Search results for: MFCC feature warping

Authors: Hae-Yeoun Lee

Abstract:

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

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

Procedia PDF Downloads 279

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

Abstract:

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

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

Procedia PDF Downloads 114

Authors: Rui Mao, Heming Ji, Xiaoyu Wang

Abstract:

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

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

Procedia PDF Downloads 155

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

Abstract:

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

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

Procedia PDF Downloads 155

Authors: Jianhong Xiang, Rui Sun, Linyu Wang

Abstract:

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

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

Procedia PDF Downloads 79

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

Abstract:

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

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

Procedia PDF Downloads 262

Authors: Mahmud Abba Tahir

Abstract:

This is report on experiment out to compare the sulphate resistance of sand mortar made with five different pozzolanic cement. The pozzolanic cement were prepared by blending powered burnt bricks from the Adamawa, Makurdi, Kano, Kaduna and Niger bricks factories with ordinary Portland cement in the ratio 1:4. Sand –pozzolanic cement mortars of mix ratio 1:6 and 1:3 with water-cement ratio of 0.65 and 0.40 respectively were used to prepare cubes and bars specimens. 150 mortar cubes of size 70mm x 70mm x 70mm and 35 mortar bars of 15mm x 15mm x 100mm dimensions were cast and cured for 28 days. The cured specimens then immersed in the solutions of K₂SO₄, (NH₄)₂SO₄ and water for 28 days and then tested. The compressive strengths of cubes in water increased by 34% while those in the sulphate solutions decreased. Strength decreases of the cubes, cracking and warping of bars immersed in K₂SO₄ were less than those in (NH₄)₂SO_4. Specimens made with Niger and Makurdi pulverized burnt bricks experienced less effect of the sulphates and can therefore be used as pozzolan in mortar and concrete to resist sulphate.

Keywords: burnt bricks powder, comparative, pozzolanic cement, sulphates

Procedia PDF Downloads 244

Authors: Adrià Arbués-Sangüesa, Coloma Ballester, Gloria Haro

Abstract:

Tracking sports players is a widely challenging scenario, specially in single-feed videos recorded in tight courts, where cluttering and occlusions cannot be avoided. This paper presents an analysis of several geometric and semantic visual features to detect and track basketball players. An ablation study is carried out and then used to remark that a robust tracker can be built with Deep Learning features, without the need of extracting contextual ones, such as proximity or color similarity, nor applying camera stabilization techniques. The presented tracker consists of: (1) a detection step, which uses a pretrained deep learning model to estimate the players pose, followed by (2) a tracking step, which leverages pose and semantic information from the output of a convolutional layer in a VGG network. Its performance is analyzed in terms of MOTA over a basketball dataset with more than 10k instances.

Keywords: basketball, deep learning, feature extraction, single-camera, tracking

Procedia PDF Downloads 138

Authors: Avatharam Ganivada, Krishna Shah

Abstract:

The Mask R-CNN is recently introduced by the team of Facebook AI Research (FAIR), which is mainly concerned with instance segmentation in images. Here, the Mask R-CNN is based on ResNet and feature pyramid network (FPN), where a single dropout method is employed. This paper provides a modified Mask R-CNN by adding multiple dropout methods into the Mask R-CNN. The proposed model has also utilized the concepts of Resnet and FPN to extract stage-wise network feature maps, wherein a top-down network path having lateral connections is used to obtain semantically strong features. The proposed model produces three outputs for each object in the image: class label, bounding box coordinates, and object mask. The performance of the proposed network is evaluated in the segmentation of every instance in images using COCO and cityscape datasets. The proposed model achieves better performance than the state-of-the-networks for the datasets.

Keywords: instance segmentation, object detection, convolutional neural networks, deep learning, computer vision

Procedia PDF Downloads 73

Authors: Farshideh Einsele, Hassan Foroosh

Abstract:

In this paper, we present a robust algorithm to recognize extracted text from grocery product images captured by mobile phone cameras. Recognition of such text is challenging since text in grocery product images varies in its size, orientation, style, illumination, and can suffer from perspective distortion. Pre-processing is performed to make the characters scale and rotation invariant. Since text degradations can not be appropriately defined using wellknown geometric transformations such as translation, rotation, affine transformation and shearing, we use the whole character black pixels as our feature vector. Classification is performed with minimum distance classifier using the maximum likelihood criterion, which delivers very promising Character Recognition Rate (CRR) of 89%. We achieve considerably higher Word Recognition Rate (WRR) of 99% when using lower level linguistic knowledge about product words during the recognition process.

Keywords: camera-based OCR, feature extraction, document, image processing, grocery products

Procedia PDF Downloads 406

Authors: Shih-Wen Hsiao, Rong-Qi Chen

Abstract:

In the field of fashion design, 3D Mannequin is a kind of assisting tool which could rapidly realize the design concepts. While the concept of 3D Mannequin is applied to the computer added fashion design, it will connect with the development and the application of design platform and system. Thus, the situation mentioned above revealed a truth that it is very critical to develop a module of 3D Mannequin which would correspond with the necessity of fashion design. This research proposes a concrete plan that developing and constructing a system of 3D Mannequin with Kinect. In the content, ergonomic measurements of objective human features could be attained real-time through the implement with depth camera of Kinect, and then the mesh morphing can be implemented through transformed the locations of the control-points on the model by inputting those ergonomic data to get an exclusive 3D mannequin model. In the proposed methodology, after the scanned points from the Kinect are revised for accuracy and smoothening, a complete human feature would be reconstructed by the ICP algorithm with the method of image processing. Also, the objective human feature could be recognized to analyze and get real measurements. Furthermore, the data of ergonomic measurements could be applied to shape morphing for the division of 3D Mannequin reconstructed by feature curves. Due to a standardized and customer-oriented 3D Mannequin would be generated by the implement of subdivision, the research could be applied to the fashion design or the presentation and display of 3D virtual clothes. In order to examine the practicality of research structure, a system of 3D Mannequin would be constructed with JAVA program in this study. Through the revision of experiments the practicability-contained research result would come out.

Keywords: 3D mannequin, kinect scanner, interactive closest point, shape morphing, subdivision

Procedia PDF Downloads 306

Authors: M. Abbasi Layegh, S. Haghipour, K. Athari, R. Khosravi, M. Tafkikialamdari

Abstract:

An approach to find the optimum mel-frequency cepstral coefficients (MFCCs) for the Radif of Mirzâ Ábdollâh, which is the principal emblem and the heart of Persian music, performed by most famous Iranian masters on two Iranian stringed instruments ‘Tar’ and ‘Setar’ is proposed. While investigating the variance of MFCC for each record in themusic database of 1500 gushe of the repertoire belonging to 12 modal systems (dastgâh and âvâz), we have applied the Fuzzy C-Mean clustering algorithm on each of the 12 coefficient and different combinations of those coefficients. We have applied the same experiment while increasing the number of coefficients but the clustering accuracy remained the same. Therefore, we can conclude that the first 7 MFCCs (V-7MFCC) are enough for classification of The Radif of Mirzâ Ábdollâh. Classical machine learning algorithms such as MLP neural networks, K-Nearest Neighbors (KNN), Gaussian Mixture Model (GMM), Hidden Markov Model (HMM) and Support Vector Machine (SVM) have been employed. Finally, it can be realized that SVM shows a better performance in this study.

Keywords: radif of Mirzâ Ábdollâh, Gushe, mel frequency cepstral coefficients, fuzzy c-mean clustering algorithm, k-nearest neighbors (KNN), gaussian mixture model (GMM), hidden markov model (HMM), support vector machine (SVM)

Procedia PDF Downloads 446

Authors: Robert Caulk

Abstract:

A generalized framework for adaptive machine learning deployments in algorithmic trading is introduced, tested, and released as open-source code. The presented software aims to test the hypothesis that recent data contains enough information to form a probabilistically favorable short-term price prediction. Further, the framework contains various adaptive machine learning techniques that are geared toward generating profit during strong trends and minimizing losses during trend changes. Results demonstrate that this adaptive machine learning approach is capable of capturing trends and generating profit. The presentation also discusses the importance of defining the parameter space associated with the dynamic training data-set and using the parameter space to identify and remove outliers from prediction data points. Meanwhile, the generalized architecture enables common users to exploit the powerful machinery while focusing on high-level feature engineering and model testing. The presentation also highlights common strengths and weaknesses associated with the presented technique and presents a broad range of well-tested starting points for feature set construction, target setting, and statistical methods for enforcing risk management and maintaining probabilistically favorable entry and exit points. The presentation also describes the end-to-end data processing tools associated with FreqAI, including automatic data fetching, data aggregation, feature engineering, safe and robust data pre-processing, outlier detection, custom machine learning and statistical tools, data post-processing, and adaptive training backtest emulation, and deployment of adaptive training in live environments. Finally, the generalized user interface is also discussed in the presentation. Feature engineering is simplified so that users can seed their feature sets with common indicator libraries (e.g. TA-lib, pandas-ta). The user also feeds data expansion parameters to fill out a large feature set for the model, which can contain as many as 10,000+ features. The presentation describes the various object-oriented programming techniques employed to make FreqAI agnostic to third-party libraries and external data sources. In other words, the back-end is constructed in such a way that users can leverage a broad range of common regression libraries (Catboost, LightGBM, Sklearn, etc) as well as common Neural Network libraries (TensorFlow, PyTorch) without worrying about the logistical complexities associated with data handling and API interactions. The presentation finishes by drawing conclusions about the most important parameters associated with a live deployment of the adaptive learning framework and provides the road map for future development in FreqAI.

Keywords: machine learning, market trend detection, open-source, adaptive learning, parameter space exploration

Procedia PDF Downloads 89

Authors: Ainagul Yermekova, Liudmila Goncharenko, Ali Baghirzade, Sergey Sybachin

Abstract:

In this article, we address the problem of Kazakhstan's transition to the Latin alphabet. The transition process started in 2017 and is scheduled to be completed in 2025. In connection with these events, the problem of recognizing the characters of the new alphabet is raised. Well-known character recognition programs such as ABBYY FineReader, FormReader, MyScript Stylus did not recognize specific Kazakh letters that were used in Cyrillic. The author tries to give an assessment of the well-known method of character recognition that could be in demand as part of the country's transition to the Latin alphabet. Three methods of character recognition: template, structured, and feature-based, are considered through the algorithms of operation. At the end of the article, a general conclusion is made about the possibility of applying a certain method to a particular recognition process: for example, in the process of population census, recognition of typographic text in Latin, or recognition of photos of car numbers, store signs, etc.

Keywords: text detection, template method, recognition algorithm, structured method, feature method

Procedia PDF Downloads 187

Authors: Tian Lan, Yixiang Wang, Wenxin Tai, Yilan Lyu, Zufeng Wu

Abstract:

The monaural speech enhancement task in the time-frequencydomain has a myriad of approaches, with the stacked con-volutional neural network (CNN) demonstrating superiorability in feature extraction and selection. However, usingstacked single convolutions method limits feature represen-tation capability and generalization ability. In order to solvethe aforementioned problem, we propose an attention-basedadaptive convolutional network that integrates the multi-scale convolutional operations into a operation-specific blockvia input dependent attention to adapt to complex auditoryscenes. In addition, we introduce a two-stage progressivelearning method to enlarge the receptive field without a dra-matic increase in computation burden. We conduct a series ofexperiments based on the TIMIT corpus, and the experimen-tal results prove that our proposed model is better than thestate-of-art models on all metrics.

Keywords: speech enhancement, adaptive convolu-tion, progressive learning, time-frequency domain

Procedia PDF Downloads 123

Authors: Bairam Khan, Premlata Vaishnava

Abstract:

The ability to conceptualize one entity in terms of another allows us to communicate through metaphors. This central feature of human cognition has evolved with the development of language, and the processing of metaphors is without any conscious appraisal and is quite effortless. South Asians, like other speech communities, have been using the kitchenary [culinary] metaphor in a very simple yet interesting way and are known for bringing into new and unique constellations wherever they are. This composite feature of our language is used to communicate in a precise and compact manner and maneuvers the expression. The present study explores the role of kitchenary metaphors in the making and shaping of idioms by applying Cognitive Metaphor Theories. Drawing on examples from a corpus of adverts, print, and electronic media, the study looks at the metaphorical language used by real people in real situations. The overarching theme throughout the course is that kitchenary metaphors are powerful tools of expression in Hindi-Urdu.

Keywords: cognitive metaphor theories, kitchenary metaphors, hindi-urdu print, and electronic media, grammatical structure of kitchenary metaphors of hindi-urdu

Procedia PDF Downloads 93

Authors: Bairam Khan, Premlata Vaishnava

Abstract:

The ability to conceptualize one entity in terms of another allows us to communicate through metaphors. This central feature of human cognition has evolved with the development of language, and the processing of metaphors is without any conscious appraisal and is quite effortless. South Asians, like other speech communities, have been using the kitchenary [culinary] metaphor in a very simple yet interesting way and are known for bringing into new and unique constellations wherever they are. This composite feature of our language is used to communicate in a precise and compact manner and maneuvers the expression. The present study explores the role of kitchenary metaphors in the making and shaping of idioms by applying Cognitive Metaphor Theories. Drawing on examples from a corpus of adverts, print, and electronic media, the study looks at the metaphorical language used by real people in real situations. The overarching theme throughout the course is that kitchenary metaphors are powerful tools of expression in Hindi-Urdu.

Keywords: cognitive metaphor theory, source domain, target domain, signifier- signified, kitchenary, ethnocultural elements of south asia and hindi- urdu language

Procedia PDF Downloads 77

Authors: Noura Al Akkari, Aurélie Foucquier, Sylvain Lespinats

Abstract:

Load monitoring is a management process for energy consumption towards energy savings and energy efficiency. Non Intrusive Load Monitoring (NILM) is one method of load monitoring used for disaggregation purposes. NILM is a technique for identifying individual appliances based on the analysis of the whole residence data retrieved from the main power meter of the house. Our NILM framework starts with data acquisition, followed by data preprocessing, then event detection, feature extraction, then general appliance modeling and identification at the final stage. The event detection stage is a core component of NILM process since event detection techniques lead to the extraction of appliance features. Appliance features are required for the accurate identification of the household devices. In this research work, we aim at developing a new event detection methodology with accurate load disaggregation to extract appliance features. Time-domain features extracted are used for tuning general appliance models for appliance identification and classification steps. We use unsupervised algorithms such as Dynamic Time Warping (DTW). The proposed method relies on detecting areas of operation of each residential appliance based on the power demand. Then, detecting the time at which each selected appliance changes its states. In order to fit with practical existing smart meters capabilities, we work on low sampling data with a frequency of (1/60) Hz. The data is simulated on Load Profile Generator software (LPG), which was not previously taken into consideration for NILM purposes in the literature. LPG is a numerical software that uses behaviour simulation of people inside the house to generate residential energy consumption data. The proposed event detection method targets low consumption loads that are difficult to detect. Also, it facilitates the extraction of specific features used for general appliance modeling. In addition to this, the identification process includes unsupervised techniques such as DTW. To our best knowledge, there exist few unsupervised techniques employed with low sampling data in comparison to the many supervised techniques used for such cases. We extract a power interval at which falls the operation of the selected appliance along with a time vector for the values delimiting the state transitions of the appliance. After this, appliance signatures are formed from extracted power, geometrical and statistical features. Afterwards, those formed signatures are used to tune general model types for appliances identification using unsupervised algorithms. This method is evaluated using both simulated data on LPG and real-time Reference Energy Disaggregation Dataset (REDD). For that, we compute performance metrics using confusion matrix based metrics, considering accuracy, precision, recall and error-rate. The performance analysis of our methodology is then compared with other detection techniques previously used in the literature review, such as detection techniques based on statistical variations and abrupt changes (Variance Sliding Window and Cumulative Sum).

Keywords: electrical disaggregation, DTW, general appliance modeling, event detection

Procedia PDF Downloads 78

Authors: Swarnadip Ghosh

Abstract:

Sentiment Analysis is the process of detecting the contextual polarity of text. In other words, it determines whether a piece of writing is positive, negative or neutral.Sentiment analysis of documents holds great importance in today's world, when numerous information is stored in databases and in the world wide web. An efficient algorithm to illicit such information, would be beneficial for social, economic as well as medical purposes. In this project, we have developed an algorithm to classify a document into positive or negative. Using our algorithm, we obtained a feature set from the data, and classified the documents based on this feature set. It is important to note that, in the classification, we have not used the independence assumption, which is considered by many procedures like the Naive Bayes. This makes the algorithm more general in scope. Moreover, because of the sparsity and high dimensionality of such data, we did not use empirical distribution for estimation, but developed a method by finding degree of close clustering of the data points. We have applied our algorithm on a movie review data set obtained from IMDb and obtained satisfactory results.

Keywords: sentiment, Run's Test, cross validation, higher dimensional pmf estimation

Procedia PDF Downloads 402

Authors: Yao-Hong Tsai

Abstract:

This paper presents an efficient fusion algorithm for iris images to generate stable feature for recognition in unconstrained environment. Recently, iris recognition systems are focused on real scenarios in our daily life without the subject’s cooperation. Under large variation in the environment, the objective of this paper is to combine information from multiple images of the same iris. The result of image fusion is a new image which is more stable for further iris recognition than each original noise iris image. A wavelet-based approach for multi-resolution image fusion is applied in the fusion process. The detection of the iris image is based on Adaboost algorithm and then local binary pattern (LBP) histogram is then applied to texture classification with the weighting scheme. Experiment showed that the generated features from the proposed fusion algorithm can improve the performance for verification system through iris recognition.

Keywords: image fusion, iris recognition, local binary pattern, wavelet

Procedia PDF Downloads 367

Authors: Bahaa Eltahawy, Mikko Ylihärsilä, Reino Virrankoski, Esko Petäjä

Abstract:

Sheet metal processing is automated, but the step from product models to the production machine control still requires human intervention. This may cause time consuming bottlenecks in the production process and increase the risk of human errors. In this paper we present a system, which automatically recognizes features from the CAD-model of the sheet metal product. By using these features, the system produces a complete model of the particular sheet metal product. Then the model is used as an input for the sheet metal processing machine. Currently the system is implemented, capable to recognize more than 11 of the most common sheet metal structural features, and the procedure is fully automated. This provides remarkable savings in the production time, and protects against the human errors. This paper presents the developed system architecture, applied algorithms and system software implementation and testing.

Keywords: feature recognition, automation, sheet metal manufacturing, CAD, CAM

Procedia PDF Downloads 355

Authors: Assma Azeroual, Karim Afdel, Mohamed El Hajji, Hassan Douzi

Abstract:

Key frame extraction methods select the most representative frames of a video, which can be used in different areas of video processing such as video retrieval, video summary, and video indexing. In this paper we present a novel approach for extracting key frames from video sequences. The frame is characterized uniquely by his contours which are represented by the dominant blocks. These dominant blocks are located on the contours and its near textures. When the video frames have a noticeable changement, its dominant blocks changed, then we can extracte a key frame. The dominant blocks of every frame is computed, and then feature vectors are extracted from the dominant blocks image of each frame and arranged in a feature matrix. Singular Value Decomposition is used to calculate sliding windows ranks of those matrices. Finally the computed ranks are traced and then we are able to extract key frames of a video. Experimental results show that the proposed approach is robust against a large range of digital effects used during shot transition.

Keywords: FSDWT, key frame extraction, shot detection, singular value decomposition

Procedia PDF Downloads 398

Authors: Alanoud Moraya Aldalan, Abdulaziz Almaleh

Abstract:

A crucial component of maintaining a customer-oriented business as in the telecom industry is understanding the reasons and factors that lead to customer churn. Competition between telecom companies has greatly increased in recent years. It has become more important to understand customers’ needs in this strong market of telecom industries, especially for those who are looking to turn over their service providers. So, predictive churn is now a mandatory requirement for retaining those customers. Machine learning can be utilized to accomplish this. Churn Prediction has become a very important topic in terms of machine learning classification in the telecommunications industry. Understanding the factors of customer churn and how they behave is very important to building an effective churn prediction model. This paper aims to predict churn and identify factors of customers’ churn based on their past service usage history. Aiming at this objective, the study makes use of feature selection, normalization, and feature engineering. Then, this study compared the performance of four different machine learning algorithms on the Orange dataset: Logistic Regression, Random Forest, Decision Tree, and Gradient Boosting. Evaluation of the performance was conducted by using the F1 score and ROC-AUC. Comparing the results of this study with existing models has proven to produce better results. The results showed the Gradients Boosting with feature selection technique outperformed in this study by achieving a 99% F1-score and 99% AUC, and all other experiments achieved good results as well.

Keywords: machine learning, gradient boosting, logistic regression, churn, random forest, decision tree, ROC, AUC, F1-score

Procedia PDF Downloads 134

Authors: Amartya Hatua, Trung Nguyen, Andrew Sung

Abstract:

In this paper, we study the information diffusion process on Twitter as a multivariate time series problem. Our model concerns three measures (volume, network influence, and sentiment of tweets) based on 10 features, and we collected 27 million tweets to build our information diffusion time series dataset for analysis. Then, different time series clustering techniques with Dynamic Time Warping (DTW) distance were used to identify different patterns of information diffusion. Finally, we built the information diffusion prediction models for new hashtags which comprise two phrases: The first phrase is recognizing the pattern using k-NN with DTW distance; the second phrase is building the forecasting model using the traditional Autoregressive Integrated Moving Average (ARIMA) model and the non-linear recurrent neural network of Long Short-Term Memory (LSTM). Preliminary results of performance evaluation between different forecasting models show that LSTM with clustering information notably outperforms other models. Therefore, our approach can be applied in real-world applications to analyze and predict the information diffusion characteristics of selected topics or memes (hashtags) in Twitter.

Keywords: ARIMA, DTW, information diffusion, LSTM, RNN, time series clustering, time series forecasting, Twitter

Procedia PDF Downloads 391

Authors: Noura Al Akkari, Aurélie Foucquier, Sylvain Lespinats

Abstract:

Load monitoring is a management process for energy consumption towards energy savings and energy efficiency. Non Intrusive Load Monitoring (NILM) is one method of load monitoring used for disaggregation purposes. NILM is a technique for identifying individual appliances based on the analysis of the whole residence data retrieved from the main power meter of the house. Our NILM framework starts with data acquisition, followed by data preprocessing, then event detection, feature extraction, then general appliance modeling and identification at the final stage. The event detection stage is a core component of NILM process since event detection techniques lead to the extraction of appliance features. Appliance features are required for the accurate identification of the household devices. In this research work, we aim at developing a new event detection methodology with accurate load disaggregation to extract appliance features. Time-domain features extracted are used for tuning general appliance models for appliance identification and classification steps. We use unsupervised algorithms such as Dynamic Time Warping (DTW). The proposed method relies on detecting areas of operation of each residential appliance based on the power demand. Then, detecting the time at which each selected appliance changes its states. In order to fit with practical existing smart meters capabilities, we work on low sampling data with a frequency of (1/60) Hz. The data is simulated on Load Profile Generator software (LPG), which was not previously taken into consideration for NILM purposes in the literature. LPG is a numerical software that uses behaviour simulation of people inside the house to generate residential energy consumption data. The proposed event detection method targets low consumption loads that are difficult to detect. Also, it facilitates the extraction of specific features used for general appliance modeling. In addition to this, the identification process includes unsupervised techniques such as DTW. To our best knowledge, there exist few unsupervised techniques employed with low sampling data in comparison to the many supervised techniques used for such cases. We extract a power interval at which falls the operation of the selected appliance along with a time vector for the values delimiting the state transitions of the appliance. After this, appliance signatures are formed from extracted power, geometrical and statistical features. Afterwards, those formed signatures are used to tune general model types for appliances identification using unsupervised algorithms. This method is evaluated using both simulated data on LPG and real-time Reference Energy Disaggregation Dataset (REDD). For that, we compute performance metrics using confusion matrix based metrics, considering accuracy, precision, recall and error-rate. The performance analysis of our methodology is then compared with other detection techniques previously used in the literature review, such as detection techniques based on statistical variations and abrupt changes (Variance Sliding Window and Cumulative Sum).

Keywords: general appliance model, non intrusive load monitoring, events detection, unsupervised techniques;

Procedia PDF Downloads 82

Authors: Christian Neunzig, Simon Fahle, Jürgen Schulz, Matthias Möller, Bernd Kuhlenkötter

Abstract:

Manufacturing companies are facing global competition and enormous cost pressure. The use of machine learning applications can help reduce production costs and create added value. Predictive quality enables the securing of product quality through data-supported predictions using machine learning models as a basis for decisions on test results. Furthermore, machine learning methods are able to process large amounts of data, deal with unfavourable row-column ratios and detect dependencies between the covariates and the given target as well as assess the multidimensional influence of all input variables on the target. Real production data are often subject to highly fluctuating boundary conditions and unbalanced data sets. Changes in production data manifest themselves in trends, systematic shifts, and seasonal effects. Thus, Machine learning applications require intensive pre-processing and feature selection. Data preprocessing includes rule-based data cleaning, the application of dimensionality reduction techniques, and the identification of comparable data subsets. Within the used real data set of Bosch hydraulic valves, the comparability of the same production conditions in the production of hydraulic valves within certain time periods can be identified by applying the concept drift method. Furthermore, a classification model is developed to evaluate the feature importance in different subsets within the identified time periods. By selecting comparable and stable features, the number of features used can be significantly reduced without a strong decrease in predictive power. The use of cross-process production data along the value chain of hydraulic valves is a promising approach to predict the quality characteristics of workpieces. In this research, the ada boosting classifier is used to predict the leakage of hydraulic valves based on geometric gauge blocks from machining, mating data from the assembly, and hydraulic measurement data from end-of-line testing. In addition, the most suitable methods are selected and accurate quality predictions are achieved.

Keywords: classification, achine learning, predictive quality, feature selection

Procedia PDF Downloads 162

Authors: Ping Tan, Xiaomeng Su, Yi Shen

Abstract:

The motion intention in the motor imagery braincomputer interface is identified by classifying the event-related desynchronization (ERD) and event-related synchronization ERS characteristics of sensorimotor rhythm (SMR) in EEG signals. When the subject imagines different limbs or different parts moving, the rhythm components and bandwidth will change, which varies from person to person. How to find the effective sensorimotor frequency band of subjects is directly related to the classification accuracy of brain-computer interface. To solve this problem, this paper proposes a Minimum Distance to Riemannian Mean Classification method based on Non-Uniform Filter Banks. During the training phase, the EEG signals are decomposed into multiple different bandwidt signals by using multiple band-pass filters firstly; Then the spatial covariance characteristics of each frequency band signal are computered to be as the feature vectors. these feature vectors will be classified by the MDRM (Minimum Distance to Riemannian Mean) method, and cross validation is employed to obtain the effective sensorimotor frequency bands. During the test phase, the test signals are filtered by the bandpass filter of the effective sensorimotor frequency bands, and the extracted spatial covariance feature vectors will be classified by using the MDRM. Experiments on the BCI competition IV 2a dataset show that the proposed method is superior to other classification methods.

Keywords: non-uniform filter banks, motor imagery, brain-computer interface, minimum distance to Riemannian mean

Procedia PDF Downloads 126

Authors: Jia-Hong Lee, Mei-Yi Wu, Hsien-Tsung Kuo

Abstract:

Texture is an important characteristic in real and synthetic scenes. Texture analysis plays a critical role in inspecting surfaces and provides important techniques in a variety of applications. Although several descriptors have been presented to extract texture features, the development of object recognition is still a difficult task due to the complex aspects of texture. Recently, many robust and scaling-invariant image features such as SIFT, SURF and ORB have been successfully used in image retrieval and object recognition. In this paper, we have tried to compare the performance for texture classification using these feature descriptors with k-means clustering. Different classifiers including K-NN, Naive Bayes, Back Propagation Neural Network , Decision Tree and Kstar were applied in three texture image sets － UIUCTex, KTH-TIPS and Brodatz, respectively. Experimental results reveal SIFTS as the best average accuracy rate holder in UIUCTex, KTH-TIPS and SURF is advantaged in Brodatz texture set. BP neuro network works best in the test set classification among all used classifiers.

Keywords: texture classification, texture descriptor, SIFT, SURF, ORB

Procedia PDF Downloads 369

Authors: Phuoc Si Nguyen

Abstract:

Infinite impulse response (IIR) filters can be designed from an analogue low pass prototype by using frequency transformation in the s-domain and bilinear z-transformation with pre-warping frequency; this method is known as frequency transformation from the s-domain to the z-domain. This paper will introduce a new method to transform an IIR digital filter to another type of IIR digital filter (low pass, high pass, band pass, band stop or narrow band) using a technique based on inverse bilinear z-transformation and inverse matrices. First, a matrix equation is derived from inverse bilinear z-transformation and Pascal’s triangle. This Low Pass Digital to Digital Filter Pascal Matrix Equation is used to transform a low pass digital filter to other digital filter types. From this equation and the inverse matrix, a Digital to Digital Filter Pascal Matrix Equation can be derived that is able to transform any IIR digital filter. This paper will also introduce some specific matrices to replace the inverse matrix, which is difficult to determine due to the larger size of the matrix in the current method. This will make computing and hand calculation easier when transforming from one IIR digital filter to another in the digital domain.

Keywords: bilinear z-transformation, frequency transformation, inverse bilinear z-transformation, IIR digital filters

Procedia PDF Downloads 423

Authors: Elia Favarelli, Enrico Testi, Andrea Giorgetti

Abstract:

Autonomous structural health monitoring (SHM) of many structures and bridges became a topic of paramount importance for maintenance purposes and safety reasons. This paper proposes a set of machine learning (ML) tools to perform automatic feature selection and detection of anomalies in a bridge from vibrational data and compare different feature extraction schemes to increase the accuracy and reduce the amount of data collected. As a case study, the Z-24 bridge is considered because of the extensive database of accelerometric data in both standard and damaged conditions. The proposed framework starts from the first four fundamental frequencies extracted through operational modal analysis (OMA) and clustering, followed by density-based time-domain filtering (tracking). The fundamental frequencies extracted are then fed to a dimensionality reduction block implemented through two different approaches: feature selection (intelligent multiplexer) that tries to estimate the most reliable frequencies based on the evaluation of some statistical features (i.e., mean value, variance, kurtosis), and feature extraction (auto-associative neural network (ANN)) that combine the fundamental frequencies to extract new damage sensitive features in a low dimensional feature space. Finally, one class classifier (OCC) algorithms perform anomaly detection, trained with standard condition points, and tested with normal and anomaly ones. In particular, a new anomaly detector strategy is proposed, namely one class classifier neural network two (OCCNN2), which exploit the classification capability of standard classifiers in an anomaly detection problem, finding the standard class (the boundary of the features space in normal operating conditions) through a two-step approach: coarse and fine boundary estimation. The coarse estimation uses classics OCC techniques, while the fine estimation is performed through a feedforward neural network (NN) trained that exploits the boundaries estimated in the coarse step. The detection algorithms vare then compared with known methods based on principal component analysis (PCA), kernel principal component analysis (KPCA), and auto-associative neural network (ANN). In many cases, the proposed solution increases the performance with respect to the standard OCC algorithms in terms of F1 score and accuracy. In particular, by evaluating the correct features, the anomaly can be detected with accuracy and an F1 score greater than 96% with the proposed method.

Keywords: anomaly detection, frequencies selection, modal analysis, neural network, sensor network, structural health monitoring, vibration measurement

Procedia PDF Downloads 123