One task of CCTV operation is to decide whether footage shown in videos depicts criminal behaviour, or allows a viewer to predict its occurrence. An increasing prevalence of cameras in the world, ...means an increase in screens in the control room. This presents a signal-to-noise challenge where the signal (criminal activity) may become more difficult to detect amongst the noise. We used signal detection approaches to understand which factors were associated with decision-making in a CCTV task. When detecting aggressive incidents, higher conscientiousness was associated with making better decisions, with a higher criterion for responding (meaning fewer false-positive responses). However, conscientious individuals tended to be less confident (in multiplex displays), and were slower in responding – which reflects that these individuals require more evidence to make these decisions. Higher trait cognitive anxiety was again associated with making earlier responses, while extraversion was also associated with earlier responding in multiplexed displays. Taken in combination, our results suggest that there is a fine balance between making correct decisions, and making early decisions – and that these need to be considered together in the CCTV task.
•Detection of aggressive events in CCTV can be predicted by individual measures of personality and anxiety.•The factors that predict performance vary in single and multiple-screen displays.•Conscientious individuals make later responses, but are more accurate.•Extraversion and trait cognitive anxiety correspond with earlier responses.•These findings may be useful in the development of recruitment materials for CCTV operators.
Cyber attacks are currently blooming, as the attackers reap significant profits from them and face a limited risk when compared to committing the "classical" crimes. One of the major components that ...leads to the successful compromising of the targeted system is malicious software. It allows using the victim's machine for various nefarious purposes, e.g., making it a part of the botnet, mining cryptocurrencies, or holding hostage the data stored there. At present, the complexity, proliferation, and variety of malware pose a real challenge for the existing countermeasures and require their constant improvements. That is why, in this paper we first perform a detailed meta-review of the existing surveys related to malware and its detection techniques, showing an arms race between these two sides of a barricade. On this basis, we review the evolution of modern threats in the communication networks, with a particular focus on the techniques employing information hiding. Next, we present the bird's eye view portraying the main development trends in detection methods with a special emphasis on the machine learning techniques. The survey is concluded with the description of potential future research directions in the field of malware detection.
Many rumors convey information about potential danger, even when these dangers are very unlikely. In four studies, we examine whether micro-processes of cultural transmission explain the spread of ...threat-related information. Three studies using transmission chain protocols suggest a) that there is indeed a preference for the deliberate transmission of threat-related information over other material, b) that it is not caused by a general negativity or emotionality bias, and c) that it is not eliminated when threats are presented as very unlikely. A forced-choice study on similar material shows the same preference when participants have to select information to acquire rather than transmit. So the cultural success of threat-related material may be explained by transmission biases, rooted in evolved threat-detection and error-management systems, that affect both supply and demand of information.
•Risk-related rumors are more common than benefit-related rumors.•Threat information is more often transmitted than non-threatening negative information.•Also, people seek additional information about threats more than about other topics.•This could explain why so many rumors are about potential danger.
Traditional methods of violence detection in public spaces often struggle with low accuracy, limited real-time capabilities, and an inability to handle complex spatiotemporal patterns. They lack the ...sophistication needed to accurately distinguish between violent and non-violent activities, and their reliance on rule-based systems hinders adaptability to diverse scenarios. Moreover, their communication channels for alerts might be slow and inefficient. Mitigating the pervasive issue of violence within public spaces demands a technologically advanced approach. Addressing this imperative, we present a novel solution encompassing a profound neural network architecture. Our method harmoniously integrates a pre-trained Darknet19 model with both Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) models, collectively orchestrated to achieve unprecedented efficacy in violence detection and prevention. Our approach commences with the extraction of spatial intricacies, meticulously executed by leveraging the potent capabilities of the Darknet19 model. Subsequently, these extracted spatial features serve as the foundational dataset for training the CNN, which in turn captures and distills essential temporal attributes inherent to the video sequences. These temporal features are then seamlessly channeled into the LSTM component of our architecture, which adeptly discerns and categorizes video-based activities into two distinct classes: manifestations of violence and non-violent behaviors. Validation and verification of our proposed model transpire upon the Fight dataset, resulting in a suite of commendable experimental outcomes. The integration of multi-modal alert dissemination mechanisms further enhances our system's efficacy. Notably, pertinent alerts are expeditiously communicated to relevant law enforcement entities through the synergistic utilization of WhatsApp, Telegram, and e-mail applications. This technologically fortified paradigm promises a transformative leap in curbing violence within public domains, empowering law enforcement agencies with real-time, actionable insights. Moreover, the proposed systems have achieved high accuracy rates of 96%, which is higher than the accuracy achieved by other state-of-the-art models.
Knowledge of how temperature influences animal behavior is critical to understanding and predicting impacts of changing climate on individual species and biotic interactions. However, the effects of ...climate change, especially winter warming in freshwater systems, on fish behaviors and the use of chemical information have been largely unexplored. Qinling lenok Brachymystax lenok tsinlingensis, an endangered salmonid species endemic to the Qinling Mountain Range, China, is currently experiencing population decline and is a potential biological indicator of warming winter climate effects on freshwater fishes due to its temperature sensitivity and required habitat of small, cold-water streams. Our objective was to determine if transient winter warming (increases of ~4 °C) consistent with seasonal maxima in line with near-future climate projections will affect antipredator responses to damage-released chemical alarm cues in B. lenok tsinlingensis. Wild fish were collected during winter and held in captivity under food deprivation for four days, during which half were acclimated to a warmer temperature (6 °C) while the other half were maintained at ambient levels (2 °C). Individual acclimated fish were then exposed to injections of either conspecific alarm cues to simulate elevated predation risk or stream water as a control treatment. Focal fish demonstrated responses consistent with antipredator behaviors to alarm cues at ambient temperature, but no significant behavioral responses to alarm cues were found relative to controls at the warmer temperature. These results support our hypothesis that winter warming will negatively influence antipredator responses and indicate that projected warmer temperature patterns in winter may have significant impacts on chemically mediated predator-prey interactions in cold-water streams.
Display omitted
•The effects of warming winter climate on freshwater fish behaviors have been largely unexplored.•Qinling lenok are endangered, temperature-sensitive salmonids vulnerable to warming effects.•Lenok demonstrated antipredator responses to chemical alarm cues at ambient temperature.•Lenok did not demonstrate antipredator responses to alarm cues at a higher temperature.•Warmer winter temperatures will likely alter predator-prey interactions in freshwater systems.
Visual systems extract multiple features from a scene using parallel neural circuits. Ultimately, the separate neural signals must come together to coherently influence action. Here, we characterize ...a circuit in Drosophila that integrates multiple visual features related to imminent threats to drive evasive locomotor turns. We identified, using genetic perturbation methods, a pair of visual projection neurons (LPLC2) and descending neurons (DNp06) that underlie evasive flight turns in response to laterally moving or approaching visual objects. Using two-photon calcium imaging or whole-cell patch clamping, we show that these cells indeed respond to both translating and approaching visual patterns. Furthermore, by measuring visual responses of LPLC2 neurons after genetically silencing presynaptic motion-sensing neurons, we show that their visual properties emerge by integrating multiple visual features across two early visual structures: the lobula and the lobula plate. This study highlights a clear example of how distinct visual signals converge on a single class of visual neurons and then activate premotor neurons to drive action, revealing a concise visuomotor pathway for evasive flight maneuvers in Drosophila.
Display omitted
•Flying flies steer away from a rapidly translating or approaching visual object•LPLC2 and DNp06 neurons are important for visually guided avoidance flight turns•LPLC2 and DNp06 are sensitive to laterally moving spot and looming disc patterns•LPLC2 integrate multiple visual features across two early visual structures
Visual features are computed in multiple structures, but how they influence action collectively is poorly understood. Kim et al. show that a Drosophila visuomotor circuit, consisting of a class of visual project neurons (LPLC2) and descending neurons (DNp06), integrate multiple visual features to drive evasive flight turns.
We propose discrimination algorithms for buried threat detection (BTD) that exploit deep convolutional neural networks (CNNs) and recurrent neural networks (RNN) to analyze 2-D GPR B-scans in the ...down-track (DT) and cross-track (CT) directions as well as 3-D GPR volumes. Instead of imposing a specific model or handcrafted features, as in most existing detectors, we use large real GPR data collections and data-driven approaches that learn: 1) features characterizing buried explosive objects (BEOs) in 2-D B-scans, both in the DT and CT directions; 2) the variation of the CNN features learned in a fixed 2-D view across the third dimension; and 3) features characterizing BEOs in the original 3-D space. The proposed algorithms were trained and evaluated using large experimental GPR data covering a surface area of 120 000 m 2 from 13 different lanes across two U.S. test sites. These data include a diverse set of BEOs consisting of varying shapes, metal content, and underground burial depths. We provide some qualitative analysis of the proposed algorithms by visually comparing their performance and consistency along different dimensions and visualizing typical features learned by some nodes of the network. We also provide quantitative analysis that compares the receiver operating characteristics (ROCs) obtained using the proposed algorithms with those obtained using existing approaches based on CNN as well as traditional learning.
Tracking multiple moving objects in real-time in a dynamic threat environment is an important element in national security and surveillance system. It helps pinpoint and distinguish potential ...candidates posing threats from other normal objects and monitor the anomalous trajectories until intervention. To locate the anomalous pattern of movements, one needs to have an accurate data association algorithm that can associate the sequential observations of locations and motion with the underlying moving objects, and therefore, build the trajectories of the objects as the objects are moving. In this work, we develop a spatio-temporal approach for tracking maritime vessels as the vessel's location and motion observations are collected by an Automatic Identification System. The proposed approach is developed as an effort to address a data association challenge in which the number of vessels as well as the vessel identification are purposely withheld and time gaps are created in the datasets to mimic the real-life operational complexities under a threat environment. Three training datasets and five test sets are provided in the challenge and a set of quantitative performance metrics is devised by the data challenge organizer for evaluating and comparing resulting methods developed by participants. When our proposed track association algorithm is applied to the five test sets, the algorithm scores a very competitive performance.