Teaching Hospital, from July 1st, 2017 to December 31st, 2018 to identify SSI. It involved a daily inpatient surveillance of patients who had had a surgical procedure, followed by post-discharge surveillance by means of a healthcare personnel-based survey and a patient-based telephone survey. We supplied quarterly feedback of results to surgeons.Findings: Among the 3267 patients included, 331 were identified with an SSI, a 10% incidence risk. Patients who acquired an SSI experienced increased morbidity including nine extra days in hospital and an adjusted relative mortality risk of 2.3 (95% confidence interval: 1.3 - 4.1; P=0.006) compared to patients without SSI. Forty-nine per cent (161/331) of SSIs were diagnosed post discharge using the healthcare personnel-based survey. The patient-based telephone survey contributed 12 additional cases. SSI incidence risk decreased from 12.8% to 7.5% during the study period.Conclusion: Post-discharge surveillance is feasible using existing healthcare personnel, and the results highlight the high risk and burden of SSIs in Ghana. A surveillance system with feedback for monitoring SSIs may contribute to reducing SSIs; however, firm conclusions regarding the impact need longer observation time. [ABSTRACT FROM AUTHOR]

Aims: The present paper aims to identify ongoing multinational surveillance systems (SURSYSs) assessing diet and nutrition targeted to adolescents, including European surveys involving multiple countries and similar initiatives conducted in non-European countries with developed economies, and to describe the dietary assessment methods used.Data Synthesis: A total of 13 SURSYSs conducted in Europe, USA, Canada, Australia and New Zealand were identified. Dietary assessment methods commonly used include 24-h recalls (24H-Rs) and questionnaires or interviews. Food frequency questionnaires (FFQs) are used in combination with 24H-Rs in six SURSYSs: only FFQs are used in four SURSYSs; 24H-Rs only in one system and a 24H-R in combination with a general questionnaire/interview in one SURSYS. Eleven systems collect information also on some dietary habits and ten systems on other nutritional indicators such as anthropometric and/or biochemical measures. The FFQs used are not homogeneous and often include limited food or beverage items such as fruits and vegetables or sugar-sweetened beverages. In seven systems, foods specifically consumed by adolescents, such as fast food or snacks, are not assessed; instead, a total of seven systems collect data on supplement intake and just in very few cases on fats, legumes and/or water.Conclusions: This study detected considerable variability across the systems identified, suggesting the need for a SURSYS targeted to adolescents that gathers as much as possible complete dietary information, with standardised methodology and regular periodicity. The detailed information provided by this review could be useful to national authorities for the choice of protocols to be applied in their own national surveys. [ABSTRACT FROM AUTHOR]

A well-functioning disease surveillance system is essential for effective control of diseases. Therefore, conducting evaluation studies on the performance of disease surveillance systems is necessary. This study was conducted to evaluate the performance of the Iranian syndrome-based surveillance system for tuberculosis (TB) in rural areas of Fars, the third largest province located in southern Iran. This was an evaluation study. Two independent sources of information (data from a population-based survey and data from the surveillance system) were used in this evaluation. A group of trained female nurses used a specially designed interview-administered questionnaire to obtain data on the health status of family members from mothers or other adult women in rural houses. Subsequently, the nurses obtained data from individuals who reported a history of TB during a specified period and defined whether the patients presented themselves to a rural or urban health centre or clinic. A total of 48,771 individuals participated in this study. Of 156 cases who reported a history of TB, 137 (87.82%) presented themselves to at least one medical care provider seeking diagnosis and treatment services. Of patients who visited a health or medical centre, only 18 (13.14%) were reported to the highest level of the surveillance system. Accordingly, the rates of underascertainment and underreporting of the Iranian surveillance system for TB were 12.18% and 86.86%, respectively. Moreover, underascertainment was significantly higher for men (19.40%) than for women (6.74%). The mean time between the date at which TB was noticed and the date of diagnosis was 56.24 days, which was longer for men (79.29 days) than for women (40.10 days). The highest and lowest levels of underreporting were observed for private general practitioners (100%) and the health centres run by the government (87%), respectively. The quality of the communicable disease surveillance system for TB in Iran is facing important challenges, including underascertainment, underreporting and timeliness, in addition to different types of bias. Informing the general population and health workforce about TB and the importance of timely diagnosis is a good approach to improve the performance of Iran's national communicable disease surveillance system. • Considerable underreporting and underascertainment was observed in the Iranian surveillance system for tuberculosis (TB). • There was a long time lag between occurrence of TB and visiting a health provider. • Timeliness and ascertainment for visiting a health provider were biased for sex. • Compared with the public sector, the private healthcare providers contributed less to the surveillance system. [ABSTRACT FROM AUTHOR]

The integration of artificial intelligence (AI) into human activity recognition (HAR) in smart surveillance systems has the potential to revolutionize behavior monitoring. These systems analyze an individual's physiological or behavioral features to continuously monitor and identify any unusual or suspicious activity in video streams, thereby improving security and surveillance measures. Traditional surveillance systems often rely on manual human monitoring, which is resource-intensive, error-prone, and time-consuming. To address these limitations, computer vision-based behavior biometrics has emerged as a solution for secure video surveillance applications. However, implementing automated HAR in real-world scenarios is challenging due to the diversity of human behavior, complex spatiotemporal patterns, varying viewpoints, and cluttered backgrounds. To tackle these challenges, an AI-based behavior biometrics framework is introduced that is based on a dynamic attention fusion unit (DAFU) followed by a temporal-spatial fusion (TSF) network to effectively recognize human activity in surveillance systems. In the first phase of the proposed framework, a lightweight EfficientNetB0 backbone is enhanced by the DAFU to extract human-centric salient features using a unified channel-spatial attention mechanism. In the second phase, the DAFU features with fixed sequence lengths are passed to the proposed TSF network to capture the temporal, spatial, and behavioral dependencies in video data streams. The integration of Echo-ConvLSTM in the TSF further enhances accuracy and robustness by combining temporal dependencies from the echo state network with spatial and temporal dependencies from the convolutional long short-term memory (ConvLSTM). The proposed AI-based behavior biometrics framework is evaluated using four publicly available HAR datasets (UCF101, HMDB51, UCF50, and YouTube Action), yielding higher accuracies of 98.734%, 80.342%, 98.987%, and 98.927%, which demonstrate the superior performance when compared with state-of-the-art (SOTA) methods. [ABSTRACT FROM AUTHOR]

This paper proposes a methodology for building a robust instance segmentation model that can effectively detect objects on construction sites under various weather conditions. We utilize generative adversarial networks (GAN) to create a dataset of construction site images containing different weather conditions and customized the GAN to generate images that reflect the characteristics of the PTZ camera view and weather conditions, while preserving unique construction site entities. The study highlights the importance of modifying deep learning models to fit the unique environment of the construction site to develop models that can detect objects under various weather conditions and improve safety at construction sites. The proposed methodology includes creating a dataset of construction site images that incorporates various weather conditions and developing an instance segmentation model that can be applied effectively to real construction sites. By training the model on images that reflect different weather conditions, the segmentation performance of YolactEdge improved by 2.5% compared to the baseline model. Our future research includes expanding to more complex visual tasks, such as visual relationship and scene-graph generation, to develop even more diverse deep learning models that can be used in construction sites and further improve safety monitoring. • We propose a training strategy for the robust detector under weather conditions. • Our method generates data reflected with weather features in outdoor site images. • The proposed model considers the perspective of top-view without sky feature. • The method can be universally applied to surveillance systems installed outdoors. [ABSTRACT FROM AUTHOR]

Fire disasters are considered to be among the most harmful hazards, causing fatalities, ecological and economic chaos, property damage, and they can even impact climate change. Early fire detection is necessary to overcome these losses and disruption. Fire detection using vision sensors is a promising research area that has gained significant attention from computer vision experts. Traditionally, low-level colour features were used for fire detection but they have now been superseded by effective deep learning models that achieve higher accuracy. However, these models also suffer from a higher false alarm rate, due to the fact that they treat fire detection as a classification task where the entire image is classified into a single class and the region of the proposal stage is ignored. Furthermore, the time complexity and model size limit these models from real-world implementation. To overcome these challenges, we propose a modified YOLOv5s model that integrates a Stem module in the backbone, replaces larger kernels with smaller ones in the SPP (Neck), and adds the P6 module into the head. This model achieves promising results with lower complexity and smaller model size, and is able to detect both small and large fire regions in images. Moreover, we contribute a medium-scale fire dataset that consists of three classes (i.e. vehicle fire, building fire, and indoor electric fire), with manual annotation according to the object detection model, where the dataset is publicly available for the research purposes. Finally, for fair evaluation, we re-implement 12 different state-of-the-art object detection models, including the proposed model, and trained them over a self-created dataset. We found that the proposed model achieved better detection performance and applicable in real-world scenario. Our codes and dataset is publicly available at https://github.com/Hikmat-Yar/Modified-YOLOv5-Code. • We integrate Stem module with backbone, a P6 module in head and modify larger kernels in SSP. • We develop a new medium-scale well annotated dataset for fire detection. • We trained 12 different object detection models using a self-created dataset. • The proposed model achieved state-of-the-art performance. [ABSTRACT FROM AUTHOR]

Introduction Two types of Japanese encephalitis (JE) vaccines, inactivated JE vaccine (JE-I) and live-attenuated JE vaccine (JE-L), are available and used in China. In particular, one JE-L, produced by a domestic manufacturer in China, was prequalified by WHO in 2013. We assessed the safety of JE vaccines in China during 2008–2013 using the Chinese National Adverse Events Following Immunization Information System (CNAEFIS) data. Methods We retrieved AEFI reporting data about JE vaccines from CNAEFIS, 2008–2013, examined demographic characteristics of AEFI cases, and used administrative data on vaccine doses as denominator to calculate and compare crude reporting rates. We also used disproportionality reporting analysis between JE-I and JE-L to assess potential safety signals. Results A total of 34,879 AEFIs related with JE-I and JE-L were reported, with a ratio of male to female as 1.3:1; 361 (1.0%) cases were classified as serious. JE vaccines were administered concurrently with one or more other vaccines in 13,592 (39.0%) of cases. The overall AEFI reporting rates were 214.4 per million vaccination doses for JE-L and 176.9 for JE-I (rate ratio [RR]: 1.2, 95% confidence interval [CI]: 1.1–1.3) in 2010–2013. Febrile convulsions (FC) following JE-I was found as a signal of disproportionate reporting (SDR). However, there was no significant difference between the reporting rates of FC of JE-I and JE-L (0.3 per million vaccination doses for JE-L, 0.4 for JE-I, p = 0.05). Conclusions While our analysis did not find apparent safety concern of JE vaccines in China, further study should consider JE-I vaccines and febrile convulsion, and taking more sensitive methods to detect signals. [ABSTRACT FROM AUTHOR]

This study aimed at comparing the surveillance program of bovine herpesvirus type 1 (BHV1) as laid down by EU Decision 2004/558/EC and 2007/584/EC (‘conventional design’) with an alternative design. The alternative design was based on monthly bulk-milk testing, clinical surveillance and a risk-based component that involves testing of animals that are purchased from non-free cattle herds. Scenario-tree analyses were carried out to determine sensitivities of the surveillance system (and its components) and the monthly confidence of freedom on herd-level. Also, the expected costs per surveillance design and components thereof were calculated. Results showed that the conventional (EU) and alternative surveillance designs to obtain a BHV1-free status performed equally well in terms of sensitivity. However, total costs per cattle herd to obtain a free status were highest in the conventional design. In an endemic situation and with a within-herd design prevalence of 10%, the conventional design led to a varying probability of freedom ranging from 99.6% to 100% per month. With the alternative design, in this situation, a constant probability of freedom of >99.9% per month was found. In a disease-free situation, both designs performed equally well (probability of freedom >99.9% per month). The yearly costs per farm for monitoring the disease-free status decreased by approximately 25% in the alternative design. The alternative strategy based on monthly bulk-milk monitoring therefore was deemed most cost-effective. This study showed that the surveillance regime to attain and maintain a BHV1-free status as described by EU-legislation can be improved to reduce the monitoring costs without reduction of the system’s sensitivity, given a within-herd design prevalence of 10%. The assessment of various surveillance designs could be highly useful to support decision-making towards a more risk-based approach of animal health surveillance. [ABSTRACT FROM AUTHOR]

• COVID-19 was interpreted not to be integrated into the communicable disease surveillance system (CDSS) in the Kurdistan region of Iraq due to political influence. • The main concerns regarding the core and support activities of CDSS were the lack of epidemic preparedness, timeliness, and partial cessation of training and supervision during the pandemic. • The main challenges include staff deficiency, absence of motivation and financial support, scarce logistics, managerial and administrative issues, and lack of cooperation, particularly among stakeholders and surveillance staff. This study aimed to determine the opportunities of and barriers to communicable diseases surveillance system (CDSS) during the COVID-19 pandemic and the extent to which the disease integrated into the CDSS in the Kurdistan region of Iraq. A descriptive qualitative approach was applied. We conducted seven semi-structured interviews and seven interviewee in a focus group discussion (FGD) with purposefully identified Key Informants (KI) from June to December 2020. All interviews were digitally recorded and transcribed verbatim. We adopted a mixed deductive-inductive approach for thematic data analysis, facilitated by using MAXQDA20 software for data management. Although the CDSS was considered appropriate and flexible, the COVID-19 was interpreted not to be integrated into the system due to political influence. The main concerns regarding core and support activities were the lack of epidemic preparedness, timeliness, and partial cessation of training and supervision during the pandemic. The existence of reasonable surveillance infrastructure, i.e., trained staff, was identified as an opportunity for improvement. The main challenges include staff deficiency, absence of motivation and financial support for present staff, scarce logistics, managerial and administrative issues, and lack of cooperation, particularly among stakeholders and surveillance staff. Our findings revealed that the CDSS in the Kurdistan region requires substantial enhancement in epidemic preparedness, strengthening human resources, and logistics. the system can be developed by fostering meaningful intersectoral collaboration. We advocate that the health authorities and policy-makers prioritise the surveillance and effective management of communicable diseases. [ABSTRACT FROM AUTHOR]

The early smoke detection in outdoor scenes using video sequences is one of the crucial tasks of modern surveillance systems. Real scenes may include objects that are similar to smoke with dynamic behavior due to low resolution cameras, blurring, or weather conditions. Therefore, verification of smoke detection is a necessary stage in such systems. Verification confirms the true smoke regions, when the regions similar to smoke are already detected in a video sequence. The contributions are two-fold. First, many types of Local Binary Patterns (LBPs) in 2D and 3D variants were investigated during experiments according to changing properties of smoke during fire gain. Second, map of brightness differences, edge map, and Laplacian map were studied in Spatio-Temporal LBP (STLBP) specification. The descriptors are based on histograms, and a classification into three classes such as dense smoke, transparent smoke, and non-smoke was implemented using Kullback-Leibler divergence. The recognition results achieved 96–99% and 86–94% of accuracy for dense smoke in dependence of various types of LPBs and shooting artifacts including noise. [ABSTRACT FROM AUTHOR]

This paper presents a robust moving object detection method by compensating for motion of an unstable camera. Assuming that global camera motion results in affine transform between two successive frames, local affine motions are separately estimated in multiple pre-specified regions for fast, robust estimation of the global motion. The global camera motion is then estimated by the least squares method using the pre-estimated multiple local affine motions. Given a current frame as the reference, the subsequent frame is registered to the current frame using the estimated global motion. The moving objects are finally detected using difference of Gaussian and non-parametric kernel density estimation from the set of registered three frames. Experimental results show that the proposed method can robustly detect moving objects in unstable imaging environment for intelligent surveillance systems using various types of cameras including pan-tilt-zoom (PTZ) and unmanned aerial vehicle (UAV) cameras. [ABSTRACT FROM AUTHOR]

We present an efficient, robust moving object segmentation method that fully utilizes block motion information for high-resolution video surveillance systems. A high-resolution video surveillance system should satisfy two conflicting goals: (i) higher computational efficiency to manage the increasing amount of data and (ii) enhanced functionality in analyzing moving objects. In pursuit of both efficiency and functionality, we first quantize the orientation of motion vectors and then segment moving objects using adaptive block partitioning algorithm. We also present motion orientation histogram-based moving direction estimation. Major contribution of this work is the fully utilization of block motion information provided by either an image signal processing (ISP) chip or a digital signal processor (DSP) built-in software and the optimal representation of moving objects by the block divide-and-merge algorithm. Comparative experiments with the conventional video analysis algorithms show that the proposed method provides better segmentation results with the regular, efficient computational structure that can be easily embedded in an ISP chip or DSP software. [ABSTRACT FROM AUTHOR]

The multi-sensor data fusion relies on a combination of information pieces to produce a more accurate or complete description of the environment. In this work, we considered the case of a surveillance system using several heterogeneous sensors in a network. In such a system, the data fusion objective is to merge the detections provided by the different sensors in order to count, locate and track all the targets in the monitored area. The problem was addressed in the context of Belief Function theory in order to cope with the high inaccuracy of information and the different forms of imprecision. In this framework, we developed a unified approach to model and merge the detections coming from various kinds of sensors with prior knowledge about target location derived from topographical elements. We showed that the developed belief model provided an efficient measurement for data association between tracks and detections. Considering scalable constraints for the system, the complexity and consistency of belief function representation should be controlled, which was achieved by implementing versatile discernment frames and by restricting the number of focal elements. The proof of concept of the proposed data fusion module was achieved by implementing it in an actual detection system. Real-world scenarios were used to draw some conclusions about localization performance and end-user perception. Further experiments were also performed on simulated data to focus on data association and belief function simplification subproblems. [ABSTRACT FROM AUTHOR]

Summary Background National surveillance systems depend on accurate and reproducible diagnosis of infections. Aim To investigate the effect of accuracy of diagnosing healthcare-associated infections (HCAIs) on HCAI rates in a national healthcare-associated surveillance system. Methods Data from the validation process from the intensive care unit (ICU) surveillance component of the German Krankenhaus Infektions Surveillance System (KISS; Hospital Infection Surveillance System) were used to calculate the accuracy of diagnosing HCAI for each individual surveillance person (SP) responsible for surveillance of HCAI in the ICU of his or her hospital. Multivariate analyses were performed to identify factors that were attributed to surveillance accuracy. Findings A total of 189 SPs responsible for surveillance in 218 ICUs assessed 30 case vignettes. The chance of belonging to the group of SPs with high accuracy was increased by being a physician (odds ratio: 3.14; P = 0.02) and by being an external SP (odds ratio: 4.69; P ≤ 0.01). ICU HCAI rates depend on the sensitivity of the ICU's SP [incidence rate ratio (IRR): 1.28 (1.07, 1.53); P ≤ 0.01]. High sensitivity increases healthcare-associated urinary tract infection rates [IRR: 1.33 (1.02, 1.75); P = 0.03] and bloodstream infection rates [IRR: 1.33 (1.06, 1.68); P = 0.01]. High specificity was not a significant factor. Conclusion In light of the link between sensitivity of diagnosing HCAI by case vignettes and the ICU HCAI rates, this validation method can be recommended for validation of other surveillance systems. [ABSTRACT FROM AUTHOR]

The field of animal syndromic surveillance (SyS) is growing, with many systems being developed worldwide. Now is an appropriate time to share ideas and lessons learned from early SyS design and implementation. Based on our practical experience in animal health SyS, with additions from the public health and animal health SyS literature, we put forward for discussion a 6-step approach to designing SyS systems for livestock and poultry. The first step is to formalise policy and surveillance goals which are considerate of stakeholder expectations and reflect priority issues (1). Next, it is important to find consensus on national priority diseases and identify current surveillance gaps. The geographic, demographic, and temporal coverage of the system must be carefully assessed (2). A minimum dataset for SyS that includes the essential data to achieve all surveillance objectives while minimizing the amount of data collected should be defined. One can then compile an inventory of the data sources available and evaluate each using the criteria developed (3). A list of syndromes should then be produced for all data sources. Cases can be classified into syndrome classes and the data can be converted into time series (4). Based on the characteristics of the syndrome-time series, the length of historic data available and the type of outbreaks the system must detect, different aberration detection algorithms can be tested (5). Finally, it is essential to develop a minimally acceptable response protocol for each statistical signal produced (6). Important outcomes of this pre-operational phase should be building of a national network of experts and collective action and evaluation plans. While some of the more applied steps (4 and 5) are currently receiving consideration, more emphasis should be put on earlier conceptual steps by decision makers and surveillance developers (1–3). [ABSTRACT FROM AUTHOR]

Provision of seamless, safe and effective surveillance services to airspace users requires high performance surveillance sensor coverage in the whole airspace. Limitations in the surveillance system will lead to an inability to provide the required surveillance services to the users. This may result in aircraft incident and accident occurrences. In this paper a case study is developed for the Norwegian airspace, based on five years of safety reports, to identify causal factors of incidents/accidents due to radar system limitations. This is conducted with a safety data analysis from Avinor – Norway's Air Navigation Service Provider (ANSP) and structured communication with Surveillance/ATM safety experts from Avinor. The case study shows that, 76 out of 124 occurrences within the five years in the Norwegian airspace/airport were related to the surveillance function, and 34 out of the 76 occurrences were due to limitations in the radar systems. The analysis identified that the highest contributing causal factors of the occurrences due to radar system limitations were limited surveillance coverage, followed by the lack of situational awareness for flight crew/controllers and unsynchronised surveillance information between flight crew and controllers. [ABSTRACT FROM AUTHOR]

• Currently tremendous growth is observed in research of surveillance system. • The surveillance cameras installed at various public places like offices, hospitals, schools, highways, etc. • This research proposed novel technique in detecting crime scene video surveillance system in real time violence detection using deep learning architectures. • Its purpose is to detect signals of hostility and violence in real time, allowing abnormalities to be distinguished from typical patterns. Surveillance system research is now experiencing great expansion. Surveillance cameras put in public locations such as offices, hospitals, schools, roads, and other locations can be utilised to capture important activities and movements for event prediction, online monitoring, goal-driven analysis, and intrusion detection. This research proposed novel technique in detecting crime scene video surveillance system in real time violence detection using deep learning architectures. Here the aim is to collect the real time crime scene video of surveillance system and extract the features using spatio temporal (ST) technique with Deep Reinforcement neural network (DRNN) based classification technique. The input video has been processed and converted as video frames and from the video frames the features has been extracted and classified. Its purpose is to detect signals of hostility and violence in real time, allowing abnormalities to be distinguished from typical patterns. To validate our system's performance, it is trained as well as tested in large-scale UCF Crime anomaly dataset. The experimental results reveal that the suggested technique performs well in real-time datasets, with accuracy of 98%, precision of 96%, recall of 80%t, and F-1 score of 78%. [Display omitted] [ABSTRACT FROM AUTHOR]

• Surveillance anomaly detection is critical in our daily life that replaces inefficient human monitoring with an automated system and provides various pattern recognition applications. • In this paper, novel architecture ITAE learns normal appearance and motion patterns by implicitly capturing static and dynamic features. • By utilizing normalizing flow generative model, we are the first to estimate the distribution of appearance and motion surveillance video features. • The proposed approach achieves superior performance on six surveillance anomaly detection benchmarks and demonstrates its effectiveness of generalization ability which is crucial issue in real-world scenarios. In contemporary society, surveillance anomaly detection, i.e., spotting anomalous events such as crimes or accidents in surveillance videos, is a critical task. As anomalies occur rarely, most training data consists of unlabeled videos without anomalous events, which makes the task challenging. Most existing methods use an autoencoder (AE) to learn to reconstruct normal videos; they then detect anomalies based on their failure to reconstruct the appearance of abnormal scenes. However, because anomalies are distinguished by appearance as well as motion, many previous approaches have explicitly separated appearance and motion informationfor example, using a pre-trained optical flow model. This explicit separation restricts reciprocal representation capabilities between two types of information. In contrast, we propose an implicit two-path AE (ITAE), a structure in which two encoders implicitly model appearance and motion features, along with a single decoder that combines them to learn normal video patterns. For the complex distribution of normal scenes, we suggest normal density estimation of ITAE features through normalizing flow (NF)-based generative models to learn the tractable likelihoods and identify anomalies using out-of-distribution detection. NF models intensify ITAE performance by learning normality through implicitly learned features. Finally, we demonstrate the effectiveness of ITAE and its feature distribution modeling on six benchmarks, including databases that contain various anomalies in real-world scenarios. [ABSTRACT FROM AUTHOR]

We introduced a real-time surgical site infections surveillance mode (SSISM) to monitor hospital-wide surgical site infections (SSIs) based on the ICD-9-CM Volume 3 operational codes and the ICD-10 disease codes. Compared with the gold standard, the SSISM confirmed 71.9% (82/114) of SSIs from 3,048 operations with a 60-fold time-savings. The SSISM could obtain the SSI rates for each type of surgery or disease among hospital-wide inpatients in a tertiary hospital with 3,800 beds. [ABSTRACT FROM AUTHOR]

Abstract: The management of public health emergencies is improved by quick, exhaustive and standardized flow of data on disease outbreaks, by using specific tools for data collection, registration and analysis. In this context, the National Information System for the Notification of Outbreaks of Animal Diseases (SIMAN) has been developed in Italy to collect and share data on the notifications of outbreaks of animal diseases. SIMAN is connected through web services to the national database of animals and holdings (BDN) and has been integrated with tools for the management of epidemic emergencies. The website has been updated with a section dedicated to the contingency planning in case of epidemic emergency. EpiTrace is one such useful tool also integrated in the BDN and based on the Social Network Analysis (SNA) and on network epidemiological models. This tool gives the possibility of assessing the risk associated to holdings and animals on the basis of their trade, in order to support the veterinary services in tracing back and forward the animals in case of outbreaks of infectious diseases. [Copyright &y& Elsevier]

Abstract: In this paper, we propose a cascade classifier combining AdaBoost and support vector machine, and applied this to pedestrian detection. The pedestrian detection involved using a window of fixed size to extract the candidate region from left to right and top to bottom of the image, and performing feature extractions on the candidate region. Finally, our proposed cascade classifier completed the classification of the candidate region. The cascade-AdaBoost classifier has been successfully used in pedestrian detection. We have improved the initial setting method for the weights of the training samples in the AdaBoost classifier, so that the selected weak classifier would be able to focus on a higher detection rate other than accuracy. The proposed cascade classifier can automatically select the AdaBoost classifier or SVM to construct a cascade classifier according to the training samples, so as to effectively improve classification performance and reduce training time. In order to verify our proposed method, we have used our extracted database of pedestrian training samples, PETs database, INRIA database and MIT database. This completed the pedestrian detection experiment whose result was compared to those of the cascade-AdaBoost classifier and support vector machine. The result of the experiment showed that in a simple environment involving campus experimental image and PETs database, both our cascade classifier and other classifiers can attain good results, while in a complicated environment involving INRA and MIT database experiments, our cascade classifier had better results than those of other classifiers. [Copyright &y& Elsevier]

Abstract: As mobile techniques are booming, the surveillance function is extended from a stationary mode to a mobile mode. In a heterogeneous network environment, cameras and viewers are located in different networks so that frame synchronization may span across diverse network domains with different transmission capabilities. The mismatch of transmission capabilities may affect the viewing continuity and playback liveness between cameras and viewers. In the article, we propose an adaptive frame synchronization mechanism for frame capturing at cameras based on the network condition to improve the frame synchronization between two sides across a heterogeneous network. Based on a brief theoretical analysis of the asynchronization effect for video communication in a heterogeneous network environment, the proposed adaptive pause time mechanism can be an effective solution to relieve the asynchronization effect in the unmatched transmission rate situation. The evaluation results show that the proposed scheme can achieve a shorter time delay between the captured frames at the camera site and the viewer site. [Copyright &y& Elsevier]

Abstract: More convenient smart home environments can be constructed by monitoring home appliances, if automated services are supported by their usage information. This paper proposes a scheme for translating association rules among appliances mined from their usage information into service scenarios. A smart home environment is unique in that there exist a limited number of home appliances, some of which operate without interruption like a refrigerator. Furthermore, the number of home appliances is much less than the number of items in itemsets to which existing algorithms for mining association rules have been applied. After showing that the existing algorithms are limited in improving the usefulness of association rule generation by means of adjusting the confidence level due to such unique characteristics, we propose a new service scenario generation scheme which calculates the confidence level based on hypothesis testing. This paper demonstrates that association rule mining based on the dependence between appliances is feasible and its performance is very much comparable with that of an existing association rule mining algorithm. Since home users are allowed to choose their favorable scenarios from meaningful service scenarios generated by the proposed scheme without their intervention, we expect that future smart homes can provide automated services more efficiently to them, especially to surveillance systems for elderly. [Copyright &y& Elsevier]

Objectives: A sentinel surveillance system (SSS) was set up in Hong Kong to monitor hand, foot and mouth disease (HFMD) trends. This evaluation assessed the performance of the SSS from 2001 to 2009, and aimed to identify areas for improvement. Study design: A retrospective review using structured guidelines for evaluating public health surveillance systems published by the US Centers for Disease Control and Prevention. Methods: The effectiveness of the SSS was evaluated using routine service statistics, laboratory surveillance data, and results of an acceptability survey conducted among the sentinel doctors. This information was used to assess various attributes of the SSS including simplicity, flexibility, data quality, usefulness, sensitivity, specificity, positive predictive value (PPV), representativeness, timeliness and acceptability. Results: The SSS was simple and flexible with high-quality data. It correlated well with the laboratory surveillance data (P < 0.001) and facilitated early detection of community epidemics. It helped to identify seasonal trends and high-risk groups. Specificity was high (83.4-88.5%), while sensitivity and PPV were borderline satisfactory (38.4-56.8%). The sentinel clinics were representative of the population distribution. The SSS was acceptable to the sentinel doctors, but 17.9-28.2% of them had delays in reporting. Conclusions: The SSS is effective for monitoring HFMD trends in Hong Kong, and is useful for initiating preventive measures. [ABSTRACT FROM AUTHOR]

Abstract: This paper presents an independent component integrated into a global surveillance system named as OCULUS. The aim of this component is to classify the speed of moving objects as normal or abnormal in order to detect anomalous events, taking into account the object class and spatio-temporal information such as locations and movements. The proposed component analyses the speed of the detected objects in real-time without needing several cameras, a 3D representation of the environment, or the estimation of precise values. Unlike other works, the proposed method does require knowing the camera parameters previously (e.g. height, angle, zoom level, etc.). The knowledge used by this component is automatically acquired by means of a learning algorithm that generates a set of highly interpretable fuzzy rules. The experimental results demonstrate that the proposed method is accurate, robust and provides a real-time analysis. [Copyright &y& Elsevier]

Abstract: Perceiving the environment is crucial in any application related to mobile robotics research. In this paper, a new approach to real-time human detection through processing video captured by a thermal infrared camera mounted on the autonomous mobile platform mSecurit is introduced. The approach starts with a phase of static analysis for the detection of human candidates through some classical image processing techniques such as image normalization and thresholding. Then, the proposal starts a dynamic image analysis phase based in optical flow or image difference. Optical flow is used when the robot is moving, whilst image difference is the preferred method when the mobile platform is still. The results of both phases are compared to enhance the human segmentation by infrared camera. Indeed, optical flow or image difference will emphasize the foreground hot spot areas obtained at the initial human candidates’ detection. [ABSTRACT FROM AUTHOR]

Abstract: Camera handoff is a crucial step to obtain a continuously tracked and consistently labeled trajectory of the object of interest in multi-camera surveillance systems. Most existing camera handoff algorithms concentrate on data association, namely consistent labeling, where images of the same object are identified across different cameras. However, there exist many unsolved questions in developing an efficient camera handoff algorithm. In this paper, we first design a trackability measure to quantitatively evaluate the effectiveness of object tracking so that camera handoff can be triggered timely and the camera to which the object of interest is transferred can be selected optimally. Three components are considered: resolution, distance to the edge of the camera’s field of view (FOV), and occlusion. In addition, most existing real-time object tracking systems see a decrease in the frame rate as the number of tracked objects increases. To address this issue, our handoff algorithm employs an adaptive resource management mechanism to dynamically allocate cameras’ resources to multiple objects with different priorities so that the required minimum frame rate is maintained. Experimental results illustrate that the proposed camera handoff algorithm can achieve a substantially improved overall tracking rate by 20% in comparison with the algorithm presented by Khan and Shah. [Copyright &y& Elsevier]

Abstract: This study compared violent death information reported in state-wide newspaper articles to the medical examiner reports collected for a state public health surveillance system—the National Violent Death Reporting System (NVDRS). While suicides accounted for 83% of deaths in the NVDRS database, more than three-quarters (79%) of violent deaths reported in newspaper articles were homicides. The majority of the suicide incidents were reported in 1–2 newspaper articles whereas the majority of homicide incidents were reported in 11–34 articles. For suicide incidents, the NVDRS reported more circumstances related to mental health problems while newspaper articles reported recent crisis more often. Results show that there is a mismatch in both frequency and type of information reported between a public health surveillance system (NVDRS) and newspaper reporting of violent deaths. As a result of these findings, scientists and other public health professionals may want to engage in media advocacy to provide newspaper reporters with timely and important health information related to the prevention and intervention of violent deaths in their community. [Copyright &y& Elsevier]

Summary: An algorithm was designed to highlight related bloodstream infections using data from a nosocomial infection surveillance system to help local public health authorities direct specific measures towards clusters of cases. The approach was based on a two-step procedure. The first was a test to identify pathogens with an abnormal number of close cases. The second modelled, for the identified pathogens, the distribution of time intervals between successive cases as a mixture of two theoretical distributions in order to determine a threshold below which a specific investigation is required. The algorithm was applied to bloodstream infection surveillance data collected during a 10-year period (1996–2005) in an 878-bed teaching hospital (24 wards) in Lyon, France. The first step identified seven pathogens among the 18 being studied. The modelling succeeded in setting time thresholds to spot clusters of cases requiring further investigation with defined sensitivity and specificity. Setting the sensitivity level at 95%, the threshold values ranged from 24 days (Acinetobacter baumannii) to 294 days (Enterobacter cloacae); the specificity was higher than 70% (up to 97.5% for A. baumannii) except for E. cloacae (52.1%). Setting the specificity level at 95% resulted in a decrease in sensitivity except for A. baumannii (it reached nearly 100%); it fell below 50% for three pathogens: around 40% for Streptococcus pneumoniae and Enterococcus faecalis and 25% for Enterobacter cloacae. The threshold values then ranged from 8 days (S. pneumoniae) to 67 days (Streptococcus pyogenes). The approach proved promising though further refinements are needed before routine use. [Copyright &y& Elsevier]

Summary: The cost of catheter-related bloodstream infection (CRBSI) is substantial in terms of morbidity, mortality and financial resources. Total parenteral nutrition (TPN) is a recognised risk factor for CRBSI. In 1997, an intravenous nutrition nurse was promoted to TPN surveillance clinical nurse manager (CNM) and quarterly infection audit meetings were introduced to monitor trends in CRBSI. Data were prospectively collected over a 15-year period using specific TPN records in a 535-bed tertiary acute university hospital. A total of 20 439 CVC-days and 307 CRBSIs were recorded. Mean number of infections before, and after, the introduction of a dedicated TPN surveillance CNM were compared. Mean CRBSI per 1000 catheter-days ±SD was 20.5±6.34 prior to 1997 and 14.64±7.81 after 1997, representing a mean reduction of 5.84 CRBSIs per 1000 catheter-days (95% CI: −4.92 to 16.60; P =0.05). Mean number of CRBSIs per year ±SD was 28.3±4.93 prior to 1997 and 18.5±7.37 after 1997, representing a mean decrease of 9.8 infections per year (95% CI: 0.01 to 19.66; P <0.05). The savings made by preventing 9.8 infections per year were calculated from data on bed-days obtained from the hospital finance office. The cost in hospital days saved per annum was €135,000. Introduction of a TPN surveillance CNM saved the hospital at least €78,300 per annum and led to a significant decrease in CRBSIs in TPN patients. [Copyright &y& Elsevier]

Intelligent multisensor surveillance systems consist of several types of sensors, which are installed on fixed and mobile devices. These components provide a huge quantity of information that has to be contrasted, correlated and integrated in order to recognize and react on special situations. These systems work in highly dynamic environments, with severe security and robustness requirements. All these characteristics imply the need for distributed solutions. In these solutions, scattered components can decide and act with some degree of autonomy (for instance, if they become isolated), or cooperate and coordinate for a complete tracking of special situations. In order to cope with these requirements and to better structure the solution, we have decided to design surveillance system control as a multiagent system. This is done by applying an agent-orientated methodology, which is assessed with concrete scenarios. [Copyright &y& Elsevier]

Summary: Surgical site infections (SSI) are a key target of nosocomial infection control policy. We evaluated the impact of a six-year surveillance system based on data from INCISO, a network of volunteer surgical wards from hospitals in Northern France. Each year surgical patients were enrolled consecutively and surveyed during their in- and out-hospital stay until 30 days following surgery. A standardised form was completed for each patient including SSI diagnosis according to standard criteria and several risk factors such as wound class, American Society of Anesthesiologists score, operation duration, elective/emergency, videoscopy and type of surgery. A dashboard was displayed at the end of each annual survey, so that participants could compare with other surgery adjusted for National Nosocomial Infections Surveillance system (NNIS) risk index and standardised incidence ratio (SIR). Over the six years, 3661 SSI were identified in 150 440 surgical patients (crude incidence: 2.4%) from 548 surgery wards. The crude SSI incidence decreased from 3.8 to 1.7% (P for trend <0.0001, relative reduction: –55%) and the NNIS-0 adjusted SSI incidence from 2.0 to 1% (P for trend <0.0001; relative reduction: –50%). An active surveillance system striving for benchmark through a network is an effective strategy to reduce SSI incidence. Sustaining control efforts have to be made to maintain low SSI level beyond the three primer years. [Copyright &y& Elsevier]

Abstract: Public health is a complex practice due to the requirements of different jurisdictions. These requirements present a challenging environment in which to develop public health applications; software must be flexible in order to adapt to the complexities of different jurisdictions. One approach is to integrate policy management. Policies that define the rules governing an application can be created, modified, or deleted based on the deployment of that application. This paper describes a software architecture and expert system implementation of a policy manager designed to address jurisdictional requirements in public health applications. We define our policy requirements and policy model, the components of the architecture, and how the architecture has been used to implement our policy manager. Finally, we present examples of how the policy manager has configured policies used in three public health applications. [Copyright &y& Elsevier]

Timeliness is a critical issue in preventing the spread of emerging/notifiable infectious diseases, such as severe acute respiratory syndrome (SARS) or avian influenza (bird flu). Current computerized surveillance systems in many countries have demonstrated their usefulness in detecting specified communicable-diseases. However, the off-line, daily or weekly data reporting mode induces a time lag in data collection, transmission, processing, and responses. This paper proposes an on-line real-time mechanism, named EDICTS, for emerging/notifiable infectious diseases control, tracking and surveillance. It is based on the on-line health IC card system and works at the registration process of primary care practices and emergency departments. Hence, should a disease defined by CDC (Center for disease control) be detected at the registration station, EDICTS responds in real time. Note that EDICTS is a mechanism; it is CDC that determines the policy and activates it. A prototype is designed and implemented on a simulated environment of the Taiwan''s national health insurance IC card system. The proposed policy and rules are defined according to the CDC regulations. Timely, sensitive and cost-effective, EDICTS complements the existing successive level of CDC reporting system as a fast-response control channel. [Copyright &y& Elsevier]

Abstract: An algorithm for color restoration under multiple luminance conditions is proposed. It automatically produces correction vectors to restore the color information in the L ∗ a ∗ b ∗ color metric space, using color values of a target object within the well-illuminated region in a given dynamic image. The use of the correction vectors provides better image quality than that obtained by the restoration algorithm using color change vectors. An experiment is done with two real dynamic images, where a walking person in a building is observed, to evaluate the performance of the proposed algorithm in terms of color-difference. The experimental results show that the restored image by the proposed algorithm decreases the color-difference by 30% compared to the restoration algorithm using color change vectors. The proposed algorithm presents the foundation to identify the person captured by a practical security system using a low cost CCD camera. [Copyright &y& Elsevier]

This paper represents the first of a series of publications describing work in progress on the research, design and testing of a control and surveillance system for a Modular Pebble Bed Reactor.The scope of the project involves the design of a simple state of the art control system for the reactor and a surveillance system based on smart instrumentation and expert system logic. It is noted that there are some physical and experimental problems unique to the MPBR family. These problems are connected with long neutron lifetimes, the need for a new evaluation of kinetic parameters and reactivity effects, and the need for very high sensitivity counting channels. [Copyright &y& Elsevier]

Due to the rapid development of technology, especially in the field of Internet systems, there is an increasing demand both for intelligent, mobile and autonomous systems and for the usage and conveyance of multi-media information through cyberspace. In this paper, we propose an innovative, intelligent multi-agent based model, namely intelligent Java Agent Development Environment (iJADE), to provide an intelligent agent-based platform in the e-commerce environment. In addition to the facilities found in contemporary agent development platforms, which focus on the autonomy and mobility of multi-agents, iJADE provides an intelligent layer (known as the “Conscious Layer”) to support the implementation of various AI functionalities in order to produce “smart” agents.From an implementation point of view, we introduce an intelligent, multi-media processing system known as “iJADE Surveillant”—an intelligent multi-resolution composite neuro-oscillatory agent-based surveillance system—which is based on the integration of the following modules. (a) An automatic coarse-to-fine figure-ground scene segmentation module using the Composite Neuro-Oscillatory Wavelet-based model. (b) An automatic human face detection and extraction module using an Active Contour Model with facial “landmarks” vectors. (c) Invariant human face identification based on the Elastic Graph Dynamic Link Model. To conform to the current (and future) multi-media system standards, all of iJADE Surveillant is implemented using the MPEG-7 system framework—with comprehensive Description Schemes, feature descriptors and a model framework.From an experimental point of view, a scene gallery of over 6000 color scene images is used to test the automatic scene segmentation. One hundred distinct human subjects (with over 1020 tested scenes) are used to test the intelligent human face identification. An overall correct (invariant) facial recognition rate of over 90% is attained. We hope that the implementation of the iJADE Surveillant can provide an invariant and higher-order intelligent object (pattern) encoding, searching and identification solution for future MPEG-7 applications. [Copyright &y& Elsevier]

Copyright of Revue Francaise des Laboratoires is the property of Elsevier B.V. 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.)

The Danish Ministry of Food, Agriculture and Fisheries funds a monitoring system based on drug usage information collected at the herd level: VETSTAT. VETSTAT is constructed as a relational database and data originates from three sources: pharmacies, veterinarians and feed mills. All administration of drugs for use in animal production is reported on a monthly basis.Pharmacies provided 95% of the total weight antimicrobial compounds used in Denmark in 2001. More than 80% of the antimicrobial compounds reported by pharmacies were sold on prescription to end-users (owners) and included information on animal species, age-group and diagnostic grouping; >90% of the total amount of antimicrobials sold on prescription was used for pigs. In 2001, sales of 96,500 kg of antimicrobials were reported. [Copyright &y& Elsevier]

Based on the verified application in China's National Foodborne Disease Outbreak Surveillance System, machine learning techniques have been indicated to have very positive effects. We summarize current positive attempts on improving case reporting, helping diagnosing and outbreak prediction. Based on the attempts, we propose a general framework to facilitate future improvements for a more intelligent foodborne disease surveillance system, which can greatly help human health. • Summarize machine learning (ML) techniques that have positive effect in case reporting, diagnosis and outbreak prediction.. • Generalize current ML effects to a more general scope, including individual, population and spatial temporal requirements. • Propose a general framework that can guide future research on using ML techniques to improve existing surveillance system. [ABSTRACT FROM AUTHOR]

While the effective utilization of drones is expected to grow in a wide range of fields, there are concerns over new threats related to the exploitation of drones that have not been considered thus far. From the perspective of surveillance, the remarkable ability of drones to fly in any arbitrary direction imposes the need for wider range sensing than ever. Cameras are commonly used as surveillance devices; however, traditional cameras capture a limited field of view and, although the output can have a spatially dense resolution, there are significant blind spots. Omnidirectional cameras are emerging as devices that can capture almost all directions simultaneously with one device. In this paper, we present a drone detection system that uses an omnidirectional camera. We use system modularization to improve the detection accuracy for small objects through a combination of image dividing and state-of-the-art object detection algorithms. Three-dimensional direction of detected objects is visualized by our system using the well-calibrated intrinsic/extrinsic parameters of the omnidirectional camera. Our system was evaluated using a dataset for actual flying drones recorded using an omnidirectional camera. Our quantitative evaluation indicates that our system achieved an at-best average precision and average recall of over 0.8 for small objects represented as 10–20 pixel squares in the original image. • Proposed surveillance support system using an omnidirectional camera. • Focusing on drone detection as a countermeasure against future threats from the air. • Achieved an at-best detection precision and recall of over 0.8 for small drones. [ABSTRACT FROM AUTHOR]