Search results for: automated feature engineering

Authors: Saurabh Farkya, Govinda Surampudi

Abstract:

Optical Character Recognition is one of the current major research areas. This paper is focussed on recognition of Devanagari script and its sound generation. This Paper consists of two parts. First, Optical Character Recognition of Devnagari handwritten Script. Second, speech synthesis of the recognized text. This paper shows an implementation of support vector machines for the purpose of Devnagari Script recognition. The Support Vector Machines was trained with Multi Domain features; Transform Domain and Spatial Domain or Structural Domain feature. Transform Domain includes the wavelet feature of the character. Structural Domain consists of Distance Profile feature and Gradient feature. The Segmentation of the text document has been done in 3 levels-Line Segmentation, Word Segmentation, and Character Segmentation. The pre-processing of the characters has been done with the help of various Morphological operations-Otsu's Algorithm, Erosion, Dilation, Filtration and Thinning techniques. The Algorithm was tested on the self-prepared database, a collection of various handwriting. Further, Unicode was used to convert recognized Devnagari text into understandable computer document. The document so obtained is an array of codes which was used to generate digitized text and to synthesize Hindi speech. Phonemes from the self-prepared database were used to generate the speech of the scanned document using concatenation technique.

Keywords: Character Recognition (OCR), Text to Speech (TTS), Support Vector Machines (SVM), Library of Support Vector Machines (LIBSVM)

Procedia PDF Downloads 469

Authors: Sujata S. Kulkarni

Abstract:

Effective and efficient texture feature extraction and classification is an important problem in image understanding and recognition. This paper gives a review on effective texture classification method. The objective of the problem of texture representation is to reduce the amount of raw data presented by the image, while preserving the information needed for the task. Texture analysis is important in many applications of computer image analysis for classification include industrial and biomedical surface inspection, for example for defects and disease, ground classification of satellite or aerial imagery and content-based access to image databases.

Keywords: compressed sensing, feature extraction, image classification, texture analysis

Procedia PDF Downloads 400

Authors: Balpreet Singh Madan

Abstract:

The Middle Eastern countries have preserved their heritage, tradition, and culture in their buildings by incorporating vernacular features of Arab-Islamic Architecture. The harsh sun and arid climate in the Gulf region make their buildings and infrastructure extremely hot and challenging to live in. One such iconic feature of Arab architecture is the Mashrabiya, which has been refined and updated for both functional and aesthetic purposes. This feature helps reduce the impact of solar radiation in buildings and lowers the energy requirements for creating livable conditions. The incorporation of Mashrabiya in modern buildings in the region symbolizes the amalgamation of tradition with innovation and modern technology. These buildings depict Mashrabiya with refinements for its better functional performance and aesthetic appeal to make superior built forms. This paper emphasizes the study of Mashrabiya as a vernacular feature with its adaptability for Energy Conservation and Sustainability, as seen in some of the recent iconic buildings of the Middle East, through a literature review and case studies of renowned buildings.

Keywords: energy efficiency, climate responsive, sustainability, innovation, heritage, vernacular

Procedia PDF Downloads 63

Authors: Radul Shishkov, Orlin Davchev

Abstract:

The digital era has revolutionized architectural practices, with building information modeling (BIM) emerging as a pivotal tool for architects, engineers, and construction professionals. However, the transition from traditional methods to BIM-centric approaches poses significant challenges, particularly in the context of existing structures. This research introduces a technical approach to bridge this gap through the development of algorithms that facilitate the automated transformation of 3D point cloud data into detailed BIM models. The core of this research lies in the application of algorithmic modeling and computational design methods to interpret and reconstruct point cloud data -a collection of data points in space, typically produced by 3D scanners- into comprehensive BIM models. This process involves complex stages of data cleaning, feature extraction, and geometric reconstruction, which are traditionally time-consuming and prone to human error. By automating these stages, our approach significantly enhances the efficiency and accuracy of creating BIM models for existing buildings. The proposed algorithms are designed to identify key architectural elements within point clouds, such as walls, windows, doors, and other structural components, and to translate these elements into their corresponding BIM representations. This includes the integration of parametric modeling techniques to ensure that the generated BIM models are not only geometrically accurate but also embedded with essential architectural and structural information. Our methodology has been tested on several real-world case studies, demonstrating its capability to handle diverse architectural styles and complexities. The results showcase a substantial reduction in time and resources required for BIM model generation while maintaining high levels of accuracy and detail. This research contributes significantly to the field of architectural technology by providing a scalable and efficient solution for the integration of existing structures into the BIM framework. It paves the way for more seamless and integrated workflows in renovation and heritage conservation projects, where the accuracy of existing conditions plays a critical role. The implications of this study extend beyond architectural practices, offering potential benefits in urban planning, facility management, and historic preservation.

Keywords: BIM, 3D point cloud, algorithmic modeling, computational design, architectural reconstruction

Procedia PDF Downloads 22

Authors: Yixiu Liu, Yunzhou Zhang, Jianning Chi, Hao Chu, Rui Zheng, Libo Sun, Guanghao Chen, Fangtong Zhou

Abstract:

In the last few years, large-scale person re-identification has attracted a lot of attention from video surveillance since it has a potential application prospect in public safety management. However, it is still a challenging job considering the variation in human pose, the changing illumination conditions and the lack of paired samples. Although the accuracy has been significantly improved, the data dependence of the sample training is serious. To tackle this problem, a new strategy is proposed based on bag of visual words (BoVW) model of designing the feature representation which has been widely used in the field of image retrieval. The local features are extracted, and more discriminative feature representation is obtained by cross-view dictionary learning (CDL), then the assignment map is obtained through k-means clustering. Finally, the BoVW histograms are formed which encodes the images with the statistics of the feature classes in the assignment map. Experiments conducted on the CUHK03, Market1501 and MARS datasets show that the proposed method performs favorably against existing approaches.

Keywords: bag of visual words, cross-view dictionary learning, person re-identification, reranking

Procedia PDF Downloads 164

Authors: Wei-Jong Yang, Wei-Hau Du, Pau-Choo Chang, Jar-Ferr Yang, Pi-Hsia Hung

Abstract:

The demands of smart visual thing recognition in various devices have been increased rapidly for daily smart production, living and learning systems in recent years. This paper proposed a visual thing recognition system, which combines binary scale-invariant feature transform (SIFT), bag of words model (BoW), and support vector machine (SVM) by using color information. Since the traditional SIFT features and SVM classifiers only use the gray information, color information is still an important feature for visual thing recognition. With color-based SIFT features and SVM, we can discard unreliable matching pairs and increase the robustness of matching tasks. The experimental results show that the proposed object recognition system with color-assistant SIFT SVM classifier achieves higher recognition rate than that with the traditional gray SIFT and SVM classification in various situations.

Keywords: color moments, visual thing recognition system, SIFT, color SIFT

Procedia PDF Downloads 438

Authors: Jiaqi Huang, Yuheng Wang

Abstract:

Premises selection, the task of selecting a set of axioms for proving a given conjecture, is a major bottleneck in automated theorem proving. An array of deep-learning-based methods has been established for premises selection, but a perfect performance remains challenging. Our study examines the inaccuracy of deep neural networks in premises selection. Through training network models using encoded conjecture and axiom pairs from the Mizar Mathematical Library, two potential biases are found: the network models classify more premises as necessary than unnecessary, referred to as the ‘positive bias’, and the network models perform better in proving conjectures that paired with more axioms, referred to as ‘length bias’. The ‘positive bias’ and ‘length bias’ discovered could inform the limitation of existing deep neural networks.

Keywords: automated theorem proving, premises selection, deep learning, interpreting deep learning

Procedia PDF Downloads 142

Authors: Toleen Alaqqad, Kadi Alshabramiy, Suad Zaafarany, Basma Musallam

Abstract:

CADmapper is a significant tool of software for transforming geographic data into realistic CAD drawings. It speeds up and simplifies the conversion process by automating it. This allows architects, urban planners, engineers, and geographic information system (GIS) experts to solely concentrate on the imaginative and scientific parts of their projects. While the future incorporation of AI has the potential for further improvements, CADmapper's current capabilities make it an indispensable asset in the business. It covers a combination of 2D and 3D city and urban area models. The user can select a specific square section of the map to view, and the fee is based on the dimensions of the area being viewed. The procedure is straightforward: you choose the area you want, then pick whether or not to include topography. 3D architectural data (if available), followed by selecting whatever design program or CAD style you want to publish the document which contains more than 200 free broad town plans in DXF format. If you desire to specify a bespoke area, it's free up to 1 km2.

Keywords: cadmaper, gdata, 2d and 3d data conversion, automated cad drawing, urban planning software

Procedia PDF Downloads 33

Authors: Manisha Mukherjee, Diptarka Saha

Abstract:

Reliable forecasts of univariate time series data are often necessary for several contexts. ARIMA models are quite popular among practitioners in this regard. Hence, choosing correct parameter values for ARIMA is a challenging yet imperative task. Thus, a stepwise algorithm is introduced to provide automatic and robust estimates for parameters (p; d; q)(P; D; Q) used in seasonal ARIMA models. This process is focused on improvising the overall quality of the estimates, and it alleviates the problems induced due to the unidimensional nature of the methods that are currently used such as auto.arima. The fast and automated search of parameter space also ensures reliable estimates of the parameters that possess several desirable qualities, consequently, resulting in higher test accuracy especially in the cases of noisy data. After vigorous testing on real as well as simulated data, the algorithm doesn’t only perform better than current state-of-the-art methods, it also completely obviates the need for human intervention due to its automated nature.

Keywords: time series, ARIMA, auto.arima, ARIMA parameters, forecast, R function

Procedia PDF Downloads 130

Authors: Haq Nawaz, Muhammad Amjad Iqbal, Kamran Malik

Abstract:

"Altasreef" is an automated system available for Web and Android users which provide facility to the users to learn the Quran verbs. It provides the facility to the users to practice the learned material and also provide facility of exams of Arabic verbs variation focusing on Quran text. Arabic is a highly inflectional language. Almost all of its words connect to roots of three, four or five letters which approach the meaning of all their inflectional forms. In Arabic, a verb is formed by inserting the consonants into one of a set of verb patterns. Suffixes and prefixes are then added to generate the meaning of number, person, and gender. The active/passive voice and perfective aspect and other patterns are than generated. This application is designed for learners of Quranic Arabic who already have learn basics of Arabic conjugation. Application also provides the facility of translation of generated patterns. These translations are generated with the help of rule-based approach to give 100% results to the learners.

Keywords: NLP, Quran, Computational Linguistics, E Learning

Procedia PDF Downloads 132

Authors: Mahdieh Khalilinezhad, Silvana Dellepiane, Gianni Vernazza

Abstract:

The aim of the present work is to build a model based on tissue characterization that is able to discriminate pathological and non-pathological regions from three-phasic CT images. Based on feature selection in different phases, in this research, we design a neural network system that has optimal neuron number in a hidden layer. Our approach consists of three steps: feature selection, feature reduction, and classification. For each ROI, 6 distinct set of texture features are extracted such as first order histogram parameters, absolute gradient, run-length matrix, co-occurrence matrix, autoregressive model, and wavelet, for a total of 270 texture features. We show that with the injection of liquid and the analysis of more phases the high relevant features in each region changed. Our results show that for detecting HCC tumor phase3 is the best one in most of the features that we apply to the classification algorithm. The percentage of detection between these two classes according to our method, relates to first order histogram parameters with the accuracy of 85% in phase 1, 95% phase 2, and 95% in phase 3.

Keywords: multi-phasic liver images, texture analysis, neural network, hidden layer

Procedia PDF Downloads 240

Authors: Adekunle K. O, Adeniyi A. E, Kolawole E

Abstract:

One of the most dramatic trends in the communications market in recent years has been the growth of prepaid services. Today, prepaid no longer constitutes the low-revenue, basic-service segment. It is driven by a high margin, value-add service customers who view it as a convenient way of retaining control over their usage and communication spending while expecting high service levels. To service providers, prepaid services offer the advantage of reducing bad accounts while allowing them to predict usage and plan network resources. Yet, the real-time demands of prepaid services require a scalable, real-time platform to manage customers through their entire life cycle. It delivers integrated real-time rating, voucher management, recharge management, customer care and service provisioning for the generation of new prepaid services. It carries high scalability that can handle millions of prepaid customers in real-time through their entire life cycle.

Keywords: prepaid billing, voucher management, customers, automated, security

Procedia PDF Downloads 83

Authors: Maurice Ntahobari, Levin Kuhlmann, Mario Boley, Zhinoos Razavi Hesabi

Abstract:

For machine learning based epileptic seizure prediction, it is important for the model to be implemented in small implantable or wearable devices that can be used to monitor epilepsy patients; however, current state-of-the-art methods are complex and computationally intensive. We use Shapley Additive Explanation (SHAP) to find relevant intracranial electroencephalogram (iEEG) features and improve the computational efficiency of a state-of-the-art seizure prediction method based on the extra trees classifier while maintaining prediction performance. Results for a small contest dataset and a much larger dataset with continuous recordings of up to 3 years per patient from 15 patients yield better than chance prediction performance (p < 0.004). Moreover, while the performance of the SHAP-based model is comparable to that of the benchmark, the overall training and prediction time of the model has been reduced by a factor of 1.83. It can also be noted that the feature called zero crossing value is the best EEG feature for seizure prediction. These results suggest state-of-the-art seizure prediction performance can be achieved using efficient methods based on optimal feature selection.

Keywords: machine learning, seizure prediction, extra tree classifier, SHAP, epilepsy

Procedia PDF Downloads 81

Authors: Fabiola M. Villalobos-Castaldi, Nicolás C. Kemper, Esther Rojas-Krugger, Laura G. Ramírez-Sánchez

Abstract:

This paper presents the classification results about exploring the combination of a motion based approach with a local appearance method to describe the facial motion caused by the muscle contractions and expansions that are presented in facial expressions. The proposed feature extraction method take advantage of the knowledge related to which parts of the face reflects the highest deformations, so we selected 4 specific facial regions at which the appearance descriptor were applied. The most common used approaches for feature extraction are the holistic and the local strategies. In this work we present the results of using a local appearance approach estimating the correlation coefficient to the 4 corresponding landmark-localized facial templates of the expression face related to the neutral face. The results let us to probe how the proposed motion estimation scheme based on the local appearance correlation computation can simply and intuitively measure the motion parameters for some of the most relevant facial regions and how these parameters can be used to recognize facial expressions automatically.

Keywords: facial expression recognition system, feature extraction, local-appearance method, motion-based approach

Procedia PDF Downloads 387

Authors: N. Arunraj, C. P. V. Paul, D. M. D. Jayawardena, W. N. D. Fernando

Abstract:

Traffic congestion with increased numbers of vehicles is already a serious issue for many countries. The absence of sufficient parking spaces adds to the issue. Motorists are forced to wait in long queues to park their vehicles. This adds to the inconvenience faced by a motorist, kept waiting for a slot allocation, manually done along with the parking payment calculation. In Sri Lanka, nowadays, parking systems use barcode technology to identify the vehicles at both the entrance and the exit points. Customer management is handled by the use of man power. A parking space is, generally permanently sub divided according to the vehicle type. Here, again, is an issue. Parking spaces are not utilized to the maximum. The current arrangement leaves room for unutilized parking spaces. Accordingly, there is a need to manage the parking space dynamically. As a vehicle enters the parking area, available space has to be assigned for the vehicle according to the vehicle type. The system, Automated Parking System (APS), provides an automated solution using RFID Technology to identify the vehicles. Simultaneously, an algorithm manages the space allocation dynamically. With this system, there is no permanent parking slot allocation for a vehicle type. A desktop application manages the customer. A Web application is used to manage the external users with their reservations. The system also has an android application to view the nearest parking area from the current location. APS is built using java and php. It uses LED panels to guide the user inside the parking area to find the allocated parking slot accurately. The system ensures efficient performance, saving precious time for a customer. Compared with the current parking systems, APS interacts with users and increases customer satisfaction as well.

Keywords: RFID, android, web based system, barcode, algorithm, LED panels

Procedia PDF Downloads 577

Authors: T. Heikkinen, J. Oksman, T. Bragge, A. Nurmi, O. Kontkanen, T. Ahtoniemi

Abstract:

Motor impairment is an inherent phenotypic feature of several chronic neurodegenerative diseases, and pharmacological therapies aimed to counterbalance the motor disability have a great market potential. Animal models of chronic neurodegenerative diseases display a number deteriorating motor phenotype during the disease progression. There is a wide array of behavioral tools to evaluate motor functions in rodents. However, currently existing methods to study motor functions in rodents are often limited to evaluate gross motor functions only at advanced stages of the disease phenotype. The most commonly applied traditional motor assays used in CNS rodent models, lack the sensitivity to capture fine motor impairments or improvements. Fine motor skill characterization in rodents provides a more sensitive tool to capture more subtle motor dysfunctions and therapeutic effects. Importantly, similar approach, kinematic movement analysis, is also used in clinic, and applied both in diagnosis and determination of therapeutic response to pharmacological interventions. The aim of this study was to apply kinematic gait analysis, a novel and automated high precision movement analysis system, to characterize phenotypic deficits in three different chronic neurodegenerative animal models, a transgenic mouse model (SOD1 G93A) for amyotrophic lateral sclerosis (ALS), and R6/2 and Q175KI mouse models for Huntington’s disease (HD). The readouts from walking behavior included gait properties with kinematic data, and body movement trajectories including analysis of various points of interest such as movement and position of landmarks in the torso, tail and joints. Mice (transgenic and wild-type) from each model were analyzed for the fine motor kinematic properties at young ages, prior to the age when gross motor deficits are clearly pronounced. Fine motor kinematic Evaluation was continued in the same animals until clear motor dysfunction with conventional motor assays was evident. Time course analysis revealed clear fine motor skill impairments in each transgenic model earlier than what is seen with conventional gross motor tests. Motor changes were quantitatively analyzed for up to ~80 parameters, and the largest data sets of HD models were further processed with principal component analysis (PCA) to transform the pool of individual parameters into a smaller and focused set of mutually uncorrelated gait parameters showing strong genotype difference. Kinematic fine motor analysis of transgenic animal models described in this presentation show that this method isa sensitive, objective and fully automated tool that allows earlier and more sensitive detection of progressive neuromuscular and CNS disease phenotypes. As a result of the analysis a comprehensive set of fine motor parameters for each model is created, and these parameters provide better understanding of the disease progression and enhanced sensitivity of this assay for therapeutic testing compared to classical motor behavior tests. In SOD1 G93A, R6/2, and Q175KI mice, the alterations in gait were evident already several weeks earlier than with traditional gross motor assays. Kinematic testing can be applied to a wider set of motor readouts beyond gait in order to study whole body movement patterns such as with relation to joints and various body parts longitudinally, providing a sophisticated and translatable method for disseminating motor components in rodent disease models and evaluating therapeutic interventions.

Keywords: Gait analysis, kinematic, motor impairment, inherent feature

Procedia PDF Downloads 331

Authors: Abe Degale D., Cheng Jian

Abstract:

When creating automated video surveillance systems, violent action recognition is crucial. In recent years, hand-crafted feature detectors have been the primary method for achieving violence detection, such as the recognition of fighting activity. Researchers have also looked into learning-based representational models. On benchmark datasets created especially for the detection of violent sequences in sports and movies, these methods produced good accuracy results. The Hockey dataset's videos with surveillance camera motion present challenges for these algorithms for learning discriminating features. Image recognition and human activity detection challenges have shown success with deep representation-based methods. For the purpose of detecting violent images and identifying aggressive human behaviours, this research suggested a deep representation-based model using the transfer learning idea. The results show that the suggested approach outperforms state-of-the-art accuracy levels by learning the most discriminating features, attaining 99.34% and 99.98% accuracy levels on the Hockey and Movies datasets, respectively.

Keywords: violence detection, faster RCNN, transfer learning and, surveillance video

Procedia PDF Downloads 67

Authors: Soyon Kim, Edward Kim

Abstract:

In order to retrieve information from the massive stream of songs in the music industry, music search by title, lyrics, artist, mood, and genre has become more important. Despite the subjectivity and controversy over the definition of music genres across different nations and cultures, automatic genre classification systems that facilitate the process of music categorization have been developed. Manual genre selection by music producers is being provided as statistical data for designing automatic genre classification systems. In this paper, an automatic music genre classification system utilizing non-negative matrix factorization (NMF) is proposed. Short-term characteristics of the music signal can be captured based on the timbre features such as mel-frequency cepstral coefficient (MFCC), decorrelated filter bank (DFB), octave-based spectral contrast (OSC), and octave band sum (OBS). Long-term time-varying characteristics of the music signal can be summarized with (1) the statistical features such as mean, variance, minimum, and maximum of the timbre features and (2) the modulation spectrum features such as spectral flatness measure, spectral crest measure, spectral peak, spectral valley, and spectral contrast of the timbre features. Not only these conventional basic long-term feature vectors, but also NMF based feature vectors are proposed to be used together for genre classification. In the training stage, NMF basis vectors were extracted for each genre class. The NMF features were calculated in the log spectral magnitude domain (NMF-LSM) as well as in the basic feature vector domain (NMF-BFV). For NMF-LSM, an entire full band spectrum was used. However, for NMF-BFV, only low band spectrum was used since high frequency modulation spectrum of the basic feature vectors did not contain important information for genre classification. In the test stage, using the set of pre-trained NMF basis vectors, the genre classification system extracted the NMF weighting values of each genre as the NMF feature vectors. A support vector machine (SVM) was used as a classifier. The GTZAN multi-genre music database was used for training and testing. It is composed of 10 genres and 100 songs for each genre. To increase the reliability of the experiments, 10-fold cross validation was used. For a given input song, an extracted NMF-LSM feature vector was composed of 10 weighting values that corresponded to the classification probabilities for 10 genres. An NMF-BFV feature vector also had a dimensionality of 10. Combined with the basic long-term features such as statistical features and modulation spectrum features, the NMF features provided the increased accuracy with a slight increase in feature dimensionality. The conventional basic features by themselves yielded 84.0% accuracy, but the basic features with NMF-LSM and NMF-BFV provided 85.1% and 84.2% accuracy, respectively. The basic features required dimensionality of 460, but NMF-LSM and NMF-BFV required dimensionalities of 10 and 10, respectively. Combining the basic features, NMF-LSM and NMF-BFV together with the SVM with a radial basis function (RBF) kernel produced the significantly higher classification accuracy of 88.3% with a feature dimensionality of 480.

Keywords: mel-frequency cepstral coefficient (MFCC), music genre classification, non-negative matrix factorization (NMF), support vector machine (SVM)

Procedia PDF Downloads 265

Authors: Linyu Wang, Liguo Qiao, Jianhong Xiang, Hao Xu

Abstract:

In semantic communication, the existing joint Source Channel coding (JSCC) wireless communication system without pilot has unstable transmission performance and can not effectively capture the global information and location information of images. In this paper, a pilot-free image transmission system of joint source channel based on multi-level semantic information (Multi-level JSCC) is proposed. The transmitter of the system is composed of two networks. The feature extraction network is used to extract the high-level semantic features of the image, compress the information transmitted by the image, and improve the bandwidth utilization. Feature retention network is used to preserve low-level semantic features and image details to improve communication quality. The receiver also is composed of two networks. The received high-level semantic features are fused with the low-level semantic features after feature enhancement network in the same dimension, and then the image dimension is restored through feature recovery network, and the image location information is effectively used for image reconstruction. This paper verifies that the proposed multi-level JSCC algorithm can effectively transmit and recover image information in both AWGN channel and Rayleigh fading channel, and the peak signal-to-noise ratio (PSNR) is improved by 1~2dB compared with other algorithms under the same simulation conditions.

Keywords: deep learning, JSCC, pilot-free picture transmission, multilevel semantic information, robustness

Procedia PDF Downloads 89

Authors: Maha Wiss, Wael Khreich

Abstract:

Animals, objects, foods, plants, and other non-human terms are commonly used as a source of metaphors to describe females in formal and slang language. Comparing women to non-human items not only reflects cultural views that might conceptualize women as subordinates or in a lower position than humans, yet it conveys this degradation to the listeners. Moreover, the dehumanizing representation of females in the language normalizes the derogation and even encourages sexism and aggressiveness against women. Although dehumanization has been a popular research topic for decades, according to our knowledge, no studies have linked women's dehumanizing language to the machine learning field. Therefore, we introduce our research work as one of the first attempts to create a tool for the automated detection of the dehumanizing depiction of females in English texts. We also present the first labeled dataset on the charted topic, which is used for training supervised machine learning algorithms to build an accurate classification model. The importance of this work is that it accomplishes the first step toward mitigating dehumanizing language against females.

Keywords: gender bias, machine learning, NLP, women dehumanization

Procedia PDF Downloads 56

Authors: Syed Basit Ali Shah Bukhari, Yan Qiang, Saad Abdul Rauf, Syed Saqlaina Bukhari

Abstract:

Text Classification is the methodology to classify any given text into the respective category from a given set of categories. It is highly important and vital to use proper set of pre-processing , feature selection and classification techniques to achieve this purpose. In this paper we have used different ensemble techniques along with variance in feature selection parameters to see the change in overall accuracy of the result and also on some other individual class based features which include precision value of each individual category of the text. After subjecting our data through pre-processing and feature selection techniques , different individual classifiers were tested first and after that classifiers were combined to form ensembles to increase their accuracy. Later we also studied the impact of decreasing the classification categories on over all accuracy of data. Text classification is highly used in sentiment analysis on social media sites such as twitter for realizing people’s opinions about any cause or it is also used to analyze customer’s reviews about certain products or services. Opinion mining is a vital task in data mining and text categorization is a back-bone to opinion mining.

Keywords: Natural Language Processing, Ensemble Classifier, Bagging Classifier, AdaBoost

Procedia PDF Downloads 206

Authors: Fatma El-Zahraa El-Taher, Ayman Taha, Jane Courtney, Susan Mckeever

Abstract:

Understanding road networks plays an important role in navigation applications such as self-driving vehicles and route planning for individual journeys. Intersections of roads are essential components of road networks. Understanding the features of an intersection, from a simple T-junction to larger multi-road junctions, is critical to decisions such as crossing roads or selecting the safest routes. The identification and profiling of intersections from satellite images is a challenging task. While deep learning approaches offer the state-of-the-art in image classification and detection, the availability of training datasets is a bottleneck in this approach. In this paper, a labelled satellite image dataset for the intersection recognition problem is presented. It consists of 14,692 satellite images of Washington DC, USA. To support other users of the dataset, an automated download and labelling script is provided for dataset replication. The challenges of construction and fine-grained feature labelling of a satellite image dataset is examined, including the issue of how to address features that are spread across multiple images. Finally, the accuracy of the detection of intersections in satellite images is evaluated.

Keywords: satellite images, remote sensing images, data acquisition, autonomous vehicles

Procedia PDF Downloads 113

Authors: Fawaz S. Al-Anzi, Dia AbuZeina

Abstract:

Speech recognition is of an important contribution in promoting new technologies in human computer interaction. Today, there is a growing need to employ speech technology in daily life and business activities. However, speech recognition is a challenging task that requires different stages before obtaining the desired output. Among automatic speech recognition (ASR) components is the feature extraction process, which parameterizes the speech signal to produce the corresponding feature vectors. Feature extraction process aims at approximating the linguistic content that is conveyed by the input speech signal. In speech processing field, there are several methods to extract speech features, however, Mel Frequency Cepstral Coefficients (MFCC) is the popular technique. It has been long observed that the MFCC is dominantly used in the well-known recognizers such as the Carnegie Mellon University (CMU) Sphinx and the Markov Model Toolkit (HTK). Hence, this paper focuses on the MFCC method as the standard choice to identify the different speech segments in order to obtain the language phonemes for further training and decoding steps. Due to MFCC good performance, the previous studies show that the MFCC dominates the Arabic ASR research. In this paper, we demonstrate MFCC as well as the intermediate steps that are performed to get these coefficients using the HTK toolkit.

Keywords: speech recognition, acoustic features, mel frequency, cepstral coefficients

Procedia PDF Downloads 232

Authors: Sandra Mitrovic, Gaurav Singh

Abstract:

In many industries, including telecommunications, churn prediction has been a topic of active research. A lot of attention has been drawn on devising the most informative features, and this area of research has gained even more focus with spread of (social) network analytics. The call detail records (CDRs) have been used to construct customer networks and extract potentially useful features. However, to the best of our knowledge, no studies including network features have yet proposed a generic way of representing network information. Instead, ad-hoc and dataset dependent solutions have been suggested. In this work, we build upon a recently presented method (node2vec) to obtain representations for nodes in observed network. The proposed approach is generic and applicable to any network and domain. Unlike node2vec, which assumes a static network, we consider a dynamic and time-evolving network. To account for this, we propose an approach that constructs the feature representation of each node by generating its node2vec representations at different timestamps, concatenating them and finally compressing using an auto-encoder-like method in order to retain reasonably long and informative feature vectors. We test the proposed method on churn prediction task in telco domain. To predict churners at timestamp ts+1, we construct training and testing datasets consisting of feature vectors from time intervals [t1, ts-1] and [t2, ts] respectively, and use traditional supervised classification models like SVM and Logistic Regression. Observed results show the effectiveness of proposed approach as compared to ad-hoc feature selection based approaches and static node2vec.

Keywords: churn prediction, dynamic networks, node2vec, auto-encoders

Procedia PDF Downloads 288

Authors: Osamah Al Qadoori

Abstract:

Using cloud computing in educational sectors grow rapidly in UAE. Initially, within Cloud-Learning Environment Students whenever and wherever can remotely join the online-classroom, on the other hand, Cloud-Based Learning is greatly decreasing the infrastructure and the maintenance cost. Nowadays in many schools (K-12), institutes, colleges as well as universities in UAE Cloud-Based Teaching and Learning environments gain a higher demand and concern. Many students don’t use the available online-educational resources effectively. The challenging question is to which extend these educational resources which are installed in the cloud environment are valuable and constructive? In this paper the researcher is seeking to design an expert agent prototype where the huge information being accommodated inside the cloud environment will go through expert filtration before going to be utilized by other clients (students). To achieve this goal, the focus of the present research would be on two different directions the educational human expertise and the automated-educational expert systems.

Keywords: cloud computing, cloud-learning environment, online-classroom, the educational human expertise, the automated-educational expert systems

Procedia PDF Downloads 516

Authors: Paloma Mendes Saldanha

Abstract:

Access to information is a prerequisite for democracy while also guiding the material construction of fundamental rights. The exercise of citizenship requires knowing, understanding, questioning, advocating for, and securing rights and responsibilities. In other words, it goes beyond mere active electoral participation and materializes through awareness and the struggle for rights and responsibilities in the various spaces occupied by the population in their daily lives. In times of hyper-cultural connectivity, active citizenship is shaped through ethical trust processes, most often established between humans and algorithms. Automated decisions, so prevalent in various everyday situations, such as purchase preference predictions, virtual voice assistants, reduction of accidents in autonomous vehicles, content removal, resume selection, etc., have already found their place as a normalized discourse that sometimes does not reveal or make clear what violations of fundamental rights may occur when algorithmic explainability is lacking. In other words, technological and market development promotes a normalization for the use of automated decisions while silencing possible restrictions and/or breaches of rights through a culturally modeled, unethical, and unexplained trust process, which hinders the possibility of the right to a healthy, transparent, and complete exercise of citizenship. In this context, the article aims to identify the violations caused by the absence of algorithmic explainability in the exercise of citizenship through the construction of an unethical and silent trust process between humans and algorithms in automated decisions. As a result, it is expected to find violations of constitutionally protected rights such as privacy, data protection, and transparency, as well as the stipulation of algorithmic explainability as a fundamental right in the exercise of Brazilian citizenship in the era of virtualization, facing a threefold foundation called trust: culture, rules, and systems. To do so, the author will use a bibliographic review in the legal and information technology fields, as well as the analysis of legal and official documents, including national documents such as the Brazilian Federal Constitution, as well as international guidelines and resolutions that address the topic in a specific and necessary manner for appropriate regulation based on a sustainable trust process for a hyperconnected world.

Keywords: artificial intelligence, ethics, citizenship, trust

Procedia PDF Downloads 33

Authors: Dimitrie Marinceu, Alan Murchison

Abstract:

The Canadian Used Fuel Container (UFC) is a mid-size hemispherical headed copper coated steel container measuring 2.5 meters in length and 0.5 meters in diameter containing 48 used fuel bundles. The contained used fuel produces significant gamma radiation requiring automated assembly processes to complete the assembly. The design throughput of 2,500 UFCs per year places constraints on equipment and hot cell design for repeatability, speed of processing, robustness and recovery from upset conditions. After UFC assembly, the UFC is inserted into a Buffer Box (BB). The BB is made from adequately pre-shaped blocks (lower and upper block) and Highly Compacted Bentonite (HCB) material. The blocks are practically ‘sandwiching’ the UFC between them after assembly. This paper identifies one possible approach for the BB automatic assembly cell and processes. Automation of the BB assembly will have a significant positive impact on nuclear safety, quality, productivity, and reliability.

Keywords: used fuel packing plant, automatic assembly cell, used fuel container, buffer box, deep geological repository

Procedia PDF Downloads 249

Authors: Seda Sahin, Emin Akata

Abstract:

Obturator foramen is a specific structure in pelvic bone images and recognition of it is a new concept in medical image processing. Moreover, segmentation of bone structures such as obturator foramen plays an essential role for clinical research in orthopedics. In this paper, we present a novel method to analyze the similarity between the substructures of the imaged region and a hand drawn template, on hip radiographs to detect obturator foramen accurately with integrated usage of Marker-controlled Watershed segmentation and Zernike moment feature descriptor. Marker-controlled Watershed segmentation is applied to seperate obturator foramen from the background effectively. Zernike moment feature descriptor is used to provide matching between binary template image and the segmented binary image for obturator foramens for final extraction. The proposed method is tested on randomly selected 100 hip radiographs. The experimental results represent that our method is able to segment obturator foramens with % 96 accuracy.

Keywords: medical image analysis, segmentation of bone structures on hip radiographs, marker-controlled watershed segmentation, zernike moment feature descriptor

Procedia PDF Downloads 401

Authors: Mafarja Majdi, Salwani Abdullah, Najmeh S. Jaddi

Abstract:

One of the global combinatorial optimization problems in machine learning is feature selection. It concerned with removing the irrelevant, noisy, and redundant data, along with keeping the original meaning of the original data. Attribute reduction in rough set theory is an important feature selection method. Since attribute reduction is an NP-hard problem, it is necessary to investigate fast and effective approximate algorithms. In this paper, we proposed two feature selection mechanisms based on memetic algorithms (MAs) which combine the genetic algorithm with a fuzzy record to record travel algorithm and a fuzzy controlled great deluge algorithm to identify a good balance between local search and genetic search. In order to verify the proposed approaches, numerical experiments are carried out on thirteen datasets. The results show that the MAs approaches are efficient in solving attribute reduction problems when compared with other meta-heuristic approaches.

Keywords: rough set theory, attribute reduction, fuzzy logic, memetic algorithms, record to record algorithm, great deluge algorithm

Procedia PDF Downloads 422

Authors: Konstantinos Pikos, Dimitrios Kaimaris

Abstract:

Although designing building blocks is a procedure used by many planners around the world, there isn’t an automated tool that will help planners and designers achieve their goals with lesser effort. The difficulty of the subject lies in the repeating process of manually drawing lines, while not only it is mandatory to maintain the desirable offset but to also achieve a lesser impact to the existing building stock. In this paper, using Geographical Information Systems (GIS) and the Python programming language, an automated tool integrated into ArcGIS PRO, is being presented. Despite its simplistic enviroment and the lack of specialized building legislation due to the complex state of the field, a planner who is aware of such technical information can use the tool to draw an initial approach of the final building blocks in an area with pre-existing buildings in an attempt to organize the usually sprawling suburbs of a city or any continuously developing area. The tool uses ESRI’s ArcPy library to handle the spatial data, while interactions with the user is made throught Tkinter. The main process consists of a modification of building edgescoordinates, using NumPy library, in an effort to draw the line of best fit, so the user can get the optimal results per block’s side. Finally, after the tool runs successfully, a table of primary planning information is shown, such as the area of the building block and its coverage rate. Regardless of the primary stage of the tool’s development, it is a solid base where potential planners with programming skills could invest, so they can make the tool adapt to their individual needs. An example of the entire procedure in a test area is provided, highlighting both the strengths and weaknesses of the final results.

Keywords: arcPy, GIS, python, building blocks

Procedia PDF Downloads 157