Search results for: fault detection and classification

Authors: Monjed Ezzeddinne, Nicolas Lefebvre, Régis Lengellé

Abstract:

This paper presents a new version of the SVM mixture algorithm initially proposed by Kwok for classification and regression problems. For both cases, a slight modification of the mixture model leads to a standard SVM training problem, to the existence of an exact solution and allows the direct use of well known decomposition and working set selection algorithms. Only the regression case is considered in this paper but classification has been addressed in a very similar way. This method has been successfully applied to engine pollutants emission modeling.

Keywords: Identification, Learning systems, Mixture ofExperts, Support Vector Machines.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1368

Authors: Antoni Ivanov, Nikolay Dandanov, Nicole Christoff, Vladimir Poulkov

Abstract:

Spectrum underutilization has made cognitive radio a promising technology both for current and future telecommunications. This is due to the ability to exploit the unused spectrum in the bands dedicated to other wireless communication systems, and thus, increase their occupancy. The essential function, which allows the cognitive radio device to perceive the occupancy of the spectrum, is spectrum sensing. In this paper, the performance of modern adaptations of the four most widely used spectrum sensing techniques namely, energy detection (ED), cyclostationary feature detection (CSFD), matched filter (MF) and eigenvalues-based detection (EBD) is compared. The implementation has been accomplished through the PlutoSDR hardware platform and the GNU Radio software package in very low Signal-to-Noise Ratio (SNR) conditions. The optimal detection performance of the examined methods in a realistic implementation-oriented model is found for the common relevant parameters (number of observed samples, sensing time and required probability of false alarm).

Keywords: Cognitive radio, dynamic spectrum access, GNU Radio, spectrum sensing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1177

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 APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2780

Authors: Enas M. F. El Houby, Marwa S. Hassan

Abstract:

Combined therapy using Interferon and Ribavirin is the standard treatment in patients with chronic hepatitis C. However, the number of responders to this treatment is low, whereas its cost and side effects are high. Therefore, there is a clear need to predict patient’s response to the treatment based on clinical information to protect the patients from the bad drawbacks, Intolerable side effects and waste of money. Different machine learning techniques have been developed to fulfill this purpose. From these techniques are Associative Classification (AC) and Decision Tree (DT). The aim of this research is to compare the performance of these two techniques in the prediction of virological response to the standard treatment of HCV from clinical information. 200 patients treated with Interferon and Ribavirin; were analyzed using AC and DT. 150 cases had been used to train the classifiers and 50 cases had been used to test the classifiers. The experiment results showed that the two techniques had given acceptable results however the best accuracy for the AC reached 92% whereas for DT reached 80%.

Keywords: Associative Classification, Data mining, Decision tree, HCV, interferon.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1901

Authors: Mylena McCoggle, Shyra Wilson, Andrea Rivera, Rocio Alba-Flores, Valentin Soloiu

Abstract:

This work describes a system that uses electromyography (EMG) signals obtained from muscle sensors and an Artificial Neural Network (ANN) for signal classification and pattern recognition that is used to control a small unmanned aerial vehicle using specific arm movements. The main objective of this endeavor is the development of an intelligent interface that allows the user to control the flight of a drone beyond direct manual control. The sensor used were the MyoWare Muscle sensor which contains two EMG electrodes used to collect signals from the posterior (extensor) and anterior (flexor) forearm, and the bicep. The collection of the raw signals from each sensor was performed using an Arduino Uno. Data processing algorithms were developed with the purpose of classifying the signals generated by the arm’s muscles when performing specific movements, namely: flexing, resting, and motion of the arm. With these arm motions roll control of the drone was achieved. MATLAB software was utilized to condition the signals and prepare them for the classification. To generate the input vector for the ANN and perform the classification, the root mean square and the standard deviation were processed for the signals from each electrode. The neuromuscular information was trained using an ANN with a single 10 neurons hidden layer to categorize the four targets. The result of the classification shows that an accuracy of 97.5% was obtained. Afterwards, classification results are used to generate the appropriate control signals from the computer to the drone through a Wi-Fi network connection. These procedures were successfully tested, where the drone responded successfully in real time to the commanded inputs.

Keywords: Biosensors, electromyography, Artificial Neural Network, Arduino, drone flight control, machine learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 563

Authors: Wojciech P. Gajewski

Abstract:

The problem of spam has been seriously troubling the Internet community during the last few years and currently reached an alarming scale. Observations made at CERN (European Organization for Nuclear Research located in Geneva, Switzerland) show that spam mails can constitute up to 75% of daily SMTP traffic. A naïve Bayesian classifier based on a Bag Of Words representation of an email is widely used to stop this unwanted flood as it combines good performance with simplicity of the training and classification processes. However, facing the constantly changing patterns of spam, it is necessary to assure online adaptability of the classifier. This work proposes combining such a classifier with another NBC (naïve Bayesian classifier) based on pairs of adjacent words. Only the latter will be retrained with examples of spam reported by users. Tests are performed on considerable sets of mails both from public spam archives and CERN mailboxes. They suggest that this architecture can increase spam recall without affecting the classifier precision as it happens when only the NBC based on single words is retrained.

Keywords: Text classification, naïve Bayesian classification, spam, email.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4417

Authors: S. Zith Dey Babu, S. Kour, S. Verma, C. Verma, V. Pathania, A. Agrawal, V. Chaudhary, A. Manoj Puthur, R. Goyal, A. Pal, T. Danti Dey, A. Kumar, K. Wadhwa, O. Ved

Abstract:

Background: Skin cancer is now is the buzzing button in the field of medical science. The cyst's pandemic is drastically calibrating the body and well-being of the global village. Methods: The extracted image of the skin tumor cannot be used in one way for diagnosis. The stored image contains anarchies like the center. This approach will locate the forepart of an extracted appearance of skin. Partitioning image models has been presented to sort out the disturbance in the picture. Results: After completing partitioning, feature extraction has been formed by using genetic algorithm and finally, classification can be performed between the trained and test data to evaluate a large scale of an image that helps the doctors for the right prediction. To bring the improvisation of the existing system, we have set our objectives with an analysis. The efficiency of the natural selection process and the enriching histogram is essential in that respect. To reduce the false-positive rate or output, GA is performed with its accuracy. Conclusions: The objective of this task is to bring improvisation of effectiveness. GA is accomplishing its task with perfection to bring down the invalid-positive rate or outcome. The paper's mergeable portion conflicts with the composition of deep learning and medical image processing, which provides superior accuracy. Proportional types of handling create the reusability without any errors.

Keywords: Computer-aided system, detection, image segmentation, morphology.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 549

Authors: Mohanchur Sakar, K.K.Shukla, K.S.Dasgupta

Abstract:

This paper attempts to establish the fact that Multi State Network Classification is essential for performance enhancement of Transport protocols over Satellite based Networks. A model to classify Multi State network condition taking into consideration both congestion and channel error is evolved. In order to arrive at such a model an analysis of the impact of congestion and channel error on RTT values has been carried out using ns2. The analysis results are also reported in the paper. The inference drawn from this analysis is used to develop a novel statistical RTT based model for multi state network classification. An Adaptive Multi State Proactive Transport Protocol consisting of Proactive Slow Start, State based Error Recovery, Timeout Action and Proactive Reduction is proposed which uses the multi state network state classification model. This paper also confirms through detail simulation and analysis that a prior knowledge about the overall characteristics of the network helps in enhancing the performance of the protocol over satellite channel which is significantly affected due to channel noise and congestion. The necessary augmentation of ns2 simulator is done for simulating the multi state network classification logic. This simulation has been used in detail evaluation of the protocol under varied levels of congestion and channel noise. The performance enhancement of this protocol with reference to established protocols namely TCP SACK and Vegas has been discussed. The results as discussed in this paper clearly reveal that the proposed protocol always outperforms its peers and show a significant improvement in very high error conditions as envisaged in the design of the protocol.

Keywords: GEO, ns2, Proactive TCP, SACK, Vegas

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1432

Authors: Sam-Ang Keo, Franck Brachelet, Florin Breaban, Didier Defer

Abstract:

This paper presents a NDT by infrared thermography with excitation CO2 Laser, wavelength of 10.6 μm. This excitation is the controllable heating beam, confirmed by a preliminary test on a wooden plate 1.2 m x 0.9 m x 1 cm. As the first practice, this method is applied to detecting the defect in CFRP heated by the Laser 300 W during 40 s. Two samples 40 cm x 40 cm x 4.5 cm are prepared, one with defect, another one without defect. The laser beam passes through the lens of a deviation device, and heats the samples placed at a determinate position and area. As a result, the absence of adhesive can be detected. This method displays prominently its application as NDT with the composite materials. This work gives a good perspective to characterize the laser beam, which is very useful for the next detection campaigns.

Keywords: CO2 LASER, Infrared Thermography, NDT, CFRP, Defect Detection.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3011

Authors: Evans Belly, Imdad Rizvi, M. M. Kadam

Abstract:

Satellite imagery is one of the emerging technologies which are extensively utilized in various applications such as detection/extraction of man-made structures, monitoring of sensitive areas, creating graphic maps etc. The main approach here is the automated detection of buildings from very high resolution (VHR) optical satellite images. Initially, the shadow, the building and the non-building regions (roads, vegetation etc.) are investigated wherein building extraction is mainly focused. Once all the landscape is collected a trimming process is done so as to eliminate the landscapes that may occur due to non-building objects. Finally the label method is used to extract the building regions. The label method may be altered for efficient building extraction. The images used for the analysis are the ones which are extracted from the sensors having resolution less than 1 meter (VHR). This method provides an efficient way to produce good results. The additional overhead of mid processing is eliminated without compromising the quality of the output to ease the processing steps required and time consumed.

Keywords: Building detection, shadow detection, landscape generation, label, partitioning, very high resolution satellite imagery.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 845

Authors: F. F. Howard, C. B. Boye, I. Yakubu, J. S. Y. Kuma

Abstract:

One of the ways that could be used for the production of land use and land cover maps by a procedure known as image classification is the use of the remote sensing technique. Numerous elements ought to be taken into consideration, including the availability of highly satisfactory Landsat imagery, secondary data and a precise classification process. The goal of this study was to classify and map the land use and land cover of the study area using remote sensing and Geospatial Information System (GIS) analysis. The classification was done using Landsat 8 satellite images acquired in December 2020 covering the study area. The Landsat image was downloaded from the USGS. The Landsat image with 30 m resolution was geo-referenced to the WGS_84 datum and Universal Transverse Mercator (UTM) Zone 30N coordinate projection system. A radiometric correction was applied to the image to reduce the noise in the image. This study consists of two sections: the Land Use/Land Cover (LULC) and Accuracy Assessments using the confusion and contingency matrix and the Kappa coefficient. The LULC classifications were vegetation (agriculture) (67.87%), water bodies (0.01%), mining areas (5.24%), forest (26.02%), and settlement (0.88%). The overall accuracy of 97.87% and the kappa coefficient (K) of 97.3% were obtained for the confusion matrix. While an overall accuracy of 95.7% and a Kappa coefficient of 0.947 were obtained for the contingency matrix, the kappa coefficients were rated as substantial; hence, the classified image is fit for further research.

Keywords: Confusion Matrix, contingency matrix, kappa coefficient, land used/ land cover, accuracy assessment.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 271

Authors: Susmita Das, Kala Praveen Bagadi

Abstract:

SDMA (Space-Division Multiple Access) is a MIMO (Multiple-Input and Multiple-Output) based wireless communication network architecture which has the potential to significantly increase the spectral efficiency and the system performance. The maximum likelihood (ML) detection provides the optimal performance, but its complexity increases exponentially with the constellation size of modulation and number of users. The QR decomposition (QRD) MUD can be a substitute to ML detection due its low complexity and near optimal performance. The minimum mean-squared-error (MMSE) multiuser detection (MUD) minimises the mean square error (MSE), which may not give guarantee that the BER of the system is also minimum. But the minimum bit error rate (MBER) MUD performs better than the classic MMSE MUD in term of minimum probability of error by directly minimising the BER cost function. Also the MBER MUD is able to support more users than the number of receiving antennas, whereas the rest of MUDs fail in this scenario. In this paper the performance of various MUD techniques is verified for the correlated MIMO channel models based on IEEE 802.16n standard.

Keywords: Multiple input multiple output, multiuser detection, orthogonal frequency division multiplexing, space division multiple access, Bit error rate

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1927

Authors: R. Arulmurugan, P. Sengottuvelan

Abstract:

Object detection using Wavelet Neural Network (WNN) plays a major contribution in the analysis of image processing. Existing cluster-based algorithm for co-saliency object detection performs the work on the multiple images. The co-saliency detection results are not desirable to handle the multi scale image objects in WNN. Existing Super Resolution (SR) scheme for landmark images identifies the corresponding regions in the images and reduces the mismatching rate. But the Structure-aware matching criterion is not paying attention to detect multiple regions in SR images and fail to enhance the result percentage of object detection. To detect the objects in the high-resolution remote sensing images, Tagged Grid Matching (TGM) technique is proposed in this paper. TGM technique consists of the three main components such as object determination, object searching and object verification in WNN. Initially, object determination in TGM technique specifies the position and size of objects in the current image. The specification of the position and size using the hierarchical grid easily determines the multiple objects. Second component, object searching in TGM technique is carried out using the cross-point searching. The cross out searching point of the objects is selected to faster the searching process and reduces the detection time. Final component performs the object verification process in TGM technique for identifying (i.e.,) detecting the dissimilarity of objects in the current frame. The verification process matches the search result grid points with the stored grid points to easily detect the objects using the Gabor wavelet Transform. The implementation of TGM technique offers a significant improvement on the multi-object detection rate, processing time, precision factor and detection accuracy level.

Keywords: Object Detection, Cross-point Searching, Wavelet Neural Network, Object Determination, Gabor Wavelet Transform, Tagged Grid Matching.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1967

Authors: C. Lodato, S. Lopes

Abstract:

This paper describes a segmentation algorithm based on the cooperation of an optical flow estimation method with edge detection and region growing procedures. The proposed method has been developed as a pre-processing stage to be used in methodologies and tools for video/image indexing and retrieval by content. The addressed problem consists in extracting whole objects from background for producing images of single complete objects from videos or photos. The extracted images are used for calculating the object visual features necessary for both indexing and retrieval processes. The first task of the algorithm exploits the cues from motion analysis for moving area detection. Objects and background are then refined using respectively edge detection and region growing procedures. These tasks are iteratively performed until objects and background are completely resolved. The developed method has been applied to a variety of indoor and outdoor scenes where objects of different type and shape are represented on variously textured background.

Keywords: Motion Detection, Object Extraction, Optical Flow, Segmentation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1899

Authors: Siau-Chuin Liew, Siau-Way Liew, Jasni Mohd Zain

Abstract:

Digital watermarking in medical images can ensure the authenticity and integrity of the image. This design paper reviews some existing watermarking schemes and proposes a reversible tamper detection and recovery watermarking scheme. Watermark data from ROI (Region Of Interest) are stored in RONI (Region Of Non Interest). The embedded watermark allows tampering detection and tampered image recovery. The watermark is also reversible and data compression technique was used to allow higher embedding capacity.

Keywords: data compression, medical image, reversible, tamperdetection and recovery, watermark.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2082

Authors: Robert E. Hursig, Jane X. Zhang

Abstract:

A robust still image face localization algorithm capable of operating in an unconstrained visual environment is proposed. First, construction of a robust skin classifier within a shifted HSV color space is described. Then various filtering operations are performed to better isolate face candidates and mitigate the effect of substantial non-skin regions. Finally, a novel Bhattacharyya-based face detection algorithm is used to compare candidate regions of interest with a unique illumination-dependent face model probability distribution function approximation. Experimental results show a 90% face detection success rate despite the demands of the visually noisy environment.

Keywords: Audio-visual speech recognition, Bhattacharyyacoefficient, face detection,

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1631

Authors: Zulhadi Zakaria, Nor Ashidi Mat Isa, Shahrel A. Suandi

Abstract:

This paper reports the study results on neural network training algorithm of numerical optimization techniques multiface detection in static images. The training algorithms involved are scale gradient conjugate backpropagation, conjugate gradient backpropagation with Polak-Riebre updates, conjugate gradient backpropagation with Fletcher-Reeves updates, one secant backpropagation and resilent backpropagation. The final result of each training algorithms for multiface detection application will also be discussed and compared.

Keywords: training algorithm, multiface, static image, neural network

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2573

Authors: Zixian Zhang, Shanliang Yao, Zile Huang, Zhaodong Wu, Xiaohui Zhu, Yong Yue, Jieming Ma

Abstract:

Unmanned Surface Vehicles (USVs) hold significant value for their capacity to undertake hazardous and labor-intensive operations over aquatic environments. Object detection tasks are significant in these applications. Nonetheless, the efficacy of USVs in object detection is impeded by several intrinsic challenges, including the intricate dispersal of obstacles, reflections emanating from coastal structures, and the presence of fog over water surfaces, among others. To address these problems, this paper provides a fusion method for USVs to effectively detect objects in the inland surface environment, utilizing vision sensors and 3+1D Millimeter-wave radar. The MMW radar is a complementary tool to vision sensors, offering reliable environmental data. This approach involves the conversion of the radar’s 3D point cloud into a 2D radar pseudo-image, thereby standardizing the format for radar and vision data by leveraging a point transformer. Furthermore, this paper proposes the development of a multi-source object detection network, named RV-YOLOX, which leverages radar-vision integration specifically tailored for inland waterway environments. The performance is evaluated on our self-recording waterways dataset. Compared with the YOLOX network, our fusion network significantly improves detection accuracy, especially for objects with bad light conditions.

Keywords: Inland waterways, object detection, YOLO, sensor fusion, self-attention, deep learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 320

Authors: Seyyed Yasser Hashemi

Abstract:

Skew detection and correction (SDC) has a direct effect in efficiency and exactitude of documents’ segmentation and analysis and thus is considered as a very important step in documents’ analysis field. Skew is a major problem in documents’ analysis for every language. For Arabic/Persian document scripts this problem is more severe because of special features of these languages. In this paper an efficient and fast algorithm for Document Skew Detection (DSD) based on the concept of segmentation and Center of Gravity (COG) is proposed. This algorithm is examined for 150 Arabic/Persian and English documents and SDC process are done successfully for 93 percent of documents with error rate of less than 1°. This algorithm shows better results for English documents compared to Arabic/Persian documents. The proposed method is also represents favorable results for handwritten, printed and also complicated documents such as newspapers and journals even with very low quality and resolution.

Keywords: Arabic/Persian document, Baseline, Centre of gravity, Document segmentation, Skew detection and correction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1914

Authors: Hoshang Kolivand, Mahyar Kolivand, Mohd Shahrizal Sunar, Mohd Azhar M. Arsad

Abstract:

Real-time shadow generation in virtual environments and Augmented Reality (AR) was always a hot topic in the last three decades. Lots of calculation for shadow generation among AR needs a fast algorithm to overcome this issue and to be capable of implementing in any real-time rendering. In this paper, a silhouette detection algorithm is presented to generate shadows for AR systems. Δ+ algorithm is presented based on extending edges of occluders to recognize which edges are silhouettes in the case of real-time rendering. An accurate comparison between the proposed algorithm and current algorithms in silhouette detection is done to show the reduction calculation by presented algorithm. The algorithm is tested in both virtual environments and AR systems. We think that this algorithm has the potential to be a fundamental algorithm for shadow generation in all complex environments.

Keywords: Silhouette detection, shadow volumes, real-time shadows, rendering, augmented reality.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2023

Authors: Anukriti Kumar, Tanmay Singh, Dinesh Kumar Vishwakarma

Abstract:

Traffic control has been one of the most common and irritating problems since the time automobiles have hit the roads. Problems like traffic congestion have led to a significant time burden around the world and one significant solution to these problems can be the proper implementation of the Intelligent Transport System (ITS). It involves the integration of various tools like smart sensors, artificial intelligence, position technologies and mobile data services to manage traffic flow, reduce congestion and enhance driver's ability to avoid accidents during adverse weather. Road and traffic signs’ recognition is an emerging field of research in ITS. Classification problem of traffic signs needs to be solved as it is a major step in our journey towards building semi-autonomous/autonomous driving systems. The purpose of this work focuses on implementing an approach to solve the problem of traffic sign classification by developing a Convolutional Neural Network (CNN) classifier using the GTSRB (German Traffic Sign Recognition Benchmark) dataset. Rather than using hand-crafted features, our model addresses the concern of exploding huge parameters and data method augmentations. Our model achieved an accuracy of around 97.6% which is comparable to various state-of-the-art architectures.

Keywords: Multiclass classification, convolution neural network, OpenCV, Data Augmentation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 822

Authors: Weitao Lin

Abstract:

To quickly extract adequate information from large-scale unstructured text data, this paper studies the representation of events in Chinese scenarios and performs the regularized abstraction. It proposes a Chinese event detection technique based on dependency parsing and rule matching. The method first performs dependency parsing on the original utterance, then performs pattern matching at the word or phrase granularity based on the results of dependent syntactic analysis, filters out the utterances with prominent non-event characteristics, and obtains the final results. The experimental results show the effectiveness of the method.

Keywords: Natural Language Processing, Chinese event detection, rules matching, dependency parsing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 180

Authors: José A. Menezes, Giordano Cabral, Bruno T. Gomes

Abstract:

Choosing good features is an essential part of machine learning. Recent techniques aim to automate this process. For instance, feature learning intends to learn the transformation of raw data into a useful representation to machine learning tasks. In automatic audio classification tasks, this is interesting since the audio, usually complex information, needs to be transformed into a computationally convenient input to process. Another technique tries to generate features by searching a feature space. Genetic algorithms, for instance, have being used to generate audio features by combining or modifying them. We find this approach particularly interesting and, despite the undeniable advances of feature learning approaches, we wanted to take a step forward in the use of genetic algorithms to find audio features, combining them with more conventional methods, like PCA, and inserting search control mechanisms, such as constraints over a confusion matrix. This work presents the results obtained on particular audio classification problems.

Keywords: Feature generation, feature learning, genetic algorithm, music information retrieval.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1084

Authors: Li Kewen, Su Zhaoxin, Wang Xingmou, Zhu Jian Bing

Abstract:

Conventional reservoir prediction methods ar not sufficient to explore the implicit relation between seismic attributes, and thus data utilization is low. In order to improve the predictive classification accuracy of reservoir lithology, this paper proposes a deep learning lithology prediction method based on ResNet (Residual Neural Network) and SENet (Squeeze-and-Excitation Neural Network). The neural network model is built and trained by using seismic attribute data and lithology data of Shengli oilfield, and the nonlinear mapping relationship between seismic attribute and lithology marker is established. The experimental results show that this method can significantly improve the classification effect of reservoir lithology, and the classification accuracy is close to 70%. This study can effectively predict the lithology of undrilled area and provide support for exploration and development.

Keywords: Convolutional neural network, lithology, prediction of reservoir lithology, seismic attributes.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 659

Authors: Ali Sarosh, Dong Yun-Feng, Muhammad Umer

Abstract:

Fully reusable spaceplanes do not exist as yet. This implies that design-qualification for optimized highly-integrated forebody-inlet configuration of booster-stage vehicle cannot be based on archival data of other spaceplanes. Therefore, this paper proposes a novel TIPSO-SVM expert system methodology. A non-trivial problem related to optimization and classification of hypersonic forebody-inlet configuration in conjunction with mass-model of the two-stage-to-orbit (TSTO) vehicle is solved. The hybrid-heuristic machine learning methodology is based on two-step improved particle swarm optimizer (TIPSO) algorithm and two-step support vector machine (SVM) data classification method. The efficacy of method is tested by first evolving an optimal configuration for hypersonic compression system using TIPSO algorithm; thereafter, classifying the results using two-step SVM method. In the first step extensive but non-classified mass-model training data for multiple optimized configurations is segregated and pre-classified for learning of SVM algorithm. In second step the TIPSO optimized mass-model data is classified using the SVM classification. Results showed remarkable improvement in configuration and mass-model along with sizing parameters.

Keywords: TIPSO-SVM expert system, TIPSO algorithm, two-step SVM method, aerothermodynamics, mass-modeling, TSTO vehicle.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2322

Authors: Aleksandra Zysk, Pawel Badura

Abstract:

Recognizing and controlling vocal registers during singing is a difficult task for beginner vocalist. It requires among others identifying which part of natural resonators is being used when a sound propagates through the body. Thus, an application has been designed allowing for sound recording, automatic vocal register recognition (VRR), and a graphical user interface providing real-time visualization of the signal and recognition results. Six spectral features are determined for each time frame and passed to the support vector machine classifier yielding a binary decision on the head or chest register assignment of the segment. The classification training and testing data have been recorded by ten professional female singers (soprano, aged 19-29) performing sounds for both chest and head register. The classification accuracy exceeded 93% in each of various validation schemes. Apart from a hard two-class clustering, the support vector classifier returns also information on the distance between particular feature vector and the discrimination hyperplane in a feature space. Such an information reflects the level of certainty of the vocal register classification in a fuzzy way. Thus, the designed recognition and training application is able to assess and visualize the continuous trend in singing in a user-friendly graphical mode providing an easy way to control the vocal emission.

Keywords: Classification, singing, spectral analysis, vocal emission, vocal register.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1314

Authors: Samiah Alammari, Nassim Ammour

Abstract:

When providing a massive number of tasks successively to a deep learning process, a good performance of the model requires preserving the previous tasks data to retrain the model for each upcoming classification. Otherwise, the model performs poorly due to the catastrophic forgetting phenomenon. To overcome this shortcoming, we developed a successful continual learning deep model for remote sensing hyperspectral image regions classification. The proposed neural network architecture encapsulates two trainable subnetworks. The first module adapts its weights by minimizing the discrimination error between the land-cover classes during the new task learning, and the second module tries to learn how to replicate the data of the previous tasks by discovering the latent data structure of the new task dataset. We conduct experiments on hyperspectral image (HSI) dataset on Indian Pines. The results confirm the capability of the proposed method.

Keywords: Continual learning, data reconstruction, remote sensing, hyperspectral image segmentation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 237

Authors: Nermin Ozgulbas, Ali Serhan Koyuncugil

Abstract:

One of the biggest problems of SMEs is their tendencies to financial distress because of insufficient finance background. In this study, an Early Warning System (EWS) model based on data mining for financial risk detection is presented. CHAID algorithm has been used for development of the EWS. Developed EWS can be served like a tailor made financial advisor in decision making process of the firms with its automated nature to the ones who have inadequate financial background. Besides, an application of the model implemented which covered 7,853 SMEs based on Turkish Central Bank (TCB) 2007 data. By using EWS model, 31 risk profiles, 15 risk indicators, 2 early warning signals, and 4 financial road maps has been determined for financial risk mitigation.

Keywords: Early Warning Systems, Data Mining, Financial Risk, SMEs.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3390

Authors: Othman Belgassim, Krzysztof Jemielniak

Abstract:

The analysis of Acoustic Emission (AE) signal generated from metal cutting processes has often approached statistically. This is due to the stochastic nature of the emission signal as a result of factors effecting the signal from its generation through transmission and sensing. Different techniques are applied in this manner, each of which is suitable for certain processes. In metal cutting where the emission generated by the deformation process is rather continuous, an appropriate method for analysing the AE signal based on the root mean square (RMS) of the signal is often used and is suitable for use with the conventional signal processing systems. The aim of this paper is to set a strategy in tool failure detection in turning processes via the statistic analysis of the AE generated from the cutting zone. The strategy is based on the investigation of the distribution moments of the AE signal at predetermined sampling. The skews and kurtosis of these distributions are the key elements in the detection. A normal (Gaussian) distribution has first been suggested then this was eliminated due to insufficiency. The so called Beta distribution was then considered, this has been used with an assumed β density function and has given promising results with regard to chipping and tool breakage detection.

Keywords: AE signal, skew, kurtosis, tool failure

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1851

Authors: Ahyoung Jeon, Geunchul Park, Jung-Hoon Ro, Gye-rok Geon

Abstract:

Falls are the primary cause of accidents in people over the age of 65, and frequently lead to serious injuries. Since the early detection of falls is an important step to alert and protect the aging population, a variety of research on detecting falls was carried out including the use of accelerators, gyroscopes and tilt sensors. In exiting studies, falls were detected using an accelerometer with errors. In this study, the proposed method for detecting falls was to use two accelerometers to reject wrong falls detection. As falls are accompanied by the acceleration of gravity and rotational motion, the falls in this study were detected by using the z-axial acceleration differences between two sites. The falls were detected by calculating the difference between the analyses of accelerometers placed on two different positions on the chest of the subject. The parameters of the maximum difference of accelerations (diff_Z) and the integration of accelerations in a defined region (Sum_diff_Z) were used to form the fall detection algorithm. The falls and the activities of daily living (ADL) could be distinguished by using the proposed parameters without errors in spite of the impact and the change in the positions of the accelerometers. By comparing each of the axial accelerations, the directions of falls and the condition of the subject afterwards could be determined.In this study, by using two accelerometers without errors attached to two sites to detect falls, the usefulness of the proposed fall detection algorithm parameters, diff_Z and Sum_diff_Z, were confirmed.

Keywords: Tri-axial accelerometer, fall detection.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2069