Surveillance Infrastructure Research Articles

Few-Shot Image Classification of Crop Diseases Based on Vision-Language Models.

Accurate crop disease classification is crucial for ensuring food security and enhancing agricultural productivity. However, the existing crop disease classification algorithms primarily focus on a single image modality and typically require a large number of samples. Our research counters these issues by using pre-trained Vision-Language Models (VLMs), which enhance the multimodal synergy for better crop disease classification than the traditional unimodal approaches. Firstly, we apply the multimodal model Qwen-VL to generate meticulous textual descriptions for representative disease images selected through clustering from the training set, which will serve as prompt text for generating classifier weights. Compared to solely using the language model for prompt text generation, this approach better captures and conveys fine-grained and image-specific information, thereby enhancing the prompt quality. Secondly, we integrate cross-attention and SE (Squeeze-and-Excitation) Attention into the training-free mode VLCD(Vision-Language model for Crop Disease classification) and the training-required mode VLCD-T (VLCD-Training), respectively, for prompt text processing, enhancing the classifier weights by emphasizing the key text features. The experimental outcomes conclusively prove our method's heightened classification effectiveness in few-shot crop disease scenarios, tackling the data limitations and intricate disease recognition issues. It offers a pragmatic tool for agricultural pathology and reinforces the smart farming surveillance infrastructure.

Urea Concentration Detection in Milk Using Microscopic Image Processing Algorithm under Ultraviolet Light Approach

The adulteration of milk is a pressing concern for the citizens of India and people all around the globe. Due to a lack of regulation compliance and insufficient surveillance infrastructure, it is noticeably worse in emerging and slow-growing nations. One of the most common and dangerous adulterants in milk is urea. If the permissible quantity of urea in milk is surpassed, it could have a major negative impact on people's health. All existing methods of urea detection require time, expertise, costly chemicals, and enzymes, along with exorbitant instruments and instrument-specific expertise. The key to overcoming this challenge is having the infrastructure to detect adulterated milk. This study aims to identify a cost- effective and largely implementable system for quantitative detection of urea content to identify adulterated milk primarily for milk distribution centers in India. The proposed milk adulteration detection system, dubbed the MADS, entails a cost-effective, rapid, accurate, precise, and completely novel method for the quantitative computation of urea levels in adulterated milk. It is a device that detects the concentration of particles of urea in milk using a microscopic image processing algorithm under ultraviolet light. Using ultraviolet light and a proprietary program in Python, the isolation of the urea particle from the rest of the milk solids is done and the area concentration, as an average of the value calculated in each of the frames of the video captured through the microscopic camera, is computed. This gives the final urea concentration in milk, which can be used to check whether the concentration follows the government guidelines and exceeds the legal limit.

Linking Maternal and Child Health Data to Enhance Public Health Surveillance in Indiana

Indiana faces significant challenges in maternal and infant health, ranking 45th worst in infant mortality with a rate of 6.5 deaths per 1,000 live-births, and 21st in stillbirths. Indiana further has the 3rd highest rate of maternal mortality with 44 deaths per 100,000 live-births. Despite these alarming statistics, comprehensive surveillance of maternal and infant health is absent, and data often remains fragmented across disparate information systems. In response, the Indiana University Fairbanks School of Public Health and Regenstrief Institute secured a cooperative agreement through the CDC's Pregnant People-Infant Linked Longitudinal Surveillance (PILLARS) program, collaborating with the Indiana Health Information Exchange, Indiana Department of Health, and Marion County Public Health Department. The initiative aims to enhance Indiana's infrastructure for surveillance of maternal and child health (MCH) using electronic health records (EHRs), public health, and administrative data. Key efforts have included development, validation, and application of linkage algorithms across records for mothers and children; integration of case data across data sources; design of routine surveillance reports; and design of longitudinal studies to examine determinants and outcomes in MCH populations. Using deterministic linkage algorithms, we have created over 800,000 mother-infant dyads; this number will expand with the implementation of probabilistic approaches. We also have developed a computational phenotype for identifying cases of pregnancy in the EHR even when not explicitly flagged in the EHR. Future efforts will build on this infrastructure to draw from additional public health data sources and/or expand surveillance efforts to include prioritized MCH outcomes.

Assessment of Public Health Agency and Utility Training Needs for CDC National Wastewater Surveillance System Jurisdictions in the United States.

Since the start of the COVID-19 pandemic, wastewater surveillance hasemerged as a critical tool for tracking the spread of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus and other pathogens in communities throughout the United States. In 2020, the Centers for Disease Control and Prevention (CDC) launched the National Wastewater Surveillance System (NWSS), which partners with state, local, tribal, and territorial health departments to develop and implement wastewater collection and analysis systems and to share data. In 2022, the CDC established the first two NWSS Centers of Excellence to lead its implementation and coordination efforts-one in Colorado (Colorado CoE) and one in Houston (Houston CoE). As the NWSS expands, it is becoming more important to support the training needs of jurisdictions at different stages of developing their wastewater surveillance infrastructure. To evaluate these needs, the Colorado CoE and Houston CoE conducted a needs assessment study of NWSS-funded public health agencies and public utilities departments located in the United States using surveys developed by the Colorado CoE. The results of the surveys showed that although some training needs were universal, it will be most beneficial to develop training modules tailored to the needs of entities that operate wastewater surveillance programs of various sizes, workforce experience levels, and at different stages in the infrastructure development process.

Linking Maternal and Child Health Data to Enhance Public Health Surveillance and Implement Sustainable Interventions.

Our initiative aims to enhance the public health informatics infrastructure for surveillance of maternal and child health (MCH) using data captured from electronic health records (EHRs), public health information systems, and administrative health data. Our work includes development, validation, and application of linkage algorithms across records for mothers and children; integration of data across myriad sources; design of routine surveillance reports; and design of longitudinal studies to examine determinants and outcomes in MCH populations. Our work is conducted in partnership with governmental public health agencies, health care providers, academic institutions, and community-based organizations. Future work will build on the enhanced informatics infrastructure to draw from additional public health data sources and/or expand surveillance efforts to include prioritized MCH outcomes. We will further translate knowledge gained from surveillance into action, working with our partners to improve and sustain better MCH equitably in our population.

Dengue Hemorrhagic Fever in Quang Nam Province (Vietnam) from 2020 to 2022-A Study on Serotypes Distribution and Immunology Factors.

Background: Dengue hemorrhagic fever (DHF) is the most prevalent and fastest-growing vector-borne disease globally, with symptoms ranging from mild to severe and, in some cases, fatal. Quang Nam province in Vietnam can serve as a model for dengue epidemiological study, as it is an endemic region for DHF with a tropical climate, which significantly constrains the health system. However, there are very few epidemiological and microbiological reports on Dengue virus (DENV) serotypes in this region due to the limited availability of advanced surveillance infrastructure. Aims of the study: This study aims to (1) assess the PCR positivity rates among hospitalized patients with clinical Dengue presentation; (2) identify the circulating DENV serotypes; and (3) assess the impact of secondary DENV infections on outbreak severity by detecting the presence of DENV-specific IgG antibodies in the plasma of DENV-infected patients. Materials and methods: Blood samples from patients clinically diagnosed with DHF and admitted to Quang Nam General Hospital (2020-2022) were analyzed. RNA extraction was performed using the NKDNA/RNAprep MAGBEAD kit, followed by Multiplex Reverse Transcription real-time Polymerase Chain Reaction (MLP RT-rPCR) for DENV detection and serotype identification. Positive samples were further tested for DENV-specific IgG antibodies using an enzyme-linked immunosorbent assay (ELISA). Results: The PCR positivity rate among hospitalized patients was approximately 68% throughout the study period. A significant shift in DENV serotypes was observed, with DENV-2 initially dominant and later giving way to DENV-1. IgG was detected in nearly half of the MPL RT-rPCR-positive samples, indicating secondary DENV infections. Conclusions: Our study highlights persistent dengue prevalence and dynamic shifts in DENV serotypes in Quang Nam province, emphasizing the need for improved diagnostic strategies and timely sample collection. The significant serotype shifts and the presence of IgG in hospitalized patients suggest potential severe outcomes from recurrent DENV infections, possibly linked to antibody-dependent enhancement (ADE) effect, underscoring the importance of advanced surveillance, vector control, vaccination campaigns, and public education to predict and prevent future DHF epidemics.

Crafting markets of exclusion: Frontex and the border security sector

This article analyzes processes, networks and actors on markets for border control as they relate to the operational work and structures of the European Border and Coast Guard (Frontex). More specifically, based on data collection and semi-structured interviews with stakeholders, it contributes new research on migration industries and infrastructures, by examining how Frontex has been reconfigured towards a functionality of generating and developing mar-kets for border security, including surveillance deportations and infrastruc-tures through tenders, contracts and company relations. The article also exam-ines how this development has facilitated the creation of EUROSUR, and EU collaboration with Libyan authorities as well as the implementation of depor-tations from Greece and Turkey. It concludes with more general observations on the political economy of border control resulting from Frontex's crafting of border markets, and the implications it has for human rights and transparency.

Real-Time Detection of Face Mask Usage Using Convolutional Neural Networks

The widespread adoption of face masks has been a crucial strategy in mitigating the spread of infectious diseases, particularly in communal settings. However, ensuring compliance with mask-wearing directives remains a significant challenge due to inconsistencies in usage and the difficulty in monitoring adherence in real time. This paper addresses these challenges by leveraging advanced deep learning techniques within computer vision to develop a real-time mask detection system. We have designed a sophisticated convolutional neural network (CNN) model, trained on a diverse and comprehensive dataset that includes various environmental conditions and mask-wearing behaviors. Our model demonstrates a high degree of accuracy in detecting proper mask usage, thereby significantly enhancing the ability of organizations and public health authorities to enforce mask-wearing rules effectively. The key contributions of this research include the development of a robust real-time monitoring system that can be integrated into existing surveillance infrastructures to improve public health safety measures during ongoing and future health crises. Furthermore, this study lays the groundwork for future advancements in automated compliance monitoring systems, extending their applicability to other areas of public health and safety.

Financing and cost-effectiveness of emergency medical services in low- and middle-income countries

In 2023, the 76th World Health Assembly declared coordinated emergency, critical, and operative care services fundamental for comprehensive universal health coverage in low- and middle-income countries. With increasing mortality from noncommunicable diseases, an organized emergency care system has the capacity to treat a variety of conditions with a common set of resources, optimizing per-unit cost efficiency by applying economies of scope and increasing cost-effectiveness. However, the financing and cost-effectiveness of emergency medical services remain poorly understood despite affordability and financial barriers comprising some of the most significant obstacles to development. Cost-effectiveness analyses generate incremental cost-effectiveness ratios for comparison against per-capita gross domestic product thresholds to determine cost-effectiveness, promoted by the World Health Organization’s Choosing Interventions that are Cost-Effective program. Incremental cost-effectiveness ratios may be used as context-specific indicators of value alongside budget impact and feasibility considerations. Currently, there are few high-quality cost-effectiveness studies of emergency care in low- and middle-income countries, demonstrating significant methodologic heterogeneity, little geographic diversity, neglecting descriptions of assumptions used in cost-effectiveness calculations and comparators used, and lacking incremental cost-effectiveness ratios for comparison. The assessment of emergency care cost-effectiveness is challenging, given the significant breadth of conditions encountered and difficulty in projecting subsequent impact. Without improved epidemiologic surveillance and data-collection infrastructure, data inputs for cost-effectiveness calculations will remain limited. Future efforts should practice standard cost-effectiveness methodologies to permit comparison of incremental cost-effectiveness ratios across interventions and settings while incorporating trauma registry data to longitudinally track patient outcomes over sufficient time horizons to determine impact. New indices that expand the scope of analysis to capture broader secondary impacts of emergency care for future cost-effectiveness studies are needed. In this article, we summarize the key steps for economic evaluations for prehospital care systems and recommend considerations for future prehospital emergency care cost-effectiveness analyses, determining the optimal structure for financing mechanisms well-suited to resource-limited settings are critical for future investigation.

Building a Low-Cost Model for Predicting Infectious Disease Burden: Dengue in Brazil

Disease surveillance is an essential function of public health ministries, but the process is expensive and slow. Here, I consider the potential of a new low-cost early warning method that policy makers could use to immediately estimate the incidence of Dengue in Brazil. Using statewide data on the frequency of “Dengue” in Google search trends, lagged epidemiological data, climate data, and state and time fixed effects, I predict values for Dengue for each month in each state. Comparing predicted values to observed Dengue incidence, this model explained 72.2% of the variation in observed Dengue but tended to underestimate Dengue incidence. Accuracy could be greatly improved using more localized data with smaller time scales. This technique uses free and instantly available data, is quite accurate, and can be modified for other diseases and geographic contexts. Google trends data, when combined with publicly available metrics, provides a viable and productive alternative or complement to current epidemiological surveillance infrastructure and could expedite public health response at little to no cost to national health ministries.

Bedaquiline-pretomanid-moxifloxacin-pyrazinamide for drug-sensitive and drug-resistant pulmonary tuberculosis treatment: a phase 2c, open-label, multicentre, partially randomised controlled trial

The current tuberculosis (TB) drug development pipeline is being re-populated with candidates, including nitroimidazoles such as pretomanid, that exhibit a potential to shorten TB therapy by exerting a bactericidal effect on non-replicating bacilli. Based on results from preclinical and early clinical studies, a four-drug combination of bedaquiline, pretomanid, moxifloxacin, and pyrazinamide (BPaMZ) regimen was identified with treatment-shortening potential for both drug-susceptible (DS) and drug-resistant (DR) TB. This trial aimed to determine the safety and efficacy of BPaMZ. We compared 4 months of BPaMZ to the standard 6 months of isoniazid, rifampicin, pyrazinamide, and ethambutol (HRZE) in DS-TB. 6 months of BPaMZ was assessed in DR-TB. SimpliciTB was a partially randomised, phase 2c, open-label, clinical trial, recruiting participants at 26 sites in eight countries. Participants aged 18 years or older with pulmonary TB who were sputum smear positive for acid-fast bacilli were eligible for enrolment. Participants with DS-TB had Mycobacterium tuberculosis with sensitivity to rifampicin and isoniazid. Participants with DR-TB had M tuberculosis with resistance to rifampicin, isoniazid, or both. Participants with DS-TB were randomly allocated in a 1:1 ratio, stratified by HIV status and cavitation on chest radiograph, using balanced block randomisation with a fixed block size of four. The primary efficacy endpoint was time to sputum culture-negative status by 8 weeks; the key secondary endpoint was unfavourable outcome at week 52. A non-inferiority margin of 12% was chosen for the key secondary outcome. Safety and tolerability outcomes are presented as descriptive analyses. The efficacy analysis population contained patients who received at least one dose of medication and who had efficacy data available and had no major protocol violations. The safety population contained patients who received at least one dose of medication. This study is registered with ClinicalTrials.gov (NCT03338621) and is completed. Between July 30, 2018, and March 2, 2020, 455 participants were enrolled and received at least one dose of study treatment. 324 (71%) participants were male and 131 (29%) participants were female. 303 participants with DS-TB were randomly assigned to 4 months of BPaMZ (n=150) or HRZE (n=153). In a modified intention-to-treat (mITT) analysis, by week 8, 122 (84%) of 145 and 70 (47%) of 148 participants were culture-negative on 4 months of BPaMZ and HRZE, respectively, with a hazard ratio for earlier negative status of 2·93 (95% CI 2·17-3·96; p<0·0001). Median time to negative culture (TTN) was 6 weeks (IQR 4-8) on 4 months of BPaMZ and 11 weeks (6-12) on HRZE. 86% of participants with DR-TB receiving 6 months of BPaMZ (n=152) reached culture-negative status by week 8, with a median TTN of 5 weeks (IQR 3-7). At week 52, 120 (83%) of 144, 134 (93%) of 144, and 111 (83%) of 133 on 4 months of BPaMZ, HRZE, and 6 months of BPaMZ had favourable outcomes, respectively. Despite bacteriological efficacy, 4 months of BPaMZ did not meet the non-inferiority margin for the key secondary endpoint in the pre-defined mITT population due to higher withdrawal rates for adverse hepatic events. Non-inferiority was demonstrated in the per-protocol population confirming the effect of withdrawals with 4 months of BPaMZ. At least one liver-related treatment-emergent adverse effect (TEAE) occurred among 45 (30%) participants on 4 months of BPaMZ, 38 (25%) on HRZE, and 33 (22%) on 6 months of BPaMZ. Serious liver-related TEAEs were reported by 20 participants overall; 11 (7%) among those on 4 months of BPaMZ, one (1%) on HRZE, and eight (5%) on 6 months of BPaMZ. The most common reasons for discontinuation of trial treatment were hepatotoxicity (ten participants [2%]), increased hepatic enzymes (nine participants [2%]), QTcF prolongation (three participants [1%]), and hypersensitivity (two participants [<1%]). For DS-TB, BPaMZ successfully met the primary efficacy endpoint of sputum culture conversion. The regimen did not meet the key secondary efficacy endpoint due to adverse events resulting in treatment withdrawal. Our study demonstrated the potential for treatment-shortening efficacy of the BPaMZ regimen for DS-TB and DR-TB, providing clinical validation of a murine model widely used to identify such regimens. It also highlights that novel, treatment-shortening TB treatment regimens require an acceptable toxicity and tolerability profile with minimal monitoring in low-resource and high-burden settings. The increased risk of unpredictable severe hepatic adverse events with 4 months of BPaMZ would be a considerable obstacle to implementation of this regimen in settings with high burdens of TB with limited infrastructure for close surveillance of liver biochemistry. Future research should focus on improving the preclinical and early clinical detection and mitigation of safety issues together and further efforts to optimise shorter treatments. TB Alliance.

Image-based security techniques for water critical infrastructure surveillance

Security-related image analysis of critical infrastructures involves using advanced technologies to analyze visual data to identify potential threats, vulnerabilities, or abnormal activities. This type of analysis can be crucial for safeguarding critical infrastructure such as water management systems, power plants, transportation systems, communication networks, and more. In this paper, we propose two-factor-based authentication and pose-based monitoring tasks for water critical infrastructures. In the first phase, we detect and recognize the faces of authorized persons and check their liveness for anti-spoofing by eye-clicking checking and multimodal ensemble methods. In the second phase, we create our dataset, WCI-Pose, and we use four pose-based approaches – OpenPose, AlphaPose, Kapao, and YOLOv8 – for human action recognition. Experimental results show that OpenPose algorithm provides more favorable results compared to the other algorithms with an accuracy of 92.4%. SVM with multimodal data has the best performance score with an accuracy of 92% for face anti-spoofing.

AUTOMATED SURVEILLANCE SYSTEM FOR MILITARY BASES THROUGH INTEGRATED FACIAL RECOGNITION AND WEAPON DETECTION

Modern military bases need the most sophisticated safety measures possible. This paper proposes a software solution that makes use of cutting-edge technology like face recognition and weapon detection to improve perimeter security. Using face recognition algorithms, the system seeks to identify possible invaders while concurrently identifying and categorizing any weapons they could be carrying. The technology is designed to detect threats and promptly notify those in authority in order to enable prompt and decisive responses. Key considerations include ensuring the accuracy, reliability, and scalability of the system, as well as addressing ethical and regulatory concerns surrounding data privacy and algorithmic biases. By integrating seamlessly with existing surveillance infrastructure, this software offers a proactive approach to safeguarding military installations, ultimately enhancing overall security and operational readiness. Key Words: Face recognition, Weapon detection, Real-time monitoring, Military base security, Alarm system

Assessing infectious disease surveillance infrastructure in Equateur province, Democratic Republic of the Congo in 2022

Introduction: This study evaluates the infectious disease detection and surveillance infrastructure in Equateur Province, Democratic Republic of the Congo, conducted as part of the Infectious Disease Detection and Surveillance (IDDS) project. The province, with a population of 2.8 million inhabitants spread over 132,518 km², faces numerous challenges due to its ecosystem, making it highly susceptible to outbreaks. The assessment, conducted from January 28 to February 04, 2023, aims to assess the functionality of the diagnostic network, specifically focusing on the capacity of the national public health laboratory in Mbandaka, sample transportation logistics, and opportunities for waste management. The assessment of the capacity of the Mbandaka public health laboratory to detect infectious diseases such as COVID-19, Ebola virus, yellow fever, and measles reveals its significance in epidemiological surveillance in Equateur Province.1. According to the World Health Organization guidelines, "laboratory biosafety is of crucial importance to ensure the safety of personnel and environmental protection when handling coronavirus samples.2 Results: Results indicate that the national public health laboratory in Mbandaka possesses equipment for analyzing various infectious diseases, including COVID-19, Ebola Virus Disease (EVD), yellow fever, and measles. However, challenges such as a non-functional incinerator due to fuel shortages and difficulties in accessing health zones, predominantly accessible by river, hinder sample transportation and waste management efforts. Moreover, there is a lack of triple packaging materials for sample transportation and a need for training health workers on biosecurity protocols. To address these challenges, the study suggests potential solutions, such as utilizing drones for sample transportation to inaccessible health zones and improving collaboration between implementation partners and the Ministry of Health. Additionally, efforts should focus on enhancing communication infrastructure and securing fuel for laboratory operations. Conclusion: In conclusion, despite the existing challenges, the Mbandaka provincial public health laboratory demonstrates the capacity to support the response to certain epidemics in Equateur Province. However, addressing the identified weaknesses is crucial for enhancing infectious disease surveillance and response capabilities in the region.

Enhanced Surveillance: Developing a Computer Vision-based CCTV Footage Analysis Tool for Improved Vehicle Number Plate Recognition

Abstract: Smart parking systems serve as integral components in augmenting the efficiency and sustainability of modern urban environments. Nonetheless, prevailing systems predominantly rely on sensors to monitor parking space occupancy, entailing substantial installation and maintenance costs while offering limited functionality in tracking vehicle movement within parking lots. To confront these challenges head-on, our solution introduces a multistage learning-based approach, capitalizing on the existing surveillance infrastructure within parking facilities and a meticulously curated dataset of Saudi license plates. Our approach amalgamates YOLOv5 for license plate detection, YOLOv8 for character detection, and a novel convolutional neural network architecture tailored for enhanced character recognition. We illustrate the superiority of our approach over single-stage methods, achieving an impressive overall accuracy of 96.1%, a notable advancement from the 83.9% accuracy of single-stage approaches. Furthermore, our solution seamlessly integrates into a web-based dashboard, facilitating real-time visualization and statistical analysis of parking space occupancy and vehicle movement, all accomplished with commendable time efficiency. This endeavor underscores the potential of leveraging existing technological resources to bolster the operational efficiency and environmental sustainability of smart cities. By harnessing the power of machine learning and computer vision, our work exemplifies a paradigm shift towards smarter and more adaptive urban infrastructure

Securing synthetic faces: A GAN-blockchain approach to privacy-enhanced facial recognition

In recent years, facial recognition technology has become increasingly integrated into society, making privacy protection crucial. Previous techniques offered minimal secrecy safeguards through simple obscuration methods. This paper addresses the strict privacy requirements of face image data by developing a novel framework that synergistically integrates Generative Adversarial Networks (GANs), clustering algorithms, and Blockchain technology. The methodology proposes a cutting-edge Privacy-Preserving Self-Attention GAN (PPSA-GAN) to generate realistic synthetic facial imagery. An integrated mini-batch K-means clustering algorithm anonymizes these images into distinct groupings, maximizing privacy preservation. Blockchain integration complements the system by fortifying trust through decentralized ledgers for transparent yet secure data storage and auditing. Rigorous benchmarking on the CelebA dataset confirms the PPSA-GAN architecture’s state-of-the-art performance, attaining an impressive Inception Score of 13.99 and a Fréchet Inception Distance of 35.50. The mini-batch clustering forms 125 distinct clusters, effectively anonymizing facial attributes within the synthetic images. Blockchain integration further bolsters privacy assurances via tamper-proof historical records, showcasing precision, recall, F1-score, and accuracy values of 0.948, 0.938, 0.943, and 0.947, respectively. This multifunctional framework represents a novel contribution, fostering an ethical technological ecosystem that balances progress and privacy. Prospective deployment horizons encompass identity verification, surveillance infrastructure, and augmentation of medical image repositories, seeding an enlightening future for facial recognition domains.

Leveraging IoT for Enhanced National Security : A Comprehensive Review

In an era marked by rapid technological advancement and evolving security threats, the integration of Internet of Things (IoT) technologies has emerged as a pivotal strategy for bolstering national security efforts. The integration of Internet of Things (IoT) technologies into national security frameworks offers unprecedented opportunities for enhancing situational awareness, proactive threat detection, and effective response mechanisms. By deploying IoT devices such as sensors, cameras, and drones across various sectors including border control, critical infrastructure protection, and emergency management, governments can achieve real-time monitoring and data-driven decision-making capabilities. This paper gives a comprehensive review of the use of IoT technologies in national security, including real-time surveillance, border control and critical infrastructure protection. It examines the challenges and propose strategies, including the development of robust regulatory frameworks.

REAL-TIME FACE MASK DETECTION SYSTEM

In real-time face mask detection system developed using Python, TensorFlow, and Keras, designed to enhance public health safety during the COVID-19 pandemic. Leveraging computer vision techniques, the system detects faces in video streams and accurately classifies the presence and correct positioning of face masks. Green and red rectangular signs overlaying individuals' faces provide real-time feedback on mask compliance. The system's versatility enables seamless integration into various surveillance infrastructures, making it a practical solution for enforcing mask-wearing mandates in high-traffic public spaces. Its implementation using widely accessible libraries enhances its potential for widespread adoption, highlighting the role of technology in mitigating the spread of infectious diseases. Key Words: face mask detection, real-time, Python, TensorFlow, Keras, computer vision, machine learning, public health safety, COVID-19, surveillance.

Between Smart Images and Fast Trucks: Digital Surveillance and Obscured Labour in Hyderabad, India

In Hyderabad, India, the growing information technology (IT) sector relies on ensuring safe and efficient movements of people and objects, and the city government and private actors have embraced the promise of digital surveillance to reach these goals. The new Telangana State, created in 2014, has built a new city-wide network of smart cameras, and at ‘hackathons’ programmers develop new digital tools, often connected to this network, that will technologically ‘solve’ social problems. In this article, I examine the system of CCTV cameras and programmers’ investments in these systems, and explore how migrant Vaddera stonecutters use cellphones to evade patrolling officers monitoring the streets where they carry the granite stones that they cut and load to construct the city’s buildings. Expanding on what Gilbert Simondon calls ‘the margin of indeterminacy’, this article reveals gaps in the digital infrastructure of surveillance—even as its integration and completion combine human and technical elements.

Capital City Cruising: Surveillance, Pleasure, and Discursive Practices of Queer Communities in Ottawa

This study investigates how men who have sex with men (MSM) discern, discuss, and defy issues of surveillance in the context of casual, public sex​​—also known as cruising—and how these exchanges constitute and inform subaltern counter-surveillance measures. Focusing on written exchanges by users of the queer hook-up website Squirt, I analyze how individuals share information about the safety and surveillance of cruising locations in the Greater Ottawa Area. This work concludes that surveillance and cruising is normalized, and that both police and ordinary citizens present safety risks. Because of this, great care is taken to act discreetly and not infringe on the safety of non-cruisers. Finally, environmental factors contribute greatly to both the construction and circumvention of surveillance infrastructure. The data additionally complicate surveillance realism (Dencik and Cable 2017), since cruisers accept the presence of surveillance but not the inevitable impact of it.