Search results for: unsupervised feature ranking

Authors: Kun Xu, Yuan Xu, Jia Qiao

Abstract:

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

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

Procedia PDF Downloads 328

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

Abstract:

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

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

Procedia PDF Downloads 223

Authors: Anna Siuda-Bak

Abstract:

This paper adopts a comparative approach to examining the determinants of international mobility of German, Italian and British researchers who completed their doctoral education in the UK. Structured sampling and data collection techniques have been developed in order to retrieve information on participants from publicly available sources. This systematically collected data was supplemented with an on-line survey which captures participants’ job trajectories, including movements between positions, institutions and countries. In total, data on 949 German, Italian and British PhDs was collected. Logistic regression was employed to identify factors associated with one’s probability of moving outside the UK after his or her graduation. The predictor variables included factors associated with one’s PhD (field of study, ranking of the university which awarded the PhD degree) and family factors (having a child, nationality of the partner). Then, 9 constrained models were estimated to test the effect each variable has on probability of going to a specific destination, being English-speaking country, non-English speaking country or returning to the home country. The results show that females, arts and humanities graduates, and respondents with a partner from the UK are less mobile than their counterparts. The effect of the ranking of the university differed in two groups. The UK graduates from higher ranked universities were more likely to move abroad than to stay in the UK after their graduation. In contrast, non-UK natives from the same universities were less likely to be internationally mobile than non-UK natives from lower ranked universities. The nationality of the partner was the most important predictor of the specific destination choices. Graduates with partner from the home county were more likely to return home and those with a partner from the third country least likely to return.

Keywords: doctoral graduates, international mobility, nationality, UK

Procedia PDF Downloads 297

Authors: Jingting Luo, Yong Wang, Ying Wang

Abstract:

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

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

Procedia PDF Downloads 116

Authors: Sokkhey Phauk, Takeo Okazaki

Abstract:

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

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

Procedia PDF Downloads 87

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

Abstract:

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

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

Procedia PDF Downloads 63

Authors: Natasha Venter

Abstract:

Recent publications, including Truth to Power by André de Ruyter, Gangster State by Pieter-Louis Myburgh, and Enemy of the People by Pieter du Toit and Adriaan Basson, expose alleged corrupt acts by high-ranking members of State, as well as those in charge of State-owned entities. These literary contributions have gripped the attention of a nation plagued by corruption scandals and the alleged misappropriation of state funds on an almost daily basis. The books, however, leave the populace with the burning question of why “nothing happens” to these individuals who are so directly implicated in the literature. The process followed by the State in the largest successful prosecution of a corrupt state official, Jackie Selebi, sheds some light as to how such high-ranking persons might be brought to book. The Supreme Court of Appeal’s definition of corruption and the interpretation of the facts (as presented by the State prosecutors) by the court is also valuable. Furthermore, some insight into the laws that criminalise corruption in South Africa, as well as applicable international instruments, is necessary. South Africa is ranked as the 70th most corrupt country out of 180 countries by Transparency International’s 2021 Corruption Perceptions Index. This is worrisome as South Africa is a signatory of the United Nations Convention Against Corruption (2004) and, as such, has certain international obligations to fulfil. However, if the political will to prosecute corrupt officials in South Africa exists, there are laws and instruments available to punish these individuals. This would not only vindicate the authors of literature about corruption in the country but also restore the hope of South Africans that, ultimately, crime does not pay.

Keywords: corruption, eskom, state capture, government, literature, united nations, law, legal, Jackie selebi, supreme court of appeal

Procedia PDF Downloads 64

Authors: Rajkumar Kolangarakandy

Abstract:

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

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

Procedia PDF Downloads 316

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

Abstract:

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

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

Procedia PDF Downloads 560

Authors: Humera Malik

Abstract:

Gender inequality, as a societal issue, is prevalent in all spheres of life in Pakistan. It is world-wide understood that gender equality is a basic right of every human being as well as the source of development and prosperity for the whole country. In fact, many countries endeavor to ensure equal opportunities for men and women which will, in turn, help to attain sustainable growth in every field. Most of the women in Pakistan live their life under the societal pressure which is exerted by centuries old traditions. This archaic setup restricts women to stay at home because their survival is conditional to their total subjugation to the male member of the family. This patriarchal structure confers men the right to deal women as their property. It is not wrong to say that women endure severe discrimination in their whole life. No doubt, women are confronted with multifaceted discrimination in the field of education, health, politics, social status, etc. The main theme of this research is to ascertain the present condition of gender inequality in the field of economy in Pakistan. Pakistan’s poor ranking in Global Gender Gap Index, 2016 clearly depicts that women are deprived of fundamental rights as well as equal opportunities of development. This very state of affairs depicts the real picture of government’s commitment to women empowerment and gender equality. The nature of this research is descriptive which helps to determine the status of women in Pakistan on the basis of labour force participation, wage gap, estimated incomes, and ratio of high ranking positions secured by women. It is an endeavor to understand the reasons of economic inequality by following qualitative method of research. Moreover, few recommendations will be suggested to get rid of this issue.

Keywords: dismal, discrimination, feudal, patriarchal, wage gap

Procedia PDF Downloads 144

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

Abstract:

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

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

Procedia PDF Downloads 252

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

Abstract:

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

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

Procedia PDF Downloads 345

Authors: Paulo Fernando Silva Filho, Elcio Hideiti Shiguemori

Abstract:

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

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

Procedia PDF Downloads 251

Authors: Baptiste Bouvier

Abstract:

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

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

Procedia PDF Downloads 136

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

Abstract:

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

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

Procedia PDF Downloads 516

Authors: Saeedeh Barzegar Khalilsaraei, Manoocheher Kelarestaghi, Farshad Eshghi

Abstract:

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

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

Procedia PDF Downloads 55

Authors: Thomas Bryan, Veton Kepuska, Ivica Kostanic

Abstract:

Speaker recognition is performed in high Additive White Gaussian Noise (AWGN) environments using principals of Computational Auditory Scene Analysis (CASA). CASA methods often classify sounds from images in the time-frequency (T-F) plane using spectrograms or cochleargrams as the image. In this paper atomic decomposition implemented by matching pursuit performs a transform from time series speech signals to the T-F plane. The atomic decomposition creates a sparsely populated T-F vector in “weight space” where each populated T-F position contains an amplitude weight. The weight space vector along with the atomic dictionary represents a denoised, compressed version of the original signal. The arraignment or of the atomic indices in the T-F vector are used for classification. Unsupervised feature learning implemented by a sparse autoencoder learns a single dictionary of basis features from a collection of envelope samples from all speakers. The approach is demonstrated using pairs of speakers from the TIMIT data set. Pairs of speakers are selected randomly from a single district. Each speak has 10 sentences. Two are used for training and 8 for testing. Atomic index probabilities are created for each training sentence and also for each test sentence. Classification is performed by finding the lowest Euclidean distance between then probabilities from the training sentences and the test sentences. Training is done at a 30dB Signal-to-Noise Ratio (SNR). Testing is performed at SNR’s of 0 dB, 5 dB, 10 dB and 30dB. The algorithm has a baseline classification accuracy of ~93% averaged over 10 pairs of speakers from the TIMIT data set. The baseline accuracy is attributable to short sequences of training and test data as well as the overall simplicity of the classification algorithm. The accuracy is not affected by AWGN and produces ~93% accuracy at 0dB SNR.

Keywords: time-frequency plane, atomic decomposition, envelope sampling, Gabor atoms, matching pursuit, sparse dictionary learning, sparse autoencoder

Procedia PDF Downloads 264

Authors: Salah Ghamari

Abstract:

In this study, the ability of self organizing map artificial (SOM) neural networks in clustering the wheat seeds varieties according to morphological properties of them was considered. The SOM is one type of unsupervised competitive learning. Experimentally, five morphological features of 300 seeds (including three varieties: gaskozhen, Md and sardari) were obtained using image processing technique. The results show that the artificial neural network has a good performance (90.33% accuracy) in classification of the wheat varieties despite of high similarity in them. The highest classification accuracy (100%) was achieved for sardari.

Keywords: artificial neural networks, clustering, self organizing map, wheat variety

Procedia PDF Downloads 617

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 253

Authors: Bahram Fathi, Karim Alizadeh, Azam Mohammadbagheri

Abstract:

The aim of this paper is to investigate the role of oil price shocks in explaining business cycles in Iran using a dynamic stochastic general equilibrium approach. This model incorporates both productivity and oil revenue shocks. The results indicate that productivity shocks are relatively more important to business cycles than oil shocks. The model with two shocks produces different values for volatility, but these values have the same ranking as that of the actual data for most variables. In addition, the actual data are close to the ratio of standard deviations to the output obtained from the model with two shocks. The results indicate that productivity shocks are relatively more important to business cycles than the oil shocks. The model with only a productivity shock produces the most similar figures in term of volatility magnitude to that of the actual data. Next, we use the Impulse Response Functions (IRF) to evaluate the capability of the model. The IRF shows no effect of an oil shock on the capital stocks and on labor hours, which is a feature of the model. When the log-linearized system of equations is solved numerically, investment and labor hours were not found to be functions of the oil shock. This research recommends using different techniques to compare the model’s robustness. One method by which to do this is to have all decision variables as a function of the oil shock by inducing the stationary to the model differently. Another method is to impose a bond adjustment cost. This study intends to fill that gap. To achieve this objective, we derive a DSGE model that allows for the world oil price and productivity shocks. Second, we calibrate the model to the Iran economy. Next, we compare the moments from the theoretical model with both single and multiple shocks with that obtained from the actual data to see the extent to which business cycles in Iran can be explained by total oil revenue shock. Then, we use an impulse response function to evaluate the role of world oil price shocks. Finally, I present implications of the findings and interpretations in accordance with economic theory.

Keywords: oil price, shocks, dynamic stochastic general equilibrium, Iran

Procedia PDF Downloads 411

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 76

Authors: Imen Aribi Ben Amor

Abstract:

The aim of the present study is to analyze the performance of requests in emails among a group of Tunisian postgraduate students. It also seeks to determine the influence of the social factors on the participants’ requests performance. For this purpose, the data were collected using a discourse completion test (DCT). Accordingly, 42 Tunisian postgraduate students were asked to respond in English to eight different situations in which they carried out the speech act of request in emails. The data were analyzed based on the degree of directness. A detailed analysis of the head acts found in the DCT revealed that Tunisian Postgraduate students use a varied repertoire of request strategies (direct, conventionally indirect and non-conventionally indirect) but at the same time rely heavily on direct request strategies. They tended to address their requestees directly except for distant superiors. DCT results suggest that the participants are to some extent aware of the influence of the ranking of imposition and social distance but fail to acknowledge the weight of social power when performing requests in emails. The preference of the participants to use direct strategies may be the result of the effect of Tunisian culture and the negative transfer of Tunisian communicative strategies. Accordingly, this study suggests some pedagogical implications and suggestions for Tunisian EFL (English as a Foreign Language) instructors. They are required to pay closer attention to the pragmalinguistic nuances of the ways in which requests in emails are realized. Teachers can also help students understand academic email etiquettes by explicitly explaining what they expect in the student email. Thus, EFL teachers and syllabus designers should devote more attention to developing EFL learners’ pragmatic competence through teaching L2 pragmatics.

Keywords: directness, ranking of imposition, request strategies, social distance, social power

Procedia PDF Downloads 205

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 127

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 112

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 44

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 230

Authors: Irina Khutsishvili

Abstract:

The presented study develops a decision support methodology for multi-criteria group decision-making problem. The proposed methodology is based on the TOPSIS (Technique for Order Performance by Similarity to Ideal Solution) approach in the hesitant fuzzy environment. The main idea of decision-making problem is a selection of one best alternative or several ranking alternatives among a set of feasible alternatives. Typically, the process of decision-making is based on an evaluation of certain criteria. In many MCDM problems (such as medical diagnosis, project management, business and financial management, etc.), the process of decision-making involves experts' assessments. These assessments frequently are expressed in fuzzy numbers, confidence intervals, intuitionistic fuzzy values, hesitant fuzzy elements and so on. However, a more realistic approach is using linguistic expert assessments (linguistic variables). In the proposed methodology both the values and weights of the criteria take the form of linguistic variables, given by all decision makers. Then, these assessments are expressed in triangular fuzzy numbers. Consequently, proposed approach is based on triangular hesitant fuzzy TOPSIS decision-making model. Following the TOPSIS algorithm, first, the fuzzy positive ideal solution (FPIS) and the fuzzy negative-ideal solution (FNIS) are defined. Then the ranking of alternatives is performed in accordance with the proximity of their distances to the both FPIS and FNIS. Based on proposed approach the software package has been developed, which was used to rank investment projects in the real investment decision-making problem. The application and testing of the software were carried out based on the data provided by the ‘Bank of Georgia’.

Keywords: fuzzy TOPSIS approach, investment project, linguistic variable, multi-criteria decision making, triangular hesitant fuzzy set

Procedia PDF Downloads 391

Authors: Fatih Gundogan, Fatih Kafali, Abdullah Karadag, Alper Baloglu, Ersoy Pehlivan, Mustafa Eruyar, Osman Bayram, Orhan Karademiroglu, Wasim Shoman

Abstract:

Nowadays many cities around the world are investing their efforts and resources for the purpose of facilitating their citizen’s life and making cities more livable and sustainable by implementing newly emerged phenomena of smart city. For this purpose, related research institutions prepare and publish smart city indices or benchmarking reports aiming to measure the city’s current ‘smartness’ status. Several functional domains, various indicators along different selection and calculation methods are found within such indices and reports. The selection criteria varied for each institution resulting in inconsistency in the ranking and evaluating. This research aims to evaluate the impact of selecting such functional domains, indicators and calculation methods which may cause change in the rank. For that, six functional domains, i.e. Environment, Mobility, Economy, People, Living and governance, were selected covering 19 focus areas and 41 sub-focus (variable) areas. 60 out of 191 indicators were also selected according to several criteria. These were identified as a result of extensive literature review for 13 well known global indices and research and the ISO 37120 standards of sustainable development of communities. The values of the identified indicators were obtained from reliable sources for ten cities. The values of each indicator for the selected cities were normalized and standardized to objectively investigate the impact of the chosen indicators. Moreover, the effect of choosing an integration method to represent the values of indicators for each city is investigated by comparing the results of two of the most used methods i.e. geometric aggregation and fuzzy logic. The essence of these methods is assigning a weight to each indicator its relative significance. However, both methods resulted in different weights for the same indicator. As a result of this study, the alternation in city ranking resulting from each method was investigated and discussed separately. Generally, each method illustrated different ranking for the selected cities. However, it was observed that within certain functional areas the rank remained unchanged in both integration method. Based on the results of the study, it is recommended utilizing a common platform and method to objectively evaluate cities around the world. The common method should provide policymakers proper tools to evaluate their decisions and investments relative to other cities. Moreover, for smart cities indices, at least 481 different indicators were found, which is an immense number of indicators to be considered, especially for a smart city index. Further works should be devoted to finding mutual indicators representing the index purpose globally and objectively.

Keywords: functional domain, urban city index, indicator, smart city

Procedia PDF Downloads 124

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 113

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 45