Search results for: classification tree method
20273 A Machine Learning Approach for Intelligent Transportation System Management on Urban Roads
Authors: Ashish Dhamaniya, Vineet Jain, Rajesh Chouhan
Abstract:
Traffic management is one of the gigantic issue in most of the urban roads in al-most all metropolitan cities in India. Speed is one of the critical traffic parameters for effective Intelligent Transportation System (ITS) implementation as it decides the arrival rate of vehicles on an intersection which are majorly the point of con-gestions. The study aimed to leverage Machine Learning (ML) models to produce precise predictions of speed on urban roadway links. The research objective was to assess how categorized traffic volume and road width, serving as variables, in-fluence speed prediction. Four tree-based regression models namely: Decision Tree (DT), Random Forest (RF), Extra Tree (ET), and Extreme Gradient Boost (XGB)are employed for this purpose. The models' performances were validated using test data, and the results demonstrate that Random Forest surpasses other machine learning techniques and a conventional utility theory-based model in speed prediction. The study is useful for managing the urban roadway network performance under mixed traffic conditions and effective implementation of ITS.Keywords: stream speed, urban roads, machine learning, traffic flow
Procedia PDF Downloads 6120272 Influence of Maturation Degree of Arbutus (Arbutus unedo L.) Fruits in Spirit Composition and Quality
Authors: Goreti Botelho, Filomena Gomes, Fernanda M. Ferreira, Ilda Caldeira
Abstract:
The strawberry tree (Arbutus unedo L.) is a small tree or shrub from botanical Ericaceae family that grows spontaneously nearby the Mediterranean basin and produce edible red fruits. A traditional processed fruit application, in Mediterranean countries, is the production of a spirit (known as aguardente de medronho, in Portugal) obtained from the fermented fruit. The main objective of our study was to contribute to the knowledge about the influence of the degree of maturation of fruits in the volatile composition and quality of arbutus spirit. The major volatiles in the three distillates fractions (head, heart and tail) obtained from fermentation of two different fruit maturation levels were quantified by GC-FID analysis and ANOVA one-way was performed. Additionally, the total antioxidant capacity and total phenolic compounds of both arbutus fruit spirits were determined, by ABTS and Folin-Ciocalteau method, respectively. The methanol concentration is superior (1022.39 g/hL a.a.) in the spirit made from fruits with highest total soluble solids, which is a value above the legal limit (1000 g/hL a.a.). Overall, our study emphasizes, for the first time, the influence of maturation degree of arbutus fruits in the spirit volatile composition and quality.Keywords: arbutus fruit, maturation, quality, spirit
Procedia PDF Downloads 37520271 Comparison of Linear Discriminant Analysis and Support Vector Machine Classifications for Electromyography Signals Acquired at Five Positions of Elbow Joint
Authors: Amna Khan, Zareena Kausar, Saad Malik
Abstract:
Bio Mechatronics has extended applications in the field of rehabilitation. It has been contributing since World War II in improving the applicability of prosthesis and assistive devices in real life scenarios. In this paper, classification accuracies have been compared for two classifiers against five positions of elbow. Electromyography (EMG) signals analysis have been acquired directly from skeletal muscles of human forearm for each of the three defined positions and at modified extreme positions of elbow flexion and extension using 8 electrode Myo armband sensor. Features were extracted from filtered EMG signals for each position. Performance of two classifiers, support vector machine (SVM) and linear discriminant analysis (LDA) has been compared by analyzing the classification accuracies. SVM illustrated classification accuracies between 90-96%, in contrast to 84-87% depicted by LDA for five defined positions of elbow keeping the number of samples and selected feature the same for both SVM and LDA.Keywords: classification accuracies, electromyography, linear discriminant analysis (LDA), Myo armband sensor, support vector machine (SVM)
Procedia PDF Downloads 36320270 Risk Assessment of Natural Gas Pipelines in Coal Mined Gobs Based on Bow-Tie Model and Cloud Inference
Authors: Xiaobin Liang, Wei Liang, Laibin Zhang, Xiaoyan Guo
Abstract:
Pipelines pass through coal mined gobs inevitably in the mining area, the stability of which has great influence on the safety of pipelines. After extensive literature study and field research, it was found that there are a few risk assessment methods for coal mined gob pipelines, and there is a lack of data on the gob sites. Therefore, the fuzzy comprehensive evaluation method is widely used based on expert opinions. However, the subjective opinions or lack of experience of individual experts may lead to inaccurate evaluation results. Hence the accuracy of the results needs to be further improved. This paper presents a comprehensive approach to achieve this purpose by combining bow-tie model and cloud inference. The specific evaluation process is as follows: First, a bow-tie model composed of a fault tree and an event tree is established to graphically illustrate the probability and consequence indicators of pipeline failure. Second, the interval estimation method can be scored in the form of intervals to improve the accuracy of the results, and the censored mean algorithm is used to remove the maximum and minimum values of the score to improve the stability of the results. The golden section method is used to determine the weight of the indicators and reduce the subjectivity of index weights. Third, the failure probability and failure consequence scores of the pipeline are converted into three numerical features by using cloud inference. The cloud inference can better describe the ambiguity and volatility of the results which can better describe the volatility of the risk level. Finally, the cloud drop graphs of failure probability and failure consequences can be expressed, which intuitively and accurately illustrate the ambiguity and randomness of the results. A case study of a coal mine gob pipeline carrying natural gas has been investigated to validate the utility of the proposed method. The evaluation results of this case show that the probability of failure of the pipeline is very low, the consequences of failure are more serious, which is consistent with the reality.Keywords: bow-tie model, natural gas pipeline, coal mine gob, cloud inference
Procedia PDF Downloads 24620269 Vegetation Assessment Under the Influence of Environmental Variables; A Case Study from the Yakhtangay Hill of Himalayan Range, Pakistan
Authors: Hameed Ullah, Shujaul Mulk Khan, Zahid Ullah, Zeeshan Ahmad Sadia Jahangir, Abdullah, Amin Ur Rahman, Muhammad Suliman, Dost Muhammad
Abstract:
The interrelationship between vegetation and abiotic variables inside an ecosystem is one of the main jobs of plant scientists. This study was designed to investigate the vegetation structure and species diversity along with the environmental variables in the Yakhtangay hill district Shangla of the Himalayan Mountain series Pakistan by using multivariate statistical analysis. Quadrat’s method was used and a total of 171 Quadrats were laid down 57 for Tree, Shrubs and Herbs, respectively, to analyze the phytosociological attributes of the vegetation. The vegetation of the selected area was classified into different Life and leaf-forms according to Raunkiaer classification, while PCORD software version 5 was used to classify the vegetation into different plants communities by Two-way indicator species Analysis (TWINSPAN). The CANOCCO version 4.5 was used for DCA and CCA analysis to find out variation directories of vegetation with different environmental variables. A total of 114 plants species belonging to 45 different families was investigated inside the area. The Rosaceae (12 species) was the dominant family followed by Poaceae (10 species) and then Asteraceae (7 species). Monocots were more dominant than Dicots and Angiosperms were more dominant than Gymnosperms. Among the life forms the Hemicryptophytes and Nanophanerophytes were dominant, followed by Therophytes, while among the leaf forms Microphylls were dominant, followed by Leptophylls. It is concluded that among the edaphic factors such as soil pH, the concentration of soil organic matter, Calcium Carbonates concentration in soil, soil EC, soil TDS, and physiographic factors such as Altitude and slope are affecting the structure of vegetation, species composition and species diversity at the significant level with p-value ≤0.05. The Vegetation of the selected area was classified into four major plants communities and the indicator species for each community was recorded. Classification of plants into 4 different communities based upon edaphic gradients favors the individualistic hypothesis. Indicator Species Analysis (ISA) shows the indicators of the study area are mostly indicators to the Himalayan or moist temperate ecosystem, furthermore, these indicators could be considered for micro-habitat conservation and respective ecosystem management plans.Keywords: species richness, edaphic gradients, canonical correspondence analysis (CCA), TWCA
Procedia PDF Downloads 14620268 Optimization Model for Support Decision for Maximizing Production of Mixed Fruit Tree Farms
Authors: Andrés I. Ávila, Patricia Aros, César San Martín, Elizabeth Kehr, Yovana Leal
Abstract:
We consider a linear programming model to help farmers to decide if it is convinient to choose among three kinds of export fruits for their future investment. We consider area, investment, water, productivitiy minimal unit, and harvest restrictions and a monthly based model to compute the average income in five years. Also, conditions on the field as area, water availability and initia investment are required. Using the Chilean costs and dollar-peso exchange rate, we can simulate several scenarios to understand the possible risks associated to this market.Keywords: mixed integer problem, fruit production, support decision model, fruit tree farms
Procedia PDF Downloads 44720267 Classification System for Soft Tissue Injuries of Face: Bringing Objectiveness to Injury Severity
Authors: Garg Ramneesh, Uppal Sanjeev, Mittal Rajinder, Shah Sheerin, Jain Vikas, Singla Bhupinder
Abstract:
Introduction: Despite advances in trauma care, a classification system for soft tissue injuries of the face still needs to be objectively defined. Aim: To develop a classification system for soft tissue injuries of the face; that is objective, easy to remember, reproducible, universally applicable, aids in surgical management and helps to develop a structured data that can be used for future use. Material and Methods: This classification system includes those patients that need surgical management of facial injuries. Associated underlying bony fractures have been intentionally excluded. Depending upon the severity of soft tissue injury, these can be graded from 0 to IV (O-Abrasions, I-lacerations, II-Avulsion injuries with no skin loss, III-Avulsion injuries with skin loss that would need graft or flap cover, and IV-complex injuries). Anatomically, the face has been divided into three zones (Zone 1/2/3), as per aesthetic subunits. Zone 1e stands for injury of eyebrows; Zones 2 a/b/c stand for nose, upper eyelid and lower eyelid respectively; Zones 3 a/b/c stand for upper lip, lower lip and cheek respectively. Suffices R and L stand for right or left involved side, B for presence of foreign body like glass or pellets, C for extensive contamination and D for depth which can be graded as D 1/2/3 if depth is still fat, muscle or bone respectively. I is for damage to facial nerve or parotid duct. Results and conclusions: This classification system is easy to remember, clinically applicable and would help in standardization of surgical management of soft tissue injuries of face. Certain inherent limitations of this classification system are inability to classify sutured wounds, hematomas and injuries along or against Langer’s lines.Keywords: soft tissue injuries, face, avulsion, classification
Procedia PDF Downloads 37820266 A Research Analysis on the Source Technology and Convergence Types
Authors: Kwounghee Choi
Abstract:
Technological convergence between the various sectors is expected to have a very large impact on future industrial and economy. This study attempts to do empirical approach between specific technologies’ classification. For technological convergence classification, it is necessary to set the target technology to be analyzed. This study selected target technology from national research and development plan. At first we found a source technology for analysis. Depending on the weight of source technology, NT-based, BT-based, IT-based, ET-based, CS-based convergence types were classified. This study aims to empirically show the concept of convergence technology and convergence types. If we use the source technology to classify convergence type, it will be useful to make practical strategies of convergence technology.Keywords: technology convergence, source technology, convergence type, R&D strategy, technology classification
Procedia PDF Downloads 47920265 Machine Learning for Feature Selection and Classification of Systemic Lupus Erythematosus
Authors: H. Zidoum, A. AlShareedah, S. Al Sawafi, A. Al-Ansari, B. Al Lawati
Abstract:
Systemic lupus erythematosus (SLE) is an autoimmune disease with genetic and environmental components. SLE is characterized by a wide variability of clinical manifestations and a course frequently subject to unpredictable flares. Despite recent progress in classification tools, the early diagnosis of SLE is still an unmet need for many patients. This study proposes an interpretable disease classification model that combines the high and efficient predictive performance of CatBoost and the model-agnostic interpretation tools of Shapley Additive exPlanations (SHAP). The CatBoost model was trained on a local cohort of 219 Omani patients with SLE as well as other control diseases. Furthermore, the SHAP library was used to generate individual explanations of the model's decisions as well as rank clinical features by contribution. Overall, we achieved an AUC score of 0.945, F1-score of 0.92 and identified four clinical features (alopecia, renal disorders, cutaneous lupus, and hemolytic anemia) along with the patient's age that was shown to have the greatest contribution on the prediction.Keywords: feature selection, classification, systemic lupus erythematosus, model interpretation, SHAP, Catboost
Procedia PDF Downloads 7620264 Design and Implementation of a Counting and Differentiation System for Vehicles through Video Processing
Authors: Derlis Gregor, Kevin Cikel, Mario Arzamendia, Raúl Gregor
Abstract:
This paper presents a self-sustaining mobile system for counting and classification of vehicles through processing video. It proposes a counting and classification algorithm divided in four steps that can be executed multiple times in parallel in a SBC (Single Board Computer), like the Raspberry Pi 2, in such a way that it can be implemented in real time. The first step of the proposed algorithm limits the zone of the image that it will be processed. The second step performs the detection of the mobile objects using a BGS (Background Subtraction) algorithm based on the GMM (Gaussian Mixture Model), as well as a shadow removal algorithm using physical-based features, followed by morphological operations. In the first step the vehicle detection will be performed by using edge detection algorithms and the vehicle following through Kalman filters. The last step of the proposed algorithm registers the vehicle passing and performs their classification according to their areas. An auto-sustainable system is proposed, powered by batteries and photovoltaic solar panels, and the data transmission is done through GPRS (General Packet Radio Service)eliminating the need of using external cable, which will facilitate it deployment and translation to any location where it could operate. The self-sustaining trailer will allow the counting and classification of vehicles in specific zones with difficult access.Keywords: intelligent transportation system, object detection, vehicle couting, vehicle classification, video processing
Procedia PDF Downloads 31720263 Microarray Gene Expression Data Dimensionality Reduction Using PCA
Authors: Fuad M. Alkoot
Abstract:
Different experimental technologies such as microarray sequencing have been proposed to generate high-resolution genetic data, in order to understand the complex dynamic interactions between complex diseases and the biological system components of genes and gene products. However, the generated samples have a very large dimension reaching thousands. Therefore, hindering all attempts to design a classifier system that can identify diseases based on such data. Additionally, the high overlap in the class distributions makes the task more difficult. The data we experiment with is generated for the identification of autism. It includes 142 samples, which is small compared to the large dimension of the data. The classifier systems trained on this data yield very low classification rates that are almost equivalent to a guess. We aim at reducing the data dimension and improve it for classification. Here, we experiment with applying a multistage PCA on the genetic data to reduce its dimensionality. Results show a significant improvement in the classification rates which increases the possibility of building an automated system for autism detection.Keywords: PCA, gene expression, dimensionality reduction, classification, autism
Procedia PDF Downloads 55620262 Automatic Classification of Lung Diseases from CT Images
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 14720261 Establishing Correlation between Urban Heat Island and Urban Greenery Distribution by Means of Remote Sensing and Statistics Data to Prioritize Revegetation in Yerevan
Authors: Linara Salikhova, Elmira Nizamova, Aleksandra Katasonova, Gleb Vitkov, Olga Sarapulova.
Abstract:
While most European cities conduct research on heat-related risks, there is a research gap in the Caucasus region, particularly in Yerevan, Armenia. This study aims to test the method of establishing a correlation between urban heat islands (UHI) and urban greenery distribution for prioritization of heat-vulnerable areas for revegetation. Armenia has failed to consider measures to mitigate UHI in urban development strategies despite a 2.1°C increase in average annual temperature over the past 32 years. However, planting vegetation in the city is commonly used to deal with air pollution and can be effective in reducing UHI if it prioritizes heat-vulnerable areas. The research focuses on establishing such priorities while considering the distribution of urban greenery across the city. The lack of spatially explicit air temperature data necessitated the use of satellite images to achieve the following objectives: (1) identification of land surface temperatures (LST) and quantification of temperature variations across districts; (2) classification of massifs of land surface types using normalized difference vegetation index (NDVI); (3) correlation of land surface classes with LST. Examination of the heat-vulnerable city areas (in this study, the proportion of individuals aged 75 years and above) is based on demographic data (Census 2011). Based on satellite images (Sentinel-2) captured on June 5, 2021, NDVI calculations were conducted. The massifs of the land surface were divided into five surface classes. Due to capacity limitations, the average LST for each district was identified using one satellite image from Landsat-8 on August 15, 2021. In this research, local relief is not considered, as the study mainly focuses on the interconnection between temperatures and green massifs. The average temperature in the city is 3.8°C higher than in the surrounding non-urban areas. The temperature excess ranges from a low in Norq Marash to a high in Nubarashen. Norq Marash and Avan have the highest tree and grass coverage proportions, with 56.2% and 54.5%, respectively. In other districts, the balance of wastelands and buildings is three times higher than the grass and trees, ranging from 49.8% in Quanaqer-Zeytun to 76.6% in Nubarashen. Studies have shown that decreased tree and grass coverage within a district correlates with a higher temperature increase. The temperature excess is highest in Erebuni, Ajapnyak, and Nubarashen districts. These districts have less than 25% of their area covered with grass and trees. On the other hand, Avan and Norq Marash districts have a lower temperature difference, as more than 50% of their areas are covered with trees and grass. According to the findings, a significant proportion of the elderly population (35%) aged 75 years and above reside in the Erebuni, Ajapnyak, and Shengavit neighborhoods, which are more susceptible to heat stress with an LST higher than in other city districts. The findings suggest that the method of comparing the distribution of green massifs and LST can contribute to the prioritization of heat-vulnerable city areas for revegetation. The method can become a rationale for the formation of an urban greening program.Keywords: heat-vulnerability, land surface temperature, urban greenery, urban heat island, vegetation
Procedia PDF Downloads 6620260 Performance Comparison of Outlier Detection Techniques Based Classification in Wireless Sensor Networks
Authors: Ayadi Aya, Ghorbel Oussama, M. Obeid Abdulfattah, Abid Mohamed
Abstract:
Nowadays, many wireless sensor networks have been distributed in the real world to collect valuable raw sensed data. The challenge is to extract high-level knowledge from this huge amount of data. However, the identification of outliers can lead to the discovery of useful and meaningful knowledge. In the field of wireless sensor networks, an outlier is defined as a measurement that deviates from the normal behavior of sensed data. Many detection techniques of outliers in WSNs have been extensively studied in the past decade and have focused on classic based algorithms. These techniques identify outlier in the real transaction dataset. This survey aims at providing a structured and comprehensive overview of the existing researches on classification based outlier detection techniques as applicable to WSNs. Thus, we have identified key hypotheses, which are used by these approaches to differentiate between normal and outlier behavior. In addition, this paper tries to provide an easier and a succinct understanding of the classification based techniques. Furthermore, we identified the advantages and disadvantages of different classification based techniques and we presented a comparative guide with useful paradigms for promoting outliers detection research in various WSN applications and suggested further opportunities for future research.Keywords: bayesian networks, classification-based approaches, KPCA, neural networks, one-class SVM, outlier detection, wireless sensor networks
Procedia PDF Downloads 49020259 Analysis on Thermococcus achaeans with Frequent Pattern Mining
Authors: Jeongyeob Hong, Myeonghoon Park, Taeson Yoon
Abstract:
After the advent of Achaeans which utilize different metabolism pathway and contain conspicuously different cellular structure, they have been recognized as possible materials for developing quality of human beings. Among diverse Achaeans, in this paper, we compared 16s RNA Sequences of four different species of Thermococcus: Achaeans genus specialized in sulfur-dealing metabolism. Four Species, Barophilus, Kodakarensis, Hydrothermalis, and Onnurineus, live near the hydrothermal vent that emits extreme amount of sulfur and heat. By comparing ribosomal sequences of aforementioned four species, we found similarities in their sequences and expressed protein, enabling us to expect that certain ribosomal sequence or proteins are vital for their survival. Apriori algorithms and Decision Tree were used. for comparison.Keywords: Achaeans, Thermococcus, apriori algorithm, decision tree
Procedia PDF Downloads 28520258 Comparison of Artificial Neural Networks and Statistical Classifiers in Olive Sorting Using Near-Infrared Spectroscopy
Authors: İsmail Kavdır, M. Burak Büyükcan, Ferhat Kurtulmuş
Abstract:
Table olive is a valuable product especially in Mediterranean countries. It is usually consumed after some fermentation process. Defects happened naturally or as a result of an impact while olives are still fresh may become more distinct after processing period. Defected olives are not desired both in table olive and olive oil industries as it will affect the final product quality and reduce market prices considerably. Therefore it is critical to sort table olives before processing or even after processing according to their quality and surface defects. However, doing manual sorting has many drawbacks such as high expenses, subjectivity, tediousness and inconsistency. Quality criterions for green olives were accepted as color and free of mechanical defects, wrinkling, surface blemishes and rotting. In this study, it was aimed to classify fresh table olives using different classifiers and NIR spectroscopy readings and also to compare the classifiers. For this purpose, green (Ayvalik variety) olives were classified based on their surface feature properties such as defect-free, with bruised defect and with fly defect using FT-NIR spectroscopy and classification algorithms such as artificial neural networks, ident and cluster. Bruker multi-purpose analyzer (MPA) FT-NIR spectrometer (Bruker Optik, GmbH, Ettlingen Germany) was used for spectral measurements. The spectrometer was equipped with InGaAs detectors (TE-InGaAs internal for reflectance and RT-InGaAs external for transmittance) and a 20-watt high intensity tungsten–halogen NIR light source. Reflectance measurements were performed with a fiber optic probe (type IN 261) which covered the wavelengths between 780–2500 nm, while transmittance measurements were performed between 800 and 1725 nm. Thirty-two scans were acquired for each reflectance spectrum in about 15.32 s while 128 scans were obtained for transmittance in about 62 s. Resolution was 8 cm⁻¹ for both spectral measurement modes. Instrument control was done using OPUS software (Bruker Optik, GmbH, Ettlingen Germany). Classification applications were performed using three classifiers; Backpropagation Neural Networks, ident and cluster classification algorithms. For these classification applications, Neural Network tool box in Matlab, ident and cluster modules in OPUS software were used. Classifications were performed considering different scenarios; two quality conditions at once (good vs bruised, good vs fly defect) and three quality conditions at once (good, bruised and fly defect). Two spectrometer readings were used in classification applications; reflectance and transmittance. Classification results obtained using artificial neural networks algorithm in discriminating good olives from bruised olives, from olives with fly defect and from the olive group including both bruised and fly defected olives with success rates respectively changing between 97 and 99%, 61 and 94% and between 58.67 and 92%. On the other hand, classification results obtained for discriminating good olives from bruised ones and also for discriminating good olives from fly defected olives using the ident method ranged between 75-97.5% and 32.5-57.5%, respectfully; results obtained for the same classification applications using the cluster method ranged between 52.5-97.5% and between 22.5-57.5%.Keywords: artificial neural networks, statistical classifiers, NIR spectroscopy, reflectance, transmittance
Procedia PDF Downloads 23920257 Deep Feature Augmentation with Generative Adversarial Networks for Class Imbalance Learning in Medical Images
Authors: Rongbo Shen, Jianhua Yao, Kezhou Yan, Kuan Tian, Cheng Jiang, Ke Zhou
Abstract:
This study proposes a generative adversarial networks (GAN) framework to perform synthetic sampling in feature space, i.e., feature augmentation, to address the class imbalance problem in medical image analysis. A feature extraction network is first trained to convert images into feature space. Then the GAN framework incorporates adversarial learning to train a feature generator for the minority class through playing a minimax game with a discriminator. The feature generator then generates features for minority class from arbitrary latent distributions to balance the data between the majority class and the minority class. Additionally, a data cleaning technique, i.e., Tomek link, is employed to clean up undesirable conflicting features introduced from the feature augmentation and thus establish well-defined class clusters for the training. The experiment section evaluates the proposed method on two medical image analysis tasks, i.e., mass classification on mammogram and cancer metastasis classification on histopathological images. Experimental results suggest that the proposed method obtains superior or comparable performance over the state-of-the-art counterparts. Compared to all counterparts, our proposed method improves more than 1.5 percentage of accuracy.Keywords: class imbalance, synthetic sampling, feature augmentation, generative adversarial networks, data cleaning
Procedia PDF Downloads 12220256 Energy Detection Based Sensing and Primary User Traffic Classification for Cognitive Radio
Authors: Urvee B. Trivedi, U. D. Dalal
Abstract:
As wireless communication services grow quickly; the seriousness of spectrum utilization has been on the rise gradually. An emerging technology, cognitive radio has come out to solve today’s spectrum scarcity problem. To support the spectrum reuse functionality, secondary users are required to sense the radio frequency environment, and once the primary users are found to be active, the secondary users are required to vacate the channel within a certain amount of time. Therefore, spectrum sensing is of significant importance. Once sensing is done, different prediction rules apply to classify the traffic pattern of primary user. Primary user follows two types of traffic patterns: periodic and stochastic ON-OFF patterns. A cognitive radio can learn the patterns in different channels over time. Two types of classification methods are discussed in this paper, by considering edge detection and by using autocorrelation function. Edge detection method has a high accuracy but it cannot tolerate sensing errors. Autocorrelation-based classification is applicable in the real environment as it can tolerate some amount of sensing errors.Keywords: cognitive radio (CR), probability of detection (PD), probability of false alarm (PF), primary user (PU), secondary user (SU), fast Fourier transform (FFT), signal to noise ratio (SNR)
Procedia PDF Downloads 34020255 An Improvement of Multi-Label Image Classification Method Based on Histogram of Oriented Gradient
Authors: Ziad Abdallah, Mohamad Oueidat, Ali El-Zaart
Abstract:
Image Multi-label Classification (IMC) assigns a label or a set of labels to an image. The big demand for image annotation and archiving in the web attracts the researchers to develop many algorithms for this application domain. The existing techniques for IMC have two drawbacks: The description of the elementary characteristics from the image and the correlation between labels are not taken into account. In this paper, we present an algorithm (MIML-HOGLPP), which simultaneously handles these limitations. The algorithm uses the histogram of gradients as feature descriptor. It applies the Label Priority Power-set as multi-label transformation to solve the problem of label correlation. The experiment shows that the results of MIML-HOGLPP are better in terms of some of the evaluation metrics comparing with the two existing techniques.Keywords: data mining, information retrieval system, multi-label, problem transformation, histogram of gradients
Procedia PDF Downloads 36920254 Angular-Coordinate Driven Radial Tree Drawing
Authors: Farshad Ghassemi Toosi, Nikola S. Nikolov
Abstract:
We present a visualization technique for radial drawing of trees consisting of two slightly different algorithms. Both of them make use of node-link diagrams for visual encoding. This visualization creates clear drawings without edge crossing. One of the algorithms is suitable for real-time visualization of large trees, as it requires minimal recalculation of the layout if leaves are inserted or removed from the tree; while the other algorithm makes better utilization of the drawing space. The algorithms are very similar and follow almost the same procedure but with different parameters. Both algorithms assign angular coordinates for all nodes which are then converted into 2D Cartesian coordinates for visualization. We present both algorithms and discuss how they compare to each other.Keywords: Radial drawing, Visualization, Algorithm, Use of node-link diagrams
Procedia PDF Downloads 33320253 Transfer Learning for Protein Structure Classification at Low Resolution
Authors: Alexander Hudson, Shaogang Gong
Abstract:
Structure determination is key to understanding protein function at a molecular level. Whilst significant advances have been made in predicting structure and function from amino acid sequence, researchers must still rely on expensive, time-consuming analytical methods to visualise detailed protein conformation. In this study, we demonstrate that it is possible to make accurate (≥80%) predictions of protein class and architecture from structures determined at low (>3A) resolution, using a deep convolutional neural network trained on high-resolution (≤3A) structures represented as 2D matrices. Thus, we provide proof of concept for high-speed, low-cost protein structure classification at low resolution, and a basis for extension to prediction of function. We investigate the impact of the input representation on classification performance, showing that side-chain information may not be necessary for fine-grained structure predictions. Finally, we confirm that high resolution, low-resolution and NMR-determined structures inhabit a common feature space, and thus provide a theoretical foundation for boosting with single-image super-resolution.Keywords: transfer learning, protein distance maps, protein structure classification, neural networks
Procedia PDF Downloads 12920252 An Empirical Evaluation of Performance of Machine Learning Techniques on Imbalanced Software Quality Data
Authors: Ruchika Malhotra, Megha Khanna
Abstract:
The development of change prediction models can help the software practitioners in planning testing and inspection resources at early phases of software development. However, a major challenge faced during the training process of any classification model is the imbalanced nature of the software quality data. A data with very few minority outcome categories leads to inefficient learning process and a classification model developed from the imbalanced data generally does not predict these minority categories correctly. Thus, for a given dataset, a minority of classes may be change prone whereas a majority of classes may be non-change prone. This study explores various alternatives for adeptly handling the imbalanced software quality data using different sampling methods and effective MetaCost learners. The study also analyzes and justifies the use of different performance metrics while dealing with the imbalanced data. In order to empirically validate different alternatives, the study uses change data from three application packages of open-source Android data set and evaluates the performance of six different machine learning techniques. The results of the study indicate extensive improvement in the performance of the classification models when using resampling method and robust performance measures.Keywords: change proneness, empirical validation, imbalanced learning, machine learning techniques, object-oriented metrics
Procedia PDF Downloads 41520251 Developing Structured Sizing Systems for Manufacturing Ready-Made Garments of Indian Females Using Decision Tree-Based Data Mining
Authors: Hina Kausher, Sangita Srivastava
Abstract:
In India, there is a lack of standard, systematic sizing approach for producing readymade garments. Garments manufacturing companies use their own created size tables by modifying international sizing charts of ready-made garments. The purpose of this study is to tabulate the anthropometric data which covers the variety of figure proportions in both height and girth. 3,000 data has been collected by an anthropometric survey undertaken over females between the ages of 16 to 80 years from some states of India to produce the sizing system suitable for clothing manufacture and retailing. This data is used for the statistical analysis of body measurements, the formulation of sizing systems and body measurements tables. Factor analysis technique is used to filter the control body dimensions from a large number of variables. Decision tree-based data mining is used to cluster the data. The standard and structured sizing system can facilitate pattern grading and garment production. Moreover, it can exceed buying ratios and upgrade size allocations to retail segments.Keywords: anthropometric data, data mining, decision tree, garments manufacturing, sizing systems, ready-made garments
Procedia PDF Downloads 12820250 Efficient Fuzzy Classified Cryptographic Model for Intelligent Encryption Technique towards E-Banking XML Transactions
Authors: Maher Aburrous, Adel Khelifi, Manar Abu Talib
Abstract:
Transactions performed by financial institutions on daily basis require XML encryption on large scale. Encrypting large volume of message fully will result both performance and resource issues. In this paper a novel approach is presented for securing financial XML transactions using classification data mining (DM) algorithms. Our strategy defines the complete process of classifying XML transactions by using set of classification algorithms, classified XML documents processed at later stage using element-wise encryption. Classification algorithms were used to identify the XML transaction rules and factors in order to classify the message content fetching important elements within. We have implemented four classification algorithms to fetch the importance level value within each XML document. Classified content is processed using element-wise encryption for selected parts with "High", "Medium" or “Low” importance level values. Element-wise encryption is performed using AES symmetric encryption algorithm and proposed modified algorithm for AES to overcome the problem of computational overhead, in which substitute byte, shift row will remain as in the original AES while mix column operation is replaced by 128 permutation operation followed by add round key operation. An implementation has been conducted using data set fetched from e-banking service to present system functionality and efficiency. Results from our implementation showed a clear improvement in processing time encrypting XML documents.Keywords: XML transaction, encryption, Advanced Encryption Standard (AES), XML classification, e-banking security, fuzzy classification, cryptography, intelligent encryption
Procedia PDF Downloads 40320249 Post-Earthquake Road Damage Detection by SVM Classification from Quickbird Satellite Images
Authors: Moein Izadi, Ali Mohammadzadeh
Abstract:
Detection of damaged parts of roads after earthquake is essential for coordinating rescuers. In this study, an approach is presented for the semi-automatic detection of damaged roads in a city using pre-event vector maps and both pre- and post-earthquake QuickBird satellite images. Damage is defined in this study as the debris of damaged buildings adjacent to the roads. Some spectral and texture features are considered for SVM classification step to detect damages. Finally, the proposed method is tested on QuickBird pan-sharpened images from the Bam City earthquake and the results show that an overall accuracy of 81% and a kappa coefficient of 0.71 are achieved for the damage detection. The obtained results indicate the efficiency and accuracy of the proposed approach.Keywords: SVM classifier, disaster management, road damage detection, quickBird images
Procedia PDF Downloads 61920248 Evaluation of Collect Tree Protocol for Structural Health Monitoring System Using Wireless Sensor Networks
Authors: Amira Zrelli, Tahar Ezzedine
Abstract:
Routing protocol may enhance the lifetime of sensor network, it has a highly importance, especially in wireless sensor network (WSN). Therefore, routing protocol has a big effect in these networks, thus the choice of routing protocol must be studied before setting up our network. In this work, we implement the routing protocol collect tree protocol (CTP) which is one of the hierarchic protocols used in structural health monitoring (SHM). Therefore, to evaluate the performance of this protocol, we choice to work with Contiki system and Cooja simulator. By throughput and RSSI evaluation of each node, we will deduce about the utility of CTP in structural monitoring system.Keywords: CTP, WSN, SHM, routing protocol
Procedia PDF Downloads 28820247 Parameter Estimation for Contact Tracing in Graph-Based Models
Authors: Augustine Okolie, Johannes Müller, Mirjam Kretzchmar
Abstract:
We adopt a maximum-likelihood framework to estimate parameters of a stochastic susceptible-infected-recovered (SIR) model with contact tracing on a rooted random tree. Given the number of detectees per index case, our estimator allows to determine the degree distribution of the random tree as well as the tracing probability. Since we do not discover all infectees via contact tracing, this estimation is non-trivial. To keep things simple and stable, we develop an approximation suited for realistic situations (contract tracing probability small, or the probability for the detection of index cases small). In this approximation, the only epidemiological parameter entering the estimator is the basic reproduction number R0. The estimator is tested in a simulation study and applied to covid-19 contact tracing data from India. The simulation study underlines the efficiency of the method. For the empirical covid-19 data, we are able to compare different degree distributions and perform a sensitivity analysis. We find that particularly a power-law and a negative binomial degree distribution meet the data well and that the tracing probability is rather large. The sensitivity analysis shows no strong dependency on the reproduction number.Keywords: stochastic SIR model on graph, contact tracing, branching process, parameter inference
Procedia PDF Downloads 7420246 A Technique for Image Segmentation Using K-Means Clustering Classification
Authors: Sadia Basar, Naila Habib, Awais Adnan
Abstract:
The paper presents the Technique for Image Segmentation Using K-Means Clustering Classification. The presented algorithms were specific, however, missed the neighboring information and required high-speed computerized machines to run the segmentation algorithms. Clustering is the process of partitioning a group of data points into a small number of clusters. The proposed method is content-aware and feature extraction method which is able to run on low-end computerized machines, simple algorithm, required low-quality streaming, efficient and used for security purpose. It has the capability to highlight the boundary and the object. At first, the user enters the data in the representation of the input. Then in the next step, the digital image is converted into groups clusters. Clusters are divided into many regions. The same categories with same features of clusters are assembled within a group and different clusters are placed in other groups. Finally, the clusters are combined with respect to similar features and then represented in the form of segments. The clustered image depicts the clear representation of the digital image in order to highlight the regions and boundaries of the image. At last, the final image is presented in the form of segments. All colors of the image are separated in clusters.Keywords: clustering, image segmentation, K-means function, local and global minimum, region
Procedia PDF Downloads 36820245 Analytical Study of Data Mining Techniques for Software Quality Assurance
Authors: Mariam Bibi, Rubab Mehboob, Mehreen Sirshar
Abstract:
Satisfying the customer requirements is the ultimate goal of producing or developing any product. The quality of the product is decided on the bases of the level of customer satisfaction. There are different techniques which have been reported during the survey which enhance the quality of the product through software defect prediction and by locating the missing software requirements. Some mining techniques were proposed to assess the individual performance indicators in collaborative environment to reduce errors at individual level. The basic intention is to produce a product with zero or few defects thereby producing a best product quality wise. In the analysis of survey the techniques like Genetic algorithm, artificial neural network, classification and clustering techniques and decision tree are studied. After analysis it has been discovered that these techniques contributed much to the improvement and enhancement of the quality of the product.Keywords: data mining, defect prediction, missing requirements, software quality
Procedia PDF Downloads 46020244 Recurrent Neural Networks with Deep Hierarchical Mixed Structures for Chinese Document Classification
Authors: Zhaoxin Luo, Michael Zhu
Abstract:
In natural languages, there are always complex semantic hierarchies. Obtaining the feature representation based on these complex semantic hierarchies becomes the key to the success of the model. Several RNN models have recently been proposed to use latent indicators to obtain the hierarchical structure of documents. However, the model that only uses a single-layer latent indicator cannot achieve the true hierarchical structure of the language, especially a complex language like Chinese. In this paper, we propose a deep layered model that stacks arbitrarily many RNN layers equipped with latent indicators. After using EM and training it hierarchically, our model solves the computational problem of stacking RNN layers and makes it possible to stack arbitrarily many RNN layers. Our deep hierarchical model not only achieves comparable results to large pre-trained models on the Chinese short text classification problem but also achieves state of art results on the Chinese long text classification problem.Keywords: nature language processing, recurrent neural network, hierarchical structure, document classification, Chinese
Procedia PDF Downloads 58