No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Fire and Smoke Detection Model for Real-Time CCTV Applications
Abstract
Since wildfires, whether they occur in a town or elsewhere, are among the most expensive and deadly disasters, there is a lot of research being done in the field of fire detection. This research is being done, in particular, to ensure the safety of people. It endangers not just their lives but also their long-term well- being. The fastest detection and notification of the location of firemen, operational forces, and even people remain the top priorities. The chance of spotting the smoke before even the development of disastrous flames is thought to make it worthwhile, though. The model should also be able to discriminate between smoke and fog to increase its quality. In order to maximize the utility of this instrument, this study discusses these concerns, including the potential use of detection based on infrared images produced by public or private cameras. Real-time detection is also a crucial tenet for developing a system capable of sending warnings with evidence produced from RGB or infrared video camera monitoring, expanding the possibilities investigated by this methodology.
ResearchGate has not been able to resolve any citations for this publication.
Texture plays a very important role in identifying and extracting the thematic information contained in the image. Texture analysis is a vast field whose objective is to identify the nature of a texture, either via. classification algorithms or via. synthetic algorithms aimed at the creation of a texture, visually similar to the original texture. As specialists are looking for radio-tracers to use in order to do a more advanced study on diseases that infect the skin and organs in general, we have come back to thinking about using ultrasound as ultrasound may well replace radiography in some cases like breast cancer screening. Our goal is to introduce methods to classify different diseases which infect the skin and organs leaving traces by adaptive texture analysis of ultrasound images, i.e., to make a recognition of different types of tumors on medical images and to describe a new approach to automatic texture recognition in digital images using Artificial Neural Networks (ANN).
The implementation of an incident detection system (IDS) is an indispensable operation in the analysis of the road traffics. However the IDS may, in no case, represent an alternative to the classical monitoring system controlled by the human eye. The aim of this work is to increase detection and prediction probability of incidents in camera-monitored areas. Knowing that, these areas are monitored by multiple cameras and few supervisors. Our solution is to use Artificial Neural Networks (ANN) to analyze moving objects trajectories on captured images. We first propose a modelling of the trajectories and their characteristics, after we develop a learning database for valid and invalid trajectories, and then we carry out a comparative study to find the artificial neural network architecture that maximizes the rate of valid and invalid trajectories recognition.
Europay-MasterCard-Visa (EMV) standard aims to improve the security and reliability of smartcards. The main concern of this contribution is to detect vulnerabilities in an EMV transaction between terminal and EMV card. In this paper, we propose a new methodology for vulnerabilities detection based on Deterministic finite automaton (DFA). In fact, we use, as a starting point, the machine state diagram which models the specifications of a secure transaction between a terminal and a payment card. Then, we provide the DFA based on this transition state graph. We also provide the implementation of our DFA in order to recognize valid and invalid patterns automatically. Our tests proved the efficiency of our algorithm and its ability to recognize the vulnerabilities in terms of sequence of orders sent by the terminal to the EMV card.
Traffic accidents are the leading cause of death and serious injury. Many accidents occur at controlled intersections, such as those with traffic lights. Artificial intelligence consists of a wide range of computer techniques intended for problems such as pairing models, language processing and solving very complex and ill-defined problems. The artificial intelligence situation analyzer can use model analysis of previous vehicle data and previous signal violation events to determine the deceleration of the threshold, or otherwise determine the probability of a signal violation. In this article, we present an on-board system to prevent traffic collisions. This system is based on the extraction of six functionalities which characterize mobile vehicles and an unsupervised learning approach based on an artificial neural network to classify functionalities. Our approach began with the description of a motion vector which describes the state of a moving object. Then, the learning database was designed. After various computer simulations, an electronic system was designed to integrate our solution.
Machine Learning automatically creates analytical models that adapt to what is in the data. After a while, the algorithm is used to deliver accurate results, whether it’s making smarter credit decisions, entering into retail deals, medical diagnostics, or detecting fraud. The use of Deep Learning technology as a new machine learning tool has experienced considerable success in digital image processing in recent years. In order to contribute to the classification and the security of Medical Images (storage, sharing, transfer …), we present, in this paper:a comparative study between the famous Convolutional Neural Network architectures and ACSA-Net that we propose concerning the classification of Brain Tumors detected in the Magnetic Resonance Imaging.a new digital signature method using Artificial and Convolutional Neural Network that consists of inserting into the Medical Image the Signature information like the hospital center and patient data, using Watermarking. It must ensure the integrity, confidentiality of the images when it is shared and the robustness to the different types of attacks (JPEG compression, copy and paste, geometric transformations, etc.). As a result, we have shown that the use of Machine and Deep Learning techniques makes it possible to detect the Brain Tumors, in particular ACSA-Net major in terms of recognition rate. And the signature process proposed resists various frequency analysis attacks.
First, export-oriented farms, irrigated, modern and highly capitalized.
Machine learning (a subset of Artificial Intelligence) automatically creates analytic models that adapt to what they find in the data. Over time, the algorithm “learns” how to deliver more accurate results, whether the goal is to make smarter credit decisions, retail offers, medical diagnoses or fraud detection. The use of Deep Learning technology as a new Machine Learning tools has had considerable success in Digital Image Processing over the past few years. It has been widely used in several of complex problems and has proven to be a powerful solving tool. In this paper we present a comparative study between the famous convolutional architectures (LeNet, AlexNet, ZF Net, GoogLeNet, VGGNet, ResNets, DenseNet) and the Convolutional Neural Networks AsilNet that we propose concerning the classification of Brain Tumors (Aneurysms, Multiple Sclerosis, Hydrocephalus, Stroke, Infections, Cysts, Swelling, Hemorrhage, Bleeding, Inflammation) detected in the Magnetic Resonance Imaging.
Currently, different forms of ransomware are increasingly threatening users. Modern ransomware encrypts important user data and it is only possible to recover it once a ransom has been paid [14]. In this paper, we classify ransomware in 10 classes which are labeled using avclass tool. In this classification, we based on artificial neural networks with multilayer perceptron function. To do this, it was necessary to build the learning base based on ransomware files. We then implemented programs in java allowing the extraction of the key strings from ransomwares files intended for the learning stage and for the test one. Once the learning and testing databases have been prepared, we started the classification with the weka tool. The objective of this contribution is to investigate if the neural networks are an effective means for the classification of this kind of ransomwares or it will be necessary to think to another method of classification.
This paper discusses the use of analytical software solutions in microfinance institutions and how it can improve the operations of the organization. The study has been conducted through a survey from MFIs located in various countries of Africa, Europe and Asia. The survey questions have been based on the kind of software solutions MFIs use and if they are able to benefit from it. Moreover, with this survey we have tried to find out if the MFIs are willing to adopt the new technologies in their system by using software solutions. The survey has been conducted with MFIs in located in different countries. Besides MFIs, the respondents included banks as well.
The determination of flame or fire edges is the process of identifying a boundary between the area where there is thermochemical reaction and those without. It is a precursor to image-based flame monitoring, early fire detection, fire evaluation, and the determination of flame and fire parameters. Several traditional edge-detection methods have been tested to identify flame edges, but the results achieved have been disappointing. Some research works related to flame and fire edge detection were reported for different applications; however, the methods do not emphasize the continuity and clarity of the flame and fire edges. A computing algorithm is thus proposed to define flame and fire edges clearly and continuously. The algorithm detects the coarse and superfluous edges in a flame/fire image first and then identifies the edges of the flame/fire and removes the irrelevant artifacts. The autoadaptive feature of the algorithm ensures that the primary symbolic flame/fire edges are identified for different scenarios. Experimental results for different flame images and video frames proved the effectiveness and robustness of the algorithm.
This paper presents some experiments on automatic fire detection and monitoring with a team of Unmanned Aerial Vehicles (UAVs). The work has been carried out in the framework of the project "COMETS: Real-time coordination and control of multiple heterogeneous unmanned aerial vehicles" (IST-2001-34304) of the IST Progra mme of the European Commission. Instead of using a single expensive UAV, the approach adopted in COMETS has been the cooperation of several low cost UAVs. The COMETS demonstrations involved the integration of 3 heterogeneous UAVs: the helicopter Marvin, the airship Karma, and the helicopter Heliv . The UAVs were equipped with heterogeneous sensors including one visual and one infrared micro-camera (Heliv) and a punctual fire sensor (Marvin). The capabilities and performa nce of the COMETS system were demonstrated in several experiments on automatic fi re detection, confirmation, localisation and monitoring. The experiments organized in Lousã (Portugal) in May 2003, May 2004 and May 2005 demonstrated the capabilities of the COMETS system. The paper includes a brief description of the COMETS system and presents some experimental results.
We prove partial regularity for the vector-valued differential forms solving the system δ(A(x, ω))=0, dω=0, and for the gradient of the vector-valued functions solving the system div A(x, Du)=B(x, u, Du). Here the mapping A, with A(x, w) ≈ (1+ + |ω|2)(p - 2)/2 ω (p≥2), satisfies a quasimonotonicity condition which, when applied to the gradient A(x, ω)=Dωf(x, ω) of a real-valued function f, is analogous to but stronger than quasiconvexity for f. The case 1<p<2 for monotone A is reduced to the case p≥2 by a duality technique.
The paper presents an early fire-alarm raising method based on video processing. The basic idea of the proposed of fire-detection is to adopt a RGB (red, green, blue) model based chromatic and disorder measurement for extracting fire-pixels and smoke-pixels. The decision function of fire-pixels is mainly deduced by the intensity and saturation of R component. The extracted fire-pixels will be verified if it is a real fire by both dynamics of growth and disorder, and further smoke. Based on iterative checking on the growing ratio of flames, a fire-alarm is given when the alarm-raising condition is met. Experimental results show that the developed technique can achieve fully automatic surveillance of fire accident with a lower false alarm rate and thus is very attractive for the important military, social security, commercial applications, and so on, at a general cost.
Describes the current status of the UK's Security and Fire
Fighting Advanced Robot (SAFFAR) project within the International
Advanced Robotic Programme (IARP). In the UK the majority of nondomestic
fire losses are as a result of arson. The SAFFAR robot is intended as a
relatively low cost high performance device which will act as a powerful
deterrent to unauthorised intrusion into a premises by markedly
increasing the incidence of arrest of such intruders. It also carries a
`first strike' fire fighting capability which should prevent, for
example petrol bomb fires, from taking hold. The robot design concept
has been to provide varying levels of performance complexity (and
associated costs), by stand alone `modules' for both hardware and
software elements which can then be `assembled' into a variety of core
designs and variants
- W Thomson
- N Bhowmik
- T P Breckon
Digital movements images restoring by artificial neural netwoks
- H Tarik
- M Kodad
- J E Miloud
On the use of stereovision to develop a novel instrumentation system to extract geometric fire fronts characteristics. Fire Saf
- L Rossi
- M Akhloufi
- Y Tison
Optimizations of distributed computing processes on apache spark platform
- T Hajji
- R Loukili
- I El Hassani
- T Masrour