Search results for: feature weighting

Authors: Hanlin Liu, Hua Li, Yintan AI

Abstract:

Network performance prediction (NPP) is essential for the management and optimization of software-defined networking (SDN) and contributes to improving the quality of service (QoS) in SDN to meet the requirements of users. Although current deep learning-based methods can achieve high effectiveness, they still suffer from some problems, such as difficulty in capturing global information of the network, inefficiency in modeling end-to-end network performance, and inadequate graph feature extraction. To cope with these issues, our proposed Graphormer-based architecture for NPP leverages the powerful graph representation ability of Graphormer to effectively model the graph structure data, and a node-edge transformation algorithm is designed to transfer the feature extraction object from nodes to edges, thereby effectively extracting the end-to-end performance characteristics of the network. Moreover, routing oriented centrality measure coefficient for nodes and edges is proposed respectively to assess their importance and influence within the graph. Based on this coefficient, an enhanced feature extraction method and an advanced centrality encoding strategy are derived to fully extract the structural information of the graph. Experimental results on three public datasets demonstrate that the proposed GraphNPP architecture can achieve state-of-the-art results compared to current NPP methods.

Keywords: software-defined networking, network performance prediction, Graphormer, graph neural network

Procedia PDF Downloads 12

Authors: Jiaqi Yan, Yani Shi

Abstract:

With the growing popularity of bitcoin transactions, criminals have exploited the bitcoin like cryptocurrencies, and cybercriminals such as money laundering have thrived. Unlike traditional currencies, the Internet-based virtual currencies can be used anonymously via the blockchain technology underpinning. In this paper, we analyze the double-edged sword features of blockchain technology in the context of money laundering. In particular, the traceability feature of blockchain-based system facilitates a level of governance, while the decentralization feature of blockchain-based system may bring governing difficulties. Based on the analysis, we propose guidelines for policy makers in governing blockchain-based cryptocurrency systems.

Keywords: cryptocurrency, money laundering, blockchain, decentralization, traceability

Procedia PDF Downloads 164

Authors: Bernd Kiefer, Abraham Gebru Tesfay, Dietrich Klakow

Abstract:

The motivation of our work is to detect different terrain types traversed by a robot based on acoustic data from the robot-terrain interaction. Different acoustic features and classifiers were investigated, such as Mel-frequency cepstral coefficient and Gamma-tone frequency cepstral coefficient for the feature extraction, and Gaussian mixture model and Feed forward neural network for the classification. We analyze the system’s performance by comparing our proposed techniques with some other features surveyed from distinct related works. We achieve precision and recall values between 87% and 100% per class, and an average accuracy at 95.2%. We also study the effect of varying audio chunk size in the application phase of the models and find only a mild impact on performance.

Keywords: acoustic features, autonomous robots, feature extraction, terrain classification

Procedia PDF Downloads 335

Authors: Belaynesh Chekol, Numan Çelebi

Abstract:

The main purpose of this work is to recognize individual characters extracted from natural scene images using scale invariant feature transform (SIFT) features as an input to K-nearest neighbor (KNN); a classification learner algorithm. For this task, 1,068 and 78 images of English alphabet characters taken from Chars74k data set is used to train and test the classifier respectively. For each character image, We have generated describing features by using SIFT algorithm. This set of features is fed to the learner so that it can recognize and label new images of English characters. Two types of KNN (fine KNN and weighted KNN) were trained and the resulted classification accuracy is 56.9% and 56.5% respectively. The training time taken was the same for both fine and weighted KNN.

Keywords: character recognition, KNN, natural scene image, SIFT

Procedia PDF Downloads 254

Authors: A. Degale Desta, Cheng Jian

Abstract:

Deep learning application in computer vision is rapidly advancing, giving it the ability to monitor the public and quickly identify potentially anomalous behaviour from crowd scenes. Therefore, the purpose of the current work is to improve the performance of safety of people in crowd events from panic behaviour through introducing the innovative idea of Aggregation of Ensembles (AOE), which makes use of the pre-trained ConvNets and a pool of classifiers to find anomalies in video data with packed scenes. According to the theory of algorithms that applied K-means, KNN, CNN, SVD, and Faster-CNN, YOLOv5 architectures learn different levels of semantic representation from crowd videos; the proposed approach leverages an ensemble of various fine-tuned convolutional neural networks (CNN), allowing for the extraction of enriched feature sets. In addition to the above algorithms, a long short-term memory neural network to forecast future feature values and a handmade feature that takes into consideration the peculiarities of the crowd to understand human behavior. On well-known datasets of panic situations, experiments are run to assess the effectiveness and precision of the suggested method. Results reveal that, compared to state-of-the-art methodologies, the system produces better and more promising results in terms of accuracy and processing speed.

Keywords: action recognition, computer vision, crowd detecting and tracking, deep learning

Procedia PDF Downloads 122

Authors: Nitin Shravan, Sudarsun Santhiappan, B. Sivaselvan

Abstract:

Subsection identification, in the context of Electronic Health Records (EHRs), is identifying the important sections for down-stream tasks like auto-coding. In this work, we classify the text present in EHRs according to their information, using machine learning and deep learning techniques. We initially describe briefly about the problem and formulate it as a text classification problem. Then, we discuss upon the methods from the literature. We try two approaches - traditional feature extraction based machine learning methods and deep learning methods. Through experiments on a private dataset, we establish that the deep learning methods perform better than the feature extraction based Machine Learning Models.

Keywords: deep learning, machine learning, semantic clinical classification, subsection identification, text classification

Procedia PDF Downloads 182

Authors: Syeda Mainaaz Unnisa, Deepa Suresh

Abstract:

Due to the increase in usage of public domain channels, such as the internet, and communication technology, there is a concern about the protection of intellectual property and security threats. This interest has led to growth in researching and implementing techniques for information hiding. Steganography is the art and science of hiding information in a private manner such that its existence cannot be recognized. Communication using steganographic techniques makes not only the secret message but also the presence of hidden communication, invisible. Steganalysis is the art of detecting the presence of this hidden communication. Parallel to steganography, steganalysis is also gaining prominence, since the detection of hidden messages can prevent catastrophic security incidents from occurring. Steganalysis can also be incredibly helpful in identifying and revealing holes with the current steganographic techniques, which makes them vulnerable to attacks. Through the formulation of new effective steganalysis methods, further research to improve the resistance of tested steganography techniques can be developed. Feature-based steganalysis method for JPEG images calculates the features of an image using the L1 norm of the difference between a stego image and the calibrated version of the image. This calibration can help retrieve some of the parameters of the cover image, revealing the variations between the cover and stego image and enabling a more accurate detection. Applying this method to various steganographic schemes, experimental results were compared and evaluated to derive conclusions and principles for more protected JPEG steganography.

Keywords: cover image, feature-based steganalysis, information hiding, steganalysis, steganography

Procedia PDF Downloads 185

Authors: Nalini C. Iyer, Shraddha H., Anagha B. Varahamurthy, Dikshith C. S., Ishwar G. Kubasad, Vinayak I. Karalatti, Pavan B. Mulimani

Abstract:

The current scenario of the pandemic due to COVID-19 has led to the awareness among the people to avoid unneces-sary contact in public places. There is a need to avoid contact with physical objects to stop the spreading of infection. The contactless feature has to be included in the systems in public places wherever possible. For example, attendance monitoring systems with fingerprint biometric can be replaced with a contactless feature. One more important protocol followed in the current situation is temperature monitoring and screening. The paper describes an attendance system with a contactless feature and temperature screening for the university. The system displays a QR code to scan, which redirects to the student login web page only if the location is valid (the location where the student scans the QR code should be the location of the display of the QR code). Once the student logs in, the temperature of the student is scanned by the contactless temperature sensor (mlx90614) with an error of 0.5°C. If the temperature falls in the range of the desired value (range of normal body temperature), then the attendance of the student is marked as present, stored in the database, and the door opens automatically. The attendance is marked as absent in the other case, alerted with the display of temperature, and the door remains closed. The door is automated with the help of a servomotor. To avoid the proxy, IR sensors are used to count the number of students in the classroom. The hardware system consisting of a contactless temperature sensor and IR sensor is implemented on the microcontroller, NodeMCU.

Keywords: NodeMCU, IR sensor, attendance monitoring, contactless, temperature

Procedia PDF Downloads 156

Authors: Kilari Nikhil, Ankur Tibrewal, Srinivas Kruthiventi S. S.

Abstract:

Conventional speaker identification systems often fall short of capturing the diverse variations present in speech data due to fixed-scale architectures. In this research, we propose a CNN-based architecture, USENet, designed to overcome these limitations. Leveraging two key techniques, our approach achieves superior performance on the VoxCeleb 1 Dataset without any pre-training. Firstly, we adopt a U-net-inspired design to extract features at multiple scales, empowering our model to capture speech characteristics effectively. Secondly, we introduce the squeeze and excitation block to enhance spatial feature learning. The proposed architecture showcases significant advancements in speaker identification, outperforming existing methods, and holds promise for future research in this domain.

Keywords: multi-scale feature extraction, squeeze and excitation, VoxCeleb1 speaker identification, mel-spectrograms, USENet

Procedia PDF Downloads 41

Authors: Kun Xu, Yuan Xu, Jia Qiao

Abstract:

The document detection plays an important role in optical character recognition and text analysis. Because the traditional detection methods have weak generalization ability, and deep neural network has complex structure and large number of parameters, which cannot be well applied in mobile devices, this paper proposes a lightweight Document Corner Detection Network (DCDNet). DCDNet is a two-stage architecture. The first stage with Encoder-Decoder structure adopts depthwise separable convolution to greatly reduce the network parameters. After introducing the Feature Attention Union (FAU) module, the second stage enhances the feature information of spatial and channel dim and adaptively adjusts the size of receptive field to enhance the feature expression ability of the model. Aiming at solving the problem of the large difference in the number of pixel distribution between corner and non-corner, Weighted Binary Cross Entropy Loss (WBCE Loss) is proposed to define corner detection problem as a classification problem to make the training process more efficient. In order to make up for the lack of Dataset of document corner detection, a Dataset containing 6620 images named Document Corner Detection Dataset (DCDD) is made. Experimental results show that the proposed method can obtain fast, stable and accurate detection results on DCDD.

Keywords: document detection, corner detection, attention mechanism, lightweight

Procedia PDF Downloads 324

Authors: Fathi Kallel, Abdulelah Alabd Uljabbar, Abdulrahman Aldukhail, Abdulaziz Alomran

Abstract:

The brain is an important organ in our body since it is responsible about the majority actions such as vision, memory, etc. However, different diseases such as Alzheimer and tumors could affect the brain and conduct to a partial or full disorder. Regular diagnosis are necessary as a preventive measure and could help doctors to early detect a possible trouble and therefore taking the appropriate treatment, especially in the case of brain tumors. Different imaging modalities are proposed for diagnosis of brain tumor. The powerful and most used modality is the Magnetic Resonance Imaging (MRI). MRI images are analyzed by doctor in order to locate eventual tumor in the brain and describe the appropriate and needed treatment. Diverse image processing methods are also proposed for helping doctors in identifying and analyzing the tumor. In fact, a large Computer Aided Diagnostic (CAD) tools including developed image processing algorithms are proposed and exploited by doctors as a second opinion to analyze and identify the brain tumors. In this paper, we proposed a new advanced CAD for brain tumor identification, classification and feature extraction. Our proposed CAD includes three main parts. Firstly, we load the brain MRI. Secondly, a robust technique for brain tumor extraction is proposed. This technique is based on both Discrete Wavelet Transform (DWT) and Principal Component Analysis (PCA). DWT is characterized by its multiresolution analytic property, that’s why it was applied on MRI images with different decomposition levels for feature extraction. Nevertheless, this technique suffers from a main drawback since it necessitates a huge storage and is computationally expensive. To decrease the dimensions of the feature vector and the computing time, PCA technique is considered. In the last stage, according to different extracted features, the brain tumor is classified into either benign or malignant tumor using Support Vector Machine (SVM) algorithm. A CAD tool for brain tumor detection and classification, including all above-mentioned stages, is designed and developed using MATLAB guide user interface.

Keywords: MRI, brain tumor, CAD, feature extraction, DWT, PCA, classification, SVM

Procedia PDF Downloads 222

Authors: Jingting Luo, Yong Wang, Ying Wang

Abstract:

Pedestrian detection in image or video data is a very important and challenging task in security surveillance. The difficulty of this task is to locate and detect pedestrians of different scales in complex scenes accurately. To solve these problems, a deep neural network (RT-YOLOv3) is proposed to realize real-time pedestrian detection at different scales in security monitoring. RT-YOLOv3 improves the traditional YOLOv3 algorithm. Firstly, the deep residual network is added to extract vehicle features. Then six convolutional neural networks with different scales are designed and fused with the corresponding scale feature maps in the residual network to form the final feature pyramid to perform pedestrian detection tasks. This method can better characterize pedestrians. In order to further improve the accuracy and generalization ability of the model, a hybrid pedestrian data set training method is used to extract pedestrian data from the VOC data set and train with the INRIA pedestrian data set. Experiments show that the proposed RT-YOLOv3 method achieves 93.57% accuracy of mAP (mean average precision) and 46.52f/s (number of frames per second). In terms of accuracy, RT-YOLOv3 performs better than Fast R-CNN, Faster R-CNN, YOLO, SSD, YOLOv2, and YOLOv3. This method reduces the missed detection rate and false detection rate, improves the positioning accuracy, and meets the requirements of real-time detection of pedestrian objects.

Keywords: pedestrian detection, feature detection, convolutional neural network, real-time detection, YOLOv3

Procedia PDF Downloads 113

Authors: Sokkhey Phauk, Takeo Okazaki

Abstract:

The challenging task in educational institutions is to maximize the high performance of students and minimize the failure rate of poor-performing students. An effective method to leverage this task is to know student learning patterns with highly influencing factors and get an early prediction of student learning outcomes at the timely stage for setting up policies for improvement. Educational data mining (EDM) is an emerging disciplinary field of data mining, statistics, and machine learning concerned with extracting useful knowledge and information for the sake of improvement and development in the education environment. The study is of this work is to propose techniques in EDM and integrate it into a web-based system for predicting poor-performing students. A comparative study of prediction models is conducted. Subsequently, high performing models are developed to get higher performance. The hybrid random forest (Hybrid RF) produces the most successful classification. For the context of intervention and improving the learning outcomes, a feature selection method MICHI, which is the combination of mutual information (MI) and chi-square (CHI) algorithms based on the ranked feature scores, is introduced to select a dominant feature set that improves the performance of prediction and uses the obtained dominant set as information for intervention. By using the proposed techniques of EDM, an academic performance prediction system (APPS) is subsequently developed for educational stockholders to get an early prediction of student learning outcomes for timely intervention. Experimental outcomes and evaluation surveys report the effectiveness and usefulness of the developed system. The system is used to help educational stakeholders and related individuals for intervening and improving student performance.

Keywords: academic performance prediction system, educational data mining, dominant factors, feature selection method, prediction model, student performance

Procedia PDF Downloads 85

Authors: Youngjae Jin, Daeshik Kim

Abstract:

This paper describes a cycle accurate simulation results of weight values learned by an auto-encoder behavior model in terms of pre-route simulation. Given the results we visualized the first layer representations with natural images. Many common deep learning threads have focused on learning high-level abstraction of unlabeled raw data by unsupervised feature learning. However, in the process of handling such a huge amount of data, the learning method’s computation complexity and time limited advanced research. These limitations came from the fact these algorithms were computed by using only single core CPUs. For this reason, parallel-based hardware, FPGAs, was seen as a possible solution to overcome these limitations. We adopted and simulated the ready-made auto-encoder to design a behavior model in Verilog HDL before designing hardware. With the auto-encoder behavior model pre-route simulation, we obtained the cycle accurate results of the parameter of each hidden layer by using MODELSIM. The cycle accurate results are very important factor in designing a parallel-based digital hardware. Finally this paper shows an appropriate operation of behavior model based pre-route simulation. Moreover, we visualized learning latent representations of the first hidden layer with Kyoto natural image dataset.

Keywords: auto-encoder, behavior model simulation, digital hardware design, pre-route simulation, Unsupervised feature learning

Procedia PDF Downloads 417

Authors: Asad Abbas, Muhammad Fezan Afzal, Muhammad Latif Anjum, Muhammad Azmat

Abstract:

The Internet of Things (IoT) is used to link up real objects that use the internet to interact. IoT applications allow handling and operating the equipment in accordance with environmental needs, such as transportation and healthcare. IoT devices are linked together via a number of agents that act as a middleman for communications. The operation of a heat sensor differs indoors and outside because agent applications work with environmental variables. In this article, we suggest using Software Product Line (SPL) to model IoT agents and applications' features on an XML-based basis. The contextual diversity within the same domain of application can be handled, and the reusability of features is increased by XML-based feature modelling. For the purpose of managing contextual variability, we have embraced XML for modelling IoT applications, agents, and internet-connected devices.

Keywords: IoT agents, IoT applications, software product line, feature model, XML

Procedia PDF Downloads 57

Authors: Silvia Faroni, Olivier Le Courtois, Krzysztof Ostaszewski

Abstract:

While a lot of research concentrates on the merits of VaR and TCE, which are the two most classic risk indicators used by financial institutions, little has been written on explaining why regulators favor the choice of VaR or TCE in their set of rules. In this paper, we investigate the preferences of regulators with the aim of understanding why, for instance, a VaR with a given confidence level is ultimately retained. Further, this paper provides equivalence rules that explain how a given choice of VaR can be equivalent to a given choice of TCE. Then, we introduce a new risk indicator that extends TCE by providing a more versatile weighting of the constituents of probability distribution tails. All of our results are illustrated using the generalized Pareto distribution.

Keywords: generalized pareto distribution, generalized tail conditional expectation, regulator preferences, risk measure

Procedia PDF Downloads 134

Authors: Deeman Yousif Mahmood, Mohammed Abdullah Hussein

Abstract:

The goal of a network-based intrusion detection system is to classify activities of network traffics into two major categories: normal and attack (intrusive) activities. Nowadays, data mining and machine learning plays an important role in many sciences; including intrusion detection system (IDS) using both supervised and unsupervised techniques. However, one of the essential steps of data mining is feature selection that helps in improving the efficiency, performance and prediction rate of proposed approach. This paper applies unsupervised K-means clustering algorithm with information gain (IG) for feature selection and reduction to build a network intrusion detection system. For our experimental analysis, we have used the new NSL-KDD dataset, which is a modified dataset for KDDCup 1999 intrusion detection benchmark dataset. With a split of 60.0% for the training set and the remainder for the testing set, a 2 class classifications have been implemented (Normal, Attack). Weka framework which is a java based open source software consists of a collection of machine learning algorithms for data mining tasks has been used in the testing process. The experimental results show that the proposed approach is very accurate with low false positive rate and high true positive rate and it takes less learning time in comparison with using the full features of the dataset with the same algorithm.

Keywords: information gain (IG), intrusion detection system (IDS), k-means clustering, Weka

Procedia PDF Downloads 263

Authors: Rajkumar Kolangarakandy

Abstract:

Feature extraction and selection is the primary part of any mammogram classification algorithms. The choice of feature, attribute or measurements have an important influence in any classification system. Discrete Wavelet Transformation (DWT) coefficients are one of the prominent features for representing images in frequency domain. The features obtained after the decomposition of the mammogram images using wavelet transformations have higher dimension. Even though the features are higher in dimension, they were highly correlated and redundant in nature. The dimensionality reduction techniques play an important role in selecting the optimum number of features from the higher dimension data, which are highly correlated. PCA is a mathematical tool that reduces the dimensionality of the data while retaining most of the variation in the dataset. In this paper, a multilevel classification of mammogram images using reduced discrete wavelet transformation coefficients and lazy classifiers is proposed. The classification is accomplished in two different levels. In the first level, mammogram ROIs extracted from the dataset is classified as normal and abnormal types. In the second level, all the abnormal mammogram ROIs is classified into benign and malignant too. A further classification is also accomplished based on the variation in structure and intensity distribution of the images in the dataset. The Lazy classifiers called Kstar, IBL and LWL are used for classification. The classification results obtained with the reduced feature set is highly promising and the result is also compared with the performance obtained without dimension reduction.

Keywords: PCA, wavelet transformation, lazy classifiers, Kstar, IBL, LWL

Procedia PDF Downloads 312

Authors: Saad M. Darwish, Mohamed A. El-Iskandarani, Guitar M. Shawkat

Abstract:

Nowadays, the amount of available multimedia data is continuously on the rise. The need to find a required image for an ordinary user is a challenging task. Content based image retrieval (CBIR) computes relevance based on the visual similarity of low-level image features such as color, textures, etc. However, there is a gap between low-level visual features and semantic meanings required by applications. The typical method of bridging the semantic gap is through the automatic image annotation (AIA) that extracts semantic features using machine learning techniques. In this paper, a multi-label image annotation system guided by Firefly and Bayesian method is proposed. Firstly, images are segmented using the maximum variance intra cluster and Firefly algorithm, which is a swarm-based approach with high convergence speed, less computation rate and search for the optimal multiple threshold. Feature extraction techniques based on color features and region properties are applied to obtain the representative features. After that, the images are annotated using translation model based on the Net Bayes system, which is efficient for multi-label learning with high precision and less complexity. Experiments are performed using Corel Database. The results show that the proposed system is better than traditional ones for automatic image annotation and retrieval.

Keywords: feature extraction, feature selection, image annotation, classification

Procedia PDF Downloads 557

Authors: Salim H. Al Salmani, Kevin Tansey, Mohammed S. Ozigis

Abstract:

The study of the growth of built-up areas and settlement expansion is a major exercise that city managers seek to undertake to establish previous and current developmental trends. This is to ensure that there is an equal match of settlement expansion needs to the appropriate levels of services and infrastructure required. This research aims at demonstrating the potential of satellite image processing technique, harnessing the utility of single feature probability-object based image analysis technique in assessing the urban growth dynamics of the Muscat Governorate in Oman for the period 1990, 2002 and 2013. This need is fueled by the continuous expansion of the Muscat Governorate beyond predicted levels of infrastructural provision. Landsat Images of the years 1990, 2002 and 2013 were downloaded and preprocessed to forestall appropriate radiometric and geometric standards. A novel approach of probability filtering of the target feature segment was implemented to derive the spatial extent of the final Built-Up Area of the Muscat governorate for the three years period. This however proved to be a useful technique as high accuracy assessment results of 55%, 70%, and 71% were recorded for the Urban Landcover of 1990, 2002 and 2013 respectively. Furthermore, the Normalized Differential Built – Up Index for the various images were derived and used to consolidate the results of the SFP-OBIA through a linear regression model and visual comparison. The result obtained showed various hotspots where urbanization have sporadically taken place. Specifically, settlement in the districts (Wilayat) of AL-Amarat, Muscat, and Qurayyat experienced tremendous change between 1990 and 2002, while the districts (Wilayat) of AL-Seeb, Bawshar, and Muttrah experienced more sporadic changes between 2002 and 2013.

Keywords: urban growth, single feature probability, object based image analysis, landcover change

Procedia PDF Downloads 250

Authors: Nikhat Nawaz, S. Srinivasulu, P. Kesava Rao

Abstract:

Feature extraction plays an important role in many remote sensing applications. Automatic extraction of water bodies is of great significance in many remote sensing applications like change detection, image retrieval etc. This paper presents a procedure for automatic extraction of water information from remote sensing images. The algorithm uses the relative location of R-colour component of the chromaticity diagram. This method is then integrated with the effectiveness of the spatial scale transformation of whole method. The whole method is based on water index fitted from spectral library. Experimental results demonstrate the improved accuracy and effectiveness of the integrated method for automatic extraction of water bodies.

Keywords: feature extraction, remote sensing, image retrieval, chromaticity, water index, spectral library, integrated method

Procedia PDF Downloads 341

Authors: Edward K. Boahen, Brunel E. Bouya-Moko, Changda Wang

Abstract:

The major threat to online social network (OSN) users is account compromisation. Spammers now spread malicious messages by exploiting the trust relationship established between account owners and their friends. The challenge in detecting a compromised account by service providers is validating the trusted relationship established between the account owners, their friends, and the spammers. Another challenge is the increase in required human interaction with the feature selection. Research available on supervised learning (machine learning) has limitations with the feature selection and accounts that cannot be profiled, like application programming interface (API). Therefore, this paper discusses the various behaviours of the OSN users and the current approaches in detecting a compromised OSN account, emphasizing its limitations and challenges. We propose a deep learning approach that addresses and resolve the constraints faced by the previous schemes. We detailed our proposed optimized nonsymmetric deep auto-encoder (OPT_NDAE) for unsupervised feature learning, which reduces the required human interaction levels in the selection and extraction of features. We evaluated our proposed classifier using the NSL-KDD and KDDCUP'99 datasets in a graphical user interface enabled Weka application. The results obtained indicate that our proposed approach outperformed most of the traditional schemes in OSN compromised account detection with an accuracy rate of 99.86%.

Keywords: computer security, network security, online social network, account compromisation

Procedia PDF Downloads 90

Authors: Paulo Fernando Silva Filho, Elcio Hideiti Shiguemori

Abstract:

The selection of specific landmarks for an Unmanned Aerial Vehicles’ Visual Navigation systems based on Automatic Landmark Recognition has significant influence on the precision of the system’s estimated position. At the same time, manual selection of the landmarks does not guarantee a high recognition rate, which would also result on a poor precision. This work aims to develop an automatic landmark selection that will take the image of the flight area and identify the best landmarks to be recognized by the Visual Navigation Landmark Recognition System. The criterion to select a landmark is based on features detected by ORB or AKAZE and edges information on each possible landmark. Results have shown that disposition of possible landmarks is quite different from the human perception.

Keywords: clustering, edges, feature points, landmark selection, X-means

Procedia PDF Downloads 247

Authors: Rammah Abdlbagi, Egmen Tazcan, Kiriti Tripathi, Vinayagam Sudhakar, Thomas Swallow, Aakash Pai

Abstract:

Introduction and Objectives: MRI has an increasing role in the diagnosis and staging of prostate cancer. Multiparametric MRI includes multiple sequences, including T2 weighting, diffusion weighting, and dynamic contrast enhancement (DCE). Administration of DCE is expensive, time-consuming, and requires medical supervision due to the risk of anaphylaxis. Biparametric MRI (bpMRI), without DCE, overcomes many of these issues; however, there is conflicting data on its accuracy. Furthermore, data on the concordance between bpMRI lesion and pathology specimen, as well as the rates of cancer stage upgrading after surgery, is limited within the available literature. This study aims to examine the diagnostic test accuracy of bpMRI in the diagnosis of prostate cancer and radiological assessment of prostate cancer staging. Specifically, we aimed to evaluate the ability of bpMRI to accurately localise malignant lesions to better understand its accuracy and application in MRI-targeted biopsies. Materials and Methods: One hundred and forty patients who underwent bpMRI prior to radical prostatectomy (RP) were retrospectively reviewed from a single institution. Histological grade from the prostate biopsy was compared with surgical specimens from RP. Clinically significant prostate cancer (csPCa) was defined as Gleason grade group ≥2. bpMRI staging was compared with RP histology. Results: Overall sensitivity of bpMRI in diagnosing csPCa independent of location and staging was 98.87%. Of the 140 patients, 29 (20.71%) had their prostate biopsy histology upgraded at RP. 61 (43.57%) patients had csPca noted on RP specimens in areas that were not identified on the bpMRI. 55 (39.29%) had upstaging after RP from the original staging with bpMRI. Conclusions: Whilst the overall sensitivity of bpMRI in predicting any clinically significant cancer was good, there was notably poor concordance in the location of the tumour between bpMRI and eventual RP specimen. The results suggest that caution should be exercised when using bpMRI for targeted prostate biopsies and validates the continued role of systemic biopsies. Furthermore, a significant number of patients were upstaged at RP from their original staging with bpMRI. Based on these findings, bpMRI results should be interpreted with caution and can underestimate TNM stage, requiring careful consideration of treatment strategy.

Keywords: biparametric MRI, Ca prostate, staging, post prostatectomy histology

Procedia PDF Downloads 39

Authors: Baptiste Bouvier

Abstract:

While we are constantly flooded with stimuli in daily life, attention allows us to select the ones we specifically process and ignore the others. Some salient stimuli may sometimes pass this filter independently of our will, in a "bottom-up" way. The role of the acoustic properties of the timbre of a sound on its salience, i.e., its ability to capture the attention of a listener, is still not well understood. We implemented a paradigm called the "additional singleton paradigm", in which participants have to discriminate targets according to their duration. This task is perturbed (higher error rates and longer response times) by the presence of an irrelevant additional sound, of which we can manipulate a feature of our choice at equal loudness. This allows us to highlight the influence of the timbre features of a sound stimulus on its salience at equal loudness. We have shown that a stimulus that is brighter than the others but not louder leads to an attentional capture phenomenon in this framework. This work opens the door to the study of the influence of any timbre feature on salience.

Keywords: attention, audition, bottom-up attention, psychoacoustics, salience, timbre

Procedia PDF Downloads 134

Authors: Somaya Adwan, Rasha Majed, Lamya'a Majed, Hamzah Arof

Abstract:

In order to produce images with whole body parts, X-ray of different portions of the body parts is assembled using image stitching methods. A new method for image stitching that exploits mutually feature based method and direct based method to identify and merge pairs of X-ray medical images is presented in this paper. The performance of the proposed method based on this hybrid approach is investigated in this paper. The ability of the proposed method to stitch and merge the overlapping pairs of images is demonstrated. Our proposed method display comparable if not superior performance to other feature based methods that are mentioned in the literature on the standard databases. These results are promising and demonstrate the potential of the proposed method for further development to tackle more advanced stitching problems.

Keywords: image stitching, direct based method, panoramic image, X-ray

Procedia PDF Downloads 514

Authors: Saeedeh Barzegar Khalilsaraei, Manoocheher Kelarestaghi, Farshad Eshghi

Abstract:

The vehicle color, as a prominent and stable feature, helps to identify a vehicle more accurately. As a result, vehicle color recognition is of great importance in intelligent transportation systems. Unlike conventional methods which use only a single Convolutional Neural Network (CNN) for feature extraction or classification, in this paper, four CNNs, with different architectures well-performing in different classes, are trained to extract various features from the input image. To take advantage of the distinct capability of each network, the multiple outputs are combined using a stack generalization algorithm as an ensemble technique. As a result, the final model performs better than each CNN individually in vehicle color identification. The evaluation results in terms of overall average accuracy and accuracy variance show the proposed method’s outperformance compared to the state-of-the-art rivals.

Keywords: Vehicle Color Recognition, Ensemble Algorithm, Stack Generalization, Convolutional Neural Network

Procedia PDF Downloads 50

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 250

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 68

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 125