Surveillance Architecture Research Articles

Towards Mine 4.0: A Proposed Multi-Layered Architecture for Real-Time Surveillance and Anomaly Detection in an Open-Pit Phosphate Mine

Given the global importance and limited availability of phosphate, optimizing the use of this critical resource and minimizing its wastage are of paramount importance. In this context, this paper proposes an innovative architecture for the implementation of an intelligent video surveillance system specifically designed for open-pit phosphate mines. The proposed architecture is designed to meet the overall functional requirements of a surveillance system in the challenging environment of open-pit mining, while aligning with the guidelines of the Mine 4.0 revolution. It incorporates advanced technologies that address the critical challenges of latency, data security, and transparency commonly encountered in traditional monitoring systems. By adopting a multi-layered approach that leverages edge, fog, and cloud computing, coupled with blockchain technology and expert collaboration, our architecture offers a comprehensive framework for efficient data processing at every stage, from initial data acquisition to real-time anomaly detection and decision-making.

The framing of Sikh Americans: White Christonormativity, discursive hyper(in)visibilities, and racialization of religion

ABSTRACT We use discourse tracing analysis to examine Sikh media representations across four U.S. newspapers in the last two decades. Guided by the theory of hyper(in)visibility, our study focuses on how representations are othered and erased through various types of discursive hyperinvisibilities, such as myopic, faulty, hazy, and selective visibilities deployed within White Christonormative structures of interpretation. Such othering and erasure then result in the looping of media reports emphasizing stereotypes, misidentification, homogenization, and simplification over 18 years, reinforcing the racialization of religious minorities in a unidimensional way that perpetuates minoritization through discursive tactics of hyper(in)visibility of multiple marginalized groups. These representations have implications that trickle down into real-world intercultural interactions across various spheres of life, including multicultural community settings and workplace interactions, and extend to policy implications such as surveillance architectures. The practical consequences result in intercultural communication outcomes involving hate speech, violence, stereotyping, and microaggressions.

Smart surveillance using IoT: a review

In today’s modern society, video surveillance is a growing trend and it can revolutionize many aspects of technology, especially in future smart cities that will transform traditional surveillance systems into intelligent and interconnected networks. It may be difficult for even well-trained employees to process and respond immediately to monitored data. Moreover, IoT-enabled surveillance systems overcome the challenges and flaws of conventional passive monitoring techniques by offering real-time surveillance and automated notifications for suspicious activity, intrusions, or anomalies. Therefore, the objective of this article is to provide an Internet of Things (IoT)-based smart surveillance system that may successfully connect the ecosystem, resulting in enhanced monitoring for smart city services. The primary goal of this study is to provide a comprehensive review of several IoT-based surveillance techniques used in various smart city applications. The categorization of tasks for each section is as follows: to present the historical context overview; to examine the significance of IoT and its application in smart cities; to present a standardized architecture for IoT-based smart city surveillance; to highlight an authoritative and thorough review of current IoT-based smart surveillance systems; and to identify various research issues. The methods used are: statistical graph or chart approach, schematic, and timeline diagram. Conclusions. This article outlines numerous research challenges for future video surveillance that may be addressed by researchers. In summary, this comprehensive review provides a valuable and streamlined resource for future researchers exploring smart city surveillance through the IoT.

Abnormal Activity Recognition with Residual Attention-based ConvLSTM Architecture for Video Surveillance

Abnormal Activity Recognition with Residual Attention-based ConvLSTM Architecture for Video Surveillance

Disrupting prison managerialism: Managing prisons in an age of pandemic

The coronavirus pandemic swept across the world in 2020, having widespread and dramatic impacts on social life. Prisons in England and Wales implemented a lock down regime for public health purposes that suppressed the spread of coronavirus but continues to have an impact on the quality of life for prisoners. This article is based on a small-scale ethnographic study of prison managers in an English prison. This builds upon studies that have documented the experiences of prison managers in England during 21st century. These studies have illustrated that prior to the pandemic, prison management was dominated by the neoliberal practices of managerialism, including an architecture of surveillance through targets, audits and inspections and the nurturing of a more compliant professional culture. The pandemic disrupted managerialism and initially saw the total dismantling of the system of monitoring and an altered relationship between the central and local levels of the organisation. Managers had to operate with greater agency and developed a stronger sense of place, focussing on the internal and local community. As the threat from the pandemic receded, there was a process of ‘managerial clawback’ with the re-establishing of the managerial architecture and a general acceptance of managerialism as a ‘return to normality’ in prisons. Yet this process was incomplete as the pandemic left complex problems including the best way to operate prison regimes that balanced ongoing health risks, maintaining order and offering constructive activity. These complex problems could not be resolved through centralised managerialism and instead required localised initiative. The pandemic had disrupted managerialism and although the architecture had largely been re-established intact, space had been created for greater autonomy in responding to the legacy. The emerging ‘new normal’ is therefore a mixed managerial economy in prison that navigates a path between managerial control and local autonomy.

On the lookout for influenza viruses in Italy during the 2021-2022 season: Along came A(H3N2) viruses with a new phylogenetic makeup of their hemagglutinin

AimsTo assess influenza viruses (IVs) circulation and to evaluate A(H3N2) molecular evolution during the 2021-2022 season in Italy. Materials and methods12,393 respiratory specimens (nasopharyngeal swabs or broncho-alveolar lavages) collected from in/outpatients with influenza illness in the period spanning from January 1, 2022 (week 2022-01) to May 31, 2022 (week 2022-22) were analysed to identify IV genome and were molecularly characterized by 12 laboratories throughout Italy. A(H3N2) evolution was studied by conducting an in-depth phylogenetic analysis of the hemagglutinin (HA) gene sequences. The predicted vaccine efficacy (pVE) of vaccine strain against circulating A(H3N2) viruses was estimated using the sequence-based Pepitope model. ResultsThe overall IV-positive rate was 7.2% (894/12,393), all were type A IVs. Almost all influenza A viruses (846/894; 94.6%) were H3N2 that circulated in Italy with a clear epidemic trend, with 10% positivity rate threshold crossed for six consecutive weeks from week 2022-11 to week 2022-16. According to the phylogenetic analysis of a subset of A(H3N2) strains (n=161), the study HA sequences were distributed into five different genetic clusters, all of them belonging to the clade 3C.2a, sub-clade 3C.2a1 and the genetic subgroup 3C.2a1b.2a.2. The selective pressure analysis of A(H3N2) sequences showed evidence of diversifying selection particularly in the amino acid position 156. The comparison between the predicted amino acid sequence of the 2021-2022 vaccine strain (A/Cambodia/e0826360/2020) and the study strains revealed 65 mutations in 59 HA amino acid positions, including the substitution H156S and Y159N in antigenic site B, within major antigenic sites adjacent to the receptor-binding site, suggesting the presence of drifted strains. According to the sequence-based Pepitope model, antigenic site B was the dominant antigenic site and the p(VE) against circulating A(H3N2) viruses was estimated to be -28.9%. Discussion and conclusionAfter a long period of very low IV activity since public health control measures have been introduced to face COVID-19 pandemic, along came A(H3N2) with a new phylogenetic makeup. Although the delayed 2021-2022 influenza season in Italy was characterized by a significant reduction of the width of the epidemic curve and in the intensity of the influenza activity compared to historical data, a marked genetic diversity of the HA of circulating A(H3N2) strains was observed. The identification of the H156S and Y159N substitutions within the main antigenic sites of most HA sequences also suggested the circulation of drifted variants with respect to the 2021-2022 vaccine strain. Molecular surveillance plays a critical role in the influenza surveillance architecture and it has to be strengthened also at local level to timely assess vaccine effectiveness and detect novel strains with potential impact on public health.

SPAM (An)Archive: Performing under Surveillance

Inspired by the attempt to disrupt data gathering and asking ourselves about “spam” digital practices as forms of resistance, the project SPAM (An)Archive brought together the work of the (post)composer and media artist Óscar Escudero and the collective SoundTrieb, whose collaboration took place digitally via Zoom and physically in Switzerland in 2021. Escudero’s collaborative work in the last few years with the (post)composer and musicologist Belenish Moreno-Gil has been fruitful at a sociological and cultural level of analysis, beyond music aesthetics, as they both deal with social networks and digital behavior in their music theater compositions. Using Facebook as a digital stage, SoundTrieb’s version of [Custom #2] (a digital melodrama) allowed performers to develop a double personalization of the piece, intervening their own social media profiles. This paper does not intend to discuss a theoretical approach to these artworks, but their subversive capability. Through a cultural analysis approach, this article recognizes the critical potential against the architecture of digital surveillance that they can achieve, while drawing attention to our complacency to ubiquitous technologies. For this purpose, I introduce notions such as DIY music and coded representation, but I also borrow concepts such as Brigitta Muntendorf’s social composing and Escudero’s spam art. This paper explores, through work examples by all the above-mentioned artists, recent models of compositional work that blur the line between the digital and the physical, the virtual and the real, the private and the public.

Smart Security Camera using Machine Learning

Numerous applications have been found for video surveillance. Smart video surveillance systems can improve situational awareness at various scales of time and space. It describes a remote control and surveillance architecture based on mobile devices. To record camera photos and detect intrusion using an image comparison technique, this project uses the Opency library. The streamed video is sent from the server to the remote administrator over the phone after the comparison is completed and an intrusion is discovered. Afterward, admin can take the necessary action. Automatic video analytics are used in smart surveillance to increase the efficiency of security measures. By automatically identifying the individual's deviant conduct, this system complements the existing video surveillance systems while also introducing intelligent analysis of single person activity to improve home security. By sending an SMS, the user is informed and the pertinent data is recorded. The user is able to watch the specific video. This system keeps the home secure, which lowers the frequency of burglary cases and improves social stability.

Panopticism, impartial spectator and digital technology

ABSTRACT Panopticism is Michel Foucault’s term for the internalisation of surveillance and cultural control that is closely linked to the panopticon or surveillance architecture (associated with prisons) of Jeremy Bentham during the 18th and 19th centuries. The purpose of this article is to argue that Adam Smith’s concept of the impartial spectator provides an alternative perspective of internal surveillance that may enhance moral development and resistance to oppressive forms of control. For Smith, this is established through analogical imagination that is used for self-observation to enhance prudent behaviour. The impartial spectator and its resistance to totalitarian behaviour is specifically relevant in contemporary society because of the dominant role of digital technology and scandals that have exposed digital media as participating in digital forms of surveillance, digital personae, artificial intelligence and control. It will also be highlighted that digital surveillance is closely connected to the capitalism that has infiltrated all domains of society, from socio-personal relationships to the workplace.

A closed-loop control architecture of UAV and WSN for traffic surveillance on highways

Excessive speed is the leading cause of accidents on highways. The use of fixed road-side surveillance systems has proven ineffective because people take caution around only those locations. With more advanced technologies and exceptional maneuvering capabilities, Unmanned Aerial Vehicles (UAVs) is a promising candidate for real-time monitoring of vehicles on the highways. The dependency of recently proposed UAV-based architectures on terrestrial networks suffers from high deployment costs. To address this shortcoming, we propose a unique closed-loop control architecture for traffic surveillance on highways that increases the surveillance effectiveness and adapts according to varying traffic patterns. The proposed scheme is comprised of Wireless Sensor Network (WSN) and UAV, named Collaborative Highway Surveillance (CHS), that works without human intervention and enables the capture of over-speeding drivers on a highway. The WSN provides routing services to the UAV and dynamically guides UAV to the best hotspot to position itself. If any vehicle exceeds the speed limit allowed, the UAV immediately informs this event to the Mobile Base Station (MBS). However, to conserve the energy resources of the WSN, low-level speed violations are forwarded to the MBS only when the UAV gets closer to the MBS. Performance results obtained with our proposed architecture show an increase in surveillance efficiency with an improved response time compared with cooperative and stand-alone unguided UAV networks.

IEEE 802.11ah-Enabled Internet of Drone Architecture

IEEE 802.11ah is considered as a promising and scalable solution for connecting a large number of drones. With the support of sub-1 GHz channel bands, relay, and a group-based channel access mechanism, 802.11ah can help drone stations to collect commands, send data, and process response to the control room. However, achieving the required throughput and latency is still challenging due to high mobility and dynamic relaying requirement. This article proposes an IEEE 802.11ah-based Internet of Drones (IoD) architecture for surveillance and remote control. It proposes a scheme for an access point to predict the location of a drone station, and transmitting the required association and channel access configuration to it, enabling it to take up the role of relay. Relay nodes use the transmission opportunity with implicit Acknowledgment to increase the efficiency of the network. The performance analysis of the proposed architecture shows significant improvement in terms of throughput and latency.

HAREDNet: A deep learning based architecture for autonomous video surveillance by recognizing human actions

Human Action Recognition (HAR) is still considered as a significant research area due to its emerging real-time applications like video surveillance, automated surveillance, real-time tracking and resecue missions. HAR domain still have gaps to cover, i.e., random changes in human variations, clothes, illumination, and backgrounds. Different camera settings, viewpoints and inter-class similarities have increased the complexity of this domain. The above-mentioned challenges in uncontrolled environment have ultimately reduced the performances of many well-designed models. The primary objective of this research is to propose and design an automated recognition system by overcoming these afore-mentioned issues. Redundant features and excessive computational time for the training and prediction process has also been a noteworthy problem. In this article, a hybrid recognition technique called HAREDNet is proposed, which has a) Encoder-Decoder Network (EDNet) to extract deep features; b) improved Scale-Invariant Feature Transform (iSIFT), improved Gabor (iGabor) and Local Maximal Occurrence (LOMO) techniques to extract local features; c) Cross-view Quadratic Discriminant Analysis (CvQDA) algorithm to reduce the feature redundancy; and d) weighted fusion strategy to merge properties of different essential features. The proposed technique is evaluated on three (3) publicly available datasets, including NTU RGB+D, HMDB51, and UCF-101, and achieved average recognition accuracy of 97.45%, 80.58%, and 97.48%, respectively, which is better than previously proposed methods.

To an Alien Mecca: Durban Port and its Waterfronts before 1914


 Between 1860 and 1914, three to four million people passed along Durban’s waterfronts, most travelling to or from an industrialising hinterland that a colonial gatekeeper called a ‘Mecca for aliens.’ This article explores mass migration through Durban and the changes the phenomenon brought to the social world and built environments around the lagoon that forms today’s large container port. Using Immigration, Harbour Department and Water Police archives, it shows how the lagoon, until the mid-nineteenth century an obscure outlier in the Indian Ocean World, became deeply integrated with processes simultaneously underway across much of maritime Asia. After an introduction that places colonial Durban alongside the wider changes common to many Indian-Ocean ports, we set the scene with an overview of the lagoon’s deep precolonial past. The core argument then moves through several phases. First, economic and technological developments from the 1850s, designed to inflate cargo capacity, also intensified transoceanic migrant traffic. This generated a rich cultural heterogeneity on the lagoon’s fringes. Second, mass migration fueled a backlash among colonial authorities, who built an elaborate architecture of detention and surveillance around the inner shore. Third, some migrants subverted the new order by ‘jumping ship’ in creative ways, ensuring the waterfronts remained, for a time, unruly heterotopia. In these ways, Durban became a characteristic Indian Ocean port city. But Durban authorities introduced an unusual element: to the north they created a recreational beachfront for settler elites. This ultimately reorientated the city’s waterfront away from the lagoon to the open ocean, casting the former’s social history into the shadows.

Secure Dengue Epidemic Prediction System: Healthcare Perspective

Viral diseases transmitted by mosquitoes are emerging public health problems across the globe. Dengue is considered to be the most significant mosquito-oriented disease. Conspicuously, the present study provides an effective architecture for Dengue Virus Infection surveillance. The proposed system involves a 4-level architecture for the prediction and prevention of dengue infection outspread. The architectural levels including Dengue Information Acquisition level, Dengue Information Classification level, Dengue-Mining and Extraction level, and Dengue-Prediction and Decision Modeling level enable an individual to periodically monitor his/her probabilistic dengue fever measure. The prediction process is carried out so that proactive measures are taken beforehand. For predictive purposes, probabilistic analysis in terms of Level of Dengue Fever (LoDF) was carried out using the Adaptive Neuro-Fuzzy Inference System. Based on the Self-Organized Mapping procedure, the presence of LoDF is visualized. Several simulations on datasets of 16 individuals cumulating to 32,255 instances were conducted to test the effectiveness of the presented model. In comparison to other decision-modeling methods, significantly improved results in form of classification efficacy, a temporal delay, prediction effectiveness, reliability, and stability were reported for the presented model.

Real-Time Traffic and Road Surveillance With Parallel Edge Intelligence

Edge computing, which is an emerging concept to complement cloud computing, processes data closer to where the data is generated at the network edge. Transportation system is a critical component of our cities and is generating more and more data. To leverage the power of the increasing amount of data from traffic sensors, researchers have started exploring the feasibility of edge computing for traffic big data analytics. Given the resource constraints on edge devices, it is very challenging to achieve high intelligence and real-time capability at the same time. There are few edge transportation systems that function in a multi-tasking mode with high efficiency and intelligence on the edge. This paper proposes a multi-thread parallel edge system architecture and several lightweight algorithms for traffic and road surveillance. The designs ensure robustness and real-time capability for the key modules of the system.

Visual Surveillance for Human Fall Detection in Healthcare IoT

This article designs a visual surveillance framework for human fall detection. In order to solve the conventional issues in fall detection, such as unsatisfactory feature generalization, low recall rates, and large computational time, we design a model that incorporates the deep convolutional neural network and the aggregated heuristic visual features in detecting the occurrence of falls. First, the convolutional neural network (Openpose model) is utilized to extract human skeleton in the image. Second, the hand-crafted spatial features, such as the angle of human shank inclination, are aggregated to determine the fall presence. It should be noticed that our fall detection method has been integrated to healthcare Internet of Things (IoT) video surveillance architecture, which has multiple graphic processing unit groups to perform real-time monitoring and alarming for the elderly in need. The experimental results prove that our method is able to accurately distinguish fall and nonfall activities with a competitive false-alarm rate.

Toward an Online Continual Learning Architecture for Intrusion Detection of Video Surveillance

With recent advances in deep learning technologies, many commercialized video surveillance systems have adopted Artificial Intelligence (AI)-powered video analytics technologies as a way to make our life smarter and safer. Nevertheless, there is no robust architecture with an appropriate network model for commercial services considering both high accuracy and low computational cost. Existing deep learning technologies would not be enough to model and represent the dynamics of the real-world scene, so it is difficult to satisfy all environments using a generic model. Appropriate training data from false-alarm and/or missed cases can address this limitation but is rarely available due to legal issues relating to the privacy of personal data and the unpredictability of new incoming data. In this paper, we propose a novel end-to-end hybrid video surveillance architecture for reliable object detection, consisting of front-end and back-end intelligence. For the intelligent front-end, we propose a new object detector with a Multi-scale ResBlock scheme to consider the scalability and flexibility of the system. We are also developing a new domain adaptation method to replace the generic model with each camera&#x2019;s individual personal model by understanding real-time space and context information for intelligent back-end architecture. It is an iterative and continuous process in which new upcoming data and previous models are consistently engaged in a continuous improvement process. We conducted a series of experiments, including an interesting proof-of-concept tests called the <i>Chameleon</i> project, which demonstrated the high accuracy and versatility of the new architecture, while producing robust results that can be implemented in practice.

CubeSat formation architecture for small space debris surveillance and orbit determination

Introduction: Satellites which face space debris cannot track it throughout the whole orbit due to natural limitations of their optical sensors, sush as field of view, Earth occultation, or solar illumination. Besides, the time of continuous observations is usually very short. Therefore, we are trying to offer the most effective configuration of optical sensors in order to provide short-arc tracking of a target piece of debris, using a scalable Extended Information Filter. Purpose: The best scenario for short-arc tracking of a space debris orbit using multipoint optical sensors. Results: We have found optimal configurations for groups of satellites with optical sensors which move along a sun-synchronous orbit. Debris orbit determination using an Extended Information Filter and measurements from multipoint sensors was simulated, and mean squared errors of the target's position were calculated. Based on the simulation results for variouos configurations, inter-satellite distances and measurement time, the most reliable scenario (four satellites in tetrahedral configuration) was found and recommended for practical use in short-arc debris tracking.

Low mammalian species richness is associated with Kyasanur Forest disease outbreak risk in deforested landscapes in the Western Ghats, India

Kyasanur forest disease virus (KFDV) is a rapidly expanding tick-borne zoonotic virus with natural foci in the forested region of the Western Ghats of South India. The Western Ghats is one of the world's most important biodiversity hotspots and, like many such areas of high biodiversity, is under significant pressure from anthropogenic landscape change. The current study sought to quantify mammalian species richness using ensemble models of the distributions of a sample of species extant in the Western Ghats and to explore its association with KFDV outbreaks, as well as the modifying effects of deforestation on this association. Species richness was quantified as a composite of individual species' distributions, as derived from ensembles of boosted regression tree, random forest, and generalised additive models. Species richness was further adjusted for the potential biotic constraints of sympatric species. Both species richness and forest loss demonstrated strong positive associations with KFDV outbreaks, however forest loss substantially modified the association between species richness and outbreaks. High species richness was associated with increased KFDV risk but only in areas of low forest loss. In contrast, lower species richness was associated with increased KFDV risk in areas of greater forest loss. This relationship persisted when species richness was adjusted for biotic constraints at the taluk-level. In addition, the taluk-level species abundances of three monkey species (Macaca radiata, Semnopithecus hypoleucus, and Semnopithecus priam) were also associated with outbreaks. These results suggest that increased monitoring of wildlife in areas of significant habitat fragmentation may add considerably to critical knowledge gaps in KFDV epidemiology and infection ecology and should be incorporated into novel One Health surveillance development for the region. In addition, the inclusion of some primate species as sentinels of KFDV circulation into general wildlife surveillance architecture may add further value.

Space surveillance architecture: issues and challenges – an integrated approach

The object of this study is space surveillance activity and the information systems involved for actors and national security organizations. Near and Deep Space Surveillance areas are presented, the former dealing with artificial objects and the latter the inner planetary system, including asteroids and its exploration and exploitation. (Near Space includes the upper layers of the atmosphere (thermosphere, exosphere) and the magnetosphere up to the limits of the magnetopause (6–15 RE). Deep Space refers to the space after the magnetopause and practically up to the limits of the Kuiper belt, about 50 A.U.) Due to the different matter of each area, the two sectors cannot have a common system for surveillance. The ever-increasing interest in natural resource extraction from the asteroid belt, the Moon, and Near-Earth Objects, combined with the explosive growth of the number of satellite commercial applications, makes the development and interconnection of the two distinct sector systems a necessity. This study describes the surveillance systems, the available technologies and methods, and develops a comprehensive oversight proposal.