Search results for: classification accuracies

Authors: Amirali Mahouti, Hooshang Katebi

Abstract:

Enlargement of Tabriz metropolis to the east and north-east caused urban construction to be built on Marl layers and because of increase in excavations depth, further information of this layer is inescapable. Looking at geotechnical investigation shows there is not enough information about Tabriz Marl and this soil has been classified only by color. Tabriz Marl is lacustrine carbonate sediment outcrops, surrounds eastern, northern and southern region of city in the East Azerbaijan Province of Iran and is known as bed rock of city under alluvium sediments. This investigation aims to characterize geotechnical parameters of this soil to identify and set it in classification system of carbonated soils. For this purpose, specimens obtained from 80 locations over the city and subjected to physical and mechanical tests, such as Atterberg limits, density, moisture content, unconfined compression, direct shear and consolidation. CaCO3 content, organic content, PH, XRD, XRF, TGA and geophysical downhole tests also have been done on some of them.

Keywords: carbonated soils, classification of soils, mineralogy, physical and mechanical tests for Marls, Tabriz Marl

Procedia PDF Downloads 317

Authors: Ronak Khosravi, Mahmood Abbasi Layegh, Siamak Haghipour, Avin Esmaili

Abstract:

In this paper, a study on classification of musical woodwind instruments using a small set of features selected from a broad range of extracted ones by the sequential forward selection method was carried out. Firstly, we extract 42 features for each record in the music database of 402 sound files belonging to five different groups of Flutes (end blown and internal duct), Single –reed, Double –reed (exposed and capped), Triple reed and Quadruple reed. Then, the sequential forward selection method is adopted to choose the best feature set in order to achieve very high classification accuracy. Two different classification techniques of support vector machines and relevance vector machines have been tested out and an accuracy of up to 96% can be achieved by using 21 time, frequency and coefficient features and relevance vector machine with the Gaussian kernel function.

Keywords: coefficient features, relevance vector machines, spectral features, support vector machines, temporal features

Procedia PDF Downloads 320

Authors: Mohammed Mustapha Alhaji, Sadiku Salawu

Abstract:

A clay soil which classified under A-7-6 soil according to AASHTO soil classification system and CH according to the unified soil classification system was stabilized using A-3 soil (AASHTO soil classification system). The clay soil was replaced with 0%, 10%, 20% to 100% A-3 soil, compacted at both the BSL and BSH compaction energy level and using unconfined compressive strength as evaluation criteria. The MDD of the compactions at both the BSL and BSH compaction energy levels showed increase in MDD from 0% A-3 soil replacement to 40% A-3 soil replacement after which the values reduced to 100% A-3 soil replacement. The trend of the OMC with varied A-3 soil replacement is similar to that of MDD but in a reversed order. The OMC reduced from 0% A-3 soil replacement to 40% A-3 soil replacement after which the values increased to 100% A-3 soil replacement. This trend was attributed to the observed reduction in the void ratio from 0% A-3 soil replacement to 40% A-3 soil replacement after which the void ratio increased to 100% A-3 soil replacement. The maximum UCS for clay at varied A-3 soil replacement increased from 272 and 770kN/m2 for BSL and BSH compaction energy level at 0% A-3 soil replacement to 295 and 795kN/m2 for BSL and BSH compaction energy level respectively at 10% A-3 soil replacement after which the values reduced to 22 and 60kN/m2 for BSL and BSH compaction energy level respectively at 70% A-3 soil replacement. Beyond 70% A-3 soil replacement, the mixture cannot be moulded for UCS test.

Keywords: A-3 soil, clay minerals, pozzolanic action, stabilization

Procedia PDF Downloads 444

Authors: Chimey Lhamo, Ngawang Tsering

Abstract:

Traditional Tibetan medicine, known as Sowa Rigpa (Science of healing), originated more than 2500 years ago with an insightful background, and it has been growing significant attention in many Asian countries like China, India, Bhutan, and Nepal. Particularly, the Indian government has targeted Traditional Tibetan medicine as its major Indian medical system, including Ayurveda. Although Traditional Tibetan medicine has been growing interest and has a long history, it is not easily recognized worldwide because it exists only in the Tibetan language and it is neither accessible nor understood by patent examiners at the international patent office, data about Traditional Tibetan medicine is not yet broadly exist in the Internet. There has also been the exploitation of traditional Tibetan medicine increasing. The Traditional Knowledge Digital Library is a database aiming to prevent the patenting and misappropriation of India’s traditional medicine knowledge by using India’s Traditional knowledge Digital Library on Sowa Rigpa in order to prevent its exploitation at international patent with the help of information technology tools and an innovative classification systems-traditional knowledge resource classification (TKRC). As of date, more than 3000 Sowa Rigpa formulations have been transcribed into a Traditional Knowledge Digital Library database. In this paper, we are presenting India's Traditional Knowledge Digital Library for Traditional Tibetan medicine, and this database system helps to preserve and prevent the exploitation of Sowa Rigpa. Gradually it will be approved and accepted globally.

Keywords: traditional Tibetan medicine, India's traditional knowledge digital library, traditional knowledge resources classification, international patent classification

Procedia PDF Downloads 128

Authors: Zahow Muoftah

Abstract:

Traditional manual visual grading of fruits has been one of the agricultural industry’s major challenges due to its laborious nature as well as inconsistency in the inspection and classification process. The main requirements for computer vision and visual processing are some effective techniques for identifying defects and estimating defect areas. Automated defect detection using computer vision and machine learning has emerged as a promising area of research with a high and direct impact on the visual inspection domain. Grading, sorting, and disease detection are important factors in determining the quality of fruits after harvest. Many studies have used computer vision to evaluate the quality level of fruits during post-harvest. Many studies have used computer vision to evaluate the quality level of fruits during post-harvest. Many studies have been conducted to identify diseases and pests that affect the fruits of agricultural crops. However, most previous studies concentrated solely on the diagnosis of a lesion or disease. This study focused on a comprehensive study to identify pests and diseases of apple and banana fruits using detection and classification defects on Banana and Apples by Computer Vision. As a result, the current article includes research from these domains as well. Finally, various pattern recognition techniques for detecting apple and banana defects are discussed.

Keywords: computer vision, banana, apple, detection, classification

Procedia PDF Downloads 106

Authors: Shahrzad Zolfagharnassab, Abdul Rashid Mohamed Shariff, Reza Ehsani, Hawa Ze Jaffar, Ishak Aris

Abstract:

Ripeness estimation of oil palm fresh fruit is important processes that affect the profitableness and salability of oil palm fruits. The adulthood or ripeness of the oil palm fruits influences the quality of oil palm. Conventional procedure includes physical grading of Fresh Fruit Bunches (FFB) maturity by calculating the number of loose fruits per bunch. This physical classification of oil palm FFB is costly, time consuming and the results may have human error. Hence, many researchers try to develop the methods for ascertaining the maturity of oil palm fruits and thereby, deviously the oil content of distinct palm fruits without the need for exhausting oil extraction and analysis. This research investigates the potential of infrared images (Thermal Images) as a predictor to classify the oil palm FFB ripeness. A total of 270 oil palm fresh fruit bunches from most common cultivar of oil palm bunches Nigresens according to three maturity categories: under ripe, ripe and over ripe were collected. Each sample was scanned by the thermal imaging cameras FLIR E60 and FLIR T440. The average temperature of each bunches were calculated by using image processing in FLIR Tools and FLIR ThermaCAM researcher pro 2.10 environment software. The results show that temperature content decreased from immature to over mature oil palm FFBs. An overall analysis-of-variance (ANOVA) test was proved that this predictor gave significant difference between underripe, ripe and overripe maturity categories. This shows that the temperature as predictors can be good indicators to classify oil palm FFB. Classification analysis was performed by using the temperature of the FFB as predictors through Linear Discriminant Analysis (LDA), Mahalanobis Discriminant Analysis (MDA), Artificial Neural Network (ANN) and K- Nearest Neighbor (KNN) methods. The highest overall classification accuracy was 88.2% by using Artificial Neural Network. This research proves that thermal imaging and neural network method can be used as predictors of oil palm maturity classification.

Keywords: artificial neural network, maturity classification, oil palm FFB, thermal imaging

Procedia PDF Downloads 360

Authors: Misrak Assefa

Abstract:

The Amharic language is the second most widely spoken Semitic language in the world. There are several new overloaded on the web. Searching some useful documents from the web on a specific topic, which is written in the Amharic language, is a challenging task. Hence, document categorization is required for managing and filtering important information. In the classification of Amharic text news, there is still a gap in the domain of information that needs to be launch. This study attempts to design an automatic Amharic news classification using a supervised learning mechanism on four un-touch classes. To achieve this research, 4,182 news articles were used. Naive Bayes (NB) and Decision tree (j48) algorithms were used to classify the given Amharic dataset. In this paper, k-fold cross-validation is used to estimate the accuracy of the classifier. As a result, it shows those algorithms can be applicable in Amharic news categorization. The best average accuracy result is achieved by j48 decision tree and naïve Bayes is 95.2345 %, and 94.6245 % respectively using three categories. This research indicated that a typical decision tree algorithm is more applicable to Amharic news categorization.

Keywords: text categorization, supervised machine learning, naive Bayes, decision tree

Procedia PDF Downloads 209

Authors: Syed Romat Ali Shah, Bilal Shoaib, Saleem Akhtar, Munib Ahmad, Shahan Sadiqui

Abstract:

Classification is a data mining technique, which is recognizedon Machine Learning (ML) algorithm. It is used to classifythe individual articlein a knownofinformation into a set of predefinemodules or group. Web mining is also a portion of that sympathetic of data mining methods. The main purpose of this paper to analysis and compare the performance of Naïve Bayse Algorithm, Decision Tree, K-Nearest Neighbor (KNN), Artificial Neural Network (ANN)and Support Vector Machine (SVM). This paper consists of different ML algorithm and their advantages and disadvantages and also define research issues.

Keywords: Data Mining, Web Mining, classification, ML Algorithms

Procedia PDF Downloads 303

Authors: Andrey V. Timofeev, Dmitry V. Egorov

Abstract:

This paper introduces an original method of parametric optimization of the structure for multimodal decision-level fusion scheme which combines the results of the partial solution of the classification task obtained from assembly of the mono-modal classifiers. As a result, a multimodal fusion classifier which has the minimum value of the total error rate has been obtained.

Keywords: classification accuracy, fusion solution, total error rate, multimodal fusion classifier

Procedia PDF Downloads 466

Authors: Hammad T. Janjuhah, Josep Sanjuan, Mohamed K. Salah

Abstract:

Biological and chemical activities in carbonates are responsible for the complexity of the pore system. Primary porosity is generally of natural origin while secondary porosity is subject to chemical reactivity through diagenetic processes. To understand the integrated part of hydrocarbon exploration, it is necessary to understand the carbonate pore system. However, the current porosity classification scheme is limited to adequately predict the petrophysical properties of different reservoirs having various origins and depositional environments. Rock classification provides a descriptive method for explaining the lithofacies but makes no significant contribution to the application of porosity and permeability (poro-perm) correlation. The Central Luconia carbonate system (Malaysia) represents a good example of pore complexity (in terms of nature and origin) mainly related to diagenetic processes which have altered the original reservoir. For quantitative analysis, 32 high-resolution images of each thin section were taken using transmitted light microscopy. The quantification of grains, matrix, cement, and macroporosity (pore types) was achieved using a petrographic analysis of thin sections and FESEM images. The point counting technique was used to estimate the amount of macroporosity from thin section, which was then subtracted from the total porosity to derive the microporosity. The quantitative observation of thin sections revealed that the mouldic porosity (macroporosity) is the dominant porosity type present, whereas the microporosity seems to correspond to a sum of 40 to 50% of the total porosity. It has been proven that these Miocene carbonates contain a significant amount of microporosity, which significantly complicates the estimation and production of hydrocarbons. Neglecting its impact can increase uncertainty about estimating hydrocarbon reserves. Due to the diversity of geological parameters, the application of existing porosity classifications does not allow a better understanding of the poro-perm relationship. However, the classification can be improved by including the pore types and pore structures where they can be divided into macro- and microporosity. Such studies of microporosity identification/classification represent now a major concern in limestone reservoirs around the world.

Keywords: overview of porosity classification, reservoir characterization, microporosity, carbonate reservoir

Procedia PDF Downloads 154

Authors: Hao-Hsiang Ku, Ching-Ho Chi

Abstract:

Big data applications have become an imperative for many fields. Many researchers have been devoted into increasing correct rates and reducing time complexities. Hence, the study designs and proposes an Ontology-based backpropagation neural network classification and reasoning strategy for NoSQL big data applications, which is called ON4NoSQL. ON4NoSQL is responsible for enhancing the performances of classifications in NoSQL and SQL databases to build up mass behavior models. Mass behavior models are made by MapReduce techniques and Hadoop distributed file system based on Hadoop service platform. The reference engine of ON4NoSQL is the ontology-based backpropagation neural network classification and reasoning strategy. Simulation results indicate that ON4NoSQL can efficiently achieve to construct a high performance environment for data storing, searching, and retrieving.

Keywords: Hadoop, NoSQL, ontology, back propagation neural network, high distributed file system

Procedia PDF Downloads 262

Authors: R. Nandhini, Gaurab Mudbhari

Abstract:

Ranging from the field of health care to self-driving cars, machine learning and deep learning algorithms have revolutionized the field with the proper utilization of images and visual-oriented data. Segmentation, regression, classification, clustering, dimensionality reduction, etc., are some of the Machine Learning tasks that helped Machine Learning and Deep Learning models to become state-of-the-art models for the field where images are key datasets. Among these tasks, classification and clustering are essential but difficult because of the intricate and high-dimensional characteristics of image data. This finding examines and assesses advanced techniques in supervised classification and unsupervised clustering for image datasets, emphasizing the relative efficiency of Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), Deep Embedded Clustering (DEC), and self-supervised learning approaches. Due to the distinctive structural attributes present in images, conventional methods often fail to effectively capture spatial patterns, resulting in the development of models that utilize more advanced architectures and attention mechanisms. In image classification, we investigated both CNNs and ViTs. One of the most promising models, which is very much known for its ability to detect spatial hierarchies, is CNN, and it serves as a core model in our study. On the other hand, ViT is another model that also serves as a core model, reflecting a modern classification method that uses a self-attention mechanism which makes them more robust as this self-attention mechanism allows them to lean global dependencies in images without relying on convolutional layers. This paper evaluates the performance of these two architectures based on accuracy, precision, recall, and F1-score across different image datasets, analyzing their appropriateness for various categories of images. In the domain of clustering, we assess DEC, Variational Autoencoders (VAEs), and conventional clustering techniques like k-means, which are used on embeddings derived from CNN models. DEC, a prominent model in the field of clustering, has gained the attention of many ML engineers because of its ability to combine feature learning and clustering into a single framework and its main goal is to improve clustering quality through better feature representation. VAEs, on the other hand, are pretty well known for using latent embeddings for grouping similar images without requiring for prior label by utilizing the probabilistic clustering method.

Keywords: machine learning, deep learning, image classification, image clustering

Procedia PDF Downloads 10

Authors: Ismail Elkhrachy

Abstract:

Determination of land use changing is an important component of regional planning for applications ranging from urban fringe change detection to monitoring change detection of land use. This data are very useful for natural resources management.On the other hand, the technologies and methods of change detection also have evolved dramatically during past 20 years. So it has been well recognized that the change detection had become the best methods for researching dynamic change of land use by multi-temporal remotely-sensed data. The objective of this paper is to assess, evaluate and monitor land use change surrounding the area of Najran city, Kingdom of Saudi Arabia (KSA) using Landsat images (June 23, 2009) and ETM+ image(June. 21, 2014). The post-classification change detection technique was applied. At last,two-time subset images of Najran city are compared on a pixel-by-pixel basis using the post-classification comparison method and the from-to change matrix is produced, the land use change information obtained.Three classes were obtained, urban, bare land and agricultural land from unsupervised classification method by using Erdas Imagine and ArcGIS software. Accuracy assessment of classification has been performed before calculating change detection for study area. The obtained accuracy is between 61% to 87% percent for all the classes. Change detection analysis shows that rapid growth in urban area has been increased by 73.2%, the agricultural area has been decreased by 10.5 % and barren area reduced by 7% between 2009 and 2014. The quantitative study indicated that the area of urban class has unchanged by 58.2 km〗^2, gained 70.3 〖km〗^2 and lost 16 〖km〗^2. For bare land class 586.4〖km〗^2 has unchanged, 53.2〖km〗^2 has gained and 101.5〖km〗^2 has lost. While agriculture area class, 20.2〖km〗^2 has unchanged, 31.2〖km〗^2 has gained and 37.2〖km〗^2 has lost.

Keywords: land use, remote sensing, change detection, satellite images, image classification

Procedia PDF Downloads 523

Authors: Atefeh Saljooghi Khoshkar, Jafar Hassanpour

Abstract:

One of the main problems of the design stage relating to many tunneling projects is the lack of an appropriate standard for the provision of engineering geological data in a predefined format. In particular, this is more reflected in highway and railroad tunnel projects in which there is a number of tunnels and different professional teams involved. In this regard, comprehensive software needs to be designed using the accepted methods in order to help engineering geologists to prepare standard reports, which contain sufficient input data for the design stage. Regarding this necessity, applied software has been designed using macro capabilities and Visual Basic programming language (VBA) through Microsoft Excel. In this software, all of the engineering geological input data, which are required for designing different parts of tunnels, such as discontinuities properties, rock mass strength parameters, rock mass classification systems, boreability classification, the penetration rate, and so forth, can be calculated and reported in a standard format.

Keywords: engineering geology, rock mass classification, rock mechanic, tunnel

Procedia PDF Downloads 80

Authors: Dongju Kim, Youngjoo Suh, Hyojin Kim, Gyeongyeong Kim

Abstract:

Acoustic Emission Testing (AET) is widely used to test the structural integrity of an operational hydrogen storage container, and clustering algorithms are frequently used in pattern recognition methods to interpret AET results. However, the interpretation of AET results can vary from user to user as the tuning of the relevant parameters relies on the user's experience and knowledge of AET. Therefore, it is necessary to use a deep learning model to identify patterns in acoustic emission (AE) signal data that can be used to classify defects instead. In this paper, a deep learning-based model for classifying the types of defects in hydrogen storage tanks, using AE sensor waveforms, is proposed. As hydrogen storage tanks are commonly constructed using carbon fiber reinforced polymer composite (CFRP), a defect classification dataset is collected through a tensile test on a specimen of CFRP with an AE sensor attached. The performance of the classification model, using one-dimensional convolutional neural network (1-D CNN) and synthetic minority oversampling technique (SMOTE) data augmentation, achieved 91.09% accuracy for each defect. It is expected that the deep learning classification model in this paper, used with AET, will help in evaluating the operational safety of hydrogen storage containers.

Keywords: acoustic emission testing, carbon fiber reinforced polymer composite, one-dimensional convolutional neural network, smote data augmentation

Procedia PDF Downloads 93

Authors: Onyedikachi Ulelu, Andrew P. Longstaff, Simon Fletcher, Simon Parkinson

Abstract:

The widespread interest in 'Industry 4.0' or 'digital manufacturing' has led to significant research requiring the acquisition of data from sensors, instruments, and machine signals. In-depth research then identifies methods of analysis of the massive amounts of data generated before and during manufacture to solve a particular problem. The ultimate goal is for industrial Internet of Things (IIoT) data to be processed automatically to assist with either visualisation or autonomous system decision-making. However, the collection and processing of data in an industrial environment come with a cost. Little research has been undertaken on how to specify optimally what data to capture, transmit, process, and store at various levels of an edge-cloud network. The first step in this specification is to categorise IIoT data for efficient and effective use. This paper proposes the required attributes and classification to take manufacturing digital data from various sources to determine the most suitable location for data processing on the edge-cloud network. The proposed classification framework will minimise overhead in terms of network bandwidth/cost and processing time of machine tool data via efficient decision making on which dataset should be processed at the ‘edge’ and what to send to a remote server (cloud). A fast-and-frugal heuristic method is implemented for this decision-making. The framework is tested using case studies from industrial machine tools for machine productivity and maintenance.

Keywords: data classification, decision making, edge computing, industrial IoT, industry 4.0

Procedia PDF Downloads 180

Authors: M. S. Wickramarachchi, L. S. Nawarathna, C. M. B. Dematawewa

Abstract:

Hatchery performance is critical for the profitability of poultry breeder operations. Some extrinsic parameters of eggs and breeders cause to increase or decrease the hatchability. This study aims to identify the affecting extrinsic parameters on the commercial hatchability of local chicken's eggs and determine the most efficient classification model with a hatchability rate greater than 90%. In this study, seven extrinsic parameters were considered: egg weight, moisture loss, breeders age, number of fertilised eggs, shell width, shell length, and shell thickness. Multiple linear regression was performed to determine the most influencing variable on hatchability. First, the correlation between each parameter and hatchability were checked. Then a multiple regression model was developed, and the accuracy of the fitted model was evaluated. Linear Discriminant Analysis (LDA), Classification and Regression Trees (CART), k-Nearest Neighbors (kNN), Support Vector Machines (SVM) with a linear kernel, and Random Forest (RF) algorithms were applied to classify the hatchability. This grouping process was conducted using binary classification techniques. Hatchability was negatively correlated with egg weight, breeders' age, shell width, shell length, and positive correlations were identified with moisture loss, number of fertilised eggs, and shell thickness. Multiple linear regression models were more accurate than single linear models regarding the highest coefficient of determination (R²) with 94% and minimum AIC and BIC values. According to the classification results, RF, CART, and kNN had performed the highest accuracy values 0.99, 0.975, and 0.972, respectively, for the commercial hatchery process. Therefore, the RF is the most appropriate machine learning algorithm for classifying the breeder outcomes, which are economically profitable or not, in a commercial hatchery.

Keywords: classification models, egg weight, fertilised eggs, multiple linear regression

Procedia PDF Downloads 87

Authors: Annalakshmi G., Sakthivel Murugan S.

Abstract:

This paper presents a local directional encoded derivative binary pattern (LDEDBP) feature extraction method that can be applied for the classification of submarine coral reef images. The classification of coral reef images using texture features is difficult due to the dissimilarities in class samples. In coral reef image classification, texture features are extracted using the proposed method called local directional encoded derivative binary pattern (LDEDBP). The proposed approach extracts the complete structural arrangement of the local region using local binary batten (LBP) and also extracts the edge information using local directional pattern (LDP) from the edge response available in a particular region, thereby achieving extra discriminative feature value. Typically the LDP extracts the edge details in all eight directions. The process of integrating edge responses along with the local binary pattern achieves a more robust texture descriptor than the other descriptors used in texture feature extraction methods. Finally, the proposed technique is applied to an extreme learning machine (ELM) method with a meta-heuristic algorithm known as weighted distance grey wolf optimizer (GWO) to optimize the input weight and biases of single-hidden-layer feed-forward neural networks (SLFN). In the empirical results, ELM-WDGWO demonstrated their better performance in terms of accuracy on all coral datasets, namely RSMAS, EILAT, EILAT2, and MLC, compared with other state-of-the-art algorithms. The proposed method achieves the highest overall classification accuracy of 94% compared to the other state of art methods.

Keywords: feature extraction, local directional pattern, ELM classifier, GWO optimization

Procedia PDF Downloads 163

Authors: C. V. Aravinda, H. N. Prakash

Abstract:

In this paper, we tried to convey fusion and state of art pertaining to SIL character recognition systems. In the first step, the text is preprocessed and normalized to perform the text identification correctly. The second step involves extracting relevant and informative features. The third step implements the classification decision. The three stages which involved are Data acquisition and preprocessing, Feature extraction, and Classification. Here we concentrated on two techniques to obtain features, Feature Extraction & Feature Selection. Edge-hinge distribution is a feature that characterizes the changes in direction of a script stroke in handwritten text. The edge-hinge distribution is extracted by means of a windowpane that is slid over an edge-detected binary handwriting image. Whenever the mid pixel of the window is on, the two edge fragments (i.e. connected sequences of pixels) emerging from this mid pixel are measured. Their directions are measured and stored as pairs. A joint probability distribution is obtained from a large sample of such pairs. Despite continuous effort, handwriting identification remains a challenging issue, due to different approaches use different varieties of features, having different. Therefore, our study will focus on handwriting recognition based on feature selection to simplify features extracting task, optimize classification system complexity, reduce running time and improve the classification accuracy.

Keywords: word segmentation and recognition, character recognition, optical character recognition, hand written character recognition, South Indian languages

Procedia PDF Downloads 494

Authors: Soyon Kim, Edward Kim

Abstract:

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

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

Procedia PDF Downloads 303

Authors: P. Bharathiraja

Abstract:

Computer Aided decision making system is used to enhance diagnosis and prognosis of diseases and also to assist clinicians and junior doctors in clinical decision making. Medical Data used for decision making should be definite and consistent. Data Mining and soft computing techniques are used for cleaning the data and for incorporating human reasoning in decision making systems. Fuzzy rule based inference technique can be used for classification in order to incorporate human reasoning in the decision making process. In this work, missing values are imputed using the mean or mode of the attribute. The data are normalized using min-ma normalization to improve the design and efficiency of the fuzzy inference system. The fuzzy inference system is used to handle the uncertainties that exist in the medical data. Equal-width-partitioning is used to partition the attribute values into appropriate fuzzy intervals. Fuzzy rules are generated using Class Based Associative rule mining algorithm. The system is trained and tested using heart disease data set from the University of California at Irvine (UCI) Machine Learning Repository. The data was split using a hold out approach into training and testing data. From the experimental results it can be inferred that classification using fuzzy inference system performs better than trivial IF-THEN rule based classification approaches. Furthermore it is observed that the use of fuzzy logic and fuzzy inference mechanism handles uncertainty and also resembles human decision making. The system can be used in the absence of a clinical expert to assist junior doctors and clinicians in clinical decision making.

Keywords: decision making, data mining, normalization, fuzzy rule, classification

Procedia PDF Downloads 517

Authors: Haonan Hu, Shuge Lei, Dasheng Sun, Huabin Zhang, Kehong Yuan, Jian Dai, Jijun Tang

Abstract:

This paper focuses on the classification task of breast ultrasound images and conducts research on the reliability measurement of classification results. A dual-channel evaluation framework was developed based on the proposed inference reliability and predictive reliability scores. For the inference reliability evaluation, human-aligned and doctor-agreed inference rationals based on the improved feature attribution algorithm SP-RISA are gracefully applied. Uncertainty quantification is used to evaluate the predictive reliability via the test time enhancement. The effectiveness of this reliability evaluation framework has been verified on the breast ultrasound clinical dataset YBUS, and its robustness is verified on the public dataset BUSI. The expected calibration errors on both datasets are significantly lower than traditional evaluation methods, which proves the effectiveness of the proposed reliability measurement.

Keywords: medical imaging, ultrasound imaging, XAI, uncertainty measurement, trustworthy AI

Procedia PDF Downloads 101

Authors: Jaiden Xuan Schraut, Leon Liu, Yiqiao Yin

Abstract:

Computer vision in medical diagnosis has achieved a high level of success in diagnosing diseases with high accuracy. However, conventional classifiers that produce an image to-label result provides insufficient information for medical professionals to judge and raise concerns over the trust and reliability of a model with results that cannot be explained. In order to gain local insight into cancerous regions, separate tasks such as imaging segmentation need to be implemented to aid the doctors in treating patients, which doubles the training time and costs which renders the diagnosis system inefficient and difficult to be accepted by the public. To tackle this issue and drive AI-first medical solutions further, this paper proposes a multi-output network that follows a U-Net architecture for image segmentation output and features an additional convolutional neural networks (CNN) module for auxiliary classification output. Class activation maps are a method of providing insight into a convolutional neural network’s feature maps that leads to its classification but in the case of lung diseases, the region of interest is enhanced by U-net-assisted Class Activation Map (CAM) visualization. Therefore, our proposed model combines image segmentation models and classifiers to crop out only the lung region of a chest X-ray’s class activation map to provide a visualization that improves the explainability and is able to generate classification results simultaneously which builds trust for AI-led diagnosis systems. The proposed U-Net model achieves 97.61% accuracy and a dice coefficient of 0.97 on testing data from the COVID-QU-Ex Dataset which includes both diseased and healthy lungs.

Keywords: multi-output network model, U-net, class activation map, image classification, medical imaging analysis

Procedia PDF Downloads 202

Authors: Mpho Mokoatle, Darlington Mapiye, James Mashiyane, Stephanie Muller, Gciniwe Dlamini

Abstract:

Great advances in high-throughput sequencing technologies have resulted in availability of huge amounts of sequencing data in public and private repositories, enabling a holistic understanding of complex biological phenomena. Sequence data are used for a wide range of applications such as gene annotations, expression studies, personalized treatment and precision medicine. However, this rapid growth in sequence data poses a great challenge which calls for novel data processing and analytic methods, as well as huge computing resources. In this work, a machine and statistical learning approach for DNA sequence classification based on $k$-mer representation of sequence data is proposed. The approach is tested using whole genome sequences of Mycobacterium tuberculosis (MTB) isolates to (i) reduce the size of genomic sequence data, (ii) identify an optimum size of k-mers and utilize it to build classification models, (iii) predict the phenotype from whole genome sequence data of a given bacterial isolate, and (iv) demonstrate computing challenges associated with the analysis of whole genome sequence data in producing interpretable and explainable insights. The classification models were trained on 104 whole genome sequences of MTB isoloates. Cluster analysis showed that k-mers maybe used to discriminate phenotypes and the discrimination becomes more concise as the size of k-mers increase. The best performing classification model had a k-mer size of 10 (longest k-mer) an accuracy, recall, precision, specificity, and Matthews Correlation coeffient of 72.0%, 80.5%, 80.5%, 63.6%, and 0.4 respectively. This study provides a comprehensive approach for resampling whole genome sequencing data, objectively selecting a k-mer size, and performing classification for phenotype prediction. The analysis also highlights the importance of increasing the k-mer size to produce more biological explainable results, which brings to the fore the interplay that exists amongst accuracy, computing resources and explainability of classification results. However, the analysis provides a new way to elucidate genetic information from genomic data, and identify phenotype relationships which are important especially in explaining complex biological mechanisms.

Keywords: AWD-LSTM, bootstrapping, k-mers, next generation sequencing

Procedia PDF Downloads 167

Authors: Darlington Mapiye, Mpho Mokoatle, James Mashiyane, Stephanie Muller, Gciniwe Dlamini

Abstract:

Great advances in high-throughput sequencing technologies have resulted in availability of huge amounts of sequencing data in public and private repositories, enabling a holistic understanding of complex biological phenomena. Sequence data are used for a wide range of applications such as gene annotations, expression studies, personalized treatment and precision medicine. However, this rapid growth in sequence data poses a great challenge which calls for novel data processing and analytic methods, as well as huge computing resources. In this work, a machine and statistical learning approach for DNA sequence classification based on k-mer representation of sequence data is proposed. The approach is tested using whole genome sequences of Mycobacterium tuberculosis (MTB) isolates to (i) reduce the size of genomic sequence data, (ii) identify an optimum size of k-mers and utilize it to build classification models, (iii) predict the phenotype from whole genome sequence data of a given bacterial isolate, and (iv) demonstrate computing challenges associated with the analysis of whole genome sequence data in producing interpretable and explainable insights. The classification models were trained on 104 whole genome sequences of MTB isoloates. Cluster analysis showed that k-mers maybe used to discriminate phenotypes and the discrimination becomes more concise as the size of k-mers increase. The best performing classification model had a k-mer size of 10 (longest k-mer) an accuracy, recall, precision, specificity, and Matthews Correlation coeffient of 72.0 %, 80.5 %, 80.5 %, 63.6 %, and 0.4 respectively. This study provides a comprehensive approach for resampling whole genome sequencing data, objectively selecting a k-mer size, and performing classification for phenotype prediction. The analysis also highlights the importance of increasing the k-mer size to produce more biological explainable results, which brings to the fore the interplay that exists amongst accuracy, computing resources and explainability of classification results. However, the analysis provides a new way to elucidate genetic information from genomic data, and identify phenotype relationships which are important especially in explaining complex biological mechanisms

Keywords: AWD-LSTM, bootstrapping, k-mers, next generation sequencing

Procedia PDF Downloads 159

Authors: Samira Taleb, Sakina Aoun, Slimane Ziani, Zoheir Mentouri, Adel Boudiaf

Abstract:

Rolling is a pressure treatment technique that modifies the shape of steel ingots or billets between rotating rollers. During this process, defects may form on the surface of the rolled sheets and are likely to affect the performance and quality of the finished product. In our study, we developed a method for detecting surface hole defects using a pixel classification approach. This work includes several steps. First, we performed image preprocessing to delimit areas with and without hole defects on the sheet image. Then, we developed the histograms of each area to generate the gray level membership intervals of the pixels that characterize each area. As we noticed an intersection between the characteristics of the gray level intervals of the images of the two areas, we finally performed a learning step based on a series of detection tests to refine the membership intervals of each area, and to choose the defect detection criterion in order to optimize the recognition of the surface hole.

Keywords: classification, defect, surface, detection, hole

Procedia PDF Downloads 15

Authors: Zoran Šverko, Saša Vlahinić, Nino Stojković, Ivan Markovinović

Abstract:

In this article, the classification of target letters is performed using data from the EEG P300 Speller paradigm. Neural networks trained with the results of dynamic connectivity analysis between different brain regions are used for classification. Dynamic connectivity analysis is based on the adaptive window size and the imaginary part of the complex Pearson correlation coefficient. Brain dynamics are analysed using the relative intersection of confidence intervals for the imaginary component of the complex Pearson correlation coefficient method (RICI-imCPCC). The RICI-imCPCC method overcomes the shortcomings of currently used dynamical connectivity analysis methods, such as the low reliability and low temporal precision for short connectivity intervals encountered in constant sliding window analysis with wide window size and the high susceptibility to noise encountered in constant sliding window analysis with narrow window size. This method overcomes these shortcomings by dynamically adjusting the window size using the RICI rule. This method extracts information about brain connections for each time sample. Seventy percent of the extracted brain connectivity information is used for training and thirty percent for validation. Classification of the target word is also done and based on the same analysis method. As far as we know, through this research, we have shown for the first time that dynamic connectivity can be used as a parameter for classifying EEG signals.

Keywords: dynamic connectivity analysis, EEG, neural networks, Pearson correlation coefficients

Procedia PDF Downloads 214

Authors: Jae Ni Jang, Young Uk Kim

Abstract:

Background: Chat Generative Pre-training Transformer-3 (ChatGPT; San Francisco, California, Open Artificial Intelligence) is an artificial intelligence chatbot based on a large language model designed to generate human-like text. As the usage of ChatGPT is increasing among less knowledgeable patients, medical students, and anesthesia and pain medicine residents or trainees, we aimed to evaluate the accuracy of ChatGPT-3 responses to questions about the American Society of Anesthesiologists (ASA) classification based on patients’ underlying diseases and assess the quality of the generated responses. Methods: A total of 47 questions were submitted to ChatGPT using textual prompts. The questions were designed for ChatGPT-3 to provide answers regarding ASA classification in response to common underlying diseases frequently observed in adult patients. In addition, we created 18 questions regarding the ASA classification for pediatric patients and pregnant women. The accuracy of ChatGPT’s responses was evaluated by cross-referencing with Miller’s Anesthesia, Morgan & Mikhail’s Clinical Anesthesiology, and the American Society of Anesthesiologists’ ASA Physical Status Classification System (2020). Results: Out of the 47 questions pertaining to adults, ChatGPT -3 provided correct answers for only 23, resulting in an accuracy rate of 48.9%. Furthermore, the responses provided by ChatGPT-3 regarding children and pregnant women were mostly inaccurate, as indicated by a 28% accuracy rate (5 out of 18). Conclusions: ChatGPT provided correct responses to questions relevant to the daily clinical routine of anesthesiologists in approximately half of the cases, while the remaining responses contained errors. Therefore, caution is advised when using ChatGPT to retrieve anesthesia-related information. Although ChatGPT may not yet be suitable for clinical settings, we anticipate significant improvements in ChatGPT and other large language models in the near future. Regular assessments of ChatGPT's ASA classification accuracy are essential due to the evolving nature of ChatGPT as an artificial intelligence entity. This is especially important because ChatGPT has a clinically unacceptable rate of error and hallucination, particularly in pediatric patients and pregnant women. The methodology established in this study may be used to continue evaluating ChatGPT.

Keywords: American Society of Anesthesiologists, artificial intelligence, Chat Generative Pre-training Transformer-3, ChatGPT

Procedia PDF Downloads 47

Authors: Eva Tsouparopoulou, Maria Symeonaki

Abstract:

The internationally documented declining survey response rates of the last two decades are mainly attributed to refusals. In fieldwork, a refusal may be obtained not only from the respondent himself/herself, but from other sources on the respondent’s behalf, such as other household members, apartment building residents or administrator(s), and neighborhood residents. In this paper, we investigate how the composition of the demographic profile of survey refusals changes when different classifications are implemented and the classification issues arising from that. The analysis is based on the 2002-2018 European Social Survey (ESS) datasets for Belgium, Germany, and United Kingdom. For these three countries, the size of selected sample units coded as a type of refusal for all nine under investigation rounds was large enough to meet the purposes of the analysis. The results indicate the existence of four different possible classifications that can be implemented and the significance of choosing the one that strengthens the contrasts of the different types of respondents' demographic profiles. Since the foundation of social quantitative research lies in the triptych of definition, classification, and measurement, this study aims to identify the multiplicity of the definition of survey refusals as a methodological tool for the continually growing research on non-response.

Keywords: non-response, refusals, European social survey, classification

Procedia PDF Downloads 85

Authors: Felipe A. Guth, Shane Ward, Kevin McDonnell

Abstract:

The assessment of disease levels in crop fields is an important and time-consuming task that generally relies on expert knowledge of trained individuals. Image classification in agriculture problems historically has been based on classical machine learning strategies that make use of hand-engineered features in the top of a classification algorithm. This approach tends to not produce results with high accuracy and generalization to the classes classified by the system when the nature of the elements has a significant variability. The advent of deep convolutional neural networks has revolutionized the field of machine learning, especially in computer vision tasks. These networks have great resourcefulness of learning and have been applied successfully to image classification and object detection tasks in the last years. The objective of this work was to propose a new method based on deep learning convolutional neural networks towards the task of disease level monitoring. Common RGB images of winter wheat were obtained during a growing season. Five categories of disease levels presence were produced, in collaboration with agronomists, for the algorithm classification. Disease level tasks performed by experts provided ground truth data for the disease score of the same winter wheat plots were RGB images were acquired. The system had an overall accuracy of 84% on the discrimination of the disease level classes.

Keywords: crop disease assessment, deep learning, precision agriculture, residual neural networks

Procedia PDF Downloads 331