Search results for: feature noise
1957 Neural Networks-based Acoustic Annoyance Model for Laptop Hard Disk Drive
Authors: Yichao Ma, Chengsiong Chin, Wailok Woo
Abstract:
Since the last decade, there has been a rapid growth in digital multimedia, such as high-resolution media files and three-dimentional movies. Hence, there is a need for large digital storage such as Hard Disk Drive (HDD). As such, users expect to have a quieter HDD in their laptop. In this paper, a jury test has been conducted on a group of 34 people where 17 of them are students who is the potential consumer, and the remaining are engineers who know the HDD. A total 13 HDD sound samples have been selected from over hundred HDD noise recordings. These samples are selected based on an agreed subjective feeling. The samples are played to the participants using head acoustic playback system which enabled them to experience as similar as possible the same environment as have been recorded. Analysis has been conducted and the obtained results have indicated different group has different perception over the noises. Two neural network-based acoustic annoyance models are established based on back propagation neural network. Four psychoacoustic metrics, loudness, sharpness, roughness and fluctuation strength, are used as the input of the model, and the subjective evaluation results are taken as the output. The developed models are reasonably accurate in simulating both training and test samples.Keywords: hdd noise, jury test, neural network model, psychoacoustic annoyance
Procedia PDF Downloads 4181956 Optimization Approach to Estimate Hammerstein–Wiener Nonlinear Blocks in Presence of Noise and Disturbance
Authors: Leili Esmaeilani, Jafar Ghaisari, Mohsen Ahmadian
Abstract:
Hammerstein–Wiener model is a block-oriented model where a linear dynamic system is surrounded by two static nonlinearities at its input and output and could be used to model various processes. This paper contains an optimization approach method for analysing the problem of Hammerstein–Wiener systems identification. The method relies on reformulate the identification problem; solve it as constraint quadratic problem and analysing its solutions. During the formulation of the problem, effects of adding noise to both input and output signals of nonlinear blocks and disturbance to linear block, in the emerged equations are discussed. Additionally, the possible parametric form of matrix operations to reduce the equation size is presented. To analyse the possible solutions to the mentioned system of equations, a method to reduce the difference between the number of equations and number of unknown variables by formulate and importing existing knowledge about nonlinear functions is presented. Obtained equations are applied to an instance H–W system to validate the results and illustrate the proposed method.Keywords: identification, Hammerstein-Wiener, optimization, quantization
Procedia PDF Downloads 2511955 Detection of Curvilinear Structure via Recursive Anisotropic Diffusion
Authors: Sardorbek Numonov, Hyohun Kim, Dongwha Shin, Yeonseok Kim, Ji-Su Ahn, Dongeun Choi, Byung-Woo Hong
Abstract:
The detection of curvilinear structures often plays an important role in the analysis of images. In particular, it is considered as a crucial step for the diagnosis of chronic respiratory diseases to localize the fissures in chest CT imagery where the lung is divided into five lobes by the fissures that are characterized by linear features in appearance. However, the characteristic linear features for the fissures are often shown to be subtle due to the high intensity variability, pathological deformation or image noise involved in the imaging procedure, which leads to the uncertainty in the quantification of anatomical or functional properties of the lung. Thus, it is desired to enhance the linear features present in the chest CT images so that the distinctiveness in the delineation of the lobe is improved. We propose a recursive diffusion process that prefers coherent features based on the analysis of structure tensor in an anisotropic manner. The local image features associated with certain scales and directions can be characterized by the eigenanalysis of the structure tensor that is often regularized via isotropic diffusion filters. However, the isotropic diffusion filters involved in the computation of the structure tensor generally blur geometrically significant structure of the features leading to the degradation of the characteristic power in the feature space. Thus, it is required to take into consideration of local structure of the feature in scale and direction when computing the structure tensor. We apply an anisotropic diffusion in consideration of scale and direction of the features in the computation of the structure tensor that subsequently provides the geometrical structure of the features by its eigenanalysis that determines the shape of the anisotropic diffusion kernel. The recursive application of the anisotropic diffusion with the kernel the shape of which is derived from the structure tensor leading to the anisotropic scale-space where the geometrical features are preserved via the eigenanalysis of the structure tensor computed from the diffused image. The recursive interaction between the anisotropic diffusion based on the geometry-driven kernels and the computation of the structure tensor that determines the shape of the diffusion kernels yields a scale-space where geometrical properties of the image structure are effectively characterized. We apply our recursive anisotropic diffusion algorithm to the detection of curvilinear structure in the chest CT imagery where the fissures present curvilinear features and define the boundary of lobes. It is shown that our algorithm yields precise detection of the fissures while overcoming the subtlety in defining the characteristic linear features. The quantitative evaluation demonstrates the robustness and effectiveness of the proposed algorithm for the detection of fissures in the chest CT in terms of the false positive and the true positive measures. The receiver operating characteristic curves indicate the potential of our algorithm as a segmentation tool in the clinical environment. This work was supported by the MISP(Ministry of Science and ICT), Korea, under the National Program for Excellence in SW (20170001000011001) supervised by the IITP(Institute for Information and Communications Technology Promotion).Keywords: anisotropic diffusion, chest CT imagery, chronic respiratory disease, curvilinear structure, fissure detection, structure tensor
Procedia PDF Downloads 2221954 Feature Extraction Based on Contourlet Transform and Log Gabor Filter for Detection of Ulcers in Wireless Capsule Endoscopy
Authors: Nimisha Elsa Koshy, Varun P. Gopi, V. I. Thajudin Ahamed
Abstract:
The entire visualization of GastroIntestinal (GI) tract is not possible with conventional endoscopic exams. Wireless Capsule Endoscopy (WCE) is a low risk, painless, noninvasive procedure for diagnosing diseases such as bleeding, polyps, ulcers, and Crohns disease within the human digestive tract, especially the small intestine that was unreachable using the traditional endoscopic methods. However, analysis of massive images of WCE detection is tedious and time consuming to physicians. Hence, researchers have developed software methods to detect these diseases automatically. Thus, the effectiveness of WCE can be improved. In this paper, a novel textural feature extraction method is proposed based on Contourlet transform and Log Gabor filter to distinguish ulcer regions from normal regions. The results show that the proposed method performs well with a high accuracy rate of 94.16% using Support Vector Machine (SVM) classifier in HSV colour space.Keywords: contourlet transform, log gabor filter, ulcer, wireless capsule endoscopy
Procedia PDF Downloads 5331953 Hybrid Deep Learning and FAST-BRISK 3D Object Detection Technique for Bin-Picking Application
Authors: Thanakrit Taweesoontorn, Sarucha Yanyong, Poom Konghuayrob
Abstract:
Robotic arms have gained popularity in various industries due to their accuracy and efficiency. This research proposes a method for bin-picking tasks using the Cobot, combining the YOLOv5 CNNs model for object detection and pose estimation with traditional feature detection (FAST), feature description (BRISK), and matching algorithms. By integrating these algorithms and utilizing a small-scale depth sensor camera for capturing depth and color images, the system achieves real-time object detection and accurate pose estimation, enabling the robotic arm to pick objects correctly in both position and orientation. Furthermore, the proposed method is implemented within the ROS framework to provide a seamless platform for robotic control and integration. This integration of robotics, cameras, and AI technology contributes to the development of industrial robotics, opening up new possibilities for automating challenging tasks and improving overall operational efficiency.Keywords: robotic vision, image processing, applications of robotics, artificial intelligent
Procedia PDF Downloads 811952 Sentiment Analysis of Fake Health News Using Naive Bayes Classification Models
Authors: Danielle Shackley, Yetunde Folajimi
Abstract:
As more people turn to the internet seeking health-related information, there is more risk of finding false, inaccurate, or dangerous information. Sentiment analysis is a natural language processing technique that assigns polarity scores to text, ranging from positive, neutral, and negative. In this research, we evaluate the weight of a sentiment analysis feature added to fake health news classification models. The dataset consists of existing reliably labeled health article headlines that were supplemented with health information collected about COVID-19 from social media sources. We started with data preprocessing and tested out various vectorization methods such as Count and TFIDF vectorization. We implemented 3 Naive Bayes classifier models, including Bernoulli, Multinomial, and Complement. To test the weight of the sentiment analysis feature on the dataset, we created benchmark Naive Bayes classification models without sentiment analysis, and those same models were reproduced, and the feature was added. We evaluated using the precision and accuracy scores. The Bernoulli initial model performed with 90% precision and 75.2% accuracy, while the model supplemented with sentiment labels performed with 90.4% precision and stayed constant at 75.2% accuracy. Our results show that the addition of sentiment analysis did not improve model precision by a wide margin; while there was no evidence of improvement in accuracy, we had a 1.9% improvement margin of the precision score with the Complement model. Future expansion of this work could include replicating the experiment process and substituting the Naive Bayes for a deep learning neural network model.Keywords: sentiment analysis, Naive Bayes model, natural language processing, topic analysis, fake health news classification model
Procedia PDF Downloads 871951 Algorithm Research on Traffic Sign Detection Based on Improved EfficientDet
Authors: Ma Lei-Lei, Zhou You
Abstract:
Aiming at the problems of low detection accuracy of deep learning algorithm in traffic sign detection, this paper proposes improved EfficientDet based traffic sign detection algorithm. Multi-head self-attention is introduced in the minimum resolution layer of the backbone of EfficientDet to achieve effective aggregation of local and global depth information, and this study proposes an improved feature fusion pyramid with increased vertical cross-layer connections, which improves the performance of the model while introducing a small amount of complexity, the Balanced L1 Loss is introduced to replace the original regression loss function Smooth L1 Loss, which solves the problem of balance in the loss function. Experimental results show, the algorithm proposed in this study is suitable for the task of traffic sign detection. Compared with other models, the improved EfficientDet has the best detection accuracy. Although the test speed is not completely dominant, it still meets the real-time requirement.Keywords: convolutional neural network, transformer, feature pyramid networks, loss function
Procedia PDF Downloads 901950 COVID-19 Analysis with Deep Learning Model Using Chest X-Rays Images
Authors: Uma Maheshwari V., Rajanikanth Aluvalu, Kumar Gautam
Abstract:
The COVID-19 disease is a highly contagious viral infection with major worldwide health implications. The global economy suffers as a result of COVID. The spread of this pandemic disease can be slowed if positive patients are found early. COVID-19 disease prediction is beneficial for identifying patients' health problems that are at risk for COVID. Deep learning and machine learning algorithms for COVID prediction using X-rays have the potential to be extremely useful in solving the scarcity of doctors and clinicians in remote places. In this paper, a convolutional neural network (CNN) with deep layers is presented for recognizing COVID-19 patients using real-world datasets. We gathered around 6000 X-ray scan images from various sources and split them into two categories: normal and COVID-impacted. Our model examines chest X-ray images to recognize such patients. Because X-rays are commonly available and affordable, our findings show that X-ray analysis is effective in COVID diagnosis. The predictions performed well, with an average accuracy of 99% on training photographs and 88% on X-ray test images.Keywords: deep CNN, COVID–19 analysis, feature extraction, feature map, accuracy
Procedia PDF Downloads 711949 Sentiment Analysis: An Enhancement of Ontological-Based Features Extraction Techniques and Word Equations
Authors: Mohd Ridzwan Yaakub, Muhammad Iqbal Abu Latiffi
Abstract:
Online business has become popular recently due to the massive amount of information and medium available on the Internet. This has resulted in the huge number of reviews where the consumers share their opinion, criticisms, and satisfaction on the products they have purchased on the websites or the social media such as Facebook and Twitter. However, to analyze customer’s behavior has become very important for organizations to find new market trends and insights. The reviews from the websites or the social media are in structured and unstructured data that need a sentiment analysis approach in analyzing customer’s review. In this article, techniques used in will be defined. Definition of the ontology and description of its possible usage in sentiment analysis will be defined. It will lead to empirical research that related to mobile phones used in research and the ontology used in the experiment. The researcher also will explore the role of preprocessing data and feature selection methodology. As the result, ontology-based approach in sentiment analysis can help in achieving high accuracy for the classification task.Keywords: feature selection, ontology, opinion, preprocessing data, sentiment analysis
Procedia PDF Downloads 1891948 Predicting Match Outcomes in Team Sport via Machine Learning: Evidence from National Basketball Association
Authors: Jacky Liu
Abstract:
This paper develops a team sports outcome prediction system with potential for wide-ranging applications across various disciplines. Despite significant advancements in predictive analytics, existing studies in sports outcome predictions possess considerable limitations, including insufficient feature engineering and underutilization of advanced machine learning techniques, among others. To address these issues, we extend the Sports Cross Industry Standard Process for Data Mining (SRP-CRISP-DM) framework and propose a unique, comprehensive predictive system, using National Basketball Association (NBA) data as an example to test this extended framework. Our approach follows a holistic methodology in feature engineering, employing both Time Series and Non-Time Series Data, as well as conducting Explanatory Data Analysis and Feature Selection. Furthermore, we contribute to the discourse on target variable choice in team sports outcome prediction, asserting that point spread prediction yields higher profits as opposed to game-winner predictions. Using machine learning algorithms, particularly XGBoost, results in a significant improvement in predictive accuracy of team sports outcomes. Applied to point spread betting strategies, it offers an astounding annual return of approximately 900% on an initial investment of $100. Our findings not only contribute to academic literature, but have critical practical implications for sports betting. Our study advances the understanding of team sports outcome prediction a burgeoning are in complex system predictions and pave the way for potential profitability and more informed decision making in sports betting markets.Keywords: machine learning, team sports, game outcome prediction, sports betting, profits simulation
Procedia PDF Downloads 871947 Pattern Recognition Using Feature Based Die-Map Clustering in the Semiconductor Manufacturing Process
Authors: Seung Hwan Park, Cheng-Sool Park, Jun Seok Kim, Youngji Yoo, Daewoong An, Jun-Geol Baek
Abstract:
Depending on the big data analysis becomes important, yield prediction using data from the semiconductor process is essential. In general, yield prediction and analysis of the causes of the failure are closely related. The purpose of this study is to analyze pattern affects the final test results using a die map based clustering. Many researches have been conducted using die data from the semiconductor test process. However, analysis has limitation as the test data is less directly related to the final test results. Therefore, this study proposes a framework for analysis through clustering using more detailed data than existing die data. This study consists of three phases. In the first phase, die map is created through fail bit data in each sub-area of die. In the second phase, clustering using map data is performed. And the third stage is to find patterns that affect final test result. Finally, the proposed three steps are applied to actual industrial data and experimental results showed the potential field application.Keywords: die-map clustering, feature extraction, pattern recognition, semiconductor manufacturing process
Procedia PDF Downloads 3941946 A Monopole Intravascular Antenna with Three Parasitic Elements Optimized for Higher Tesla MRI Systems
Authors: Mohammad Mohammadzadeh, Alireza Ghasempour
Abstract:
In this paper, a new design of monopole antenna has been proposed that increases the contrast of intravascular magnetic resonance images through increasing the homogeneity of the intrinsic signal-to-noise ratio (ISNR) distribution around the antenna. The antenna is made of a coaxial cable with three parasitic elements. Lengths and positions of the elements are optimized by the improved genetic algorithm (IGA) for 1.5, 3, 4.7, and 7Tesla MRI systems based on a defined cost function. Simulations were also conducted to verify the performance of the designed antenna. Our simulation results show that each time IGA is executed different values for the parasitic elements are obtained so that the cost functions of those antennas are high. According to the obtained results, IGA can also find the best values for the parasitic elements (regarding cost function) in the next executions. Additionally, two dimensional and one-dimensional maps of ISNR were drawn for the proposed antenna and compared to the previously published monopole antenna with one parasitic element at the frequency of 64MHz inside a saline phantom. Results verified that in spite of ISNR decreasing, there is a considerable improvement in the homogeneity of ISNR distribution of the proposed antenna so that their multiplication increases.Keywords: intravascular MR antenna, monopole antenna, parasitic elements, signal-to-noise ratio (SNR), genetic algorithm
Procedia PDF Downloads 2881945 Urban Freight Station: An Innovative Approach to Urban Freight
Authors: Amit Kumar Jain, Surbhi Jain
Abstract:
The urban freight in a city constitutes 10 to 18 per cent of all city road traffic, and 40 per cent of air pollution and noise emissions, are directly related to commercial transport. The policy measures implemented by urban planners have sought to restrict rather than assist goods-vehicle operations. This approach has temporarily controlled the urban transport demand during peak hours of traffic but has not effectively solved transport congestion. The solution discussed in the paper envisages the development of a comprehensive network of Urban Freight Stations (UFS) connected through underground conveyor belts in the city in line with baggage segregation and distribution in any of the major airports. The transportation of freight shall be done in standard size containers/cars through rail borne carts. The freight can be despatched or received from any of the UFS. Once freight is booked for a destination from any of the UFS, it would be stuffed in the container and digitally tagged for the destination. The container would reach the destination UFS through a network of rail borne carts. The container would be de-stuffed at the destination UFS and sent for further delivery, or the consignee may be asked to collect the consignment from urban freight station. The obvious benefits would be decongestion of roads, reduction in air and noise pollution, saving in manpower used for freight transportation.Keywords: congestion, urban freight, intelligent transport system, pollution
Procedia PDF Downloads 2951944 Drug-Drug Interaction Prediction in Diabetes Mellitus
Authors: Rashini Maduka, C. R. Wijesinghe, A. R. Weerasinghe
Abstract:
Drug-drug interactions (DDIs) can happen when two or more drugs are taken together. Today DDIs have become a serious health issue due to adverse drug effects. In vivo and in vitro methods for identifying DDIs are time-consuming and costly. Therefore, in-silico-based approaches are preferred in DDI identification. Most machine learning models for DDI prediction are used chemical and biological drug properties as features. However, some drug features are not available and costly to extract. Therefore, it is better to make automatic feature engineering. Furthermore, people who have diabetes already suffer from other diseases and take more than one medicine together. Then adverse drug effects may happen to diabetic patients and cause unpleasant reactions in the body. In this study, we present a model with a graph convolutional autoencoder and a graph decoder using a dataset from DrugBank version 5.1.3. The main objective of the model is to identify unknown interactions between antidiabetic drugs and the drugs taken by diabetic patients for other diseases. We considered automatic feature engineering and used Known DDIs only as the input for the model. Our model has achieved 0.86 in AUC and 0.86 in AP.Keywords: drug-drug interaction prediction, graph embedding, graph convolutional networks, adverse drug effects
Procedia PDF Downloads 881943 Recurrent Neural Networks for Complex Survival Models
Authors: Pius Marthin, Nihal Ata Tutkun
Abstract:
Survival analysis has become one of the paramount procedures in the modeling of time-to-event data. When we encounter complex survival problems, the traditional approach remains limited in accounting for the complex correlational structure between the covariates and the outcome due to the strong assumptions that limit the inference and prediction ability of the resulting models. Several studies exist on the deep learning approach to survival modeling; moreover, the application for the case of complex survival problems still needs to be improved. In addition, the existing models need to address the data structure's complexity fully and are subject to noise and redundant information. In this study, we design a deep learning technique (CmpXRnnSurv_AE) that obliterates the limitations imposed by traditional approaches and addresses the above issues to jointly predict the risk-specific probabilities and survival function for recurrent events with competing risks. We introduce the component termed Risks Information Weights (RIW) as an attention mechanism to compute the weighted cumulative incidence function (WCIF) and an external auto-encoder (ExternalAE) as a feature selector to extract complex characteristics among the set of covariates responsible for the cause-specific events. We train our model using synthetic and real data sets and employ the appropriate metrics for complex survival models for evaluation. As benchmarks, we selected both traditional and machine learning models and our model demonstrates better performance across all datasets.Keywords: cumulative incidence function (CIF), risk information weight (RIW), autoencoders (AE), survival analysis, recurrent events with competing risks, recurrent neural networks (RNN), long short-term memory (LSTM), self-attention, multilayers perceptrons (MLPs)
Procedia PDF Downloads 781942 Measurement of Magnetic Properties of Grainoriented Electrical Steels at Low and High Fields Using a Novel Single
Authors: Nkwachukwu Chukwuchekwa, Joy Ulumma Chukwuchekwa
Abstract:
Magnetic characteristics of grain-oriented electrical steel (GOES) are usually measured at high flux densities suitable for its typical applications in power transformers. There are limited magnetic data at low flux densities which are relevant for the characterization of GOES for applications in metering instrument transformers and low frequency magnetic shielding in magnetic resonance imaging medical scanners. Magnetic properties such as coercivity, B-H loop, AC relative permeability and specific power loss of conventional grain oriented (CGO) and high permeability grain oriented (HGO) electrical steels were measured and compared at high and low flux densities at power magnetising frequency. 40 strips comprising 20 CGO and 20 HGO, 305 mm x 30 mm x 0.27 mm from a supplier were tested. The HGO and CGO strips had average grain sizes of 9 mm and 4 mm respectively. Each strip was singly magnetised under sinusoidal peak flux density from 8.0 mT to 1.5 T at a magnetising frequency of 50 Hz. The novel single sheet tester comprises a personal computer in which LabVIEW version 8.5 from National Instruments (NI) was installed, a NI 4461 data acquisition (DAQ) card, an impedance matching transformer, to match the 600 minimum load impedance of the DAQ card with the 5 to 20 low impedance of the magnetising circuit, and a 4.7 Ω shunt resistor. A double vertical yoke made of GOES which is 290 mm long and 32 mm wide is used. A 500-turn secondary winding, about 80 mm in length, was wound around a plastic former, 270 mm x 40 mm, housing the sample, while a 100-turn primary winding, covering the entire length of the plastic former was wound over the secondary winding. A standard Epstein strip to be tested is placed between the yokes. The magnetising voltage was generated by the LabVIEW program through a voltage output from the DAQ card. The voltage drop across the shunt resistor and the secondary voltage were acquired by the card for calculation of magnetic field strength and flux density respectively. A feedback control system implemented in LabVIEW was used to control the flux density and to make the induced secondary voltage waveforms sinusoidal to have repeatable and comparable measurements. The low noise NI4461 card with 24 bit resolution and a sampling rate of 204.8 KHz and 92 KHz bandwidth were chosen to take the measurements to minimize the influence of thermal noise. In order to reduce environmental noise, the yokes, sample and search coil carrier were placed in a noise shielding chamber. HGO was found to have better magnetic properties at both high and low magnetisation regimes. This is because of the higher grain size of HGO and higher grain-grain misorientation of CGO. HGO is better CGO in both low and high magnetic field applications.Keywords: flux density, electrical steel, LabVIEW, magnetization
Procedia PDF Downloads 2861941 An Improved Tracking Approach Using Particle Filter and Background Subtraction
Authors: Amir Mukhtar, Dr. Likun Xia
Abstract:
An improved, robust and efficient visual target tracking algorithm using particle filtering is proposed. Particle filtering has been proven very successful in estimating non-Gaussian and non-linear problems. In this paper, the particle filter is used with color feature to estimate the target state with time. Color distributions are applied as this feature is scale and rotational invariant, shows robustness to partial occlusion and computationally efficient. The performance is made more robust by choosing the different (YIQ) color scheme. Tracking is performed by comparison of chrominance histograms of target and candidate positions (particles). Color based particle filter tracking often leads to inaccurate results when light intensity changes during a video stream. Furthermore, background subtraction technique is used for size estimation of the target. The qualitative evaluation of proposed algorithm is performed on several real-world videos. The experimental results demonstrate that the improved algorithm can track the moving objects very well under illumination changes, occlusion and moving background.Keywords: tracking, particle filter, histogram, corner points, occlusion, illumination
Procedia PDF Downloads 3661940 The Convolution Recurrent Network of Using Residual LSTM to Process the Output of the Downsampling for Monaural Speech Enhancement
Authors: Shibo Wei, Ting Jiang
Abstract:
Convolutional-recurrent neural networks (CRN) have achieved much success recently in the speech enhancement field. The common processing method is to use the convolution layer to compress the feature space by multiple upsampling and then model the compressed features with the LSTM layer. At last, the enhanced speech is obtained by deconvolution operation to integrate the global information of the speech sequence. However, the feature space compression process may cause the loss of information, so we propose to model the upsampling result of each step with the residual LSTM layer, then join it with the output of the deconvolution layer and input them to the next deconvolution layer, by this way, we want to integrate the global information of speech sequence better. The experimental results show the network model (RES-CRN) we introduce can achieve better performance than LSTM without residual and overlaying LSTM simply in the original CRN in terms of scale-invariant signal-to-distortion ratio (SI-SNR), speech quality (PESQ), and intelligibility (STOI).Keywords: convolutional-recurrent neural networks, speech enhancement, residual LSTM, SI-SNR
Procedia PDF Downloads 1881939 Continuous Differential Evolution Based Parameter Estimation Framework for Signal Models
Authors: Ammara Mehmood, Aneela Zameer, Muhammad Asif Zahoor Raja, Muhammad Faisal Fateh
Abstract:
In this work, the strength of bio-inspired computational intelligence based technique is exploited for parameter estimation for the periodic signals using Continuous Differential Evolution (CDE) by defining an error function in the mean square sense. Multidimensional and nonlinear nature of the problem emerging in sinusoidal signal models along with noise makes it a challenging optimization task, which is dealt with robustness and effectiveness of CDE to ensure convergence and avoid trapping in local minima. In the proposed scheme of Continuous Differential Evolution based Signal Parameter Estimation (CDESPE), unknown adjustable weights of the signal system identification model are optimized utilizing CDE algorithm. The performance of CDESPE model is validated through statistics based various performance indices on a sufficiently large number of runs in terms of estimation error, mean squared error and Thiel’s inequality coefficient. Efficacy of CDESPE is examined by comparison with the actual parameters of the system, Genetic Algorithm based outcomes and from various deterministic approaches at different signal-to-noise ratio (SNR) levels.Keywords: parameter estimation, bio-inspired computing, continuous differential evolution (CDE), periodic signals
Procedia PDF Downloads 2931938 Marker-Controlled Level-Set for Segmenting Breast Tumor from Thermal Images
Authors: Swathi Gopakumar, Sruthi Krishna, Shivasubramani Krishnamoorthy
Abstract:
Contactless, painless and radiation-free thermal imaging technology is one of the preferred screening modalities for detection of breast cancer. However, poor signal to noise ratio and the inexorable need to preserve edges defining cancer cells and normal cells, make the segmentation process difficult and hence unsuitable for computer-aided diagnosis of breast cancer. This paper presents key findings from a research conducted on the appraisal of two promising techniques, for the detection of breast cancer: (I) marker-controlled, Level-set segmentation of anisotropic diffusion filtered preprocessed image versus (II) Segmentation using marker-controlled level-set on a Gaussian-filtered image. Gaussian-filtering processes the image uniformly, whereas anisotropic filtering processes only in specific areas of a thermographic image. The pre-processed (Gaussian-filtered and anisotropic-filtered) images of breast samples were then applied for segmentation. The segmentation of breast starts with initial level-set function. In this study, marker refers to the position of the image to which initial level-set function is applied. The markers are generally placed on the left and right side of the breast, which may vary with the breast size. The proposed method was carried out on images from an online database with samples collected from women of varying breast characteristics. It was observed that the breast was able to be segmented out from the background by adjustment of the markers. From the results, it was observed that as a pre-processing technique, anisotropic filtering with level-set segmentation, preserved the edges more effectively than Gaussian filtering. Segmented image, by application of anisotropic filtering was found to be more suitable for feature extraction, enabling automated computer-aided diagnosis of breast cancer.Keywords: anisotropic diffusion, breast, Gaussian, level-set, thermograms
Procedia PDF Downloads 3681937 A Comparative Analysis of Classification Models with Wrapper-Based Feature Selection for Predicting Student Academic Performance
Authors: Abdullah Al Farwan, Ya Zhang
Abstract:
In today’s educational arena, it is critical to understand educational data and be able to evaluate important aspects, particularly data on student achievement. Educational Data Mining (EDM) is a research area that focusing on uncovering patterns and information in data from educational institutions. Teachers, if they are able to predict their students' class performance, can use this information to improve their teaching abilities. It has evolved into valuable knowledge that can be used for a wide range of objectives; for example, a strategic plan can be used to generate high-quality education. Based on previous data, this paper recommends employing data mining techniques to forecast students' final grades. In this study, five data mining methods, Decision Tree, JRip, Naive Bayes, Multi-layer Perceptron, and Random Forest with wrapper feature selection, were used on two datasets relating to Portuguese language and mathematics classes lessons. The results showed the effectiveness of using data mining learning methodologies in predicting student academic success. The classification accuracy achieved with selected algorithms lies in the range of 80-94%. Among all the selected classification algorithms, the lowest accuracy is achieved by the Multi-layer Perceptron algorithm, which is close to 70.45%, and the highest accuracy is achieved by the Random Forest algorithm, which is close to 94.10%. This proposed work can assist educational administrators to identify poor performing students at an early stage and perhaps implement motivational interventions to improve their academic success and prevent educational dropout.Keywords: classification algorithms, decision tree, feature selection, multi-layer perceptron, Naïve Bayes, random forest, students’ academic performance
Procedia PDF Downloads 1551936 Deep Learning to Improve the 5G NR Uplink Control Channel
Authors: Ahmed Krobba, Meriem Touzene, Mohamed Debeyche
Abstract:
The wireless communications system (5G) will provide more diverse applications and higher quality services for users compared to the long-term evolution 4G (LTE). 5G uses a higher carrier frequency, which suffers from information loss in 5G coverage. Most 5G users often cannot obtain high-quality communications due to transmission channel noise and channel complexity. Physical Uplink Control Channel (PUCCH-NR: Physical Uplink Control Channel New Radio) plays a crucial role in 5G NR telecommunication technology, which is mainly used to transmit link control information uplink (UCI: Uplink Control Information. This study based of evaluating the performance of channel physical uplink control PUCCH-NR under low Signal-to-Noise Ratios with various antenna numbers reception. We propose the artificial intelligence approach based on deep neural networks (Deep Learning) to estimate the PUCCH-NR channel in comparison with this approach with different conventional methods such as least-square (LS) and minimum-mean-square-error (MMSE). To evaluate the channel performance we use the block error rate (BLER) as an evaluation criterion of the communication system. The results show that the deep neural networks method gives best performance compared with MMSE and LSKeywords: 5G network, uplink (Uplink), PUCCH channel, NR-PUCCH channel, deep learning
Procedia PDF Downloads 611935 KCBA, A Method for Feature Extraction of Colonoscopy Images
Authors: Vahid Bayrami Rad
Abstract:
In recent years, the use of artificial intelligence techniques, tools, and methods in processing medical images and health-related applications has been highlighted and a lot of research has been done in this regard. For example, colonoscopy and diagnosis of colon lesions are some cases in which the process of diagnosis of lesions can be improved by using image processing and artificial intelligence algorithms, which help doctors a lot. Due to the lack of accurate measurements and the variety of injuries in colonoscopy images, the process of diagnosing the type of lesions is a little difficult even for expert doctors. Therefore, by using different software and image processing, doctors can be helped to increase the accuracy of their observations and ultimately improve their diagnosis. Also, by using automatic methods, the process of diagnosing the type of disease can be improved. Therefore, in this paper, a deep learning framework called KCBA is proposed to classify colonoscopy lesions which are composed of several methods such as K-means clustering, a bag of features and deep auto-encoder. Finally, according to the experimental results, the proposed method's performance in classifying colonoscopy images is depicted considering the accuracy criterion.Keywords: colorectal cancer, colonoscopy, region of interest, narrow band imaging, texture analysis, bag of feature
Procedia PDF Downloads 431934 Analysis of Cardiovascular Diseases Using Artificial Neural Network
Authors: Jyotismita Talukdar
Abstract:
In this paper, a study has been made on the possibility and accuracy of early prediction of several Heart Disease using Artificial Neural Network. (ANN). The study has been made in both noise free environment and noisy environment. The data collected for this analysis are from five Hospitals. Around 1500 heart patient’s data has been collected and studied. The data is analysed and the results have been compared with the Doctor’s diagnosis. It is found that, in noise free environment, the accuracy varies from 74% to 92%and in noisy environment (2dB), the results of accuracy varies from 62% to 82%. In the present study, four basic attributes considered are Blood Pressure (BP), Fasting Blood Sugar (FBS), Thalach (THAL) and Cholesterol (CHOL.). It has been found that highest accuracy(93%), has been achieved in case of PPI( Post-Permanent-Pacemaker Implementation ), around 79% in case of CAD(Coronary Artery disease), 87% in DCM (Dilated Cardiomyopathy), 89% in case of RHD&MS(Rheumatic heart disease with Mitral Stenosis), 75 % in case of RBBB +LAFB (Right Bundle Branch Block + Left Anterior Fascicular Block), 72% for CHB(Complete Heart Block) etc. The lowest accuracy has been obtained in case of ICMP (Ischemic Cardiomyopathy), about 38% and AF( Atrial Fibrillation), about 60 to 62%.Keywords: coronary heart disease, chronic stable angina, sick sinus syndrome, cardiovascular disease, cholesterol, Thalach
Procedia PDF Downloads 1651933 Robust Medical Image Watermarking based on Contourlet and Extraction Using ICA
Authors: S. Saju, G. Thirugnanam
Abstract:
In this paper, a medical image watermarking algorithm based on contourlet is proposed. Medical image watermarking is a special subcategory of image watermarking in the sense that images have special requirements. Watermarked medical images should not differ perceptually from their original counterparts because clinical reading of images must not be affected. Watermarking techniques based on wavelet transform are reported in many literatures but robustness and security using contourlet are better when compared to wavelet transform. The main challenge in exploring geometry in images comes from the discrete nature of the data. In this paper, original image is decomposed to two level using contourlet and the watermark is embedded in the resultant sub-bands. Sub-band selection is based on the value of Peak Signal to Noise Ratio (PSNR) that is calculated between watermarked and original image. To extract the watermark, Kernel ICA is used and it has a novel characteristic is that it does not require the transformation process to extract the watermark. Simulation results show that proposed scheme is robust against attacks such as Salt and Pepper noise, Median filtering and rotation. The performance measures like PSNR and Similarity measure are evaluated and compared with Discrete Wavelet Transform (DWT) to prove the robustness of the scheme. Simulations are carried out using Matlab Software.Keywords: digital watermarking, independent component analysis, wavelet transform, contourlet
Procedia PDF Downloads 5191932 A Geometric Based Hybrid Approach for Facial Feature Localization
Authors: Priya Saha, Sourav Dey Roy Jr., Debotosh Bhattacharjee, Mita Nasipuri, Barin Kumar De, Mrinal Kanti Bhowmik
Abstract:
Biometric face recognition technology (FRT) has gained a lot of attention due to its extensive variety of applications in both security and non-security perspectives. It has come into view to provide a secure solution in identification and verification of person identity. Although other biometric based methods like fingerprint scans, iris scans are available, FRT is verified as an efficient technology for its user-friendliness and contact freeness. Accurate facial feature localization plays an important role for many facial analysis applications including biometrics and emotion recognition. But, there are certain factors, which make facial feature localization a challenging task. On human face, expressions can be seen from the subtle movements of facial muscles and influenced by internal emotional states. These non-rigid facial movements cause noticeable alterations in locations of facial landmarks, their usual shapes, which sometimes create occlusions in facial feature areas making face recognition as a difficult problem. The paper proposes a new hybrid based technique for automatic landmark detection in both neutral and expressive frontal and near frontal face images. The method uses the concept of thresholding, sequential searching and other image processing techniques for locating the landmark points on the face. Also, a Graphical User Interface (GUI) based software is designed that could automatically detect 16 landmark points around eyes, nose and mouth that are mostly affected by the changes in facial muscles. The proposed system has been tested on widely used JAFFE and Cohn Kanade database. Also, the system is tested on DeitY-TU face database which is created in the Biometrics Laboratory of Tripura University under the research project funded by Department of Electronics & Information Technology, Govt. of India. The performance of the proposed method has been done in terms of error measure and accuracy. The method has detection rate of 98.82% on JAFFE database, 91.27% on Cohn Kanade database and 93.05% on DeitY-TU database. Also, we have done comparative study of our proposed method with other techniques developed by other researchers. This paper will put into focus emotion-oriented systems through AU detection in future based on the located features.Keywords: biometrics, face recognition, facial landmarks, image processing
Procedia PDF Downloads 4021931 Hyperspectral Data Classification Algorithm Based on the Deep Belief and Self-Organizing Neural Network
Authors: Li Qingjian, Li Ke, He Chun, Huang Yong
Abstract:
In this paper, the method of combining the Pohl Seidman's deep belief network with the self-organizing neural network is proposed to classify the target. This method is mainly aimed at the high nonlinearity of the hyperspectral image, the high sample dimension and the difficulty in designing the classifier. The main feature of original data is extracted by deep belief network. In the process of extracting features, adding known labels samples to fine tune the network, enriching the main characteristics. Then, the extracted feature vectors are classified into the self-organizing neural network. This method can effectively reduce the dimensions of data in the spectrum dimension in the preservation of large amounts of raw data information, to solve the traditional clustering and the long training time when labeled samples less deep learning algorithm for training problems, improve the classification accuracy and robustness. Through the data simulation, the results show that the proposed network structure can get a higher classification precision in the case of a small number of known label samples.Keywords: DBN, SOM, pattern classification, hyperspectral, data compression
Procedia PDF Downloads 3341930 Developing Wearable EMG Sensor Designed for Parkinson's Disease (PD) Monitoring, and Treatment
Authors: Bulcha Belay Etana
Abstract:
Electromyography is used to measure the electrical activity of muscles for various health monitoring applications using surface electrodes or needle electrodes. Recent developments in electromyogram signal acquisition using textile electrodes open the door for wearable health monitoring which enables patients to monitor and control their health issues outside of traditional healthcare facilities. The aim of this research is therefore to develop and analyze wearable textile electrodes for the acquisition of electromyography signals for Parkinson’s patients and apply an appropriate thermal stimulus to relieve muscle cramping. In order to achieve this, textile electrodes are sewn with a silver-coated thread in an overlapping zigzag pattern into an inextensible fabric, and stainless steel knitted textile electrodes attached to a sleeve were prepared and its electrical characteristics including signal to noise ratio were compared with traditional electrodes. To relieve muscle cramping, a heating element using stainless steel conductive yarn Sewn onto a cotton fabric, coupled with a vibration system were developed. The system was integrated using a microcontroller and a Myoware muscle sensor so that when muscle cramping occurs, measured by the system activates the heating elements and vibration motors. The optimum temperature considered for treatment was 35.50c, so a Temperature measurement system was incorporated to deactivate the heating system when the temperature reaches this threshold, and the signals indicating muscle cramping have subsided. The textile electrode exhibited a signal to noise ratio of 6.38dB while the signal to noise ratio of the traditional electrode was 7.05dB. The rise time of the developed heating element was about 6 minutes to reach the optimum temperature using a 9volt power supply. The treatment of muscle cramping in Parkinson's patients using heat and muscle vibration simultaneously with a wearable electromyography signal acquisition system will improve patients’ livelihoods and enable better chronic pain management.Keywords: electromyography, heating textile, vibration therapy, parkinson’s disease, wearable electronic textile
Procedia PDF Downloads 1241929 Model Predictive Control with Unscented Kalman Filter for Nonlinear Implicit Systems
Authors: Takashi Shimizu, Tomoaki Hashimoto
Abstract:
A class of implicit systems is known as a more generalized class of systems than a class of explicit systems. To establish a control method for such a generalized class of systems, we adopt model predictive control method which is a kind of optimal feedback control with a performance index that has a moving initial time and terminal time. However, model predictive control method is inapplicable to systems whose all state variables are not exactly known. In other words, model predictive control method is inapplicable to systems with limited measurable states. In fact, it is usual that the state variables of systems are measured through outputs, hence, only limited parts of them can be used directly. It is also usual that output signals are disturbed by process and sensor noises. Hence, it is important to establish a state estimation method for nonlinear implicit systems with taking the process noise and sensor noise into consideration. To this purpose, we apply the model predictive control method and unscented Kalman filter for solving the optimization and estimation problems of nonlinear implicit systems, respectively. The objective of this study is to establish a model predictive control with unscented Kalman filter for nonlinear implicit systems.Keywords: optimal control, nonlinear systems, state estimation, Kalman filter
Procedia PDF Downloads 1881928 Deep Learning Based Fall Detection Using Simplified Human Posture
Authors: Kripesh Adhikari, Hamid Bouchachia, Hammadi Nait-Charif
Abstract:
Falls are one of the major causes of injury and death among elderly people aged 65 and above. A support system to identify such kind of abnormal activities have become extremely important with the increase in ageing population. Pose estimation is a challenging task and to add more to this, it is even more challenging when pose estimations are performed on challenging poses that may occur during fall. Location of the body provides a clue where the person is at the time of fall. This paper presents a vision-based tracking strategy where available joints are grouped into three different feature points depending upon the section they are located in the body. The three feature points derived from different joints combinations represents the upper region or head region, mid-region or torso and lower region or leg region. Tracking is always challenging when a motion is involved. Hence the idea is to locate the regions in the body in every frame and consider it as the tracking strategy. Grouping these joints can be beneficial to achieve a stable region for tracking. The location of the body parts provides a crucial information to distinguish normal activities from falls.Keywords: fall detection, machine learning, deep learning, pose estimation, tracking
Procedia PDF Downloads 179