Search results for: feature detection and description

Authors: Yushuai Wang, Feng Xu, Junbo Tan, Xueqian Wang, Bin Liang

Abstract:

In this paper, a sensor fault-tolerant control (FTC) scheme using robust model predictive control (RMPC) and set theoretic fault detection and isolation (FDI) is extended to linear parameter varying (LPV) systems. First, a group of set-valued observers are designed for passive fault detection (FD) and the observer gains are obtained through minimizing the size of invariant set of state estimation-error dynamics. Second, an input set for fault isolation (FI) is designed offline through set theory for actively isolating faults after FD. Third, an RMPC controller based on state estimation for LPV systems is designed to control the system in the presence of disturbance and measurement noise and tolerate faults. Besides, an FTC algorithm is proposed to maintain the plant operate in the corresponding mode when the fault occurs. Finally, a numerical example is used to show the effectiveness of the proposed results.

Keywords: fault detection, linear parameter varying, model predictive control, set theory

Procedia PDF Downloads 234

Authors: Farheen Tabassum, Shoab Ahmed Khan

Abstract:

The brutality of attacks on networks and decisive infrastructures are on the climb over recent years and appears to continue to do so. Distributed Denial of service attack is the most prevalent and easy attack on the availability of a service due to the easy availability of large botnet computers at cheap price and the general lack of protection against these attacks. Application layer DDoS attack is DDoS attack that is targeted on wed server, application server or database server. These types of attacks are much more sophisticated and challenging as they get around most conventional network security devices because attack traffic often impersonate normal traffic and cannot be recognized by network layer anomalies. Conventional techniques of single-hosted security systems are becoming gradually less effective in the face of such complicated and synchronized multi-front attacks. In order to protect from such attacks and intrusion, corporation among all network devices is essential. To overcome this issue, a collaborative intrusion detection system (CIDS) is proposed in which multiple network devices share valuable information to identify attacks, as a single device might not be capable to sense any malevolent action on its own. So it helps us to take decision after analyzing the information collected from different sources. This novel attack detection technique helps to detect seemingly benign packets that target the availability of the critical infrastructure, and the proposed solution methodology shall enable the incident response teams to detect and react to DDoS attacks at the earliest stage to ensure that the uptime of the service remain unaffected. Experimental evaluation shows that the proposed collaborative detection approach is much more effective and efficient than the previous approaches.

Keywords: Distributed Denial-of-Service (DDoS), Collaborative Intrusion Detection System (CIDS), Slowloris, OSSIM (Open Source Security Information Management tool), OSSEC HIDS

Procedia PDF Downloads 346

Authors: M. Ahmadi, M. Kafil, H. Ebrahimi

Abstract:

Nowadays, induction motors have a significant role in industries. Condition monitoring (CM) of this equipment has gained a remarkable importance during recent years due to huge production losses, substantial imposed costs and increases in vulnerability, risk, and uncertainty levels. Motor current signature analysis (MCSA) is one of the most important techniques in CM. This method can be used for rotor broken bars detection. Signal processing methods such as Fast Fourier transformation (FFT), Wavelet transformation and Empirical Mode Decomposition (EMD) are used for analyzing MCSA output data. In this study, these signal processing methods are used for broken bar problem detection of Mobarakeh steel company induction motors. Based on wavelet transformation method, an index for fault detection, CF, is introduced which is the variation of maximum to the mean of wavelet transformation coefficients. We find that, in the broken bar condition, the amount of CF factor is greater than the healthy condition. Based on EMD method, the energy of intrinsic mode functions (IMF) is calculated and finds that when motor bars become broken the energy of IMFs increases.

Keywords: broken bar, condition monitoring, diagnostics, empirical mode decomposition, fourier transform, wavelet transform

Procedia PDF Downloads 141

Authors: Nemi Bhattarai

Abstract:

In recent years, there has been a rapid increase in the use of Unmanned Aerial Vehicle (UAVs) in search and rescue (SAR) operations, disaster management, and many more areas where information about the location of human beings are important. This research will primarily focus on the use of optical and thermal camera via UAV platform in real-time detection, localization, and visualization of human beings on GIS. This research will be beneficial in disaster management search of lost humans in wilderness or difficult terrain, detecting abnormal human behaviors in border or security tight areas, studying distribution of people at night, counting people density in crowd, manage people flow during evacuation, planning provisions in areas with high human density and many more.

Keywords: UAV, human detection, real-time, localization, visualization, haar-like, GIS, thermal sensor

Procedia PDF Downloads 450

Authors: Arvin Ludovice

Abstract:

The modern way of communicating and connecting people has been in its easiest forms nowadays, one of it is blog. Blogs, nowadays, are truly relevant in informing people of different as aspects, interests, and fields through these blogs. The evidentiality and testimony of collective people are easily been accessed. However, the description of blog in the making is persuading people, choice of language is one—adverbial intensifiers. Measuring the language on a scale of its intensity subdue the intensity per se. The present study determines, scrutinizes and analyses the adverbial intensifiers used in Filipino and Malaysian. The corpus consists of 30 top travel blogs written by Filipinos and 30 top travel blogs written by Malaysian for a total of 60 travel blogs. The application AntConc was utilized to tag the necessary intensifiers. A frequency distribution of the scores is used to identify the most common intensifiers used by travel bloggers from the Philippines and Malaysia. The scale or degree of intensifier is taken from Quirk Degree of Intensifiers as the basis for the functions of intensifiers. The result found that Malaysian travel blogs are more expressive with the use of the adverbial intensifiers vis-à-vis Filipino travel bloggers, consequently, ranking of the intensifiers, boosters are most used one in expressing and utilizing the language choice a more. The conclusion states that Malaysian travel bloggers are of using the functionality of the adverbial intensifiers. The distinction on the pedagogical implications are hereunto stated as well to deepen and give its significant and importance in language teaching.

Keywords: adverbial intensifiers, blogs, Filipino and Malaysian blogs, AntConc

Procedia PDF Downloads 175

Authors: Hyojin Lim, Cuong Nguyen Khac, Yeongyu Choi, Ho-Youl Jung

Abstract:

In this paper, we propose a simple moving object detection, which is based on motion vectors obtained from pyramidal Lucas-Kanade optical flow. The proposed method detects moving objects such as pedestrians, the other vehicles and some obstacles at the front-side of the host vehicle, and it can provide the warning to the driver. Motion vectors are obtained by using pyramidal Lucas-Kanade optical flow, and some outliers are eliminated by comparing the amplitude of each vector with the pre-defined threshold value. The background model is obtained by calculating the mean and the variance of the amplitude of recent motion vectors in the rectangular shaped local region called the cell. The model is applied as the reference to classify motion vectors of moving objects and those of background. Motion vectors are clustered to rectangular regions by using the unsupervised clustering K-means algorithm. Labeling method is applied to label groups which is close to each other, using by distance between each center points of rectangular. Through the simulations tested on four kinds of scenarios such as approaching motorbike, vehicle, and pedestrians to host vehicle, we prove that the proposed is simple but efficient for moving object detection in parking lots.

Keywords: moving object detection, dynamic scene, optical flow, pyramidal optical flow

Procedia PDF Downloads 332

Authors: Budhvin T. Withana, Sulochana Rupasinghe

Abstract:

The problem of Dyslexia and Dysgraphia, two learning disabilities that affect reading and writing abilities, respectively, is a major concern for the educational system. Due to the complexity and uniqueness of the Sinhala language, these conditions are especially difficult for children who speak it. The traditional risk detection methods for Dyslexia and Dysgraphia frequently rely on subjective assessments, making it difficult to cover a wide range of risk detection and time-consuming. As a result, diagnoses may be delayed and opportunities for early intervention may be lost. The project was approached by developing a hybrid model that utilized various deep learning techniques for detecting risk of Dyslexia and Dysgraphia. Specifically, Resnet50, VGG16 and YOLOv8 were integrated to detect the handwriting issues, and their outputs were fed into an MLP model along with several other input data. The hyperparameters of the MLP model were fine-tuned using Grid Search CV, which allowed for the optimal values to be identified for the model. This approach proved to be effective in accurately predicting the risk of Dyslexia and Dysgraphia, providing a valuable tool for early detection and intervention of these conditions. The Resnet50 model achieved an accuracy of 0.9804 on the training data and 0.9653 on the validation data. The VGG16 model achieved an accuracy of 0.9991 on the training data and 0.9891 on the validation data. The MLP model achieved an impressive training accuracy of 0.99918 and a testing accuracy of 0.99223, with a loss of 0.01371. These results demonstrate that the proposed hybrid model achieved a high level of accuracy in predicting the risk of Dyslexia and Dysgraphia.

Keywords: neural networks, risk detection system, Dyslexia, Dysgraphia, deep learning, learning disabilities, data science

Procedia PDF Downloads 86

Authors: James Kaweesa

Abstract:

The Internet of Things (IoT) has become a critical component of modern technology, enabling the connection of numerous devices to the internet. The interconnected nature of IoT devices, along with their heterogeneous and resource-constrained nature, makes them vulnerable to various types of attacks, such as malware, denial-of-service attacks, and network scanning. Intrusion Detection Systems (IDSs) are a key mechanism for protecting IoT networks and from attacks by identifying and alerting administrators to suspicious activities. In this review, the paper will discuss the different types of IDSs available for IoT systems and evaluate their effectiveness in detecting and preventing attacks. Also, examine the various evaluation methods used to assess the performance of IDSs and the challenges associated with evaluating them in IoT environments. The review will highlight the need for effective and efficient IDSs that can cope with the unique characteristics of IoT networks, including their heterogeneity, dynamic topology, and resource constraints. The paper will conclude by indicating where further research is needed to develop IDSs that can address these challenges and effectively protect IoT systems from cyber threats.

Keywords: cyber-threats, iot, intrusion detection system, networks

Procedia PDF Downloads 68

Authors: Desissa Yadeta Muleta

Abstract:

Purely organic long-persistent luminescence materials (OLPLMs) have been developed as emerging organic materials due to their simple production process, low preparation cost and better biocompatibilities. Notably, OLPLMs with afterglow-time-tunable long-persistent luminescence (LPL) characteristics enable higher-level protection applications and have great prospects in biological applications. The realization of these advanced performances depends on our ability to gradually tune LPL duration under ambient conditions, however, the strategies to achieve this are few due to the lack of unambiguous mechanisms. Here, we propose a two-step strategy to gradually tune LPL duration of OLPLMs over a wide range of seconds in water and air, by using derivatives as the guest and introducing a third-party material into the host-immobilized host–guest doping system. Based on this strategy, we develop an analysis method for deoxyribonucleic acid (DNA) content detection without DNA separation in aqueous samples, which circumvents the influence of the chromophore, fluorophore and other interferents in vivo, enabling a certain degree of in situ detection that is difficult to achieve using today’s methods. This work will expedite the development of afterglow-time-tunable OLPLMs and expand new horizons for their applications in data protection, bio-detection, and bio-sensing

Keywords: deoxyribonucliec acid, long persistent luminescent materials, water, air

Procedia PDF Downloads 62

Authors: H. Abu-Ali, A. Nabok, T. Smith

Abstract:

Aptamers are single-strand of DNA or RNA nucleotides sequence which is designed in vitro using selection process known as SELEX (systematic evolution of ligands by exponential enrichment) were developed for the selective detection of many toxic materials. In this work, we have developed an electrochemical biosensor for highly selective and sensitive detection of Hg2+ and Pb2+ using a specific aptamer probe (SAP) labelled with ferrocene (or methylene blue) in (5′) end and the thiol group at its (3′) termini, respectively. The SAP has a specific coil structure that matching with G-G for Pb2+ and T-T for Hg2+ interaction binding nucleotides ions, respectively. Aptamers were immobilized onto surface of screen-printed gold electrodes via SH groups; then the cyclic voltammograms were recorded in binding buffer with the addition of the above metal salts in different concentrations. The resulted values of anode current increase upon binding heavy metal ions to aptamers and analyte due to the presence of electrochemically active probe, i.e. ferrocene or methylene blue group. The correlation between the anodic current values and the concentrations of Hg2+ and Pb2+ ions has been established in this work. To the best of our knowledge, this is the first example of using a specific DNA aptamers for electrochemical detection of heavy metals. Each increase in concentration of 0.1 μM results in an increase in the anode current value by simple DC electrochemical test i.e (Cyclic Voltammetry), thus providing an easy way of determining Hg2+ and Pb2+concentration.

Keywords: aptamer, based, biosensor, DNA, electrochemical, highly, specific

Procedia PDF Downloads 149

Authors: Sujay Kotwale, Ramasubba Reddy M.

Abstract:

Electrocardiogram (ECG) is a non-invasive technique used to study and analyze various heart diseases. Cardiac arrhythmia is a serious heart disease which leads to death of the patients, when left untreated. An early-time detection of cardiac arrhythmia would help the doctors to do proper treatment of the heart. In the past, various algorithms and machine learning (ML) models were used to early-time detection of cardiac arrhythmia, but few of them have achieved better results. In order to improve the performance, this paper implements principal component analysis (PCA) along with XGBoost model. The PCA was implemented to the raw ECG signals which suppress redundancy information and extracted significant features. The obtained significant ECG features were fed into XGBoost model and the performance of the model was evaluated. In order to valid the proposed technique, raw ECG signals obtained from standard MIT-BIH database were employed for the analysis. The result shows that the performance of proposed method is superior to the several state-of-the-arts techniques.

Keywords: cardiac arrhythmia, electrocardiogram, principal component analysis, XGBoost

Procedia PDF Downloads 100

Authors: McClain Thiel

Abstract:

Object detection and localization has historically required two or more sensors due to the loss of information from 3D to 2D space, however, most surveillance systems currently in use in the real world only have one sensor per location. Generally, this consists of a single low-resolution camera positioned above the area under observation (mall, jewelry store, traffic camera). This is not sufficient for robust 3D tracking for applications such as security or more recent relevance, contract tracing. This paper proposes a lightweight system for 3D person tracking that requires no additional hardware, based on compressed object detection convolutional-nets, facial landmark detection, and projective geometry. This approach involves classifying the target into a demographic category and then making assumptions about the relative locations of facial landmarks from the demographic information, and from there using simple projective geometry and known constants to find the target's location in 3D space. Preliminary testing, although severely lacking, suggests reasonable success in 3D tracking under ideal conditions.

Keywords: monocular distancing, computer vision, facial analysis, 3D localization

Procedia PDF Downloads 129

Authors: Hae-Yeoun Lee

Abstract:

Mosaic refers to a technique that makes image by gathering lots of small materials in various colours. This paper presents an automatic algorithm that makes the photomosaic image using photos. The algorithm is composed of four steps: Partition and feature extraction, block matching, redundancy removal and colour adjustment. The input image is partitioned in the small block to extract feature. Each block is matched to find similar photo in database by comparing similarity with Euclidean difference between blocks. The intensity of the block is adjusted to enhance the similarity of image by replacing the value of light and darkness with that of relevant block. Further, the quality of image is improved by minimizing the redundancy of tiles in the adjacent blocks. Experimental results support that the proposed algorithm is excellent in quantitative analysis and qualitative analysis.

Keywords: photomosaic, Euclidean distance, block matching, intensity adjustment

Procedia PDF Downloads 271

Authors: Jan Schwennen, Harlad Schmid, Juergen Fleischer

Abstract:

Lightweight design plays an important role in the automotive industry. Especially the combination of metal and CFRP shows great potential for future vehicle concepts. This requires joining technologies that are cost-efficient and appropriate for the materials involved. Previous investigations show that integrating load introduction elements during CFRP part manufacturing offers great advantages in mechanical performance. However, it is not yet clear how to integrate the elements in an automated process without harming the fiber structure. In this paper, a test rig is build up to investigate the effect of different parameters during insert integration experimentally. After a short description of the experimental equipment, preliminary tests are performed to determine a set of important process parameters. Based on that, the planning of design of experiments is given. The interpretation and evaluation of the test results show that with a minimization of the insert diameter and the peak angle less harm on the fiber structure can be achieved. Furthermore, a maximization of the die diameter above the insert shows a positive effect on the fiber structure. At the end of this paper, a theoretical description of alternative peak shaping is given and then the results get validated on the basis of an industrial reference part.

Keywords: CFRP, fabrics, insert, load introduction element, integration

Procedia PDF Downloads 230

Authors: M. A. Alavianmehr, A. Tashk, A. Sodagaran

Abstract:

Modeling background and moving objects are significant techniques for video surveillance and other video processing applications. This paper presents a foreground detection algorithm that is robust against illumination changes and noise based on adaptive mixture Gaussian model (GMM), and provides a novel and practical choice for intelligent video surveillance systems using static cameras. In the previous methods, the image of still objects (background image) is not significant. On the contrary, this method is based on forming a meticulous background image and exploiting it for separating moving objects from their background. The background image is specified either manually, by taking an image without vehicles, or is detected in real-time by forming a mathematical or exponential average of successive images. The proposed scheme can offer low image degradation. The simulation results demonstrate high degree of performance for the proposed method.

Keywords: image processing, background models, video surveillance, foreground detection, Gaussian mixture model

Procedia PDF Downloads 507

Authors: Jia Li, Xing Wei, Yuchen Hong, Yang Lu

Abstract:

Detecting vehicle behavior has always been the focus of intelligent transportation, but with the explosive growth of the number of vehicles and the complexity of the road environment, the vehicle behavior videos captured by traditional surveillance have been unable to satisfy the study of vehicle behavior. The traditional method of manually labeling vehicle behavior is too time-consuming and labor-intensive, but the existing object detection and tracking algorithms have poor practicability and low behavioral location detection rate. This paper proposes a vehicle behavior detection algorithm based on the dual-stream convolution network and the multi-dimensional video dynamic detection network. In the videos, the straight-line behavior of the vehicle will default to the background behavior. The Changing lanes, turning and turning around are set as target behaviors. The purpose of this model is to automatically mark the target behavior of the vehicle from the untrimmed videos. First, the target behavior proposals in the long video are extracted through the dual-stream convolution network. The model uses a dual-stream convolutional network to generate a one-dimensional action score waveform, and then extract segments with scores above a given threshold M into preliminary vehicle behavior proposals. Second, the preliminary proposals are pruned and identified using the multi-dimensional video dynamic detection network. Referring to the hierarchical reinforcement learning, the multi-dimensional network includes a Timer module and a Spacer module, where the Timer module mines time information in the video stream and the Spacer module extracts spatial information in the video frame. The Timer and Spacer module are implemented by Long Short-Term Memory (LSTM) and start from an all-zero hidden state. The Timer module uses the Transformer mechanism to extract timing information from the video stream and extract features by linear mapping and other methods. Finally, the model fuses time information and spatial information and obtains the location and category of the behavior through the softmax layer. This paper uses recall and precision to measure the performance of the model. Extensive experiments show that based on the dataset of this paper, the proposed model has obvious advantages compared with the existing state-of-the-art behavior detection algorithms. When the Time Intersection over Union (TIoU) threshold is 0.5, the Average-Precision (MP) reaches 36.3% (the MP of baselines is 21.5%). In summary, this paper proposes a vehicle behavior detection model based on multi-dimensional dynamic detection network. This paper introduces spatial information and temporal information to extract vehicle behaviors in long videos. Experiments show that the proposed algorithm is advanced and accurate in-vehicle timing behavior detection. In the future, the focus will be on simultaneously detecting the timing behavior of multiple vehicles in complex traffic scenes (such as a busy street) while ensuring accuracy.

Keywords: vehicle behavior detection, convolutional neural network, long short-term memory, deep learning

Procedia PDF Downloads 117

Authors: Uduak Umoh, Imo Eyoh, Emmauel Nyoho

Abstract:

This paper compares fuzzy-machine learning algorithms such as Support Vector Machine (SVM), and K-Nearest Neighbor (KNN) for the predicting cases of fire outbreak. The paper uses the fire outbreak dataset with three features (Temperature, Smoke, and Flame). The data is pre-processed using Interval Type-2 Fuzzy Logic (IT2FL) algorithm. Min-Max Normalization and Principal Component Analysis (PCA) are used to predict feature labels in the dataset, normalize the dataset, and select relevant features respectively. The output of the pre-processing is a dataset with two principal components (PC1 and PC2). The pre-processed dataset is then used in the training of the aforementioned machine learning models. K-fold (with K=10) cross-validation method is used to evaluate the performance of the models using the matrices – ROC (Receiver Operating Curve), Specificity, and Sensitivity. The model is also tested with 20% of the dataset. The validation result shows KNN is the better model for fire outbreak detection with an ROC value of 0.99878, followed by SVM with an ROC value of 0.99753.

Keywords: Machine Learning Algorithms , Interval Type-2 Fuzzy Logic, Fire Outbreak, Support Vector Machine, K-Nearest Neighbour, Principal Component Analysis

Procedia PDF Downloads 168

Authors: Zeynep R. Ege, Aydin Akan, Faik N. Oktar, Betul Karademir, Oguzhan Gunduz

Abstract:

Early detection of cancer could save human life and quality in insidious cases by advanced biomedical imaging techniques. Designing targeted detection system is necessary in order to protect of healthy cells. Electrospun nanofibers are efficient and targetable nanocarriers which have important properties such as nanometric diameter, mechanical properties, elasticity, porosity and surface area to volume ratio. In the present study, indocyanine green (ICG) organic dye was stabilized and encapsulated in polymer matrix which polyethylene oxide (PEO) and chitosan (CHI) multilayer nanofibers via co-axial electrospinning method at one step. The co-axial electrospun nanofibers were characterized as morphological (SEM), molecular (FT-IR), and entrapment efficiency of Indocyanine Green (ICG) (confocal imaging). Controlled release profile of PEO/CHI/ICG nanofiber was also evaluated up to 40 hours.

Keywords: chitosan, coaxial electrospinning, controlled releasing, drug delivery, indocyanine green, polyethylene oxide

Procedia PDF Downloads 156

Authors: Sirajdin Olagoke Adeshina, Haidi Ibrahim, Akeem Salawu

Abstract:

large lecture theatres cannot be covered by a single camera but rather by a multicamera setup because of their size, shape, and seating arrangements. Although, classroom capture is achievable through a single camera. Therefore, a design and implementation of a multicamera setup for a large lecture hall were considered. Researchers have shown emphasis on the impact of class attendance taken on the academic performance of students. However, the traditional method of carrying out this exercise is below standard, especially for large lecture theatres, because of the student population, the time required, sophistication, exhaustiveness, and manipulative influence. An automated large classroom attendance system is, therefore, imperative. The common approach in this system is face detection and recognition, where known student faces are captured and stored for recognition purposes. This approach will require constant face database updates due to constant changes in the facial features. Alternatively, face counting can be performed by cropping the localized faces on the video or image into a folder and then count them. This research aims to develop a face localization-based approach to detect student faces in classroom images captured using a multicamera setup. A selected Haar-like feature cascade face detector trained with an asymmetric goal to minimize the False Rejection Rate (FRR) relative to the False Acceptance Rate (FAR) was applied on Raspberry Pi 4B. A relationship between the two factors (FRR and FAR) was established using a constant (λ) as a trade-off between the two factors for automatic adjustment during training. An evaluation of the proposed approach and the conventional AdaBoost on classroom datasets shows an improvement of 8% TPR (output result of low FRR) and 7% minimization of the FRR. The average learning speed of the proposed approach was improved with 1.19s execution time per image compared to 2.38s of the improved AdaBoost. Consequently, the proposed approach achieved 97% TPR with an overhead constraint time of 22.9s compared to 46.7s of the improved Adaboost when evaluated on images obtained from a large lecture hall (DK5) USM.

Keywords: automatic attendance, face detection, haar-like cascade, manual attendance

Procedia PDF Downloads 62

Authors: Nishant Rodrigues, Nicole Spanedda, Chilukuri K. Mohan, Arindam Chakraborty

Abstract:

A crucial objective in quantum chemistry is the computation of the energy levels of chemical systems. This task requires electron-repulsion integrals as inputs, and the steep computational cost of evaluating these integrals poses a major numerical challenge in efficient implementation of quantum chemical software. This work presents a moment-based machine-learning approach for the efficient evaluation of electron-repulsion integrals. These integrals were approximated using linear combinations of a small number of moments. Machine learning algorithms were applied to estimate the coefficients in the linear combination. A random forest approach was used to identify promising features using a recursive feature elimination approach, which performed best for learning the sign of each coefficient but not the magnitude. A neural network with two hidden layers were then used to learn the coefficient magnitudes along with an iterative feature masking approach to perform input vector compression, identifying a small subset of orbitals whose coefficients are sufficient for the quantum state energy computation. Finally, a small ensemble of neural networks (with a median rule for decision fusion) was shown to improve results when compared to a single network.

Keywords: quantum energy calculations, atomic orbitals, electron-repulsion integrals, ensemble machine learning, random forests, neural networks, feature extraction

Procedia PDF Downloads 96

Authors: Rui Mao, Heming Ji, Xiaoyu Wang

Abstract:

Keystroke dynamics are widely used in identity recognition. It has the advantage that the individual typing rhythm is difficult to imitate. It also supports continuous authentication through the keyboard without extra devices. The existing keystroke dynamics authentication methods based on machine learning have a drawback in supporting relatively complex scenarios with massive data. There are drawbacks to both feature extraction and model optimization in these methods. To overcome the above weakness, an authentication model of keystroke dynamics based on deep learning is proposed. The model uses feature vectors formed by keystroke content and keystroke time. It ensures efficient continuous authentication by cooperating attention mechanisms with the combination of CNN and Bi-LSTM. The model has been tested with Open Data Buffalo dataset, and the result shows that the FRR is 3.09%, FAR is 3.03%, and EER is 4.23%. This proves that the model is efficient and accurate on continuous authentication.

Keywords: keystroke dynamics, identity authentication, deep learning, CNN, LSTM

Procedia PDF Downloads 140

Authors: Abobaker Mohammed Qasem Farhan, Shangming Yang, Mohammed Al-Nehari

Abstract:

Pneumonia is a kind of lung disease that creates congestion in the chest. Such pneumonic conditions lead to loss of life of the severity of high congestion. Pneumonic lung disease is caused by viral pneumonia, bacterial pneumonia, or Covidi-19 induced pneumonia. The early prediction and classification of such lung diseases help to reduce the mortality rate. We propose the automatic Computer-Aided Diagnosis (CAD) system in this paper using the deep learning approach. The proposed CAD system takes input from raw computerized tomography (CT) scans of the patient's chest and automatically predicts disease classification. We designed the Hybrid Deep Learning Algorithm (HDLA) to improve accuracy and reduce processing requirements. The raw CT scans have pre-processed first to enhance their quality for further analysis. We then applied a hybrid model that consists of automatic feature extraction and classification. We propose the robust 2D Convolutional Neural Network (CNN) model to extract the automatic features from the pre-processed CT image. This CNN model assures feature learning with extremely effective 1D feature extraction for each input CT image. The outcome of the 2D CNN model is then normalized using the Min-Max technique. The second step of the proposed hybrid model is related to training and classification using different classifiers. The simulation outcomes using the publically available dataset prove the robustness and efficiency of the proposed model compared to state-of-art algorithms.

Keywords: CT scan, Covid-19, deep learning, image processing, lung disease classification

Procedia PDF Downloads 141

Authors: Elmahdi Khalil, Saad Enniari, Mostapha Zbakh

Abstract:

Cloud computing promises to increase innovation and the velocity with witch applications are deployed, all while helping any enterprise meet most IT service needs at a lower total cost of ownership and higher return investment. As the march of cloud continues, it brings both new opportunities and new security challenges. To take advantages of those opportunities while minimizing risks, we think that Intrusion Detection Systems (IDS) integrated in the cloud is one of the best existing solutions nowadays in the field. The concept of intrusion detection was known since past and was first proposed by a well-known researcher named Anderson in 1980's. Since that time IDS's are evolving. Although, several efforts has been made in the area of Intrusion Detection systems for cloud computing environment, many attacks still prevail. Therefore, the work presented in this paper proposes a multi criteria analysis and a comparative study between several IDS architectures designated to work in a cloud computing environments. To achieve this objective, in the first place we will search in the state of the art of several consistent IDS architectures designed to work in a cloud environment. Whereas, in a second step we will establish the criteria that will be useful for the evaluation of architectures. Later, using the approach of multi criteria decision analysis Mac Beth (Measuring Attractiveness by a Categorical Based Evaluation Technique we will evaluate the criteria and assign to each one the appropriate weight according to their importance in the field of IDS architectures in cloud computing. The last step is to evaluate architectures against the criteria and collecting results of the model constructed in the previous steps.

Keywords: cloud computing, cloud security, intrusion detection/prevention system, multi-criteria decision analysis

Procedia PDF Downloads 459

Authors: Nadia Masood Khan, Muhammad Salman Khan, Gul Muhammad Khan

Abstract:

Cardiologists perform cardiac auscultation to detect abnormalities in heart sounds. Since accurate auscultation is a crucial first step in screening patients with heart diseases, there is a need to develop computer-aided detection/diagnosis (CAD) systems to assist cardiologists in interpreting heart sounds and provide second opinions. In this paper different algorithms are implemented for automated heart sound classification using unsegmented phonocardiogram (PCG) signals. Support vector machine (SVM), artificial neural network (ANN) and cartesian genetic programming evolved artificial neural network (CGPANN) without the application of any segmentation algorithm has been explored in this study. The signals are first pre-processed to remove any unwanted frequencies. Both time and frequency domain features are then extracted for training the different models. The different algorithms are tested in multiple scenarios and their strengths and weaknesses are discussed. Results indicate that SVM outperforms the rest with an accuracy of 73.64%.

Keywords: pattern recognition, machine learning, computer aided diagnosis, heart sound classification, and feature extraction

Procedia PDF Downloads 246

Authors: Samhita Mummadi, Sree Divya Nagalli, Harshini Vemuri, Saketh Charan Nakka, Sumesh K. J.

Abstract:

One of the most significant challenges faced by people in today’s digital era is an alarming increase in fraudulent activities on online platforms. The fascination with online shopping to avoid long queues in shopping malls, the availability of a variety of products, and home delivery of goods have paved the way for a rapid increase in vast online shopping platforms. This has had a major impact on increasing fraudulent activities as well. This loop of online shopping and transactions has paved the way for fraudulent users to commit fraud. For instance, consider a store that orders thousands of products all at once, but what’s fishy about this is the massive number of items purchased and their transactions turning out to be fraud, leading to a huge loss for the seller. Considering scenarios like these underscores the urgent need to introduce machine learning approaches to combat fraud in online shopping. By leveraging robust algorithms, namely KNN, Decision Trees, and Random Forest, which are highly effective in generating accurate results, this research endeavors to discern patterns indicative of fraudulent behavior within transactional data. Introducing a comprehensive solution to this problem in order to empower e-commerce administrators in timely fraud detection and prevention is the primary motive and the main focus. In addition to that, sentiment analysis is harnessed in the model so that the e-commerce admin can tailor to the customer’s and consumer’s concerns, feedback, and comments, allowing the admin to improve the user’s experience. The ultimate objective of this study is to ramp up online shopping platforms against fraud and ensure a safer shopping experience. This paper underscores a model accuracy of 84%. All the findings and observations that were noted during our work lay the groundwork for future advancements in the development of more resilient and adaptive fraud detection systems, which will become crucial as technologies continue to evolve.

Keywords: behavior analysis, feature selection, Fraudulent pattern recognition, imbalanced classification, transactional anomalies

Procedia PDF Downloads 8

Authors: Jianhong Xiang, Rui Sun, Linyu Wang

Abstract:

In recent years, due to the continuous improvement of deep learning theory, Convolutional Neural Network (CNN) has played a great superior performance in the research of Hyperspectral Image (HSI) classification. Since HSI has rich spatial-spectral information, only utilizing a single dimensional or single size convolutional kernel will limit the detailed feature information received by CNN, which limits the classification accuracy of HSI. In this paper, we design a multi-scale CNN with MLP based on residual and attention modules (INRAM-3DCNN) for the HSI classification task. We propose to use multiple 3D convolutional kernels to extract the packet feature information and fully learn the spatial-spectral features of HSI while designing residual 3D convolutional branches to avoid the decline of classification accuracy due to network degradation. Secondly, we also design the 2D Inception module with a joint channel attention mechanism to quickly extract key spatial feature information at different scales of HSI and reduce the complexity of the 3D model. Due to the high parallel processing capability and nonlinear global action of the Multilayer Perceptron (MLP), we use it in combination with the previous CNN structure for the final classification process. The experimental results on two HSI datasets show that the proposed INRAM-3DCNN method has superior classification performance and can perform the classification task excellently.

Keywords: INRAM-3DCNN, residual, channel attention, hyperspectral image classification

Procedia PDF Downloads 67

Authors: Mounia El Jaouhari, Mira Goral, Samir Diouny

Abstract:

Introduction: Previous research has indicated that language impairments are recognized as a feature of many neurodegenerative disorders, including non-language-led dementia subtypes such as Alzheimer´s disease (AD). In this preliminary study, the focal aim is to quantify the semantic content of naming and connected speech samples of Moroccan patients diagnosed with AD using two tasks taken from the culturally adapted and validated Moroccan version of the Boston Diagnostic Aphasia Examination. Methods: Five individuals with AD and five neurologically healthy individuals matched for age, gender, and education will participate in the study. Participants with AD will be diagnosed on the basis of the Moroccan version of the Diagnostic and Statistial Manual of Mental Disorders (DSM-4) screening test, the Moroccan version of the Mini Mental State Examination (MMSE) test scores, and neuroimaging analyses. The participants will engage in two tasks taken from the MDAE-SF: 1) Picture description and 2) Naming. Expected findings: Consistent with previous studies conducted on English speaking AD patients, we expect to find significant word production and retrieval impairments in AD patients in all measures. Moreover, we expect to find category fluency impairments that further endorse semantic breakdown accounts. In sum, not only will the findings of the current study shed more light on the locus of word retrieval impairments noted in AD, but also reflect the nature of Arabic morphology. In addition, the error patterns are expected to be similar to those found in previous AD studies in other languages.

Keywords: alzheimer's disease, anomia, connected speech, semantic impairments, moroccan arabic

Procedia PDF Downloads 132

Authors: B. Lokuketagoda, M. Weerakoon, U. Madushan, A. N. Senaratne, K. Y. Abeywardena

Abstract:

Ransomware has become a common threat in past few years and the recent threat reports show an increase of growth in Ransomware infections. Researchers have identified different variants of Ransomware families since 2015. Lack of knowledge of the user about the threat is a major concern. Ransomware detection methodologies are still growing through the industry. Email is the easiest method to send Ransomware to its victims. Uninformed users tend to click on links and attachments without much consideration assuming the emails are genuine. As a solution to this in this paper R-Killer Ransomware detection tool is introduced. Tool can be integrated with existing email services. The core detection Engine (CDE) discussed in the paper focuses on separating suspicious samples from emails and handling them until a decision is made regarding the suspicious mail. It has the capability of preventing execution of identified ransomware processes. On the other hand, Sandboxing and URL analyzing system has the capability of communication with public threat intelligence services to gather known threat intelligence. The R-Killer has its own mechanism developed in its Proactive Monitoring System (PMS) which can monitor the processes created by downloaded email attachments and identify potential Ransomware activities. R-killer is capable of gathering threat intelligence without exposing the user’s data to public threat intelligence services, hence protecting the confidentiality of user data.

Keywords: ransomware, deep learning, recurrent neural networks, email, core detection engine

Procedia PDF Downloads 198

Authors: Shen Jian, Hu Jie, Qi Jin, Liu Wei Jie, Chen Ji Yi, Peng Ying Hong

Abstract:

In order to settle the problem of acquiring case in biological related to design problems, a biometrics instance acquisition method based on text mining is presented. Through the construction of corpus text vector space and knowledge mining, the feature selection, similarity measure and case retrieval method of text in the field of biology are studied. First, we establish a vector space model of the corpus in the biological field and complete the preprocessing steps. Then, the corpus is retrieved by using the vector space model combined with the functional keywords to obtain the biological domain examples related to the design problems. Finally, we verify the validity of this method by taking the example of text.

Keywords: text mining, vector space model, feature selection, biologically inspired design

Procedia PDF Downloads 250

Authors: Mohamad Kassab, Amal El Fallah Seghrouchni, Frederic Barbaresco, Raed Abu Zitar

Abstract:

Detecting objects such as drones is a challenging task as their relative size and maneuvering capabilities deceive machine learning models and cause them to misclassify drones as birds or other objects. In this work, we investigate applying several deep learning techniques to benchmark real data sets of flying drones. A deep learning paradigm is proposed for the purpose of mitigating the complexity of those systems. The proposed paradigm consists of a hybrid between the AdderNet deep learning paradigm and the Single Shot Detector (SSD) paradigm. The goal was to minimize multiplication operations numbers in the filtering layers within the proposed system and, hence, reduce complexity. Some standard machine learning technique, such as SVM, is also tested and compared to other deep learning systems. The data sets used for training and testing were either complete or filtered in order to remove the images with mall objects. The types of data were RGB or IR data. Comparisons were made between all these types, and conclusions were presented.

Keywords: drones detection, deep learning, birds versus drones, precision of detection, AdderNet

Procedia PDF Downloads 166