Search results for: classification quality

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 37

Authors: Mais Nijim, Rama Devi Chennuboyina, Waseem Al Aqqad

Abstract:

Advances in spatial and spectral resolution of satellite images have led to tremendous growth in large image databases. The data we acquire through satellites, radars and sensors consists of important geographical information that can be used for remote sensing applications such as region planning, disaster management. Spatial data classification and object recognition are important tasks for many applications. However, classifying objects and identifying them manually from images is a difficult task. Object recognition is often considered as a classification problem, this task can be performed using machine-learning techniques. Despite of many machine-learning algorithms, the classification is done using supervised classifiers such as Support Vector Machines (SVM) as the area of interest is known. We proposed a classification method, which considers neighboring pixels in a region for feature extraction and it evaluates classifications precisely according to neighboring classes for semantic interpretation of region of interest (ROI). A dataset has been created for training and testing purpose; we generated the attributes by considering pixel intensity values and mean values of reflectance. We demonstrated the benefits of using knowledge discovery and data-mining techniques, which can be on image data for accurate information extraction and classification from high spatial resolution remote sensing imagery.

Keywords: remote sensing, object recognition, classification, data mining, waterbody identification, feature extraction

Procedia PDF Downloads 333

Authors: Faisal Muhibuddin, Ani Dijah Rahajoe

Abstract:

This in-depth exploration, through a systematic literature review, scrutinizes the nuanced role of data mining in the classification of criminal activities. The research focuses on investigating various methodological aspects and recent developments in leveraging data mining techniques to enhance the effectiveness and precision of crime categorization. Commencing with an exposition of the foundational concepts of crime classification and its evolutionary dynamics, this study details the paradigm shift from conventional methods towards approaches supported by data mining, addressing the challenges and complexities inherent in the modern crime landscape. Specifically, the research delves into various data mining techniques, including K-means clustering, Naïve Bayes, K-nearest neighbour, and clustering methods. A comprehensive review of the strengths and limitations of each technique provides insights into their respective contributions to improving crime classification models. The integration of diverse data sources takes centre stage in this research. A detailed analysis explores how the amalgamation of structured data (such as criminal records) and unstructured data (such as social media) can offer a holistic understanding of crime, enriching classification models with more profound insights. Furthermore, the study explores the temporal implications in crime classification, emphasizing the significance of considering temporal factors to comprehend long-term trends and seasonality. The availability of real-time data is also elucidated as a crucial element in enhancing responsiveness and accuracy in crime classification.

Keywords: data mining, classification algorithm, naïve bayes, k-means clustering, k-nearest neigbhor, crime, data analysis, sistematic literature review

Procedia PDF Downloads 59

Authors: Kemal Polat

Abstract:

In this paper, three feature weighting methods have been used to improve the classification performance of diabetic retinopathy (DR). To classify the diabetic retinopathy, features extracted from the output of several retinal image processing algorithms, such as image-level, lesion-specific and anatomical components, have been used and fed them into the classifier algorithms. The dataset used in this study has been taken from University of California, Irvine (UCI) machine learning repository. Feature weighting methods including the fuzzy c-means clustering based feature weighting, subtractive clustering based feature weighting, and Gaussian mixture clustering based feature weighting, have been used and compered with each other in the classification of DR. After feature weighting, five different classifier algorithms comprising multi-layer perceptron (MLP), k- nearest neighbor (k-NN), decision tree, support vector machine (SVM), and Naïve Bayes have been used. The hybrid method based on combination of subtractive clustering based feature weighting and decision tree classifier has been obtained the classification accuracy of 100% in the screening of DR. These results have demonstrated that the proposed hybrid scheme is very promising in the medical data set classification.

Keywords: machine learning, data weighting, classification, data mining

Procedia PDF Downloads 320

Authors: Feda Negesse

Abstract:

One of the most important indicators of research quality is a good data - collection instrument that can yield reliable and valid data. The Swadesh wordlist has been used for more than half a century for collecting data in comparative and historical linguistics though arbitrariness is observed in its application and size. This research compare s the classification results of the 100 Swadesh wordlist with those of its subsets to determine if reducing the size of the wordlist impact s its effectiveness. In the comparison, the 100, 50 and 40 wordlists were used to compute lexical distances of 29 Cushitic and Semitic languages spoken in Ethiopia and neighbouring countries. Gabmap, a based application, was employed to compute the lexical distances and to divide the languages into related clusters. The study shows that the subsets are not as effective as the 100 wordlist in clustering languages into smaller subgroups but they are equally effective in di viding languages into bigger groups such as subfamilies. It is noted that the subsets may lead to an erroneous classification whereby unrelated languages by chance form a cluster which is not attested by a comparative study. The chance to get a wrong result is higher when the subsets are used to classify languages which are not closely related. Though a further study is still needed to settle the issues around the size of the Swadesh wordlist, this study indicates that the 50 and 40 wordlists cannot be recommended as reliable substitute s for the 100 wordlist under all circumstances. The choice seems to be determined by the objective of a researcher and the degree of affiliation among the languages to be classified.

Keywords: classification, Cushitic, Swadesh, wordlist

Procedia PDF Downloads 293

Authors: Nasar Aldian Ambark Shashoa

Abstract:

Classification with a dimension reduction based on Bayesian approach is proposed in this paper . The first step is to generate a sample (parameter) of fault-free mode class and faulty mode class. The second, in order to obtain good classification performance, a selection of important features is done with the discrete karhunen-loeve expansion. Next, the Bayes test for minimum error is used to classify the classes. Finally, the results for simulated data demonstrate the capabilities of the proposed procedure.

Keywords: analytical redundancy, fault detection, feature extraction, Bayesian approach

Procedia PDF Downloads 521

Authors: Yaser Miaji, Mohammed Aloryani

Abstract:

The rise of recent applications in everyday implementation like videoconferencing, online recreation and voice speech communication leads to pressing the need for novel mechanism and policy to serve this steep improvement within the application itself and users‟ wants. This diversity in web traffics needs some classification and prioritization of the traffics since some traffics merit abundant attention with less delay and loss, than others. This research is intended to reinforce the mechanism by analysing the performance in application according to the proposed mechanism implemented. The mechanism used is quite direct and analytical. The mechanism is implemented by modifying the queue limit in the algorithm.

Keywords: traffic classification, IPv6, internet, application categorization

Procedia PDF Downloads 558

Authors: Zhiyan Meng, Dan Liu, Jintao Meng

Abstract:

Dependable encrypted traffic classification is crucial for improving cybersecurity and handling the growing amount of data. Large language models have shown that learning from large datasets can be effective, making pre-trained methods for encrypted traffic classification popular. However, attention-based pre-trained methods face two main issues: their large neural parameters are not suitable for low-computation environments like mobile devices and real-time applications, and they often overfit by getting stuck in local minima. To address these issues, we developed a lightweight transformer model, which reduces the computational parameters through lightweight vocabulary construction and Squeeze-and-Excitation Block. We use sharpness-aware optimization to avoid local minima during pre-training and capture temporal features with relative positional embeddings. Our approach keeps the model's classification accuracy high for downstream tasks. We conducted experiments on four datasets -USTC-TFC2016, VPN 2016, Tor 2016, and CICIOT 2022. Even with fewer than 18 million parameters, our method achieves classification results similar to methods with ten times as many parameters.

Keywords: sharpness-aware optimization, encrypted traffic classification, squeeze-and-excitation block, pretrained model

Procedia PDF Downloads 9

Authors: Ole-Christian Galbo Engstrøm, Erik Schou Dreier, Birthe Møller Jespersen, Kim Steenstrup Pedersen

Abstract:

Grain quality analysis is a multi-parameterized problem that includes a variety of qualitative and quantitative parameters such as grain type classification, damage type classification, and nutrient regression. Currently, these parameters require human inspection, a multitude of instruments employing a variety of sensor technologies, and predictive model types or destructive and slow chemical analysis. This paper investigates the feasibility of applying near-infrared hyperspectral imaging (NIR-HSI) to grain quality analysis. For this study two datasets of NIR hyperspectral images in the wavelength range of 900 nm - 1700 nm have been used. Both datasets contain images of sparsely and densely packed grain kernels. The first dataset contains ~87,000 image crops of bulk wheat samples from 63 harvests where protein value has been determined by the FOSS Infratec NOVA which is the golden industry standard for protein content estimation in bulk samples of cereal grain. The second dataset consists of ~28,000 image crops of bulk grain kernels from seven different wheat varieties and a single rye variety. In the first dataset, protein regression analysis is the problem to solve while variety classification analysis is the problem to solve in the second dataset. Deep convolutional neural networks (CNNs) have the potential to utilize spatio-spectral correlations within a hyperspectral image to simultaneously estimate the qualitative and quantitative parameters. CNNs can autonomously derive meaningful representations of the input data reducing the need for advanced preprocessing techniques required for classical chemometric model types such as artificial neural networks (ANNs) and partial least-squares regression (PLS-R). A comparison between different CNN architectures utilizing 2D and 3D convolution is conducted. These results are compared to the performance of ANNs and PLS-R. Additionally, a variety of preprocessing techniques from image analysis and chemometrics are tested. These include centering, scaling, standard normal variate (SNV), Savitzky-Golay (SG) filtering, and detrending. The results indicate that the combination of NIR-HSI and CNNs has the potential to be the foundation for an automatic system unifying qualitative and quantitative grain quality analysis within a single sensor technology and predictive model type.

Keywords: deep learning, grain analysis, hyperspectral imaging, preprocessing techniques

Procedia PDF Downloads 93

Authors: Dechen Tshering Vogel, Johannes T. Heverhagen, Bernard Kiss, Spyridon Arampatzis

Abstract:

In addition to computed tomography (CT), contrast enhanced ultrasound (CEUS), and magnetic resonance imaging (MRI) are being increasingly used for imaging of renal lesions. The aim of this prospective study was to compare the classification of complex cystic renal lesions using the Bosniak classification with CEUS and MRI to CT. Forty-eight patients with 65 cystic renal lesions were included in this study. All participants signed written informed consent. The agreement between the Bosniak classifications of complex renal lesions ( ≥ BII-F) on CEUS and MRI were compared to that of CT and were tested using Cohen’s Kappa. Sensitivity, specificity, positive and negative predictive values (PPV/NPV) and the accuracy of CEUS and MRI compared to CT in the detection of complex renal lesions were calculated. Twenty-nine (45%) out of 65 cystic renal lesions were classified as complex using CT. The agreement between CEUS and CT in the classification of complex cysts was fair (agreement 50.8%, Kappa 0.31), and was excellent between MRI and CT (agreement 93.9%, Kappa 0.88). Compared to CT, MRI had a sensitivity of 96.6%, specificity of 91.7%, a PPV of 54.7%, and an NPV of 54.7% with an accuracy of 63.1%. The corresponding values for CEUS were sensitivity 100.0%, specificity 33.3%, PPV 90.3%, and NPV 97.1% with an accuracy 93.8%. The classification of complex renal cysts based on MRI and CT scans correlated well, and MRI can be used instead of CT for this purpose. CEUS can exclude complex lesions, but due to higher sensitivity, cystic lesions tend to be upgraded. However, it is useful for initial imaging, for follow up of lesions and in those patients with contraindications to CT and MRI.

Keywords: Bosniak classification, computed tomography, contrast enhanced ultrasound, cystic renal lesions, magnetic resonance imaging

Procedia PDF Downloads 139

Authors: Zhang Shuqi, Liu Dan

Abstract:

For the problems in intelligent network anomaly traffic detection models, such as low detection accuracy caused by the lack of training samples, poor effect with small sample attack detection, a classification model enhancement method, F-ACGAN(Flow Auxiliary Classifier Generative Adversarial Network) which introduces generative adversarial network and adversarial training, is proposed to solve these problems. Generating adversarial data with category labels could enhance the training effect and improve classification accuracy and model robustness. FACGAN consists of three steps: feature preprocess, which includes data type conversion, dimensionality reduction and normalization, etc.; A generative adversarial network model with feature learning ability is designed, and the sample generation effect of the model is improved through adversarial iterations between generator and discriminator. The adversarial disturbance factor of the gradient direction of the classification model is added to improve the diversity and antagonism of generated data and to promote the model to learn from adversarial classification features. The experiment of constructing a classification model with the UNSW-NB15 dataset shows that with the enhancement of FACGAN on the basic model, the classification accuracy has improved by 8.09%, and the score of F1 has improved by 6.94%.

Keywords: data imbalance, GAN, ACGAN, anomaly detection, adversarial training, data augmentation

Procedia PDF Downloads 98

Authors: Grmanesh Gidey Kahsay

Abstract:

In modern technical engineering applications, quality is defined in two ways. The first one is that quality is the parameter that measures a product or service’s characteristics to meet and satisfy the pre-stated or fundamental needs (reliability, durability, serviceability). The second one is the quality of a product or service free of any defect or deficiencies. The American Society for Quality (ASQ) describes quality as a pursuit of optimal solutions to confirm successes and fulfillment to be accountable for the product or service's requirements and expectations. This article focuses on quality engineering tools in modern industrial applications. Quality engineering is a field of engineering that deals with the principles, techniques, models, and applications of the product or service to guarantee quality. Including the entire activities to analyze the product’s design and development, quality engineering emphasizes how to make sure that products and services are designed and developed to meet consumers’ requirements. This episode acquaints with quality tools such as quality systems, auditing, product design, and process control. The finding presents thoughts that aim to improve quality engineering proficiency and effectiveness by introducing essential quality techniques and tools in some selected industries.

Keywords: essential quality tools, quality systems and models, quality management systems, and quality assurance

Procedia PDF Downloads 147

Authors: Alberto Piatto, Zaza Nadja Lee Hansen, Peter Jacobsen

Abstract:

This paper examines the quantitative and qualitative factors influencing the buyer-supplier relationship. Understanding and acting on the right factors influencing supplier relationship management is crucial when a company outsource an important part of its business as it can be for engineering to order (ETO) company executing only the designing part in-house. Acting on these factors increase the quality of the relationship obtaining for both parties what they want and expect from an improved relationship. Best practices in supplier relationship management are considered and a case study of a large global company, called Cement A/S, operating in the cement business is carried out. One study is conducted including a large international company and hundreds of its suppliers. Data from the company is collected using semi-structured interviews and data from the suppliers is collected using a survey. Based on these inputs and an extensive literature review a classification of factors influencing the relationship buyer-supplier is presented and discussed. The results show that different managers among the company are assessing supplier from various perspectives, a standard approach to measure the performance of suppliers does not exist. The factors used nowadays in the company to measure performances of the suppliers are mostly related to time and cost. Quality is a key factor, but it has not been addressed properly since no data are available in the system. From a practical perspective, managers can learn from this paper which factors to consider when applying best practices of Supplier Relationship Management. Furthermore, from a theoretical perspective, this paper contributes with new knowledge in the area as limited research in collaboration with the company has been conducted. For this reason, a company, its suppliers and few studies for this type of industry have been conducted. For further research, it is suggested to define the correlation of factors to the profitability of the company and calculate its impact. When conducting this analysis it is important to focus on the efficient and effective use of factors that can be measurable and accepted from the supplier.

Keywords: buyer-supplier relationship, cement industry, classification of factors, ETO

Procedia PDF Downloads 273

Authors: Souhir Chelly, Chahida Harizi, Aicha Hechaichi, Sihem Aissaoui, Leila Ben Ayed, Maha Bergaoui, Mohamed Kouni Chahed

Abstract:

Introduction: The International Classification of Primary Care (ICPC) is part of the morbidity classification system. It had 17 chapters, and each is coded by an alphanumeric code: the letter corresponds to the chapter, the number to a paragraph in the chapter. The objective of this study is to show the utility of this classification in the coding of the reasons for demand for care in Primary health care (PHC), its advantages and limits. Methods: This is a cross-sectional descriptive study conducted in 4 PHC in Ariana district. Data on the demand for care during 2 days in the same week were collected. The coding of the information was done according to the CISP. The data was entered and analyzed by the EPI Info 7 software. Results: A total of 523 demands for care were investigated. The patients who came for the consultation are predominantly female (62.72%). Most of the consultants are young with an average age of 35 ± 26 years. In the ICPC, there are 7 rubrics: 'infections' is the most common reason with 49.9%, 'other diagnoses' with 40.2%, 'symptoms and complaints' with 5.5%, 'trauma' with 2.1%, 'procedures' with 2.1% and 'neoplasm' with 0.3%. The main advantage of the ICPC is the fact of being a standardized tool. It is very suitable for classification of the reasons for demand for care in PHC according to their specificity, capacity to be used in a computerized medical file of the PHC. Its current limitations are related to the difficulty of classification of some reasons for demand for care. Conclusion: The ICPC has been developed to provide healthcare with a coding reference that takes into account their specificity. The CIM is in its 10th revision; it would gain from revision to revision to be more efficient to be generalized and used by the teams of PHC.

Keywords: international classification of primary care, medical file, primary health care, Tunisia

Procedia PDF Downloads 258

Authors: B. S. Harish, M. B. Revanasiddappa

Abstract:

Due to rapid growth of text documents in digital form, automated text classification has become an important research in the last two decades. The major challenge of text document representations are high dimension, sparsity, volume and semantics. Since the terms are only features that can be found in documents, selection of good terms (features) plays an very important role. In text classification, feature selection is a strategy that can be used to improve classification effectiveness, computational efficiency and accuracy. In this paper, we present a quantitative analysis of most widely used feature selection (FS) methods, viz. Term Frequency-Inverse Document Frequency (tf
idf ), Mutual Information (MI), Information Gain (IG), CHISquare (x2), Term Frequency-Relevance Frequency (tf
rf ), Term Strength (TS), Ambiguity Measure (AM) and Symbolic Feature Selection (SFS) to classify text documents. We evaluated all the feature selection methods on standard datasets like 20 Newsgroups, 4 University dataset and Reuters-21578.

Keywords: classifiers, feature selection, text classification

Procedia PDF Downloads 453

Authors: Tianyi Wang, Hieyong Jeong, An Guo, Yuko Ohno

Abstract:

Healthcare robot for assisting sit-to-stand (STS) performance had aroused numerous research interests. To author’s best knowledge, knowledge about how evaluating healthcare robot is still unknown. Robot should be labeled as fault if users feel demanding during STS when they are assisted by robot. In this research, we aim to propose a method to evaluate sit-to-stand assist robot through center of pressure (CoP), then classify different STS performance. Experiments were executed five times with ten healthy subjects under four conditions: two self-performed STSs with chair heights of 62 cm and 43 cm, and two robot-assisted STSs with chair heights of 43 cm and robot end-effect speed of 2 s and 5 s. CoP was measured using a Wii Balance Board (WBB). Bayesian classification was utilized to classify STS performance. The results showed that faults occurred when decreased the chair height and slowed robot assist speed. Proposed method for fault classification showed high probability of classifying fault classes form others. It was concluded that faults for STS assist robot could be detected by inspecting center of pressure and be classified through proposed classification algorithm.

Keywords: center of pressure, fault classification, healthcare robot, sit-to-stand movement

Procedia PDF Downloads 192

Authors: Lidija R. Jevrić, Sanja O. Podunavac-Kuzmanović, Strahinja Z. Kovačević

Abstract:

This study considers the selection of the most suitable in silico molecular descriptors that could be used for s-triazine pesticides characterization. Suitable descriptors among topological, geometrical and physicochemical are used for quantitative structure-retention relationships (QSRR) model establishment. Established models were obtained using linear regression (LR) and multiple linear regression (MLR) analysis. In this paper, MLR models were established avoiding multicollinearity among the selected molecular descriptors. Statistical quality of established models was evaluated by standard and cross-validation statistical parameters. For detection of similarity or dissimilarity among investigated s-triazine pesticides and their classification, principal component analysis (PCA) and hierarchical cluster analysis (HCA) were used and gave similar grouping. This study is financially supported by COST action TD1305.

Keywords: chemometrics, classification analysis, molecular descriptors, pesticides, regression analysis

Procedia PDF Downloads 387

Authors: Jameela Ali Alkrimi, Abdul Rahim Ahmad, Azizah Suliman, Loay E. George

Abstract:

Red blood cells (RBCs) are among the most commonly and intensively studied type of blood cells in cell biology. The lack of RBCs is a condition characterized by lower than normal hemoglobin level; this condition is referred to as 'anemia'. In this study, a software was developed to isolate RBCs by using a machine learning approach to classify anemic RBCs in microscopic images. Several features of RBCs were extracted using image processing algorithms, including principal component analysis (PCA). With the proposed method, RBCs were isolated in 34 second from an image containing 18 to 27 cells. We also proposed that PCA could be performed to increase the speed and efficiency of classification. Our classifier algorithm yielded accuracy rates of 100%, 99.99%, and 96.50% for K-nearest neighbor (K-NN) algorithm, support vector machine (SVM), and neural network ANN, respectively. Classification was evaluated in highly sensitivity, specificity, and kappa statistical parameters. In conclusion, the classification results were obtained for a short time period with more efficient when PCA was used.

Keywords: red blood cells, pre-processing image algorithms, classification algorithms, principal component analysis PCA, confusion matrix, kappa statistical parameters, ROC

Procedia PDF Downloads 400

Authors: Jerzy Banski

Abstract:

The basic aim of this study is to discuss and assess different classifications and research approaches to small towns that take their social and economic functions into account, as well as relations with surrounding areas. The subject literature typically includes three types of approaches to the classification of small towns: 1) the structural, 2) the location-related, and 3) the mixed. The structural approach allows for the grouping of towns from the point of view of the social, cultural and economic functions they discharge. The location-related approach draws on the idea of there being a continuum between the center and the periphery. A mixed classification making simultaneous use of the different approaches to research brings the most information to bear in regard to categories of the urban locality. Bearing in mind the approaches to classification, it is possible to propose a synthetic method for classifying small towns that takes account of economic structure, location and the relationship between the towns and their surroundings. In the case of economic structure, the small centers may be divided into two basic groups – those featuring a multi-branch structure and those that are specialized economically. A second element of the classification reflects the locations of urban centers. Two basic types can be identified – the small town within the range of impact of a large agglomeration, or else the town outside such areas, which is to say located peripherally. The third component of the classification arises out of small towns’ relations with their surroundings. In consequence, it is possible to indicate 8 types of small-town: from local centers enjoying good accessibility and a multi-branch economic structure to peripheral supra-local centers characterised by a specialized economic structure.

Keywords: small towns, classification, functional structure, localization

Procedia PDF Downloads 176

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

Abstract:

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

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

Procedia PDF Downloads 227

Authors: Taner Ersoz, Filiz Ersoz, Seyma Ozbilge

Abstract:

In this study, the clients who applied to a bank branch for loan were analyzed through data mining. The study was composed of the information such as amounts of loans received by personal and SME clients working with the bank branch, installment numbers, number of delays in loan installments, payments available in other banks and number of banks to which they are in debt between 2010 and 2013. The client risk profile was examined through Classification and Regression Tree (CART) analysis, one of the decision tree classification methods. At the end of the study, 5 different types of customers have been determined on the decision tree. The classification of these types of customers has been created with the rating of those posing a risk for the bank branch and the customers have been classified according to the risk ratings.

Keywords: client classification, loan suitability, risk rating, CART analysis

Procedia PDF Downloads 333

Authors: F. Jiménez, R. Jódar, M. Martín, G. Sánchez, G. Sciavicco

Abstract:

Abstract—Attribute or feature selection is one of the basic strategies to improve the performances of data classification tasks, and, at the same time, to reduce the complexity of classifiers, and it is a particularly fundamental one when the number of attributes is relatively high. Its application to unsupervised classification is restricted to a limited number of experiments in the literature. Evolutionary computation has already proven itself to be a very effective choice to consistently reduce the number of attributes towards a better classification rate and a simpler semantic interpretation of the inferred classifiers. We present a feature selection wrapper model composed by a multi-objective evolutionary algorithm, the clustering method Expectation-Maximization (EM), and the classifier C4.5 for the unsupervised classification of data extracted from a psychological test named BASC-II (Behavior Assessment System for Children - II ed.) with two objectives: Maximizing the likelihood of the clustering model and maximizing the accuracy of the obtained classifier. We present a methodology to integrate feature selection for unsupervised classification, model evaluation, decision making (to choose the most satisfactory model according to a a posteriori process in a multi-objective context), and testing. We compare the performance of the classifier obtained by the multi-objective evolutionary algorithms ENORA and NSGA-II, and the best solution is then validated by the psychologists that collected the data.

Keywords: evolutionary computation, feature selection, classification, clustering

Procedia PDF Downloads 365

Authors: Vishwa Joshi

Abstract:

The study of mood recognition in the field of music has gained a lot of momentum in the recent years with machine learning and data mining techniques and many audio features contributing considerably to analyze and identify the relation of mood plus music. In this paper we consider the same idea forward and come up with making an effort to build a system for automatic recognition of mood underlying the audio song’s clips by mining their audio features and have evaluated several data classification algorithms in order to learn, train and test the model describing the moods of these audio songs and developed an open source framework. Before classification, Preprocessing and Feature Extraction phase is necessary for removing noise and gathering features respectively.

Keywords: music, mood, features, classification

Procedia PDF Downloads 491

Authors: Jorge A. Ruiz-Vanoye, Ocotlán Díaz-Parra, Alejandro Fuentes-Penna, Daniel Vélez-Díaz, Edith Olaco García

Abstract:

In this paper, we present the use of the discriminant analysis to select evolutionary algorithms that better solve instances of the vehicle routing problem with time windows. We use indicators as independent variables to obtain the classification criteria, and the best algorithm from the generic genetic algorithm (GA), random search (RS), steady-state genetic algorithm (SSGA), and sexual genetic algorithm (SXGA) as the dependent variable for the classification. The discriminant classification was trained with classic instances of the vehicle routing problem with time windows obtained from the Solomon benchmark. We obtained a classification of the discriminant analysis of 66.7%.

Keywords: Intelligent Transportation Systems, data-mining techniques, evolutionary algorithms, discriminant analysis, machine learning

Procedia PDF Downloads 460

Authors: Catarina Grande, Barbara Mota

Abstract:

The main goal of the present study was to understand the impact of childhood cancer on the quality of life of survivors and the extent to which oncologic disease affects the functionality and participation of survivors at the present time, compared to the time of diagnosis. Six survivors of pediatric cancer participated in the study. Participants were interviewed using a semi-structured interview, adapted from two instruments present in the literature - QALY and QLACS - and piloted through a previous study. This study is based on a qualitative approach using content analysis, allowing the identification of categories and subcategories. Subsequently, the correspondence between the units of meaning and the codes in the International Classification of Functioning, Disability, and Health for Children and Young, which contributed to a more detailed analysis of the impact on the quality of life of survivors in relation to the domains under study. The results showed significant changes between the moment of diagnosis and the present moment, concretely at the microsystem of the survivor. Regarding functionality and participation, the results show that the functions of the body are the most affected domain, emphasizing the emotional component that currently has a greater impact on the quality of life of survivors. The present study allowed identifying a set of codes for the development of a CIF-CJ core set for pediatric cancer survivors. He also indicated the need for future studies to validate and deepen these issues.

Keywords: cancer, participation, quality of life, survivor

Procedia PDF Downloads 233

Authors: C. Lanzerstorfer

Abstract:

The off-gas from the basic oxygen furnace (BOF), where pig iron is converted into steel, is treated in the primary ventilation system. This system is in full operation only during oxygen-blowing when the BOF converter vessel is in a vertical position. When pig iron and scrap are charged into the BOF and when slag or steel are tapped, the vessel is tilted. The generated emissions during charging and tapping cannot be captured by the primary off-gas system. To capture these emissions, a secondary ventilation system is usually installed. The emissions are captured by a canopy hood installed just above the converter mouth in tilted position. The aim of this study was to investigate the dependence of Zn and other components on the particle size of BOF secondary ventilation dust. Because of the high temperature of the BOF process it can be expected that Zn will be enriched in the fine dust fractions. If Zn is enriched in the fine fractions, classification could be applied to split the dust into two size fractions with a different content of Zn. For this air classification experiments with dust from the secondary ventilation system of a BOF were performed. The results show that Zn and Pb are highly enriched in the finest dust fraction. For Cd, Cu and Sb the enrichment is less. In contrast, the non-volatile metals Al, Fe, Mn and Ti were depleted in the fine fractions. Thus, air classification could be considered for the treatment of dust from secondary BOF off-gas cleaning.

Keywords: air classification, converter dust, recycling, zinc

Procedia PDF Downloads 424

Authors: Jiahe Liu, Hongyang Yu, Feng Qian, Miao Luo

Abstract:

SMPL-X was a powerful parametric human body model that included male, neutral, and female models, with significant gender differences between these three models. During the process of 3D human body reconstruction, the correct selection of standard templates was crucial for obtaining accurate results. To address this issue, we developed an efficient gender classification algorithm to automatically select the appropriate template for 3D human body reconstruction. The key to this gender classification algorithm was the precise analysis of human body features. By using the SMPL-X model, the algorithm could detect and identify gender features of the human body, thereby determining which standard template should be used. The accuracy of this algorithm made the 3D reconstruction process more accurate and reliable, as it could adjust model parameters based on individual gender differences. SMPL-X and the related gender classification algorithm have brought important advancements to the field of 3D human body reconstruction. By accurately selecting standard templates, they have improved the accuracy of reconstruction and have broad potential in various application fields. These technologies continue to drive the development of the 3D reconstruction field, providing us with more realistic and accurate human body models.

Keywords: gender classification, joint detection, SMPL-X, 3D reconstruction

Procedia PDF Downloads 64

Authors: M. Eckert, D. Mendes, J P. Gonçalves, C. Moço, M. Oliveira

Abstract:

The intensive extraction of natural aggregates leads to both depletion of natural resources and unwanted environmental impacts. On the other hand, uncontrolled disposal of Construction and Demolition Wastes (C&DW) causes the lifetime reduction of landfills. It is known that the European Union produces, each year, about 850 million tons of C&DW. For all the member States of the European Union, one of the milestones to be reached by 2020, according to the Resource Efficiency Roadmap (COM (2011) 571) of the European Commission, is to recycle 70% of the C&DW. In this work, properties of different types of recycled C&DW aggregates and natural aggregates were compared. Assays were performed according to European Standards (EN 13285; EN 13242+A1; EN 12457-4; EN 12620; EN 13139) for the characterization of there: physical, mechanical and chemical properties. Not standardized tests such as water absorption over time, mass stability and post compaction sieve analysis were also carried out. The tested recycled C&DW aggregates were classified according to the requirements of the European Standards regarding there potential use in concrete, mortar, unbound layers of road pavements and embankments. The results of the physical and mechanical properties of recycled C&DW aggregates indicated, in general, lower quality properties when compared to natural aggregates, particularly, for concrete preparation and unbound layers of road pavements. The results of the chemical properties attested that the C&DW aggregates constitute no environmental risk. It was concluded that recycled aggregates produced from C&DW have the potential to be used in many applications.

Keywords: recycled aggregate, sustainability, aggregate properties, European Standard Classification

Procedia PDF Downloads 658

Authors: Zhong Ma, Zhuping Wang, Congxin Liu, Xiangzeng Liu

Abstract:

Satellite imagery classification is a challenging problem with many practical applications. In this paper, we designed a deep convolution neural network (DCNN) to classify the satellite imagery. The contributions of this paper are twofold — First, to cope with the large-scale variance in the satellite image, we introduced the inception module, which has multiple filters with different size at the same level, as the building block to build our DCNN model. Second, we proposed a genetic algorithm based method to efficiently search the best hyper-parameters of the DCNN in a large search space. The proposed method is evaluated on the benchmark database. The results of the proposed hyper-parameters search method show it will guide the search towards better regions of the parameter space. Based on the found hyper-parameters, we built our DCNN models, and evaluated its performance on satellite imagery classification, the results show the classification accuracy of proposed models outperform the state of the art method.

Keywords: satellite imagery classification, deep convolution network, genetic algorithm, hyper-parameter optimization

Procedia PDF Downloads 294

Authors: Qamar Iqbal

Abstract:

Companies strive to improve their forecasting methods to predict the fluctuations in customer demand. These fluctuation and variation in demand affect the manufacturing operations and can limit a company’s ability to fulfill customer demand on time. Companies keep the inventory buffer and maintain the stocking levels to reduce the impact of demand variation. A mid-size company deals with thousands of stock keeping units (skus). It is neither easy and nor efficient to control and manage each sku. Inventory classification provides a tool to the management to increase their ability to support customer demand. The paper presents a framework that shows how inventory classification can play a role to increase supply chain responsiveness. A case study will be presented to further elaborate the method both for build-to-order and build-to-forecast manufacturing environments. Results will be compared that will show which manufacturing setting has advantage over another under different circumstances. The outcome of this study is very useful to the management because this will give them an insight on how inventory classification can be used to increase their ability to respond to changing customer needs.

Keywords: inventory classification, supply chain responsiveness, forecast, manufacturing environment

Procedia PDF Downloads 591