Search results for: classification model

Authors: Mohammad H. Taheri, David J. Brown, Nasser Sherkat

Abstract:

Engagement is one of the most important factors in determining successful outcomes and deep learning in students. Existing approaches to detect student engagement involve periodic human observations that are subject to inter-rater reliability. Our solution uses real-time multimodal multisensor data labeled by objective performance outcomes to infer the engagement of students. The study involves four students with a combined diagnosis of cerebral palsy and a learning disability who took part in a 3-month trial over 59 sessions. Multimodal multisensor data were collected while they participated in a continuous performance test. Eye gaze, electroencephalogram, body pose, and interaction data were used to create a model of student engagement through objective labeling from the continuous performance test outcomes. In order to achieve this, a type of continuous performance test is introduced, the Seek-X type. Nine features were extracted including high-level handpicked compound features. Using leave-one-out cross-validation, a series of different machine learning approaches were evaluated. Overall, the random forest classification approach achieved the best classification results. Using random forest, 93.3% classification for engagement and 42.9% accuracy for disengagement were achieved. We compared these results to outcomes from different models: AdaBoost, decision tree, k-Nearest Neighbor, naïve Bayes, neural network, and support vector machine. We showed that using a multisensor approach achieved higher accuracy than using features from any reduced set of sensors. We found that using high-level handpicked features can improve the classification accuracy in every sensor mode. Our approach is robust to both sensor fallout and occlusions. The single most important sensor feature to the classification of engagement and distraction was shown to be eye gaze. It has been shown that we can accurately predict the level of engagement of students with learning disabilities in a real-time approach that is not subject to inter-rater reliability, human observation or reliant on a single mode of sensor input. This will help teachers design interventions for a heterogeneous group of students, where teachers cannot possibly attend to each of their individual needs. Our approach can be used to identify those with the greatest learning challenges so that all students are supported to reach their full potential.

Keywords: affective computing in education, affect detection, continuous performance test, engagement, flow, HCI, interaction, learning disabilities, machine learning, multimodal, multisensor, physiological sensors, student engagement

Procedia PDF Downloads 72

Authors: Younghoon Kim, Seoung Bum Kim

Abstract:

One-class classification plays an important role in detecting outlier and abnormality from normal observations. In the previous research, several attempts were made to extend the scope of application of the one-class classification techniques to statistical process control problems. For most previous approaches, such as support vector data description (SVDD) control chart, the design of the control limits is commonly based on the assumption that the proportion of abnormal observations is approximately equal to an expected Type I error rate in Phase I process. Because of the limitation of the one-class classification techniques based on convex optimization, we cannot make the proportion of abnormal observations exactly equal to expected Type I error rate: controlling Type I error rate requires to optimize constraints with integer decision variables, but convex optimization cannot satisfy the requirement. This limitation would be undesirable in theoretical and practical perspective to construct effective control charts. In this work, to address the limitation of previous approaches, we propose the one-class classification algorithm based on the mixed integer programming technique, which can solve problems formulated with continuous and integer decision variables. The proposed method minimizes the radius of a spherically shaped boundary subject to the number of normal data to be equal to a constant value specified by users. By modifying this constant value, users can exactly control the proportion of normal data described by the spherically shaped boundary. Thus, the proportion of abnormal observations can be made theoretically equal to an expected Type I error rate in Phase I process. Moreover, analogous to SVDD, the boundary can be made to describe complex structures by using some kernel functions. New multivariate control chart applying the effectiveness of the algorithm is proposed. This chart uses a monitoring statistic to characterize the degree of being an abnormal point as obtained through the proposed one-class classification. The control limit of the proposed chart is established by the radius of the boundary. The usefulness of the proposed method was demonstrated through experiments with simulated and real process data from a thin film transistor-liquid crystal display.

Keywords: control chart, mixed integer programming, one-class classification, support vector data description

Procedia PDF Downloads 154

Authors: Zainab Mutlaq Ibrahim, Mohamed Bader-El-Den, Mihaela Cocea

Abstract:

Students' textual feedback can hold unique patterns and useful information about learning process, it can hold information about advantages and disadvantages of teaching methods, assessment components, facilities, and other aspects of teaching. The results of analysing such a feedback can form a key point for institutions’ decision makers to advance and update their systems accordingly. This paper proposes a data mining framework for analysing end of unit general textual feedback using part of speech feature (PoS) with four machine learning algorithms: support vector machines, decision tree, random forest, and naive bays. The proposed framework has two tasks: first, to use the above algorithms to build an optimal model that automatically classifies the whole data set into two subsets, one subset is tailored to assessment practices (assessment related), and the other one is the non-assessment related data. Second task to use the same algorithms to build an optimal model for whole data set, and the new data subsets to automatically detect their sentiment. The significance of this paper is to compare the performance of the above four algorithms using part of speech feature to the performance of the same algorithms using n-grams feature. The paper follows Knowledge Discovery and Data Mining (KDDM) framework to construct the classification and sentiment analysis models, which is understanding the assessment domain, cleaning and pre-processing the data set, selecting and running the data mining algorithm, interpreting mined patterns, and consolidating the discovered knowledge. The results of this paper experiments show that both models which used both features performed very well regarding first task. But regarding the second task, models that used part of speech feature has underperformed in comparison with models that used unigrams and bigrams.

Keywords: assessment, part of speech, sentiment analysis, student feedback

Procedia PDF Downloads 113

Authors: Taylor Kolody, Farkhund Iqbal, Rabia Batool, Benjamin Fung, Mohammed Hussaeni, Saiqa Aleem

Abstract:

The rising threat of climate change has led to an increase in public awareness and care about our collective and individual environmental impact. A key component of this impact is our use of cars and other polluting forms of transportation, but it is often difficult for an individual to know how severe this impact is. While there are applications that offer this feedback, they require manual entry of what transportation mode was used for a given trip, which can be burdensome. In order to alleviate this shortcoming, a data from the 2016 TRIPlab datasets has been used to train a variety of machine learning models to automatically recognize the mode of transportation. The accuracy of 89.6% is achieved using single deep neural network model with Gated Recurrent Unit (GRU) architecture applied directly to trip data points over 4 primary classes, namely walking, public transit, car, and bike. These results are comparable in accuracy to results achieved by others using ensemble methods and require far less computation when classifying new trips. The lack of trip context data, e.g., bus routes, bike paths, etc., and the need for only a single set of weights make this an appropriate methodology for applications hoping to reach a broad demographic and have responsive feedback.

Keywords: classification, gated recurrent unit, recurrent neural network, transportation

Procedia PDF Downloads 108

Authors: Abdulaziz Alsadhan, Naveed Khan

Abstract:

In recent years intrusions on computer network are the major security threat. Hence, it is important to impede such intrusions. The hindrance of such intrusions entirely relies on its detection, which is primary concern of any security tool like Intrusion Detection System (IDS). Therefore, it is imperative to accurately detect network attack. Numerous intrusion detection techniques are available but the main issue is their performance. The performance of IDS can be improved by increasing the accurate detection rate and reducing false positive. The existing intrusion detection techniques have the limitation of usage of raw data set for classification. The classifier may get jumble due to redundancy, which results incorrect classification. To minimize this problem, Principle Component Analysis (PCA), Linear Discriminant Analysis (LDA), and Local Binary Pattern (LBP) can be applied to transform raw features into principle features space and select the features based on their sensitivity. Eigen values can be used to determine the sensitivity. To further classify, the selected features greedy search, back elimination, and Particle Swarm Optimization (PSO) can be used to obtain a subset of features with optimal sensitivity and highest discriminatory power. These optimal feature subset used to perform classification. For classification purpose, Support Vector Machine (SVM) and Multilayer Perceptron (MLP) used due to its proven ability in classification. The Knowledge Discovery and Data mining (KDD’99) cup dataset was considered as a benchmark for evaluating security detection mechanisms. The proposed approach can provide an optimal intrusion detection mechanism that outperforms the existing approaches and has the capability to minimize the number of features and maximize the detection rates.

Keywords: Particle Swarm Optimization (PSO), Principle Component Analysis (PCA), Linear Discriminant Analysis (LDA), Local Binary Pattern (LBP), Support Vector Machine (SVM), Multilayer Perceptron (MLP)

Procedia PDF Downloads 343

Authors: Rana Alaa El-Deen Ahmed, M. Elemam Shehab, Shereen Morsy, Nermeen Mekawie

Abstract:

With the growing popularity and acceptance of e-commerce platforms, users face an ever increasing burden in actually choosing the right product from the large number of online offers. Thus, techniques for personalization and shopping guides are needed by users. For a pleasant and successful shopping experience, users need to know easily which products to buy with high confidence. Since selling a wide variety of products has become easier due to the popularity of online stores, online retailers are able to sell more products than a physical store. The disadvantage is that the customers might not find products they need. In this research the customer will be able to find the products he is searching for, because recommender systems are used in some ecommerce web sites. Recommender system learns from the information about customers and products and provides appropriate personalized recommendations to customers to find the needed product. In this paper eleven classification algorithms are comparatively tested to find the best classifier fit for consumer online shopping attitudes and behavior in the experimented dataset. The WEKA knowledge analysis tool, which is an open source data mining workbench software used in comparing conventional classifiers to get the best classifier was used in this research. In this research by using the data mining tool (WEKA) with the experimented classifiers the results show that decision table and filtered classifier gives the highest accuracy and the lowest accuracy classification via clustering and simple cart.

Keywords: classification, data mining, machine learning, online shopping, WEKA

Procedia PDF Downloads 331

Authors: Jameela Ali, Hamid A. Jalab, Loay E. George, Abdul Rahim Ahmad, Azizah Suliman, Karim Al-Jashamy

Abstract:

Red blood cells (RBC) are the most common types of blood cells and are the most intensively studied in cell biology. The lack of RBCs is a condition in which the amount of hemoglobin level is lower than normal and is referred to as “anemia”. Abnormalities in RBCs will affect the exchange of oxygen. This paper presents a comparative study for various techniques for classifying the RBCs as normal, or abnormal (anemic) using WEKA. WEKA is an open source consists of different machine learning algorithms for data mining applications. The algorithm tested are Radial Basis Function neural network, Support vector machine, and K-Nearest Neighbors algorithm. Two sets of combined features were utilized for classification of blood cells images. The first set, exclusively consist of geometrical features, was used to identify whether the tested blood cell has a spherical shape or non-spherical cells. While the second set, consist mainly of textural features was used to recognize the types of the spherical cells. We have provided an evaluation based on applying these classification methods to our RBCs image dataset which were obtained from Serdang Hospital-alaysia, and measuring the accuracy of test results. The best achieved classification rates are 97%, 98%, and 79% for Support vector machines, Radial Basis Function neural network, and K-Nearest Neighbors algorithm respectively.

Keywords: K-nearest neighbors algorithm, radial basis function neural network, red blood cells, support vector machine

Procedia PDF Downloads 383

Authors: Hamidreza Fallah Lajimi , Elham Karami, Fatemeh Ali nasab, Mostafa Mahdavikia

Abstract:

Being responsive is an increasingly important skill for firms in today’s global economy; thus firms must be agile. Naturally, it follows that an organization’s agility depends on its supply chain being agile. However, achieving supply chain agility is a function of other abilities within the organization. This paper analyses results from a survey of 71 Iran manufacturing companies in order to identify some of the factors for agile organizations in managing their supply chains. Then we classification this company in four cluster with fuzzy c-mean technique and with four validations functional determine automatically the optimal number of clusters.

Keywords: agile supply chain, clustering, fuzzy clustering

Procedia PDF Downloads 434

Authors: Nadia Masood Khan, Muhammad Salman Khan, Gul Muhammad Khan

Abstract:

Cardiologists perform cardiac auscultation to detect abnormalities in heart sounds. Since accurate auscultation is a crucial first step in screening patients with heart diseases, there is a need to develop computer-aided detection/diagnosis (CAD) systems to assist cardiologists in interpreting heart sounds and provide second opinions. In this paper different algorithms are implemented for automated heart sound classification using unsegmented phonocardiogram (PCG) signals. Support vector machine (SVM), artificial neural network (ANN) and cartesian genetic programming evolved artificial neural network (CGPANN) without the application of any segmentation algorithm has been explored in this study. The signals are first pre-processed to remove any unwanted frequencies. Both time and frequency domain features are then extracted for training the different models. The different algorithms are tested in multiple scenarios and their strengths and weaknesses are discussed. Results indicate that SVM outperforms the rest with an accuracy of 73.64%.

Keywords: pattern recognition, machine learning, computer aided diagnosis, heart sound classification, and feature extraction

Procedia PDF Downloads 228

Authors: Jesús Horacio, Alfredo Ollero, Víctor Bouzas-Blanco, Augusto Pérez-Alberti

Abstract:

Rivers have traditionally been classified, assessed and managed in terms of hydrological, chemical and / or biological criteria. Geomorphological classifications had in the past a secondary role, although proposals like River Styles Framework, Catchment Baseline Survey or Stroud Rural Sustainable Drainage Project did incorporate geomorphology for management decision-making. In recent years many studies have been attracted to the geomorphological component. The geomorphological processes and their associated forms determine the structure of a river system. Understanding these processes and forms is a critical component of the sustainable rehabilitation of aquatic ecosystems. The fluvial auto-classification approach suggests that a river is a self-built natural system, with processes and forms designed to effectively preserve their ecological function (hydrologic, sedimentological and biological regime). Fluvial systems are formed by a wide range of elements with multiple non-linear interactions on different spatial and temporal scales. Besides, the fluvial auto-classification concept is built using data from the river itself, so that each classification developed is peculiar to the river studied. The variables used in the classification are specific stream power and mean grain size. A discriminant analysis showed that these variables are the best characterized processes and forms. The statistical technique applied allows to get an individual discriminant equation for each geomorphological type. The geomorphological classification was developed using sites with high naturalness. Each site is a control point of high ecological and geomorphological quality. The changes in the conditions of the control points will be quickly recognizable, and easy to apply a right management measures to recover the geomorphological type. The study focused on Galicia (NW Spain) and the mapping was made analyzing 122 control points (sites) distributed over eight river basins. In sum, this study provides a method for fluvial geomorphological classification that works as an open and flexible tool underlying the fluvial auto-classification concept. The hydrographic mapping is the visual expression of the results, such that each river has a particular map according to its geomorphological characteristics. Each geomorphological type is represented by a particular type of hydraulic geometry (channel width, width-depth ratio, hydraulic radius, etc.). An alteration of this geometry is indicative of a geomorphological disturbance (whether natural or anthropogenic). Hydrographic mapping is also dynamic because its meaning changes if there is a modification in the specific stream power and/or the mean grain size, that is, in the value of their equations. The researcher has to check annually some of the control points. This procedure allows to monitor the geomorphology quality of the rivers and to see if there are any alterations. The maps are useful to researchers and managers, especially for conservation work and river restoration.

Keywords: fluvial auto-classification concept, mapping, geomorphology, river

Procedia PDF Downloads 349

Authors: H. Jung, N. Kim, B. Kang, J. Choe

Abstract:

History matching is a crucial procedure for predicting reservoir performances and making future decisions. However, it is difficult due to uncertainties of initial reservoir models. Therefore, it is important to have reliable initial models for successful history matching of highly heterogeneous reservoirs such as channel reservoirs. In this paper, we proposed a novel scheme for regenerating geological models using support vector machine (SVM) and principal component analysis (PCA). First, we perform PCA for figuring out main geological characteristics of models. Through the procedure, permeability values of each model are transformed to new parameters by principal components, which have eigenvalues of large magnitude. Secondly, the parameters are projected into two-dimensional plane by multi-dimensional scaling (MDS) based on Euclidean distances. Finally, we train an SVM classifier using 20% models which show the most similar or dissimilar well oil production rates (WOPR) with the true values (10% for each). Then, the other 80% models are classified by trained SVM. We select models on side of low WOPR errors. One hundred channel reservoir models are initially generated by single normal equation simulation. By repeating the classification process, we can select models which have similar geological trend with the true reservoir model. The average field of the selected models is utilized as a probability map for regeneration. Newly generated models can preserve correct channel features and exclude wrong geological properties maintaining suitable uncertainty ranges. History matching with the initial models cannot provide trustworthy results. It fails to find out correct geological features of the true model. However, history matching with the regenerated ensemble offers reliable characterization results by figuring out proper channel trend. Furthermore, it gives dependable prediction of future performances with reduced uncertainties. We propose a novel classification scheme which integrates PCA, MDS, and SVM for regenerating reservoir models. The scheme can easily sort out reliable models which have similar channel trend with the reference in lowered dimension space.

Keywords: history matching, principal component analysis, reservoir modelling, support vector machine

Procedia PDF Downloads 136

Authors: A. Deswal, N. S. Deora, H. N. Mishra

Abstract:

The aim of the present study was to develop a rapid method for electronic nose for online quality control of oat milk. Analysis by electronic nose and bacteriological measurements were performed to analyse spoilage kinetics of oat milk samples stored at room temperature and refrigerated conditions for up to 15 days. Principal component analysis (PCA), discriminant factorial analysis (DFA) and soft independent modelling by class analogy (SIMCA) classification techniques were used to differentiate the samples of oat milk at different days. The total plate count (bacteriological method) was selected as the reference method to consistently train the electronic nose system. The e-nose was able to differentiate between the oat milk samples of varying microbial load. The results obtained by the bacteria total viable counts showed that the shelf-life of oat milk stored at room temperature and refrigerated conditions were 20 hours and 13 days, respectively. The models built classified oat milk samples based on the total microbial population into “unspoiled” and “spoiled”.

Keywords: electronic-nose, bacteriological, shelf-life, classification

Procedia PDF Downloads 236

Authors: Reza Shakoori

Abstract:

This paper presents a structural correction of Arabic and Persian strokes using manipulation of their chain codes in order to improve the rate and performance of Persian and Arabic handwritten word recognition systems. It collects pure and effective features to represent a character with one consolidated feature vector and reduces variations in order to decrease the number of training samples and increase the chance of successful classification. Our results also show that how the proposed approaches can simplify classification and consequently recognition by reducing variations and possible noises on the chain code by keeping orientation of characters and their backbone structures.

Keywords: Arabic, chain code normalization, OCR systems, image processing

Procedia PDF Downloads 373

Authors: Monica Racha, Siva Chandrasekaran, Alex Stojcevski

Abstract:

The engineering programs focus on promoting students' personal and professional development by ensuring that students acquire technical and professional competencies during four-year studies. The traditional engineering laboratory provides an opportunity for students to "practice by doing," and laboratory facilities aid them in obtaining insight and understanding of their discipline. Due to rapid technological advancements and the current COVID-19 outbreak, the traditional labs were transforming into virtual learning environments. Aim: To better understand the limitations of the physical laboratory, this research study aims to use a Machine Learning (ML) algorithm that interfaces with the Augmented Reality HoloLens and predicts the image behavior to classify and detect the electronic components. The automated electronic components error classification and detection automatically detect and classify the position of all components on a breadboard by using the ML algorithm. This research will assist first-year undergraduate engineering students in conducting laboratory practices without any supervision. With the help of HoloLens, and ML algorithm, students will reduce component placement error on a breadboard and increase the efficiency of simple laboratory practices virtually. Method: The images of breadboards, resistors, capacitors, transistors, and other electrical components will be collected using HoloLens 2 and stored in a database. The collected image dataset will then be used for training a machine learning model. The raw images will be cleaned, processed, and labeled to facilitate further analysis of components error classification and detection. For instance, when students conduct laboratory experiments, the HoloLens captures images of students placing different components on a breadboard. The images are forwarded to the server for detection in the background. A hybrid Convolutional Neural Networks (CNNs) and Support Vector Machines (SVMs) algorithm will be used to train the dataset for object recognition and classification. The convolution layer extracts image features, which are then classified using Support Vector Machine (SVM). By adequately labeling the training data and classifying, the model will predict, categorize, and assess students in placing components correctly. As a result, the data acquired through HoloLens includes images of students assembling electronic components. It constantly checks to see if students appropriately position components in the breadboard and connect the components to function. When students misplace any components, the HoloLens predicts the error before the user places the components in the incorrect proportion and fosters students to correct their mistakes. This hybrid Convolutional Neural Networks (CNNs) and Support Vector Machines (SVMs) algorithm automating electronic component error classification and detection approach eliminates component connection problems and minimizes the risk of component damage. Conclusion: These augmented reality smart glasses powered by machine learning provide a wide range of benefits to supervisors, professionals, and students. It helps customize the learning experience, which is particularly beneficial in large classes with limited time. It determines the accuracy with which machine learning algorithms can forecast whether students are making the correct decisions and completing their laboratory tasks.

Keywords: augmented reality, machine learning, object recognition, virtual laboratories

Procedia PDF Downloads 112

Authors: Xiaohua Zhu, Lingling Ma, Yongguang Zhao

Abstract:

Leaf Area Index (LAI) is a key structural characteristic of crops and plays a significant role in precision agricultural management and farmland ecosystem modeling. However, LAI retrieved from different resolution data contain a scaling bias due to the spatial heterogeneity and model non-linearity, that is, there is scale effect during multi-scale LAI estimate. In this article, a typical farmland in semi-arid regions of Chinese Inner Mongolia is taken as the study area, based on the combination of PROSPECT model and SAIL model, a multiple dimensional Look-Up-Table (LUT) is generated for multiple crops LAI estimation from unmanned aerial vehicle (UAV) hyperspectral data. Based on Taylor expansion method and computational geometry model, a scale transfer model considering both difference between inter- and intra-class is constructed for scale effect analysis of LAI inversion over inhomogeneous surface. The results indicate that, (1) the LUT method based on classification and parameter sensitive analysis is useful for LAI retrieval of corn, potato, sunflower and melon on the typical farmland, with correlation coefficient R2 of 0.82 and root mean square error RMSE of 0.43m2/m-2. (2) The scale effect of LAI is becoming obvious with the decrease of image resolution, and maximum scale bias is more than 45%. (3) The scale effect of inter-classes is higher than that of intra-class, which can be corrected efficiently by the scale transfer model established based Taylor expansion and Computational geometry. After corrected, the maximum scale bias can be reduced to 1.2%.

Keywords: leaf area index (LAI), scale effect, UAV-based hyperspectral data, look-up-table (LUT), remote sensing

Procedia PDF Downloads 422

Authors: Gulfam Haider, sana danish

Abstract:

Convolutional Neural Networks (CNNs) have emerged as powerful tools for image classification, and the choice of optimizers profoundly affects their performance. The study of optimizers and their adaptations remains a topic of significant importance in machine learning research. While numerous studies have explored and advocated for various optimizers, the efficacy of these optimization techniques is still subject to scrutiny. This work aims to address the challenges surrounding the effectiveness of optimizers by conducting a comprehensive analysis and evaluation. The primary focus of this investigation lies in examining the performance of different optimizers when employed in conjunction with the popular activation function, Rectified Linear Unit (ReLU). By incorporating ReLU, known for its favorable properties in prior research, the aim is to bolster the effectiveness of the optimizers under scrutiny. Specifically, we evaluate the adjustment of these optimizers with both the original Softmax activation function and the modified ReLU activation function, carefully assessing their impact on overall performance. To achieve this, a series of experiments are conducted using a well-established benchmark dataset for image classification tasks, namely the Canadian Institute for Advanced Research dataset (CIFAR-10). The selected optimizers for investigation encompass a range of prominent algorithms, including Adam, Root Mean Squared Propagation (RMSprop), Adaptive Learning Rate Method (Adadelta), Adaptive Gradient Algorithm (Adagrad), and Stochastic Gradient Descent (SGD). The performance analysis encompasses a comprehensive evaluation of the classification accuracy, convergence speed, and robustness of the CNN models trained with each optimizer. Through rigorous experimentation and meticulous assessment, we discern the strengths and weaknesses of the different optimization techniques, providing valuable insights into their suitability for image classification tasks. By conducting this in-depth study, we contribute to the existing body of knowledge surrounding optimizers in CNNs, shedding light on their performance characteristics for image classification. The findings gleaned from this research serve to guide researchers and practitioners in making informed decisions when selecting optimizers and activation functions, thus advancing the state-of-the-art in the field of image classification with convolutional neural networks.

Keywords: deep neural network, optimizers, RMsprop, ReLU, stochastic gradient descent

Procedia PDF Downloads 82

Authors: Asma A. Alsufyani, Maram A. Alharthi, Maha J. Althobaiti, Manal S. Alharthi, Huda Rizq

Abstract:

Twitter is one of the most popular microblogging sites that allows users to publish short text messages called 'tweets'. Increasing the number of accounts to follow (followings) increases the number of tweets that will be displayed from different topics in an unclassified manner in the timeline of the user. Therefore, it can be a vital solution for many Twitter users to have their tweets in a timeline classified into general categories to save the user’s time and to provide easy and quick access to tweets based on topics. In this paper, we developed a classifier for timeline tweets trained on a dataset consisting of 3600 tweets in total, which were collected from Saudi Twitter and annotated manually. We experimented with the well-known Bag-of-Words approach to text classification, and we used support vector machines (SVM) in the training process. The trained classifier performed well on a test dataset, with an average F1-measure equal to 92.3%. The classifier has been integrated into an application, which practically proved the classifier’s ability to classify timeline tweets of the user.

Keywords: corpus creation, feature extraction, machine learning, short text classification, social media, support vector machine, Twitter

Procedia PDF Downloads 130

Authors: Seynabou Toure, Oumar Diop, Kidiyo Kpalma, Amadou S. Maiga

Abstract:

Color and texture are the two most determinant elements for perception and recognition of the objects in an image. For this reason, color and texture analysis find a large field of application, for example in image classification and segmentation. But, the pioneering work in texture analysis was conducted on grayscale images, thus discarding color information. Many grey-level texture descriptors have been proposed and successfully used in numerous domains for image classification: face recognition, industrial inspections, food science medical imaging among others. Taking into account color in the definition of these descriptors makes it possible to better characterize images. Color texture is thus the subject of recent work, and the analysis of color texture images is increasingly attracting interest in the scientific community. In optical remote sensing systems, sensors measure separately different parts of the electromagnetic spectrum; the visible ones and even those that are invisible to the human eye. The amounts of light reflected by the earth in spectral bands are then transformed into grayscale images. The primary natural colors Red (R) Green (G) and Blue (B) are then used in mixtures of different spectral bands in order to produce RGB images. Thus, good color texture discrimination can be achieved using RGB under controlled illumination conditions. Some previous works investigate the effect of using different color space for color texture classification. However, the selection of the best performing color space in land-sea segmentation is an open question. Its resolution may bring considerable improvements in certain applications like coastline detection, where the detection result is strongly dependent on the performance of the land-sea segmentation. The aim of this paper is to present the results of a study conducted on different color spaces in order to show the best-performing color space for land-sea segmentation. In this sense, an experimental analysis is carried out using five different color spaces (RGB, XYZ, Lab, HSV, YCbCr). For each color space, the Haar wavelet decomposition is used to extract different color texture features. These color texture features are then used for Fusion of Over Segmentation (FOOS) based classification; this allows segmentation of the land part from the sea one. By analyzing the different results of this study, the HSV color space is found as the best classification performance while using color and texture features; which is perfectly coherent with the results presented in the literature.

Keywords: classification, coastline, color, sea-land segmentation

Procedia PDF Downloads 221

Authors: Chia-Hao Chang, Geng-Gui Wang, Jee-Cheng Wu

Abstract:

The prediction of a landslide is a difficult task because it requires a detailed study of past activities using a complete range of investigative methods to determine the changing condition. In this research, first step, LiDAR 1-meter by 1-meter resolution of digital elevation model (DEM) was used to generate six environmental factors of landslide. Then, back-propagation neural networks (BPNN) was adopted to identify scarp, landslide areas and non-landslide areas. The BPNN uses 6 environmental factors in input layer and 1 output layer. Moreover, 6 landslide areas are used as training areas and 4 landslide areas as test areas in the BPNN. The hidden layer is set to be 1 and 2; the hidden layer neurons are set to be 4, 5, 6, 7 and 8; the learning rates are set to be 0.01, 0.1 and 0.5. When using 1 hidden layer with 7 neurons and the learning rate sets to be 0.5, the result of Network training root mean square error is 0.001388. Finally, evaluation of BPNN classification accuracy by the confusion matrix shows that the overall accuracy can reach 94.4%, and the Kappa value is 0.7464.

Keywords: digital elevation model, DEM, environmental factors, back-propagation neural network, BPNN, LiDAR

Procedia PDF Downloads 113

Authors: Dmitriy Babenko, Sergey Yegorov, Ilya Korshukov, Aidana Sultanbekova, Valentina Barkhanskaya, Tatiana Bashirova, Yerzhan Zhunusov, Yevgeniya Li, Viktoriya Parakhina, Svetlana Kolesnichenko, Yeldar Baiken, Aruzhan Pralieva, Zhibek Zhumadilova, Matthew S. Miller, Gonzalo H. Hortelano, Anar Turmuhambetova, Antonella E. Chesca, Irina Kadyrova

Abstract:

Introduction: The rapidly evolving COVID-19 pandemic, along with the re-emergence of pathogens causing acute respiratory infections (ARI), has necessitated the development of novel diagnostic tools to differentiate various causes of ARI. MALDI-MS, due to its wide usage and affordability, has been proposed as a potential instrument for diagnosing SARS-CoV-2 versus non-SARS-CoV-2 ARI. The aim of this study was to investigate the potential of MALDI-MS in conjunction with a machine learning model to accurately distinguish between symptomatic infections caused by SARS-CoV-2 and non-SARS-CoV-2 during both the early and later phases of the pandemic. Furthermore, this study aimed to analyze mass spectrometry (MS) data obtained from nasal swabs of healthy individuals. Methods: We gathered mass spectra from 252 samples, comprising 108 SARS-CoV-2-positive samples obtained in 2020 (Covid 2020), 7 SARS-CoV- 2-positive samples obtained in 2023 (Covid 2023), 71 samples from symptomatic individuals without SARS-CoV-2 (Control non-Covid ARVI), and 66 samples from healthy individuals (Control healthy). All the samples were subjected to RT-PCR testing. For data analysis, we employed the caret R package to train and test seven machine-learning algorithms: C5.0, KNN, NB, RF, SVM-L, SVM-R, and XGBoost. We conducted a training process using a five-fold (outer) nested repeated (five times) ten-fold (inner) cross-validation with a randomized stratified splitting approach. Results: In this study, we utilized the Covid 2020 dataset as a case group and the non-Covid ARVI dataset as a control group to train and test various machine learning (ML) models. Among these models, XGBoost and SVM-R demonstrated the highest performance, with accuracy values of 0.97 [0.93, 0.97] and 0.95 [0.95; 0.97], specificity values of 0.86 [0.71; 0.93] and 0.86 [0.79; 0.87], and sensitivity values of 0.984 [0.984; 1.000] and 1.000 [0.968; 1.000], respectively. When examining the Covid 2023 dataset, the Naive Bayes model achieved the highest classification accuracy of 43%, while XGBoost and SVM-R achieved accuracies of 14%. For the healthy control dataset, the accuracy of the models ranged from 0.27 [0.24; 0.32] for k-nearest neighbors to 0.44 [0.41; 0.45] for the Support Vector Machine with a radial basis function kernel. Conclusion: Therefore, ML models trained on MALDI MS of nasopharyngeal swabs obtained from patients with Covid during the initial phase of the pandemic, as well as symptomatic non-Covid individuals, showed excellent classification performance, which aligns with the results of previous studies. However, when applied to swabs from healthy individuals and a limited sample of patients with Covid in the late phase of the pandemic, ML models exhibited lower classification accuracy.

Keywords: SARS-CoV-2, MALDI-TOF MS, ML models, nasopharyngeal swabs, classification

Procedia PDF Downloads 80

Authors: Zhou Jianhong

Abstract:

Model averaging is a desirable approach to deal with model uncertainty, which, however, has rarely been explored for Poisson regression. In this paper, we propose a model averaging procedure based on an unbiased estimator of the expected Kullback-Leibler distance for the Poisson regression. Simulation study shows that the proposed model average estimator outperforms some other commonly used model selection and model average estimators in some situations. Our proposed methods are further applied to a real data example and the advantage of this method is demonstrated again.

Keywords: model averaging, poission regression, Kullback-Leibler distance, statistics

Procedia PDF Downloads 493

Authors: Yavuz Unal, Kemal Polat, H. Erdinc Kocer

Abstract:

In this study, a decision support system comprising three stages has been proposed to detect the disc abnormalities of the lumbar region. In the first stage named the feature extraction, T2-weighted sagittal and axial Magnetic Resonance Images (MRI) were taken from 55 people and then 27 appearance and shape features were acquired from both sagittal and transverse images. In the second stage named the feature weighting process, k-means clustering based feature weighting (KMCBFW) proposed by Gunes et al. Finally, in the third stage named the classification process, the classifier algorithms including multi-layer perceptron (MLP- neural network), support vector machine (SVM), Naïve Bayes, and decision tree have been used to classify whether the subject has lumbar disc or not. In order to test the performance of the proposed method, the classification accuracy (%), sensitivity, specificity, precision, recall, f-measure, kappa value, and computation times have been used. The best hybrid model is the combination of k-means clustering based feature weighting and decision tree in the detecting of lumbar disc disease based on both sagittal and axial MR images.

Keywords: lumbar disc abnormality, lumbar MRI, lumbar spine, hybrid models, hybrid features, k-means clustering based feature weighting

Procedia PDF Downloads 499

Authors: Seyhan Karaçavuş, Bülent Yılmaz, Ömer Kayaaltı, Semra İçer, Arzu Taşdemir, Oğuzhan Ayyıldız, Kübra Eset, Eser Kaya

Abstract:

In this study, our goal was to perform tumor staging and subtype determination automatically using different texture analysis approaches for a very common cancer type, i.e., non-small cell lung carcinoma (NSCLC). Especially, we introduced a texture analysis approach, called Law’s texture filter, to be used in this context for the first time. The 18F-FDG PET images of 42 patients with NSCLC were evaluated. The number of patients for each tumor stage, i.e., I-II, III or IV, was 14. The patients had ~45% adenocarcinoma (ADC) and ~55% squamous cell carcinoma (SqCCs). MATLAB technical computing language was employed in the extraction of 51 features by using first order statistics (FOS), gray-level co-occurrence matrix (GLCM), gray-level run-length matrix (GLRLM), and Laws’ texture filters. The feature selection method employed was the sequential forward selection (SFS). Selected textural features were used in the automatic classification by k-nearest neighbors (k-NN) and support vector machines (SVM). In the automatic classification of tumor stage, the accuracy was approximately 59.5% with k-NN classifier (k=3) and 69% with SVM (with one versus one paradigm), using 5 features. In the automatic classification of tumor subtype, the accuracy was around 92.7% with SVM one vs. one. Texture analysis of FDG-PET images might be used, in addition to metabolic parameters as an objective tool to assess tumor histopathological characteristics and in automatic classification of tumor stage and subtype.

Keywords: cancer stage, cancer cell type, non-small cell lung carcinoma, PET, texture analysis

Procedia PDF Downloads 301

Authors: Talal Alshammari, Nasser Alshammari, Mohamed Sedky, Chris Howard

Abstract:

With the widespread adoption of the Internet-connected devices, and with the prevalence of the Internet of Things (IoT) applications, there is an increased interest in machine learning techniques that can provide useful and interesting services in the smart home domain. The areas that machine learning techniques can help advance are varied and ever-evolving. Classifying smart home inhabitants’ Activities of Daily Living (ADLs), is one prominent example. The ability of machine learning technique to find meaningful spatio-temporal relations of high-dimensional data is an important requirement as well. This paper presents a comparative evaluation of state-of-the-art machine learning techniques to classify ADLs in the smart home domain. Forty-two synthetic datasets and two real-world datasets with multiple inhabitants are used to evaluate and compare the performance of the identified machine learning techniques. Our results show significant performance differences between the evaluated techniques. Such as AdaBoost, Cortical Learning Algorithm (CLA), Decision Trees, Hidden Markov Model (HMM), Multi-layer Perceptron (MLP), Structured Perceptron and Support Vector Machines (SVM). Overall, neural network based techniques have shown superiority over the other tested techniques.

Keywords: activities of daily living, classification, internet of things, machine learning, prediction, smart home

Procedia PDF Downloads 321

Authors: Eiman Kattan, Hong Wei

Abstract:

In using Convolutional Neural Network (CNN) for classification, there is a set of hyperparameters available for the configuration purpose. This study aims to evaluate the impact of a range of parameters in CNN architecture i.e. AlexNet on land cover classification based on four remotely sensed datasets. The evaluation tests the influence of a set of hyperparameters on the classification performance. The parameters concerned are epoch values, batch size, and convolutional filter size against input image size. Thus, a set of experiments were conducted to specify the effectiveness of the selected parameters using two implementing approaches, named pertained and fine-tuned. We first explore the number of epochs under several selected batch size values (32, 64, 128 and 200). The impact of kernel size of convolutional filters (1, 3, 5, 7, 10, 15, 20, 25 and 30) was evaluated against the image size under testing (64, 96, 128, 180 and 224), which gave us insight of the relationship between the size of convolutional filters and image size. To generalise the validation, four remote sensing datasets, AID, RSD, UCMerced and RSCCN, which have different land covers and are publicly available, were used in the experiments. These datasets have a wide diversity of input data, such as number of classes, amount of labelled data, and texture patterns. A specifically designed interactive deep learning GPU training platform for image classification (Nvidia Digit) was employed in the experiments. It has shown efficiency in both training and testing. The results have shown that increasing the number of epochs leads to a higher accuracy rate, as expected. However, the convergence state is highly related to datasets. For the batch size evaluation, it has shown that a larger batch size slightly decreases the classification accuracy compared to a small batch size. For example, selecting the value 32 as the batch size on the RSCCN dataset achieves the accuracy rate of 90.34 % at the 11th epoch while decreasing the epoch value to one makes the accuracy rate drop to 74%. On the other extreme, setting an increased value of batch size to 200 decreases the accuracy rate at the 11th epoch is 86.5%, and 63% when using one epoch only. On the other hand, selecting the kernel size is loosely related to data set. From a practical point of view, the filter size 20 produces 70.4286%. The last performed image size experiment shows a dependency in the accuracy improvement. However, an expensive performance gain had been noticed. The represented conclusion opens the opportunities toward a better classification performance in various applications such as planetary remote sensing.

Keywords: CNNs, hyperparamters, remote sensing, land cover, land use

Procedia PDF Downloads 147

Authors: Altilio Rosa, Chirico Francesco, Foglia Goffredo

Abstract:

In recent years, the number of Unmanned Aerial Vehicles (UAVs) has significantly increased. The rapid development of commercial and recreational drones makes them an important part of our society. Despite the growing list of their applications, these vehicles pose a huge threat to civil and military installations: detection, classification and neutralization of such flying objects become an urgent need. Radar is an effective remote sensing tool for detecting and tracking flying objects, but scenarios characterized by the presence of a high number of tracks related to flying birds make especially challenging the drone detection task: operator PPI is cluttered with a huge number of potential threats and his reaction time can be severely affected. Flying birds compared to UAVs show similar velocity, RADAR cross-section and, in general, similar characteristics. Building from the absence of a single feature that is able to distinguish UAVs and birds, this paper uses a multiple features approach where an original feature selection technique is developed to feed binary classifiers trained to distinguish birds and UAVs. RADAR tracks acquired on the field and related to different UAVs and birds performing various trajectories were used to extract specifically designed target movement-related features based on velocity, trajectory and signal strength. An optimization strategy based on a genetic algorithm is also introduced to select the optimal subset of features and to estimate the performance of several classification algorithms (Neural network, SVM, Logistic regression…) both in terms of the number of selected features and misclassification error. Results show that the proposed methods are able to reduce the dimension of the data space and to remove almost all non-drone false targets with a suitable classification accuracy (higher than 95%).

Keywords: birds, classification, machine learning, UAVs

Procedia PDF Downloads 188

Authors: Rehan Siddiqui, Brendan Quine

Abstract:

The Radiance Enhancement (RE) and integrated absorption technique is applied to develop a synthetic model to determine the enhancement in radiance due to cloud scene and Shortwave upwelling Radiances (SHupR) by O2, H2O, CO2 and CH4. This new model is used to estimate the magnitude variation for RE and SHupR over spectral range of 900 nm to 1700 nm by varying surface altitude, mixing ratios and surface reflectivity. In this work, we employ satellite real observation of space orbiting Argus 1000 especially for O2, H2O, CO2 and CH4 together with synthetic model by using line by line GENSPECT radiative transfer model. All the radiative transfer simulations have been performed by varying over a different range of percentages of water vapor contents and carbon dioxide with the fixed concentration oxygen and methane. We calculate and compare both the synthetic and real measured observed data set of different week per pass of Argus flight. Results are found to be comparable for both approaches, after allowing for the differences with the real and synthetic technique. The methodology based on RE and SHupR of the space spectral data can be promising for the instant and reliable classification of the cloud scenes.

Keywords: radiance enhancement, radiative transfer, shortwave upwelling radiative flux, cloud reflectivity, greenhouse gases

Procedia PDF Downloads 309

Authors: Paul R Armstrong

Abstract:

Doubled haploids (DHs) have become an important breeding tool for creating maize inbred lines, although several bottlenecks in the DH production process limit wider development, application, and adoption of the technique. DH kernels are typically sorted manually and represent about 10% of the seeds in a much larger pool where the remaining 90% are hybrid siblings. This introduces time constraints on DH production and manual sorting is often not accurate. Automated sorting based on the chemical composition of the kernel can be effective, but devices, namely NMR, have not achieved the sorting speed to be a cost-effective replacement to manual sorting. This study evaluated a single kernel near-infrared reflectance spectroscopy (skNIR) platform to accurately identify DH kernels based on oil content. The skNIR platform is a higher-throughput device, approximately 3 seeds/s, that uses spectra to predict oil content of each kernel from maize crosses intentionally developed to create larger than normal oil differences, 1.5%-2%, between DH and hybrid kernels. Spectra from the skNIR were used to construct a partial least squares regression (PLS) model for oil and for a categorical reference model of 1 (DH kernel) or 2 (hybrid kernel) and then used to sort several crosses to evaluate performance. Two approaches were used for sorting. The first used a general PLS model developed from all crosses to predict oil content and then used for sorting each induction cross, the second was the development of a specific model from a single induction cross where approximately fifty DH and one hundred hybrid kernels used. This second approach used a categorical reference value of 1 and 2, instead of oil content, for the PLS model and kernels selected for the calibration set were manually referenced based on traditional commercial methods using coloration of the tip cap and germ areas. The generalized PLS oil model statistics were R2 = 0.94 and RMSE = .93% for kernels spanning an oil content of 2.7% to 19.3%. Sorting by this model resulted in extracting 55% to 85% of haploid kernels from the four induction crosses. Using the second method of generating a model for each cross yielded model statistics ranging from R2s = 0.96 to 0.98 and RMSEs from 0.08 to 0.10. Sorting in this case resulted in 100% correct classification but required models that were cross. In summary, the first generalized model oil method could be used to sort a significant number of kernels from a kernel pool but was not close to the accuracy of developing a sorting model from a single cross. The penalty for the second method is that a PLS model would need to be developed for each individual cross. In conclusion both methods could find useful application in the sorting of DH from hybrid kernels.

Keywords: NIR, haploids, maize, sorting

Procedia PDF Downloads 281

Authors: Tamas Madl

Abstract:

Sudden cardiac death (SCD) constitutes a large proportion of cardiovascular mortalities, provides little advance warning, and the risk is difficult to recognize based on ubiquitous, low cost medical equipment such as the standard, 12-lead, ten second ECG. Autonomic abnormalities have been shown to be strongly predictive of SCD risk; yet current methods are not trivially applicable to the brevity and low temporal and electrical resolution of standard ECGs. Here, we build horizontal visibility graph representations of very short inter-beat interval time series, and perform unsuper- vised representation learning in order to convert these variable size objects into fixed-length vectors preserving similarity rela- tions. We show that such representations facilitate classification into healthy vs. at-risk patients on two different datasets, the Mul- tiparameter Intelligent Monitoring in Intensive Care II and the PhysioNet Sudden Cardiac Death Holter Database. Our results suggest that graph representation learning of heartbeat interval time series facilitates robust classification even in sequences as short as ten seconds.

Keywords: sudden cardiac death, heart rate variability, ECG analysis, time series classification

Procedia PDF Downloads 211

Authors: Pam Bitrus Marcus

Abstract:

Compounds in Berom, a Niger-Congo language that is spoken in parts of central Nigeria, have been understudied, and the semantics of N-V nominal compounds have not been sufficiently delineated. This study describes the lexical classification of compounds in Berom and, specifically, examines the semantics of nominal compounds with N-V constituents. The study relied on a data set of 200 compounds that were drawn from Bere Naha (a newsletter publication in Berom). Contrary to the nominalization process in defining the lexical class of compounds in languages, the study revealed that verbal and adjectival classes of compounds are also attested in Berom and N-V nominal compounds have an agentive or locative interpretation that is not solely determined by the meaning of the constituents of the compound but by the context of the usage.

Keywords: berom, berom compounds, nominal compound, N-V compounds

Procedia PDF Downloads 44