Explore the vast range of titles available.

Human violence recognition is an area of great interest in the scientific community due to its broad spectrum of applications, especially in video surveillance systems, because detecting violence in real time can prevent criminal acts and save lives. The majority of existing proposals and studies focus on result precision, neglecting efficiency and practical implementations. Thus, in this work, we propose a model that is effective and efficient in recognizing human violence in real time. The proposed model consists of three modules: the Spatial Motion Extractor (SME) module, which extracts regions of interest from a frame; the Short Temporal Extractor (STE) module, which extracts temporal characteristics of rapid movements; and the Global Temporal Extractor (GTE) module, which is responsible for identifying long-lasting temporal features and fine-tuning the model. The proposal was evaluated for its efficiency, effectiveness, and ability to operate in real time. The results obtained on the Hockey, Movies, and RWF-2000 datasets demonstrated that this approach is highly efficient compared to various alternatives. In addition, the VioPeru dataset was created, which contains violent and non-violent videos captured by real video surveillance cameras in Peru, to validate the real-time applicability of the model. When tested on this dataset, the effectiveness of our model was superior to the best existing models.

Dose-response analysis can be carried out using multi-purpose commercial statistical software, but except for a few special cases the analysis easily becomes cumbersome as relevant, non-standard output requires manual programming. The extension package drc for the statistical environment R provides a flexible and versatile infrastructure for dose-response analyses in general. The present version of the package, reflecting extensions and modifications over the last decade, provides a user-friendly interface to specify the model assumptions about the dose-response relationship and comes with a number of extractors for summarizing fitted models and carrying out inference on derived parameters. The aim of the present paper is to provide an overview of state-of-the-art dose-response analysis, both in terms of general concepts that have evolved and matured over the years and by means of concrete examples.

We provide formal definitions and efficient secure techniques for turning noisy information into keys usable for any cryptographic application, and, in particular, reliably and securely authenticating biometric data. Our techniques apply not just to biometric information, but to any keying material that, unlike traditional cryptographic keys, is (1) not reproducible precisely and (2) not distributed uniformly. We propose two primitives: a fuzzy extractor reliably extracts nearly uniform randomness$R$from its input; the extraction is error-tolerant in the sense that$R$will be the same even if the input changes, as long as it remains reasonably close to the original. Thus,$R$can be used as a key in a cryptographic application. A secure sketch produces public information about its input$w$that does not reveal$w$and yet allows exact recovery of$w$given another value that is close to$w$ . Thus, it can be used to reliably reproduce error-prone biometric inputs without incurring the security risk inherent in storing them. We define the primitives to be both formally secure and versatile, generalizing much prior work. In addition, we provide nearly optimal constructions of both primitives for various measures of \"closeness\" of input data, such as Hamming distance, edit distance, and set difference.

Object detection using remote sensing data is a key task of the perception systems of self-driving vehicles. While many generic deep learning architectures have been proposed for this problem, there is little guidance on their suitability when using them in a particular scenario such as autonomous driving. In this work, we aim to assess the performance of existing 2D detection systems on a multi-class problem (vehicles, pedestrians, and cyclists) with images obtained from the on-board camera sensors of a car. We evaluate several one-stage (RetinaNet, FCOS, and YOLOv3) and two-stage (Faster R-CNN) deep learning meta-architectures under different image resolutions and feature extractors (ResNet, ResNeXt, Res2Net, DarkNet, and MobileNet). These models are trained using transfer learning and compared in terms of both precision and efficiency, with special attention to the real-time requirements of this context. For the experimental study, we use the Waymo Open Dataset, which is the largest existing benchmark. Despite the rising popularity of one-stage detectors, our findings show that two-stage detectors still provide the most robust performance. Faster R-CNN models outperform one-stage detectors in accuracy, being also more reliable in the detection of minority classes. Faster R-CNN Res2Net-101 achieves the best speed/accuracy tradeoff but needs lower resolution images to reach real-time speed. Furthermore, the anchor-free FCOS detector is a slightly faster alternative to RetinaNet, with similar precision and lower memory usage.

In this study, we determine the liquid limit ( ), plasticity index (PI), and plastic limit ( ) of several natural fine-grained soil samples with the help of machine-learning and statistical methods. This enables us to locate each soil type analysed in the Casagrande plasticity chart with a single measure in pressure-membrane extractors. These machine-learning models showed adjustments in the determination of the liquid limit for design purposes when compared with standardised methods. Similar adjustments were achieved in the determination of the plasticity index, whereas the plastic limit determinations were applicable for control works. Because the best techniques were based in Multiple Linear Regression and Support Vector Machines Regression, they provide explainable plasticity models. In this sense, =(9.94±4.2)+(2.25 ±0.3)∙ F4.2, PI=(−20.47±5.6)+(1.48 ±0.3)∙ F4.2+(0.21±0.1)∙ , and =(23.32±3.5)+(0.60 ±0.2)∙ F4.2−(0.13±0.04)∙ . So that, we propose an alternative, automatic, multi-sample, and static method to address current issues on Atterberg limits determination with standardised tests.

It has been over six years since the Transformer architecture was put forward. Surprisingly, the vanilla Transformer architecture is still widely used today. One reason is that the lack of deep understanding and comprehensive interpretation of the Transformer architecture makes it more challenging to improve the Transformer architecture. In this paper, we first interpret the Transformer architecture comprehensively in plain words based on our understanding and experiences. The interpretations are further proved and verified. These interpretations also cover the Extractor, a family of drop-in replacements for the multi-head self-attention in the Transformer architecture. Then, we propose an improvement on a type of the Extractor that outperforms the self-attention, without introducing additional trainable parameters. Experimental results demonstrate that the improved Extractor performs even better, showing a way to improve the Transformer architecture.

With the continuous increase in Internet of Things (IoT) device usage, more interest has been shown in internet security, specifically focusing on protecting these vulnerable devices from malicious traffic. Such threats are difficult to distinguish, so an advanced intrusion detection system (IDS) is becoming necessary. Machine learning (ML) is one of the promising techniques as a smart IDS in different areas, including IoT. However, the input to ML models should be extracted from the IoT environment by feature extraction models, which play a significant role in the detection rate and accuracy. Therefore, this research aims to introduce a study on ML-based IDS in IoT, considering different feature extraction algorithms with several ML models. This study evaluated several feature extractors, including image filters and transfer learning models, such as VGG-16 and DenseNet. Additionally, several machine learning algorithms, including random forest, K-nearest neighbors, SVM, and different stacked models were assessed considering all the explored feature extraction algorithms. The study presented a detailed evaluation of all combined models using the IEEE Dataport dataset. Results showed that VGG-16 combined with stacking resulted in the highest accuracy of 98.3%.

Security vulnerabilities associated with Internet of Medical Things (IoMT) may lead to health disasters. The researchers already have designed several lightweight authentication techniques to provide secure communication towards physical layer security in a heterogeneous IoMT environment. Blockchain technology is utilized to solve the existing security issues of IoMT ensuring the network layer security. This paper presents a lightweight two factor authentication scheme (TFAS) for a blockchain-enabled IoMT environment which focuses on both the physical and network layer security without involvement of any centralized third party. The proposed TFAS involves device, user and data authentication along with user authorization for improved access control of medical data. It is a two-phase authenticity verification method which involves the authentication of users and devices using the PUF and fuzzy extractor in the first phase and blockchain-based data authentication along with authorization of users in the second phase. It also improves storage capacity of blockchain-enabled IoMT network and ensures its scalability using a cluster of smart-contract enabled inter planetary file systems servers. The formal security analysis has been performed using the real-or-random model for evaluating security of session key and mutual authentication protocol. The informal security analysis provides strong evidences for resilience of TFAS from various known attacks. Moreover, the proposed scheme outperformed other existing schemes in terms of communication cost, computational cost and storage.

A fuzzy extractor is a foundational cryptographic component that enables the extraction of reproducible and uniformly random strings from sources with inherent noise, such as biometric traits. Reusable fuzzy extractor guarantees the security of multiple extractions from the same noisy source. In addition, although isogeny-based cryptography has become an important branch in post-quantum cryptography, the study of fuzzy extractors based on isogeny assumptions is still in its early stages and holds much room for improvement. In this paper, we give two reusable fuzzy extractor schemes derived from isogeny-based assumptions: one is based on the linear hidden shift assumption over group actions, while the other is built upon the group-action decisional Diffie–Hellman assumption within the isogeny framework. Both proposed constructions achieve post-quantum security and are capable of correcting a linear proportion of errors. They rely solely on fundamental cryptographic primitives, which ensure simplicity and efficiency. Additionally, the second construction is based on restricted effective group action, which is weaker than the effective group action used in the first construction, thereby offering greater practical applicability.

Advances in parallel computing, GPU technology and deep learning facilitate the tools for processing complex images. The purpose of this research was focused on a review of the state of the art, related to the performance of pre-trained models for the detection of objects in order to make a comparison of these algorithms in terms of reliability, ac-curacy, time processed and Problems detected The consulted models are based on the Python programming language, the use of libraries based on TensorFlow, OpenCv and free image databases (Microsoft COCO and PAS-CAL VOC 2007/2012). These systems are not only focused on the recognition and classification of the objects in the images, but also on the location of the objects within it, drawing a bounding box around the appropriate way. For this research, different pre-trained models were re-viewed for the detection of objects such as R-CNN, R-FCN, SSD (single-shot multibox) and YOLO (You Only Look Once), with different extractors of characteristics such as VGG16, ResNet, Inception, MobileNet. As a result, it is not prudent to make direct and parallel analyzes between the different architecture and models, because each case has a particular solution for each problem, the purpose of this research is to generate an approximate notion of the experiments that have been carried out and conceive a starting point in the use that they are intended to give.