To see the other types of publications on this topic, follow the link: Electronic surveillance in art.
Journal articles on the topic 'Electronic surveillance in art'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Electronic surveillance in art.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Piszczek, Martyna. "CRIMINAL LIABILITY RELATED TO THE SYSTEM OF ELECTRONIC SURVEILLANCE AND CIRCUMSTANCES IN WHICH SENTENCED PERSON AVOIDS PERFORMING DUTIES ORDERED BY THE COURT." Probacja 3 (September 30, 2021): 29–70. http://dx.doi.org/10.5604/01.3001.0015.2708.
Full textAbstract:
The crucial aim of this article is to indicate grounds of legal liability connected with situations in which person sentenced to penalty, punitive measure or safeguard measure, within the system of electronic surveillance, violates certain duties. Considerations concerning the aforementioned issues are preceded by the analysis on the essence of the electronic surveillance, reasons for its implementation into the applicable legal system and means of its usage related to legal instruments of penal reaction to perpetrator’s behavior. Moreover, author of the article analyses legal character of the prison sentence performed with the usage of electronic surveillance. This constitutes starting point for answering practically important question: whether leaving the place of performing prison sentence within the system of electronic surveillance can be qualified as the offence of self-release, determined in art. 242 § 1 of the Criminal Code. At the end of the article, author presents de lege ferenda postulates concerning normative solution related to the legal ground of qualifying behaviors consisting in avoiding electronic surveillance.
2
Peter, Johannes Maxmillian. "Electronic Article Surveillance Marker." Journal of the Acoustical Society of America 129, no. 2 (2011): 1134. http://dx.doi.org/10.1121/1.3561527.
Full text
3
Abril-Nieto, Christian Stiven, and Andrés Escobar-Díaz. "Electronic civil surveillance: review oriented to communications for monitoring and a case." Visión electrónica 2, no. 2 (December 6, 2019): 366–80. http://dx.doi.org/10.14483/22484728.18438.
Full textAbstract:
This article, in the context of documentary research carried out and interpreted for that was taken as baseline in investigations on electronic security and their themes for the ORCA group, it´s describe the state of the art of electronic surveillance focused in communications for monitoring stations. It’s set up chronologically in the last decade, in Latin America, and Colombia particularly. The subject has been categorized and subcategorized in such a way that keys are established sources extraction: university digital repositories, online academic magazines and corporate web page. As a product produced by the review, a particular communication model is presented for a case of a monitoring center and a equipment for tracking people.
4
Дундуков, Михаил, and Mikhail Dundukov. "FOREIGN INTELLIGENCE SURVEILLANCE ACT OF 1978 AND MODERN LEGAL STANDARDS IN THE FIELD OF INFORMATION COLLECTION AND ACQUISITION BY U. S. INTELLIGENCE AGENCIES." Journal of Foreign Legislation and Comparative Law 1, no. 4 (October 29, 2015): 0. http://dx.doi.org/10.12737/14314.
Full textAbstract:
This article reviews the development process for the legislation, regulating the U. S. intelligence agencies’ activities in the field of electronic surveillance. The article displays the reasons which prompted U. S. lawmakers to pass the Foreign Intelligence Surveillance Act of 1978; it analyzes the provisions of the law, governing the conditions and procedures for obtaining judicial order or Attorney General authorization on the implementation of electronic surveillance. Considerable attention is paid to the evolution of legal standards, added to the Foreign Intelligence Surveillance Act after the events of September 11, 2001. In particular, it analyzes amendments and additions to the Foreign Intelligence Surveillance Act, introduced on the basis of the USA Patriot Act of 2001, Intelligence Reform and Terrorism Prevention Act of 2004, Protect America Act of 2007, and other laws. The article also shows the patterns of formation of the legislative balance between the interests of the intelligence services and the need to respect the constitutional rights and liberties of American citizens.
5
Schnuch, A., M. Wilkinson, A. Dugonik, B. Dugonik, T. Ganslandt, and W. Uter. "Registries in Clinical Epidemiology: the European Surveillance System on Contact Allergies (ESSCA)." Methods of Information in Medicine 55, no. 02 (2016): 193–99. http://dx.doi.org/10.3414/me15-01-0099.
Full textAbstract:
SummaryBackground: Disease registries rely on consistent electronic data capturing (EDC) pertinent to their objectives; either by using existing electronic data as far as available, or by implementing specific software solutions.Objectives: To describe the current practice of an international disease registry (European Surveillance System on Contact Allergies, ESSCA, www.essca-dc.org) against different state of the art approaches for EDC.Methods: Since 2002, ESSCA is collecting data, currently from 53 departments in 12 countries. Departmental EDC software ranges from spreadsheets to comprehensive “patch test software” based on a relational database. In the Erlangen data centre, such diverse data is imported, converted to a common format, quality checked and pooled for scientific analyses.Results: Feed-back to participating departments for quality control is provided by standardised reports. Varying author teams publish scientific analyses addressing the objective of contact allergy surveillance.Conclusions: Although ESSCA represents a historically grown, heterogeneous network and not one unified approach to EDC, some of its features have contributed to its viability in the last 12 years and may be useful to consider for similar investigator-initiated networks.
6
Rodríguez-Moreno, Itsaso, José María Martínez-Otzeta, Basilio Sierra, Igor Rodriguez, and Ekaitz Jauregi. "Video Activity Recognition: State-of-the-Art." Sensors 19, no. 14 (July 18, 2019): 3160. http://dx.doi.org/10.3390/s19143160.
Full textAbstract:
Video activity recognition, although being an emerging task, has been the subject of important research efforts due to the importance of its everyday applications. Surveillance by video cameras could benefit greatly by advances in this field. In the area of robotics, the tasks of autonomous navigation or social interaction could also take advantage of the knowledge extracted from live video recording. The aim of this paper is to survey the state-of-the-art techniques for video activity recognition while at the same time mentioning other techniques used for the same task that the research community has known for several years. For each of the analyzed methods, its contribution over previous works and the proposed approach performance are discussed.
7
Rojszczak, Marcin. "Extraterritorial Bulk Surveillance after the German BND Act Judgment." European Constitutional Law Review 17, no. 1 (March 2021): 53–77. http://dx.doi.org/10.1017/s1574019621000055.
Full textAbstract:
Foreign surveillance as a means of circumventing existing legal safeguards – Different perspectives on the problem of the extraterritorial application of fundamental rights in US and EU legal models – The limited usefulness of effective control tests for establishing the responsibility of states for action taken in cyberspace – Judgment of Bundesverfassungsgericht in the BND Act case as an interpretative guideline for the regulation of foreign surveillance in EU member states – Electronic surveillance as a threat to European integration process.
8
Giansanti, Daniele, Antonia Pirrera, Paola Meli, Mauro Grigioni, Marta De Santis, and Domenica Taruscio. "Technologies to Support Frailty, Disability, and Rare Diseases: Towards a Monitoring Experience during the COVID-19 Pandemic Emergency." Healthcare 10, no. 2 (January 26, 2022): 235. http://dx.doi.org/10.3390/healthcare10020235.
Full textAbstract:
This report illustrates the design and results of an activity of surveillance proposed by the National Centre for Innovative Technologies in Public Health and the National Centre for Rare Diseases of the Istituto Superiore di Sanità with the aim of monitoring the state-of-use of technologies by people with frailty, disabilities, and rare diseases. The results of the surveillance activity reported in this report are as follows: (a) An international Webinar; (b) A Full report published by the Istituto Superiore di Sanità (ISS); (c) an electronic survey tool, for periodic monitoring; (d) an initial summary of the survey (15 September–30 November 2020), giving an overall picture relating to the state-of-use of technologies by the interviewed; (e) an understanding of the needs that emerged, causing reflection on the current state-of-the-art and offering important stimuli for all the stakeholders involved.
9
Zhang, Tianhao, Waqas Aftab, Lyudmila Mihaylova, Christian Langran-Wheeler, Samuel Rigby, David Fletcher, Steve Maddock, and Garry Bosworth. "Recent Advances in Video Analytics for Rail Network Surveillance for Security, Trespass and Suicide Prevention—A Survey." Sensors 22, no. 12 (June 7, 2022): 4324. http://dx.doi.org/10.3390/s22124324.
Full textAbstract:
Railway networks systems are by design open and accessible to people, but this presents challenges in the prevention of events such as terrorism, trespass, and suicide fatalities. With the rapid advancement of machine learning, numerous computer vision methods have been developed in closed-circuit television (CCTV) surveillance systems for the purposes of managing public spaces. These methods are built based on multiple types of sensors and are designed to automatically detect static objects and unexpected events, monitor people, and prevent potential dangers. This survey focuses on recently developed CCTV surveillance methods for rail networks, discusses the challenges they face, their advantages and disadvantages and a vision for future railway surveillance systems. State-of-the-art methods for object detection and behaviour recognition applied to rail network surveillance systems are introduced, and the ethics of handling personal data and the use of automated systems are also considered.
10
Bloomfield, Brian. "In the Right Place at the Right Time: Electronic Tagging and Problems of Social Order/Disorder." Sociological Review 49, no. 2 (May 2001): 174–201. http://dx.doi.org/10.1111/1467-954x.00251.
Full textAbstract:
This paper explores the relationship between technology and problems of social order/disorder in the context of discussions of surveillance and ‘virtuality'. The emphasis is on understanding the connections between technology and social relations in areas where issues of social order/disorder are a prominent feature of concern and where one can identify the emergence of new regimes of virtual control which are directed at solving the (supposed) deficits in order or the threats posed to it. Rather than constituting a ‘technical fix’ for the problems of social order/disorder, it is argued that forms of virtual control both presuppose a reconstruction of social order and at the same time aim to effect a suppression of disorder. Focusing in particular on various manifestations of electronic tagging – from prisoners to babies, from retail goods to works of art, from television programmes to Personal Identification Numbers – the paper argues that these share a problematic which interrelates technology, order/disorder, subjects/objects, time, and space. It thus seeks to generalize the concept of electronic tagging, to regard it as a practice rather than a specific set of artefacts. Moreover, in contrast to the negative, panoptic reading of tagging technologies, the paper considers the active public participation in systems of surveillance and thereby the more positive or productive exercises of power which they may be taken to constitute.
11
Peterson, Kari E., Donna M. Hacek, Ari Robicsek, Richard B. Thomson, and Lance R. Peterson. "Electronic Surveillance for Infectious Disease Trend Analysis following a Quality Improvement Intervention." Infection Control & Hospital Epidemiology 33, no. 8 (August 2012): 790–95. http://dx.doi.org/10.1086/666625.
Full textAbstract:
Objective.Interventions for reducing methicillin-resistant Staphylococcus aureus (MRSA) healthcare-associated disease require outcome assessment; this is typically done by manual chart review to determine infection, which can be labor intensive. The purpose of this study was to validate electronic tools for MRSA healthcare-associated infection (HAI) trending that can replace manual medical record review.Design and Setting.This was an observational study comparing manual medical record review with 3 electronic methods: raw culture data from the laboratory information system (LIS) in use by our healthcare organization, LIS data combined with admission-discharge-transfer (ADT) data to determine which cultures were healthcare associated (LIS + ADT), and the CareFusion MedMined Nosocomial Infection Marker (NIM). Each method was used for the same 7-year period from August 2003 through July 2010.Patients.The data set was from a 3-hospital organization covering 342,492 admissions.Results.Correlation coefficients for raw LIS, LIS + ADT, and NIM were 0.976, 0.957, and 0.953, respectively, when assessed on an annual basis. Quarterly performance for disease trending was also good, with R2 values exceeding 0.7 for all methods.Conclusions.The electronic tools accurately identified trends in MRSA HAI incidence density when all infections were combined as quarterly or annual data; the performance is excellent when annual assessment is done. These electronic surveillance systems can significantly reduce (93% [in-house-developed program] to more than 99.9999% [commercially available systems]) the personnel resources needed to monitor the impact of a disease control program.
12
Vu, Tuan-Hung, Jacques Boonaert, Sebastien Ambellouis, and Abdelmalik Taleb-Ahmed. "Multi-Channel Generative Framework and Supervised Learning for Anomaly Detection in Surveillance Videos." Sensors 21, no. 9 (May 3, 2021): 3179. http://dx.doi.org/10.3390/s21093179.
Full textAbstract:
Recently, most state-of-the-art anomaly detection methods are based on apparent motion and appearance reconstruction networks and use error estimation between generated and real information as detection features. These approaches achieve promising results by only using normal samples for training steps. In this paper, our contributions are two-fold. On the one hand, we propose a flexible multi-channel framework to generate multi-type frame-level features. On the other hand, we study how it is possible to improve the detection performance by supervised learning. The multi-channel framework is based on four Conditional GANs (CGANs) taking various type of appearance and motion information as input and producing prediction information as output. These CGANs provide a better feature space to represent the distinction between normal and abnormal events. Then, the difference between those generative and ground-truth information is encoded by Peak Signal-to-Noise Ratio (PSNR). We propose to classify those features in a classical supervised scenario by building a small training set with some abnormal samples of the original test set of the dataset. The binary Support Vector Machine (SVM) is applied for frame-level anomaly detection. Finally, we use Mask R-CNN as detector to perform object-centric anomaly localization. Our solution is largely evaluated on Avenue, Ped1, Ped2, and ShanghaiTech datasets. Our experiment results demonstrate that PSNR features combined with supervised SVM are better than error maps computed by previous methods. We achieve state-of-the-art performance for frame-level AUC on Ped1 and ShanghaiTech. Especially, for the most challenging Shanghaitech dataset, a supervised training model outperforms up to 9% the state-of-the-art an unsupervised strategy.
13
Ullah, Waseem, Amin Ullah, Tanveer Hussain, Zulfiqar Ahmad Khan, and Sung Wook Baik. "An Efficient Anomaly Recognition Framework Using an Attention Residual LSTM in Surveillance Videos." Sensors 21, no. 8 (April 16, 2021): 2811. http://dx.doi.org/10.3390/s21082811.
Full textAbstract:
Video anomaly recognition in smart cities is an important computer vision task that plays a vital role in smart surveillance and public safety but is challenging due to its diverse, complex, and infrequent occurrence in real-time surveillance environments. Various deep learning models use significant amounts of training data without generalization abilities and with huge time complexity. To overcome these problems, in the current work, we present an efficient light-weight convolutional neural network (CNN)-based anomaly recognition framework that is functional in a surveillance environment with reduced time complexity. We extract spatial CNN features from a series of video frames and feed them to the proposed residual attention-based long short-term memory (LSTM) network, which can precisely recognize anomalous activity in surveillance videos. The representative CNN features with the residual blocks concept in LSTM for sequence learning prove to be effective for anomaly detection and recognition, validating our model’s effective usage in smart cities video surveillance. Extensive experiments on the real-world benchmark UCF-Crime dataset validate the effectiveness of the proposed model within complex surveillance environments and demonstrate that our proposed model outperforms state-of-the-art models with a 1.77%, 0.76%, and 8.62% increase in accuracy on the UCF-Crime, UMN and Avenue datasets, respectively.
14
Choqueluque-Roman, David, and Guillermo Camara-Chavez. "Weakly Supervised Violence Detection in Surveillance Video." Sensors 22, no. 12 (June 14, 2022): 4502. http://dx.doi.org/10.3390/s22124502.
Full textAbstract:
Automatic violence detection in video surveillance is essential for social and personal security. Monitoring the large number of surveillance cameras used in public and private areas is challenging for human operators. The manual nature of this task significantly increases the possibility of ignoring important events due to human limitations when paying attention to multiple targets at a time. Researchers have proposed several methods to detect violent events automatically to overcome this problem. So far, most previous studies have focused only on classifying short clips without performing spatial localization. In this work, we tackle this problem by proposing a weakly supervised method to detect spatially and temporarily violent actions in surveillance videos using only video-level labels. The proposed method follows a Fast-RCNN style architecture, that has been temporally extended. First, we generate spatiotemporal proposals (action tubes) leveraging pre-trained person detectors, motion appearance (dynamic images), and tracking algorithms. Then, given an input video and the action proposals, we extract spatiotemporal features using deep neural networks. Finally, a classifier based on multiple-instance learning is trained to label each action tube as violent or non-violent. We obtain similar results to the state of the art in three public databases Hockey Fight, RLVSD, and RWF-2000, achieving an accuracy of 97.3%, 92.88%, 88.7%, respectively.
15
Tokunaga, Robert S. "Social networking site or social surveillance site? Understanding the use of interpersonal electronic surveillance in romantic relationships." Computers in Human Behavior 27, no. 2 (March 2011): 705–13. http://dx.doi.org/10.1016/j.chb.2010.08.014.
Full text
16
Lucero, Robert, Renessa Williams, Tanisia Esalomi, Paula Alexander-Delpech, Christa Cook, and Ragnhildur I. Bjarnadottir. "Using an Electronic Medication Event–Monitoring System for Antiretroviral Therapy Self-Management Among African American Women Living With HIV in Rural Florida: Cohort Study." JMIR Formative Research 4, no. 2 (February 19, 2020): e14888. http://dx.doi.org/10.2196/14888.
Full textAbstract:
Background HIV remains a significant health issue in the United States and disproportionately affects African Americans. African American women living with HIV (AAWH) experience a particularly high number of barriers when attempting to manage their HIV care, including antiretroviral therapy (ART) adherence. To enable the development and assessment of effective interventions that address these barriers to support ART adherence, there is a critical need to understand more fully the use of objective measures of ART adherence among AAWH, including electronic medication dispensers for real-time surveillance. Objective This study aimed to evaluate the use of the Wisepill medication event–monitoring system (MEMS) and compare the objective and subjective measures of ART adherence. Methods We conducted a 30-day exploratory pilot study of the MEMS among a convenience sample of community-dwelling AAWH (N=14) in rural Florida. AAWH were trained on the use of the MEMS to determine the feasibility of collecting, capturing, and manipulating the MEMS data for an objective measure of ART adherence. Self-reported sociodemographic information, including a self-reported measure of ART adherence, was also collected from AAWH. Results We found that the majority of participants were successful at using the electronic MEMS. Daily use of the MEMS tended to be outside of the usual time participants took their medication. Three 30-day medication event patterns were found that characterized ART adherence, specifically uniform and nonuniform medication adherence and nonuniform medication nonadherence. There were relatively few MEMS disruptions among study participants. Overall, adjusted daily ART adherence was 81.08% and subjective ART adherence was 77.78%. Conclusions This pilot study on the use and evaluation of the Wisepill MEMS among AAWH in rural Florida is the first such study in the United States. The findings of this study are encouraging because 10 out of 12 participants consistently used the MEMS, there were relatively few failures, and objective adjusted daily and overall subjective ART adherence were very similar. On the basis of these findings, we think researchers should consider using the Wisepill MEMS in future studies of AAWH and people living with HIV in the United States after taking into account our practical suggestions. The following practical considerations are suggested when measuring objective medication adherence: (1) before using an MEMS, be familiar with the targeted populations’ characteristics; (2) choose an MEMS that aligns with the participants’ day-to-day activities; (3) ensure the MEMS’ features and resulting data support the research goals; (4) assess the match among the user’s ability, wireless features of the MEMS, and the geographic location of the participants; and (5) consider the cost of MEMS and the research budget.
17
Cosma, Adrian, and Ion Emilian Radoi. "WildGait: Learning Gait Representations from Raw Surveillance Streams." Sensors 21, no. 24 (December 15, 2021): 8387. http://dx.doi.org/10.3390/s21248387.
Full textAbstract:
The use of gait for person identification has important advantages such as being non-invasive, unobtrusive, not requiring cooperation and being less likely to be obscured compared to other biometrics. Existing methods for gait recognition require cooperative gait scenarios, in which a single person is walking multiple times in a straight line in front of a camera. We address the challenges of real-world scenarios in which camera feeds capture multiple people, who in most cases pass in front of the camera only once. We address privacy concerns by using only motion information of walking individuals, with no identifiable appearance-based information. As such, we propose a self-supervised learning framework, WildGait, which consists of pre-training a Spatio-Temporal Graph Convolutional Network on a large number of automatically annotated skeleton sequences obtained from raw, real-world surveillance streams to learn useful gait signatures. We collected and compiled the largest pretraining dataset to date of anonymized walking skeletons called Uncooperative Wild Gait, containing over 38k tracklets of anonymized walking 2D skeletons. We make the dataset available to the research community. Our results surpass the current state-of-the-art pose-based gait recognition solutions. Our proposed method is reliable in training gait recognition methods in unconstrained environments, especially in settings with scarce amounts of annotated data.
18
de Paula, Davi D., Denis H. P. Salvadeo, and Darlan M. N. de Araujo. "CamNuvem: A Robbery Dataset for Video Anomaly Detection." Sensors 22, no. 24 (December 19, 2022): 10016. http://dx.doi.org/10.3390/s222410016.
Full textAbstract:
(1) Background: The research area of video surveillance anomaly detection aims to automatically detect the moment when a video surveillance camera captures something that does not fit the normal pattern. This is a difficult task, but it is important to automate, improve, and lower the cost of the detection of crimes and other accidents. The UCF–Crime dataset is currently the most realistic crime dataset, and it contains hundreds of videos distributed in several categories; it includes a robbery category, which contains videos of people stealing material goods using violence, but this category only includes a few videos. (2) Methods: This work focuses only on the robbery category, presenting a new weakly labelled dataset that contains 486 new real–world robbery surveillance videos acquired from public sources. (3) Results: We have modified and applied three state–of–the–art video surveillance anomaly detection methods to create a benchmark for future studies. We showed that in the best scenario, taking into account only the anomaly videos in our dataset, the best method achieved an AUC of 66.35%. When all anomaly and normal videos were taken into account, the best method achieved an AUC of 88.75%. (4) Conclusion: This result shows that there is a huge research opportunity to create new methods and approaches that can improve robbery detection in video surveillance.
19
Skare, Erik. "Digital Surveillance/Militant Resistance: Categorizing the “Proto-state Hacker”." Television & New Media 20, no. 7 (August 10, 2018): 670–85. http://dx.doi.org/10.1177/1527476418793509.
Full textAbstract:
Rapid developments in digital infrastructure have made all-encompassing surveillance all too possible. However, the same infrastructure has simultaneously enabled the use of new possibility spaces that react to, shape, and resist these structures of control and surveillance. The Israel/Palestine conflict is no different, and Palestinian Islamic Jihad (PIJ) has created an electronic unit with hackers to circumvent and resist the Israeli matrix of control and its surveillance. I argue that out of this dialectical relationship in Palestine, between new possibility spaces of resistance and structures of control, new phenomena arise in the gray area between the nation state hacker and the hacktivist as PIJ emulates the features of a modern state army. To understand the nature of its electronic unit, one must take this dialectic into account by introducing the category, “proto-state hacker.”
20
Asbury, M. J. A., and R. Johannessen. "Single Points of Failure in Complex Aviation Systems of Communication, Navigation and Surveillance." Journal of Navigation 48, no. 2 (May 1995): 192–203. http://dx.doi.org/10.1017/s0373463300012650.
Full textAbstract:
State-of-the-art avionics achieves very good reliability, and the electronics in the current generation of communication and navigation satellites is sufficiently good to allow a design-life of around 10 years. Nevertheless, failures will arise. The purpose of failure analysis is to identify the consequences if a particular module does encounter a failure, and to ensure that, by system redundancy or through operational procedures, the effect and/or its probability of occurrence will be acceptably safe. This paper is a contribution to the discussion on the strength and weakness of redundancy in satellite-based Communication, Navigation and Surveillance (CNS) systems as envisaged by the International Civil Aviation Organization (ICAO) to be an integral part of the future air navigation system. This particular paper makes a comparison with today's terrestrial-based systems.
21
Xie, Jiyang, Yixiao Zheng, Ruoyi Du, Weiyu Xiong, Yufei Cao, Zhanyu Ma, Dongpu Cao, and Jun Guo. "Deep Learning-Based Computer Vision for Surveillance in ITS: Evaluation of State-of-the-Art Methods." IEEE Transactions on Vehicular Technology 70, no. 4 (April 2021): 3027–42. http://dx.doi.org/10.1109/tvt.2021.3065250.
Full text
22
Schreiber, David, and Andreas Opitz. "A Novel Background Modeling Algorithm for Hyperspectral Ground-Based Surveillance and Through-Foliage Detection." Sensors 22, no. 20 (October 11, 2022): 7720. http://dx.doi.org/10.3390/s22207720.
Full textAbstract:
Foliage penetration is an unsolved important part of border surveillance of remote areas between regular border crossing points. Detecting penetrating objects (e.g., persons and cars) through dense foliage in various climate conditions using visual sensors is prone to high fault rates. Through-foliage scenarios contain an unprecedented amount of occlusion—in fact, they often contain fragmented occlusion (for example, looking through the branches of a tree). Current state-of-the-art detectors based on deep learning perform inadequately under moderate-to-heavy fragmented occlusion. The FOLDOUT project builds a system that combines various sensors and technologies to tackle this problem. Consequently, a hyperspectral sensor was investigated due to its extended spectral bandwidth, beyond the range of typical RGB sensors, where vegetation exhibits pronounced reflectance. Due to the poor performance of deep learning approaches in through-foliage scenarios, a novel background modeling-based detection approach was developed, dedicated to the characteristics of the hyperspectral sensor, namely strong correlations between adjacent spectral bands and high redundancy. The algorithm is based on local dimensional reduction, where the principal subspace of each pixel is maintained and adapted individually over time. The successful application of the proposed algorithm is demonstrated in a through-foliage scenario comprised of heavy fragmented occlusion and a highly dynamical background, where state-of-the-art deep learning detectors perform poorly.
23
Ahn, Jinkook. "The Multilayeredness of Mobility and the Visual Art Language: The Material Turn, the Inequality in ‘Mobility Capital’, the Hierarchy in Mobility, and Art." Center for Asia and Diaspora 12, no. 2 (August 31, 2022): 6–50. http://dx.doi.org/10.15519/dcc.2022.08.12.2.6.
Full textAbstract:
This study explores what mobility means from the social science perspective and how it becomes a form of capital in todays modern highly mobile society. It also investigates how it appears in arts by analyzing the artworks in the exhibition titled To you: Move Toward Where You Are.
It seems that mobility characterized by complexity, hybridity, vitality, materiality, and assemblage is somehow part of the Material Turn. Transportation, capital, power, cities, refugees, migration, tourism, climate crisis, systems, infrastructure, control, surveillance, communications, gender, race, disability, and so on. These may seem heterogeneous multi-layered issues, but all these relate to uneven mobility. And mobility inequalities occur in the dynamics of their relations.
In the highly-mobile society where the fetishism of movement prevails, mobility becomes more uneven. When freedom, acceleration, convenience and safety increase, so does censorship, control and restriction. Gaining velocity, efficiency, convenience, and safety of movement can undermine the rights of others. We should envisage the hidden power relations under the rights of (im)mobility.
Characteristics of mobility and its inequalities directly and indirectly emerge in the artworks exhibited in To you: Move Toward Where You Are. We need to consider how mobility justice can be practiced against mobility inequalities in the hierarchy of mobility capital, uneven mobility, and mobility injustice. Art which thinks beyond thinking will provide new stimulus and imagination to the practice.
24
Bhatia, Monish. "Racial surveillance and the mental health impacts of electronic monitoring on migrants." Race & Class 62, no. 3 (January 2021): 18–36. http://dx.doi.org/10.1177/0306396820963485.
Full textAbstract:
Since the late 1990s, the government has used outsourced electronic monitoring (also known as tagging) in England and Wales for criminal sentencing and punishment. Under the Asylum and Immigration (Treatment of Claimants) Act 2004, s36, the use of this technology extended to immigration controls, and individuals deemed as ‘high risk’ of harm, reoffending or absconding can be fitted with an ankle device and subjected to curfew. The tagging of migrants is not authorised by the criminal court and therefore not considered a punitive sanction. It is managed by the immigration system and treated as an administrative matter. Nevertheless, people who are tagged experience it as imprisonment and punishment. Drawing on data from an eighteen-month ethnographic research project, this article examines the impact of electronic monitoring on people seeking asylum, who completed their sentences for immigration offences. It uncovers the psychological effects and mental health impacts of such technologies of control. The article sheds light on how tagging is experienced by racialised minorities, and adds to the literature on migration, surveillance studies, state racism and violence.
25
Walker, Clive, and Yaman Akdeniz. "Anti-terrorism laws and data retention: war is over?" Northern Ireland Legal Quarterly 54, no. 2 (August 5, 2020): 159–82. http://dx.doi.org/10.53386/nilq.v54i2.737.
Full textAbstract:
The Anti-terrorism, Crime and Security Act 2001 signals a determined response to the attacks of September 11th. One aspect involves the facilitation of the use of electronic surveillance in order to prevent, detect or prosecute the perpetrators of terrorism. The role of Part XI of the 2001 Act is to augment existing surveillance powers in the Regulation of Investigatory Powers Act 2000. This paper plots the relationships between those two statutes and also their relationship to data protection laws. Delays and difficulties in enforcement are noted and are related to a process of return to greater normality after an initial period of panic.
26
Liang, Dong, Jiaxing Pan, Han Sun, and Huiyu Zhou. "Spatio-Temporal Attention Model for Foreground Detection in Cross-Scene Surveillance Videos." Sensors 19, no. 23 (November 24, 2019): 5142. http://dx.doi.org/10.3390/s19235142.
Full textAbstract:
Foreground detection is an important theme in video surveillance. Conventional background modeling approaches build sophisticated temporal statistical model to detect foreground based on low-level features, while modern semantic/instance segmentation approaches generate high-level foreground annotation, but ignore the temporal relevance among consecutive frames. In this paper, we propose a Spatio-Temporal Attention Model (STAM) for cross-scene foreground detection. To fill the semantic gap between low and high level features, appearance and optical flow features are synthesized by attention modules via the feature learning procedure. Experimental results on CDnet 2014 benchmarks validate it and outperformed many state-of-the-art methods in seven evaluation metrics. With the attention modules and optical flow, its F-measure increased 9 % and 6 % respectively. The model without any tuning showed its cross-scene generalization on Wallflower and PETS datasets. The processing speed was 10.8 fps with the frame size 256 by 256.
27
Luna, Elena, Juan San Miguel, Diego Ortego, and José Martínez. "Abandoned Object Detection in Video-Surveillance: Survey and Comparison." Sensors 18, no. 12 (December 5, 2018): 4290. http://dx.doi.org/10.3390/s18124290.
Full textAbstract:
During the last few years, abandoned object detection has emerged as a hot topic in the video-surveillance community. As a consequence, a myriad of systems has been proposed for automatic monitoring of public and private places, while addressing several challenges affecting detection performance. Due to the complexity of these systems, researchers often address independently the different analysis stages such as foreground segmentation, stationary object detection, and abandonment validation. Despite the improvements achieved for each stage, the advances are rarely applied to the full pipeline, and therefore, the impact of each stage of improvement on the overall system performance has not been studied. In this paper, we formalize the framework employed by systems for abandoned object detection and provide an extensive review of state-of-the-art approaches for each stage. We also build a multi-configuration system allowing one to select a range of alternatives for each stage with the objective of determining the combination achieving the best performance. This multi-configuration is made available online to the research community. We perform an extensive evaluation by gathering a heterogeneous dataset from existing data. Such a dataset allows considering multiple and different scenarios, whereas presenting various challenges such as illumination changes, shadows, and a high density of moving objects, unlike existing literature focusing on a few sequences. The experimental results identify the most effective configurations and highlight design choices favoring robustness to errors. Moreover, we validated such an optimal configuration on additional datasets not previously considered. We conclude the paper by discussing open research challenges arising from the experimental comparison.
28
Savkin, Andrey, and Hailong Huang. "Proactive Deployment of Aerial Drones for Coverage over Very Uneven Terrains: A Version of the 3D Art Gallery Problem." Sensors 19, no. 6 (March 23, 2019): 1438. http://dx.doi.org/10.3390/s19061438.
Full textAbstract:
The paper focuses on surveillance and monitoring using aerial drones. The aim is to estimate the minimal number of drones necessary to monitor a given area of a very uneven terrain. The proposed problem may be viewed as a drone version of the 3D Art Gallery Problem. A computationally simple algorithm to calculate an upper estimate of the minimal number of drones together with their locations is developed. Computer simulations are conducted to demonstrate the effectiveness of the proposed method.
29
Sarker, Mohammad Ibrahim, Cristina Losada-Gutiérrez, Marta Marrón-Romera, David Fuentes-Jiménez, and Sara Luengo-Sánchez. "Semi-Supervised Anomaly Detection in Video-Surveillance Scenes in the Wild." Sensors 21, no. 12 (June 9, 2021): 3993. http://dx.doi.org/10.3390/s21123993.
Full textAbstract:
Surveillance cameras are being installed in many primary daily living places to maintain public safety. In this video-surveillance context, anomalies occur only for a very short time, and very occasionally. Hence, manual monitoring of such anomalies may be exhaustive and monotonous, resulting in a decrease in reliability and speed in emergency situations due to monitor tiredness. Within this framework, the importance of automatic detection of anomalies is clear, and, therefore, an important amount of research works have been made lately in this topic. According to these earlier studies, supervised approaches perform better than unsupervised ones. However, supervised approaches demand manual annotation, making dependent the system reliability of the different situations used in the training (something difficult to set in anomaly context). In this work, it is proposed an approach for anomaly detection in video-surveillance scenes based on a weakly supervised learning algorithm. Spatio-temporal features are extracted from each surveillance video using a temporal convolutional 3D neural network (T-C3D). Then, a novel ranking loss function increases the distance between the classification scores of anomalous and normal videos, reducing the number of false negatives. The proposal has been evaluated and compared against state-of-art approaches, obtaining competitive performance without fine-tuning, which also validates its generalization capability. In this paper, the proposal design and reliability is presented and analyzed, as well as the aforementioned quantitative and qualitative evaluation in-the-wild scenarios, demonstrating its high sensitivity in anomaly detection in all of them.
30
Izwan Heroza, Rahmat, Hamzah Hasyim, Rita Kusriastuti, and Pat Dale. "Design and Evaluation of Mobile-Based Applications for Supporting Malaria Surveillance Activities in Indonesian Regions." International Journal of Advanced Multidisciplinary Research 9, no. 1 (January 30, 2022): 37–45. http://dx.doi.org/10.22192/ijamr.2022.09.01.003.
Full textAbstract:
In malaria elimination programs, surveillance is a critical component. In Indonesia, an electronic information system was created to carry out malaria surveillance inthe form of a structured excel file as part of an attempt to enhance the validity andcompleteness of reporting malaria data. However, the use of this method hasseveral obstacles that are still felt by health workers. This study designed anAndroid-based malaria surveillance application as an alternative solution to themethod that has been applied. The evaluation results show that the overall impression of this application is very good (mean, median (on a 9-point scale) andstandard deviation equal to 6.84, 6.88 and 0.29, respectively). This means that ingeneral, health officers as application users are satisfied with the applications that have been developed. Keywords: malaria, surveillance, Android, design,evaluation
31
Shin, Hyunah, Jaehun Cha, Youngho Lee, Jong-Yeup Kim, and Suehyun Lee. "Real-world data-based adverse drug reactions detection from the Korea Adverse Event Reporting System databases with electronic health records-based detection algorithm." Health Informatics Journal 27, no. 3 (July 2021): 146045822110330. http://dx.doi.org/10.1177/14604582211033014.
Full textAbstract:
Pharmacovigilance involves monitoring of drugs and their adverse drug reactions (ADRs) and is essential for their safety post-marketing. Because of the different types and structures of medical databases, several previous surveillance studies have analyzed only one database. In the present study, we extracted potential drug–ADR pairs from electronic health record (EHR) data using the MetaNurse algorithm and analyzed them using the Korean Adverse Event Reporting System (KAERS) database for systematic validation. The Medical Dictionary for Regulatory Activities (MedDRA) and World Health Organization (WHO) Adverse Reactions Terminology (WHO-ART) were mapped for signal detection. We used the Side Effect Resource (SIDER) database to select 2663 drug-ADR pairs to investigate unknown drug-induced ADRs. The reporting odds ratio (ROR) value was calculated for the drug-exposed and non-exposed groups of drug–ADR pairs, and 19 potential pairs showed significant signals. Appropriate terminology systems and criteria are needed to handle diverse medical databases.
32
Gogula, Sreenivasulu, M. Rajesh Khanna, Neelappa Neelappa, Ajith Sundaram, E. Rajesh Kumar, and Sravanth Kumar R. "Modernized Wildlife Surveillance and Behaviour Detection using a Novel Machine Learning Algorithm." International Journal on Recent and Innovation Trends in Computing and Communication 10, no. 2s (December 31, 2022): 50–62. http://dx.doi.org/10.17762/ijritcc.v10i2s.5911.
Full textAbstract:
In a natural ecosystem, understanding the difficulties of the wildlife surveillance is helpful to protect and manage animals also gain knowledge around animals count, behaviour and location. Moreover, camera trap images allow the picture of wildlife as unobtrusively, inexpensively and high volume it can identify animals, and behaviour but it has the issues of high expensive, time consuming, error, and low accuracy. So, in this research work, designed a novel wildlife surveillance framework using DCNN for accurate prediction of animals and enhance the performance of detection accuracy. The executed research work is implemented in the python tool and 2700 sample input frame datasets are tested and trained to the system. Furthermore, analyze whether animals are present or not using background subtraction and features extracted is performed to extract the significant features. Finally, classification is executed to predict the animal using the fitness of seagull. Additionally, attained results of the developed framework are compared with other state-of-the-art techniques in terms of detection accuracy, sensitivity, F-measure and error.
33
Shade, Starley B., Elliot Marseille, Valerie Kirby, Deepalika Chakravarty, Wayne T. Steward, Kimberly K. Koester, Adan Cajina, and Janet J. Myers. "Health information technology interventions and engagement in HIV care and achievement of viral suppression in publicly funded settings in the US: A cost-effectiveness analysis." PLOS Medicine 18, no. 4 (April 7, 2021): e1003389. http://dx.doi.org/10.1371/journal.pmed.1003389.
Full textAbstract:
Background The US National HIV/AIDS Strategy (NHAS) emphasizes the use of technology to facilitate coordination of comprehensive care for people with HIV. We examined cost-effectiveness from the health system perspective of 6 health information technology (HIT) interventions implemented during 2008 to 2012 in a Ryan White HIV/AIDS Program (RWHAP) Special Projects of National Significance (SPNS) Program demonstration project. Methods/findings HIT interventions were implemented at 6 sites: Bronx, New York; Durham, North Carolina; Long Beach, California; New Orleans, Louisiana; New York, New York (2 sites); and Paterson, New Jersey. These interventions included: (1) use of HIV surveillance data to identify out-of-care individuals; (2) extension of access to electronic health records (EHRs) to support service providers; (3) use of electronic laboratory ordering and prescribing; and (4) development of a patient portal. We employed standard microcosting techniques to estimate costs (in 2018 US dollars) associated with intervention implementation. Data from a sample of electronic patient records from each demonstration site were analyzed to compare prescription of antiretroviral therapy (ART), CD4 cell counts, and suppression of viral load, before and after implementation of interventions. Markov models were used to estimate additional healthcare costs and quality-adjusted life-years saved as a result of each intervention. Overall, demonstration site interventions cost $3,913,313 (range = $287,682 to $998,201) among 3,110 individuals (range = 258 to 1,181) over 3 years. Changes in the proportion of patients prescribed ART ranged from a decrease from 87.0% to 72.7% at Site 4 to an increase from 74.6% to 94.2% at Site 6; changes in the proportion of patients with 0 to 200 CD4 cells/mm3 ranged from a decrease from 20.2% to 11.0% in Site 6 to an increase from 16.7% to 30.2% in Site 2; and changes in the proportion of patients with undetectable viral load ranged from a decrease from 84.6% to 46.0% in Site 1 to an increase from 67.0% to 69.9% in Site 5. Four of the 6 interventions—including use of HIV surveillance data to identify out-of-care individuals, use of electronic laboratory ordering and prescribing, and development of a patient portal—were not only cost-effective but also cost saving ($6.87 to $14.91 saved per dollar invested). In contrast, the 2 interventions that extended access to EHRs to support service providers were not effective and, therefore, not cost-effective. Most interventions remained either cost-saving or not cost-effective under all sensitivity analysis scenarios. The intervention that used HIV surveillance data to identify out-of-care individuals was no longer cost-saving when the effect of HIV on an individual’s health status was reduced and when the natural progression of HIV was increased. The results of this study are limited in that we did not have contemporaneous controls for each intervention; thus, we are only able to assess sites against themselves at baseline and not against standard of care during the same time period. Conclusions These results provide additional support for the use of HIT as a tool to enhance rapid and effective treatment of HIV to achieve sustained viral suppression. HIT has the potential to increase utilization of services, improve health outcomes, and reduce subsequent transmission of HIV.
34
Ruggieri, Stefano, Rubinia C. Bonfanti, Alessia Passanisi, Ugo Pace, and Adriano Schimmenti. "Electronic surveillance in the couple: The role of self-efficacy and commitment." Computers in Human Behavior 114 (January 2021): 106577. http://dx.doi.org/10.1016/j.chb.2020.106577.
Full text
35
Ingle, Palash Yuvraj, and Young-Gab Kim. "Real-Time Abnormal Object Detection for Video Surveillance in Smart Cities." Sensors 22, no. 10 (May 19, 2022): 3862. http://dx.doi.org/10.3390/s22103862.
Full textAbstract:
With the adaptation of video surveillance in many areas for object detection, monitoring abnormal behavior in several cameras requires constant human tracking for a single camera operative, which is a tedious task. In multiview cameras, accurately detecting different types of guns and knives and classifying them from other video surveillance objects in real-time scenarios is difficult. Most detecting cameras are resource-constrained devices with limited computational capacities. To mitigate this problem, we proposed a resource-constrained lightweight subclass detection method based on a convolutional neural network to classify, locate, and detect different types of guns and knives effectively and efficiently in a real-time environment. In this paper, the detection classifier is a multiclass subclass detection convolutional neural network used to classify object frames into different sub-classes such as abnormal and normal. The achieved mean average precision by the best state-of-the-art framework to detect either a handgun or a knife is 84.21% or 90.20% on a single camera view. After extensive experiments, the best precision obtained by the proposed method for detecting different types of guns and knives was 97.50% on the ImageNet dataset and IMFDB, 90.50% on the open-image dataset, 93% on the Olmos dataset, and 90.7% precision on the multiview cameras. This resource-constrained device has shown a satisfactory result, with a precision score of 85.5% for detection in a multiview camera.
36
Perez-Montes, Filiberto, Jesus Olivares-Mercado, Gabriel Sanchez-Perez, Gibran Benitez-Garcia, Lidia Prudente-Tixteco, and Osvaldo Lopez-Garcia. "Analysis of Real-Time Face-Verification Methods for Surveillance Applications." Journal of Imaging 9, no. 2 (January 18, 2023): 21. http://dx.doi.org/10.3390/jimaging9020021.
Full textAbstract:
In the last decade, face-recognition and -verification methods based on deep learning have increasingly used deeper and more complex architectures to obtain state-of-the-art (SOTA) accuracy. Hence, these architectures are limited to powerful devices that can handle heavy computational resources. Conversely, lightweight and efficient methods have recently been proposed to achieve real-time performance on limited devices and embedded systems. However, real-time face-verification methods struggle with problems usually solved by their heavy counterparts—for example, illumination changes, occlusions, face rotation, and distance to the subject. These challenges are strongly related to surveillance applications that deal with low-resolution face images under unconstrained conditions. Therefore, this paper compares three SOTA real-time face-verification methods for coping with specific problems in surveillance applications. To this end, we created an evaluation subset from two available datasets consisting of 3000 face images presenting face rotation and low-resolution problems. We defined five groups of face rotation with five levels of resolutions that can appear in common surveillance scenarios. With our evaluation subset, we methodically evaluated the face-verification accuracy of MobileFaceNet, EfficientNet-B0, and GhostNet. Furthermore, we also evaluated them with conventional datasets, such as Cross-Pose LFW and QMUL-SurvFace. When examining the experimental results of the three mentioned datasets, we found that EfficientNet-B0 could deal with both surveillance problems, but MobileFaceNet was better at handling extreme face rotation over 80 degrees.
37
Subha, I., P. Narmadha, S. Nivedha, and T. Sethukarasi. "Real-Time Suspicious Human Action Recognition from Surveillance Videos for Resource-Constrained Devices." Journal of Computational and Theoretical Nanoscience 17, no. 8 (August 1, 2020): 3790–97. http://dx.doi.org/10.1166/jctn.2020.9322.
Full textAbstract:
Recent developments in computer vision are seen as a vital advancement in video surveillance. The goal of this research is to build a deep learning model that is capable of analyzing and classifying the video from running CCTV streams to detect criminal actions and identify suspects on the scene. In particular, we focus on the detection of dangerous human behaviors in surveillance videos. This work provides a low cost embedded solution that can be integrated with the existing CCTV cameras. This integration can reduce the cost of transmitting the data to any centralized server, which may have various privacy implications and takes much inference time. We also benchmark our models performance with the existing real-world dataset in terms of accuracy and resource constraints. Using the concept of Multiple Instance Learning on the histogram of the optical flow of the videos combined with the pose estimation of the persons on scene, we provide a lightweight model which has 13 times lesser inference time than the existing very deep models. Focusing on one important thing, this research will expand to which state-of-the-art deep neural networks will “see” violence in photographs and videos, and recognize criminal behavior using characteristics such as gestures, gait, and unethical behavior. This helps enforcement agencies to unravel crime cases faster and also to scale back crimes by identifying the suspects in the surveillance videos.
38
Schiller, Eryk, Elfat Esati, and Burkhard Stiller. "IoT-Based Access Management Supported by AI and Blockchains." Electronics 11, no. 18 (September 19, 2022): 2971. http://dx.doi.org/10.3390/electronics11182971.
Full textAbstract:
Internet-of-Things (IoT), Artificial Intelligence (AI), and Blockchains (BCs) are essential techniques that are heavily researched and investigated today. This work here specifies, implements, and evaluates an IoT architecture with integrated BC and AI functionality to manage access control based on facial detection and recognition by incorporating the most recent state-of-the-art techniques. The system developed uses IoT devices for video surveillance, AI for face recognition, and BCs for immutable permanent storage to provide excellent properties in terms of image quality, end-to-end delay, and energy efficiency.
39
Li, Hui, Hang Zhou, Xiaoguo Liang, Fen Cai, Lingwei Xu, Wei Kong, and Ying Guo. "Human Detection via Image Denoising for 5G-Enabled Intelligent Applications." Wireless Communications and Mobile Computing 2021 (November 23, 2021): 1–14. http://dx.doi.org/10.1155/2021/5344890.
Full textAbstract:
5G technology strongly supports the development of various intelligent applications, such as intelligent video surveillance and autonomous driving. And the human detection technology in intelligent video surveillance has also ushered in new challenges. A number of video images will be compressed for efficient transmission; the resulting incomplete feature representation of images will drop the human detection performance. Therefore, in this work, we propose a new human detection method based on compressed denoising. We exploit the quality factor in the compressed image and incorporate the pixel_shuffle inverse transform based on FFDNet to effectively improve the performance of image compression denoising, then HRNet and HRFPN are used to extract and fuse high-resolution features of denoised images, respectively, to obtain high-quality feature representation, and finally, a cascaded object detector is used for classification and bounding box regression to further improve object detection performance. At last, the experimental results on PASCAL VOC show that the proposed method effectively removes the compression noise and further detects human objects with multiple scales and different postures. Compared with the state-of-the-art methods, our method achieved better detection performance and is, therefore, more suited for human detection tasks.
40
Halpern, David, Patrick J. Reville, and Donald Grunewald. "Management and Legal Issues Regarding Electronic Surveillance of Employees in the Workplace." Journal of Business Ethics 80, no. 2 (June 6, 2007): 175–80. http://dx.doi.org/10.1007/s10551-007-9449-6.
Full text
41
Jin, Yonghao, Fei Li, Varsha G. Vimalananda, and Hong Yu. "Automatic Detection of Hypoglycemic Events From the Electronic Health Record Notes of Diabetes Patients: Empirical Study." JMIR Medical Informatics 7, no. 4 (November 8, 2019): e14340. http://dx.doi.org/10.2196/14340.
Full textAbstract:
Background Hypoglycemic events are common and potentially dangerous conditions among patients being treated for diabetes. Automatic detection of such events could improve patient care and is valuable in population studies. Electronic health records (EHRs) are valuable resources for the detection of such events. Objective In this study, we aim to develop a deep-learning–based natural language processing (NLP) system to automatically detect hypoglycemic events from EHR notes. Our model is called the High-Performing System for Automatically Detecting Hypoglycemic Events (HYPE). Methods Domain experts reviewed 500 EHR notes of diabetes patients to determine whether each sentence contained a hypoglycemic event or not. We used this annotated corpus to train and evaluate HYPE, the high-performance NLP system for hypoglycemia detection. We built and evaluated both a classical machine learning model (ie, support vector machines [SVMs]) and state-of-the-art neural network models. Results We found that neural network models outperformed the SVM model. The convolutional neural network (CNN) model yielded the highest performance in a 10-fold cross-validation setting: mean precision=0.96 (SD 0.03), mean recall=0.86 (SD 0.03), and mean F1=0.91 (SD 0.03). Conclusions Despite the challenges posed by small and highly imbalanced data, our CNN-based HYPE system still achieved a high performance for hypoglycemia detection. HYPE can be used for EHR-based hypoglycemia surveillance and population studies in diabetes patients.
42
Domingos, Lucas C. F., Paulo E. Santos, Phillip S. M. Skelton, Russell S. A. Brinkworth, and Karl Sammut. "A Survey of Underwater Acoustic Data Classification Methods Using Deep Learning for Shoreline Surveillance." Sensors 22, no. 6 (March 11, 2022): 2181. http://dx.doi.org/10.3390/s22062181.
Full textAbstract:
This paper presents a comprehensive overview of current deep-learning methods for automatic object classification of underwater sonar data for shoreline surveillance, concentrating mostly on the classification of vessels from passive sonar data and the identification of objects of interest from active sonar (such as minelike objects, human figures or debris of wrecked ships). Not only is the contribution of this work to provide a systematic description of the state of the art of this field, but also to identify five main ingredients in its current development: the application of deep-learning methods using convolutional layers alone; deep-learning methods that apply biologically inspired feature-extraction filters as a preprocessing step; classification of data from frequency and time–frequency analysis; methods using machine learning to extract features from original signals; and transfer learning methods. This paper also describes some of the most important datasets cited in the literature and discusses data-augmentation techniques. The latter are used for coping with the scarcity of annotated sonar datasets from real maritime missions.
43
Ullah, Fath U. Min, Amin Ullah, Khan Muhammad, Ijaz Ul Haq, and Sung Wook Baik. "Violence Detection Using Spatiotemporal Features with 3D Convolutional Neural Network." Sensors 19, no. 11 (May 30, 2019): 2472. http://dx.doi.org/10.3390/s19112472.
Full textAbstract:
The worldwide utilization of surveillance cameras in smart cities has enabled researchers to analyze a gigantic volume of data to ensure automatic monitoring. An enhanced security system in smart cities, schools, hospitals, and other surveillance domains is mandatory for the detection of violent or abnormal activities to avoid any casualties which could cause social, economic, and ecological damages. Automatic detection of violence for quick actions is very significant and can efficiently assist the concerned departments. In this paper, we propose a triple-staged end-to-end deep learning violence detection framework. First, persons are detected in the surveillance video stream using a light-weight convolutional neural network (CNN) model to reduce and overcome the voluminous processing of useless frames. Second, a sequence of 16 frames with detected persons is passed to 3D CNN, where the spatiotemporal features of these sequences are extracted and fed to the Softmax classifier. Furthermore, we optimized the 3D CNN model using an open visual inference and neural networks optimization toolkit developed by Intel, which converts the trained model into intermediate representation and adjusts it for optimal execution at the end platform for the final prediction of violent activity. After detection of a violent activity, an alert is transmitted to the nearest police station or security department to take prompt preventive actions. We found that our proposed method outperforms the existing state-of-the-art methods for different benchmark datasets.
44
Mukherjee, Shouvik, Shariq Suleman, Roberto Pilloton, Jagriti Narang, and Kirti Rani. "State of the Art in Smart Portable, Wearable, Ingestible and Implantable Devices for Health Status Monitoring and Disease Management." Sensors 22, no. 11 (June 1, 2022): 4228. http://dx.doi.org/10.3390/s22114228.
Full textAbstract:
Several illnesses that are chronic and acute are becoming more relevant as the world’s aging population expands, and the medical sector is transforming rapidly, as a consequence of which the need for “point-of-care” (POC), identification/detection, and real time management of health issues that have been required for a long time are increasing. Biomarkers are biological markers that help to detect status of health or disease. Biosensors’ applications are for screening for early detection, chronic disease treatment, health management, and well-being surveillance. Smart devices that allow continual monitoring of vital biomarkers for physiological health monitoring, medical diagnosis, and assessment are becoming increasingly widespread in a variety of applications, ranging from biomedical to healthcare systems of surveillance and monitoring. The term “smart” is used due to the ability of these devices to extract data with intelligence and in real time. Wearable, implantable, ingestible, and portable devices can all be considered smart devices; this is due to their ability of smart interpretation of data, through their smart sensors or biosensors and indicators. Wearable and portable devices have progressed more and more in the shape of various accessories, integrated clothes, and body attachments and inserts. Moreover, implantable and ingestible devices allow for the medical diagnosis and treatment of patients using tiny sensors and biomedical gadgets or devices have become available, thus increasing the quality and efficacy of medical treatments by a significant margin. This article summarizes the state of the art in portable, wearable, ingestible, and implantable devices for health status monitoring and disease management and their possible applications. It also identifies some new technologies that have the potential to contribute to the development of personalized care. Further, these devices are non-invasive in nature, providing information with accuracy and in given time, thus making these devices important for the future use of humanity.
45
Gan, Jiayan, Ang Hu, Ziyi Kang, Zhipeng Qu, Zhanxiang Yang, Rui Yang, Yibing Wang, Huaizong Shao, and Jun Zhou. "SAS-SEINet: A SNR-Aware Adaptive Scalable SEI Neural Network Accelerator Using Algorithm–Hardware Co-Design for High-Accuracy and Power-Efficient UAV Surveillance." Sensors 22, no. 17 (August 30, 2022): 6532. http://dx.doi.org/10.3390/s22176532.
Full textAbstract:
As a potential air control measure, RF-based surveillance is one of the most commonly used unmanned aerial vehicles (UAV) surveillance methods that exploits specific emitter identification (SEI) technology to identify captured RF signal from ground controllers to UAVs. Recently many SEI algorithms based on deep convolution neural network (DCNN) have emerged. However, there is a lack of the implementation of specific hardware. This paper proposes a high-accuracy and power-efficient hardware accelerator using an algorithm–hardware co-design for UAV surveillance. For the algorithm, we propose a scalable SEI neural network with SNR-aware adaptive precision computation. With SNR awareness and precision reconfiguration, it can adaptively switch between DCNN and binary DCNN to cope with low SNR and high SNR tasks, respectively. In addition, a short-time Fourier transform (STFT) reusing DCNN method is proposed to pre-extract feature of UAV signal. For hardware, we designed a SNR sensing engine, denoising engine, and specialized DCNN engine with hybrid-precision convolution and memory access, aiming at SEI acceleration. Finally, we validate the effectiveness of our design on a FPGA, using a public UAV dataset. Compared with a state-of-the-art algorithm, our method can achieve the highest accuracy of 99.3% and an F1 score of 99.3%. Compared with other hardware designs, our accelerator can achieve the highest power efficiency of 40.12 Gops/W and 96.52 Gops/W with INT16 precision and binary precision.
46
Stewart, Garrett. "Digital Fatigue: Imaging War in Recent American Film." Film Quarterly 62, no. 4 (2009): 45–55. http://dx.doi.org/10.1525/fq.2009.62.4.45.
Full textAbstract:
Abstract The new wired combat in Iraq, alternating in American films between aerial surveillance and camcorder logs or cell-phone video, tends to displace the failed resolutions of plot onto an electronic mediation that not only turns virtual on the spot, but anticipates the post-traumatic flashback as digital playback.
47
Dandala, Bharath, Venkata Joopudi, Ching-Huei Tsou, Jennifer J. Liang, and Parthasarathy Suryanarayanan. "Extraction of Information Related to Drug Safety Surveillance From Electronic Health Record Notes: Joint Modeling of Entities and Relations Using Knowledge-Aware Neural Attentive Models." JMIR Medical Informatics 8, no. 7 (July 10, 2020): e18417. http://dx.doi.org/10.2196/18417.
Full textAbstract:
Background An adverse drug event (ADE) is commonly defined as “an injury resulting from medical intervention related to a drug.” Providing information related to ADEs and alerting caregivers at the point of care can reduce the risk of prescription and diagnostic errors and improve health outcomes. ADEs captured in structured data in electronic health records (EHRs) as either coded problems or allergies are often incomplete, leading to underreporting. Therefore, it is important to develop capabilities to process unstructured EHR data in the form of clinical notes, which contain a richer documentation of a patient’s ADE. Several natural language processing (NLP) systems have been proposed to automatically extract information related to ADEs. However, the results from these systems showed that significant improvement is still required for the automatic extraction of ADEs from clinical notes. Objective This study aims to improve the automatic extraction of ADEs and related information such as drugs, their attributes, and reason for administration from the clinical notes of patients. Methods This research was conducted using discharge summaries from the Medical Information Mart for Intensive Care III (MIMIC-III) database obtained through the 2018 National NLP Clinical Challenges (n2c2) annotated with drugs, drug attributes (ie, strength, form, frequency, route, dosage, duration), ADEs, reasons, and relations between drugs and other entities. We developed a deep learning–based system for extracting these drug-centric concepts and relations simultaneously using a joint method enhanced with contextualized embeddings, a position-attention mechanism, and knowledge representations. The joint method generated different sentence representations for each drug, which were then used to extract related concepts and relations simultaneously. Contextualized representations trained on the MIMIC-III database were used to capture context-sensitive meanings of words. The position-attention mechanism amplified the benefits of the joint method by generating sentence representations that capture long-distance relations. Knowledge representations were obtained from graph embeddings created using the US Food and Drug Administration Adverse Event Reporting System database to improve relation extraction, especially when contextual clues were insufficient. Results Our system achieved new state-of-the-art results on the n2c2 data set, with significant improvements in recognizing crucial drug−reason (F1=0.650 versus F1=0.579) and drug−ADE (F1=0.490 versus F1=0.476) relations. Conclusions This study presents a system for extracting drug-centric concepts and relations that outperformed current state-of-the-art results and shows that contextualized embeddings, position-attention mechanisms, and knowledge graph embeddings effectively improve deep learning–based concepts and relation extraction. This study demonstrates the potential for deep learning–based methods to help extract real-world evidence from unstructured patient data for drug safety surveillance.
48
Planthaber, Steffen, Daniel Kuehn, Kerstin Rohde, and Christian Hartberger. "Future control stations for heavy machinery." at - Automatisierungstechnik 70, no. 10 (October 1, 2022): 912–17. http://dx.doi.org/10.1515/auto-2022-0059.
Full textAbstract:
Abstract Robots and industrial vehicles are becoming more and more autonomous. Currently, the robots are not able to carry out all tasks autonomously, but the number of those tasks is increasing. Semi- autonomous robots are changing the requirements of control stations for their surveillance and control. These new technologies will provide the possibility to have a single operator command and supervise multiple (semi-) autonomous systems. This requires new control stations, which support remote control and also commanding autonomous actions, like executing a movement command to a specific position. Here, we provide a concept that combines classic and future control stations, that can already be used with the current state of the art in robotics.
49
Ha, Synh Viet-Uyen, Nhat Minh Chung, Hung Ngoc Phan, and Cuong Tien Nguyen. "TensorMoG: A Tensor-Driven Gaussian Mixture Model with Dynamic Scene Adaptation for Background Modelling." Sensors 20, no. 23 (December 6, 2020): 6973. http://dx.doi.org/10.3390/s20236973.
Full textAbstract:
Decades of ongoing research have shown that background modelling is a very powerful technique, which is used in intelligent surveillance systems, in order to extract features of interest, known as foregrounds. In order to work with the dynamic nature of different scenes, many techniques of background modelling adopted the unsupervised approach of Gaussian Mixture Model with an iterative paradigm. Although the technique has had much success, a problem occurs in cases of sudden scene changes with high variation (e.g., illumination changes, camera jittering) that the model unknowingly and unnecessarily takes into account those effects and distorts the results. Therefore, this paper proposes an unsupervised, parallelized, and tensor-based approach that algorithmically works with entropy estimations. These entropy estimations are used in order to assess the uncertainty level of a constructed background, which predicts both the present and future variations from the inputs, thereby opting to use either the incoming frames to update the background or simply discard them. Our experiments suggest that this method is highly integrable into a surveillance system that consists of other functions and can be competitive with state-of-the-art methods in terms of processing speed.
50
Deng, Yulan, Shaohua Teng, Lunke Fei, Wei Zhang, and Imad Rida. "A Multifeature Learning and Fusion Network for Facial Age Estimation." Sensors 21, no. 13 (July 5, 2021): 4597. http://dx.doi.org/10.3390/s21134597.
Full textAbstract:
Age estimation from face images has attracted much attention due to its favorable and many real-world applications such as video surveillance and social networking. However, most existing studies usually learn a single kind of age feature and ignore other appearance features such as gender and race, which have a great influence on the age pattern. In this paper, we proposed a compact multifeature learning and fusion method for age estimation. Specifically, we first used three subnetworks to learn gender, race, and age information. Then, we fused these complementary features to further form more robust features for age estimation. Finally, we engineered a regression-ranking age-feature estimator to convert the fusion features into the exact age numbers. Experimental results on three benchmark databases demonstrated the effectiveness and efficiency of the proposed method on facial age estimation in comparison to previous state-of-the-art methods. Moreover, compared with previous state-of-the-art methods, our model was more compact with only a 20 MB memory overhead and is suitable for deployment on mobile or embedded devices for age estimation.