Search results for: hierarchical text classification models

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: Ahmad Alwosheel, Ahmed Alqaraawi

Abstract:

This work proposes an unsupervised text-independent probabilistic approach to recognize Quran reciter voice. It is an accurate approach that works on real time applications. This approach does not require a prior information about reciter models. It has two phases, where in the training phase the reciters' acoustical features are modeled using Gaussian Mixture Models, while in the testing phase, unlabeled reciter's acoustical features are examined among GMM models. Using this approach, a high accuracy results are achieved with efficient computation time process.

Keywords: Quran, speaker recognition, reciter recognition, Gaussian Mixture Model

Procedia PDF Downloads 380

Authors: Dasom Kim, William Xiu Shun Wong, Yoonjin Hyun, Donghoon Lee, Minji Paek, Sungho Byun, Namgyu Kim

Abstract:

There have been many researches on document classification for classifying voluminous documents automatically. Through document classification, we can assign a specific category to each unlabeled document on the basis of various machine learning algorithms. However, providing labeled documents manually requires considerable time and effort. To overcome the limitations, the semi-supervised learning which uses unlabeled document as well as labeled documents has been invented. However, traditional document classifiers, regardless of supervised or semi-supervised ones, cannot sufficiently explain the reason or the process of the classification. Thus, in this paper, we proposed a methodology to visualize major topics and class components of each document. We believe that our methodology for visualizing topics and classes of each document can enhance the reliability and explanatory power of document classifiers.

Keywords: data mining, document classifier, text mining, topic modeling

Procedia PDF Downloads 402

Authors: Othmane Touri, Sanaa El Filali, El Habib Benlahmar

Abstract:

Natural Language Processing (NLP) has gained significant attention lately. It has proved its ability to analyze and extract insights from unstructured text data in various languages. It is found that one of the most popular NLP applications is sentiment analysis which aims to identify the sentiment expressed in a piece of text, such as positive, negative, or neutral, in multiple languages. While there are several multilingual NLP models available for sentiment analysis, there is a need to investigate their effectiveness in different contexts and applications. In this study, we aim to investigate the effectiveness of different multilingual NLP models for sentiment analysis on a dataset of online product reviews in multiple languages. The performance of several NLP models, including Google Cloud Natural Language API, Microsoft Azure Cognitive Services, Amazon Comprehend, Stanford CoreNLP, spaCy, and Hugging Face Transformers are being compared. The models based on several metrics, including accuracy, precision, recall, and F1 score, are being evaluated and compared to their performance across different categories of product reviews. In order to run the study, preprocessing of the dataset has been performed by cleaning and tokenizing the text data in multiple languages. Then training and testing each model has been applied using a cross-validation approach where randomly dividing the dataset into training and testing sets and repeating the process multiple times has been used. A grid search approach to optimize the hyperparameters of each model and select the best-performing model for each category of product reviews and language has been applied. The findings of this study provide insights into the effectiveness of different multilingual NLP models for Multilingual Sentiment Analysis and their suitability for different languages and applications. The strengths and limitations of each model were identified, and recommendations for selecting the most performant model based on the specific requirements of a project were provided. This study contributes to the advancement of research methods in multilingual NLP and provides a practical guide for researchers and practitioners in the field.

Keywords: NLP, multilingual, sentiment analysis, texts

Procedia PDF Downloads 102

Authors: Ivan Potapov

Abstract:

Background: The aim of this paper is to investigate poly code texts in the communication of youth antisocial groups. Nowadays, the notion of a text has numerous interpretations. Besides all the approaches to defining a text, we must take into account semiotic and cultural-semiotic ones. Rapidly developing IT, world globalization, and new ways of coding of information increase the role of the cultural-semiotic approach. However, the development of computer technologies leads also to changes in the text itself. Polycode texts play a more and more important role in the everyday communication of the younger generation. Therefore, the research of functional and pragmatic aspects of both verbal and non-verbal content is actually quite important. Methods and Material: For this survey, we applied the combination of four methods of text investigation: not only intention and content analysis but also semantic and syntactic analysis. Using these methods provided us with information on general text properties, the content of transmitted messages, and each communicants’ intentions. Besides, during our research, we figured out the social background; therefore, we could distinguish intertextual connections between certain types of polycode texts. As the sources of the research material, we used 20 public channels in the popular messenger Telegram and data extracted from smartphones, which belonged to arrested members of antisocial groups. Findings: This investigation let us assert that polycode texts can be characterized as highly intertextual language unit. Moreover, we could outline the classification of these texts based on communicants’ intentions. The most common types of antisocial polycode texts are a call to illegal actions and agitation. What is more, each type has its own semantic core: it depends on the sphere of communication. However, syntactic structure is universal for most of the polycode texts. Conclusion: Polycode texts play important role in online communication. The results of this investigation demonstrate that in some social groups using these texts has a destructive influence on the younger generation and obviously needs further researches.

Keywords: text, polycode text, internet linguistics, text analysis, context, semiotics, sociolinguistics

Procedia PDF Downloads 132

Authors: Samuel Munaf, Kevin Swingler, Franz Brülisauer, Anthony O’Hare, George Gunn, Aaron Reeves

Abstract:

Web scraping and text mining are popular computer science methods deployed by public health researchers to augment traditional epidemiological surveillance. However, within veterinary disease surveillance, such techniques are still in the early stages of development and have not yet been fully utilised. This study presents an exploration into the utility of incorporating internet-based data to better understand the smallholder farming communities within Scotland by using online text extraction and the subsequent mining of this data. Web scraping of the livestock fora was conducted in conjunction with text mining of the data in search of common themes, words, and topics found within the text. Results from bi-grams and topic modelling uncover four main topics of interest within the data pertaining to aspects of livestock husbandry: feeding, breeding, slaughter, and disposal. These topics were found amongst both the poultry and pig sub-forums. Topic modeling appears to be a useful method of unsupervised classification regarding this form of data, as it has produced clusters that relate to biosecurity and animal welfare. Internet data can be a very effective tool in aiding traditional veterinary surveillance methods, but the requirement for human validation of said data is crucial. This opens avenues of research via the incorporation of other dynamic social media data, namely Twitter and Facebook/Meta, in addition to time series analysis to highlight temporal patterns.

Keywords: veterinary epidemiology, disease surveillance, infodemiology, infoveillance, smallholding, social media, web scraping, sentiment analysis, geolocation, text mining, NLP

Procedia PDF Downloads 98

Authors: Mohsen Maraoui

Abstract:

In the aim of natural language processing applications improvement, such as information retrieval, machine translation, lexical disambiguation, we focus on statistical approach to semantic indexing for multilingual text documents based on conceptual network formalism. We propose to use this formalism as an indexing language to represent the descriptive concepts and their weighting. These concepts represent the content of the document. Our contribution is based on two steps. In the first step, we propose the extraction of index terms using the multilingual lexical resource Euro WordNet (EWN). In the second step, we pass from the representation of index terms to the representation of index concepts through conceptual network formalism. This network is generated using the EWN resource and pass by a classification step based on association rules model (in attempt to discover the non-taxonomic relations or contextual relations between the concepts of a document). These relations are latent relations buried in the text and carried by the semantic context of the co-occurrence of concepts in the document. Our proposed indexing approach can be applied to text documents in various languages because it is based on a linguistic method adapted to the language through a multilingual thesaurus. Next, we apply the same statistical process regardless of the language in order to extract the significant concepts and their associated weights. We prove that the proposed indexing approach provides encouraging results.

Keywords: concept extraction, conceptual network formalism, fuzzy association rules, multilingual thesaurus, semantic indexing

Procedia PDF Downloads 141

Authors: Kamal KC, Zhendong Yin, Dasen Li, Zhilu Wu

Abstract:

Intra-plant disease classification based on leaf images is a challenging computer vision task due to similarities in texture, color, and shape of leaves with a slight variation of leaf spot; and external environmental changes such as lighting and background noises. Deep convolutional neural network (DCNN) has proven to be an effective tool for binary classification. In this paper, two methods for binary classification of diseased plant leaves using DCNN are presented; model created from scratch and transfer learning. Our main contribution is a thorough evaluation of 4 networks created from scratch and transfer learning of 5 pre-trained models. Training and testing of these models were performed on a plant leaf images dataset belonging to 16 distinct classes, containing a total of 22,265 images from 8 different plants, consisting of a pair of healthy and diseased leaves. We introduce a deep CNN model, Optimized MobileNet. This model with depthwise separable CNN as a building block attained an average test accuracy of 99.77%. We also present a fine-tuning method by introducing the concept of a convolutional block, which is a collection of different deep neural layers. Fine-tuned models proved to be efficient in terms of accuracy and computational cost. Fine-tuned MobileNet achieved an average test accuracy of 99.89% on 8 pairs of [healthy, diseased] leaf ImageSet.

Keywords: deep convolution neural network, depthwise separable convolution, fine-grained classification, MobileNet, plant disease, transfer learning

Procedia PDF Downloads 186

Authors: Bandhan Dey, Muhsina Bintoon Yiasha, Gulam Sulaman Choudhury

Abstract:

Chest disease is one of the most problematic ailments in our regular life. There are many known chest diseases out there. Diagnosing them correctly plays a vital role in the process of treatment. There are many methods available explicitly developed for different chest diseases. But the most common approach for diagnosing these diseases is through X-ray. In this paper, we proposed a multi-classification deep learning model for diagnosing COVID-19, lung cancer, pneumonia, tuberculosis, and atelectasis from chest X-rays. In the present work, we used the transfer learning method for better accuracy and fast training phase. The performance of three architectures is considered: InceptionV3, VGG-16, and VGG-19. We evaluated these deep learning architectures using public digital chest x-ray datasets with six classes (i.e., COVID-19, lung cancer, pneumonia, tuberculosis, atelectasis, and normal). The experiments are conducted on six-classification, and we found that VGG16 outperforms other proposed models with an accuracy of 95%.

Keywords: deep learning, image classification, X-ray images, Tensorflow, Keras, chest diseases, convolutional neural networks, multi-classification

Procedia PDF Downloads 92

Authors: Kavita Bodke

Abstract:

Structural health monitoring (SHM) is experiencing growth, necessitating the development of distinct methodologies to address its expanding scope effectively. In this study, we developed automatic structure damage identification, which incorporates three unique types of a building’s structural integrity. The first pertains to the presence of fractures within the structure, the second relates to the issue of dampness within the structure, and the third involves corrosion inside the structure. This study employs image classification techniques to discern between intact and impaired structures within structural data. The aim of this research is to find automatic damage detection with the probability of each damage class being present in one image. Based on this probability, we know which class has a higher probability or is more affected than the other classes. Utilizing photographs captured by a mobile camera serves as the input for an image classification system. Image classification was employed in our study to perform multi-class and multi-label classification. The objective was to categorize structural data based on the presence of cracks, moisture, and corrosion. In the context of multi-class image classification, our study employed three distinct methodologies: Random Forest, Multilayer Perceptron, and CNN. For the task of multi-label image classification, the models employed were Rasnet, Xceptionet, and Inception.

Keywords: SHM, CNN, deep learning, multi-class classification, multi-label classification

Procedia PDF Downloads 36

Authors: Sujata S. Kulkarni

Abstract:

Effective and efficient texture feature extraction and classification is an important problem in image understanding and recognition. This paper gives a review on effective texture classification method. The objective of the problem of texture representation is to reduce the amount of raw data presented by the image, while preserving the information needed for the task. Texture analysis is important in many applications of computer image analysis for classification include industrial and biomedical surface inspection, for example for defects and disease, ground classification of satellite or aerial imagery and content-based access to image databases.

Keywords: compressed sensing, feature extraction, image classification, texture analysis

Procedia PDF Downloads 434

Authors: Mina Elhjouji

Abstract:

The aim of this paper is to raise awareness of the untranslatability of the Qur’an and to suggest some solutions that can help the translator in the process of transferring the meaning from the source text to the target text as much as possible. After the introduction, the miraculous character of the Qur’an shall be illustrated. Then, the difficulty of translating religious texts will be shown in terms of different causes; thematic, cultural, and linguistic. Some examples shall illustrate each type of these difficulties. Finally, some strategies that can help translate the Quran’s meanings will be suggested.

Keywords: translation, religious text, untranslatability, The Qur’an miracle, communicative theory

Procedia PDF Downloads 11

Authors: Hang Lo Lee, Ki Il Song, Hee Hwan Ryu

Abstract:

An accurate prediction of TBM(Tunnel Boring Machine) performance is very difficult for reliable estimation of the construction period and cost in preconstruction stage. For this purpose, the aim of this study is to analyze the evaluation process of various prediction models published since 2000 for TBM performance, and to select the optimal input parameters for the prediction model. A classification system of TBM performance prediction model and applied methodology are proposed in this research. Input and output parameters applied for prediction models are also represented. Based on these results, a statistical analysis is performed using the collected data from shield TBM tunnel in South Korea. By performing a simple regression and residual analysis utilizinFg statistical program, R, the optimal input parameters are selected. These results are expected to be used for development of prediction model of TBM performance.

Keywords: TBM performance prediction model, classification system, simple regression analysis, residual analysis, optimal input parameters

Procedia PDF Downloads 309

Authors: Fayssal Ynineb, Toufik Hadjersi, Fatsah Moulai, Wafa Achour

Abstract:

Currently, tremendous attention has been paid to the rational design and synthesis of core/shell heterostructures for high-performance supercapacitors. In this study, the hierarchical NiO/ZnCo₂O₄ Core-Shell Nanorods Arrays were successfully deposited onto ITO substrate via a two-step hydrothermal and electrodeposition methods. The effect of the thin carbon layer between NiO and ZnCo₂O₄ in this multi-scale hierarchical structure was investigated. The selection of this structure was based on: (i) a high specific area of pseudo-capacitive NiO to maximize specific capacitance; (ii) an effective NiO-electrolyte interface to facilitate fast charging/discharging; and (iii) conducting carbon layer between ZnCo₂O₄ and NiO enhance the electric conductivity which reduces energy loss, and the corrosion protection of ZnCo₂O₄ in alkaline electrolyte. The obtained results indicate that hierarchical NiO/ZnCo₂O₄ present a high specific capacitance of 63 mF.cm⁻² at a current density of 0.05 mA.cm⁻² higher than that of pristine NiO and ZnCo₂O₄ of 6 and 3 mF.cm⁻², respectively. The carbon layer improves the electrical conductivity among NiO and ZnCo₂O₄ in the hierarchical NiO/C/ZnCo₂O₄ electrode. As well, the specific capacitance drastically increased to reach 125 mF.cm⁻². Moreover, this multi-scale hierarchical structure exhibits superior cycling stability with ~ 95.7 % capacitance retention after 65k cycles. These results indicate that the NiO/C/ZnCo₂O₄ nanocomposite material is an outstanding electrode material for supercapacitors.

Keywords: NiO/C/ZnCo₂O₄, specific capacitance, hydrothermal, supercapacitors

Procedia PDF Downloads 99

Authors: Sarthak Deshpande, Akshay Patil, Pradip Pandhare, Nikhil Wankhede, Rushali Deshmukh

Abstract:

Among the highly significant duties for any language most effective is the sentiment analysis, which is also a key area of NLP, that recently made impressive strides. There are several models and datasets available for those tasks in popular and commonly used languages like English, Russian, and Spanish. While sentiment analysis research is performed extensively, however it is lagging behind for the regional languages having few resources such as Hindi, Marathi. Marathi is one of the languages that included in the Indian Constitution’s 8th schedule and is the third most widely spoken language in the country and primarily spoken in the Deccan region, which encompasses Maharashtra and Goa. There isn’t sufficient study on sentiment analysis methods based on Marathi text due to lack of available resources, information. Therefore, this project proposes the use of different ML/NLP models for the analysis of Marathi data from the comments below YouTube content, tweets or Instagram posts. We aim to achieve a short and precise analysis and summary of the related data using our dataset (Dates, names, root words) and lexicons to locate exact information.

Keywords: multilingual sentiment analysis, Marathi, natural language processing, text summarization, lexicon-based approaches

Procedia PDF Downloads 73

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 261

Authors: Wajahat Ali, Shakeel Javaid

Abstract:

In this study, we have developed a mathematical programming model for a solid transportation problem with three objective functions arranged in hierarchical order. The mathematical programming models with more than one objective function to be solved in hierarchical order is termed as a multi-level programming model. Our study explores a Multi-Level Solid Transportation Problem with Uncertain Parameters (MLSTPWU). The proposed MLSTPWU model consists of three objective functions, viz. minimization of transportation cost, minimization of total transportation time, and minimization of deterioration during transportation. These three objective functions are supposed to be solved by decision-makers at three consecutive levels. Three constraint functions are added to the model, restricting the total availability, total demand, and capacity of modes of transportation. All the parameters involved in the model are assumed to be uncertain in nature. A solution method based on fuzzy logic is also discussed to obtain the compromise solution for the proposed model. Further, a simulated numerical example is discussed to establish the efficiency and applicability of the proposed model.

Keywords: solid transportation problem, multi-level programming, uncertain variable, uncertain environment

Procedia PDF Downloads 83

Authors: Danilo Habermann, Aleksander Medella, Carla Cremon, Yusef Caceres

Abstract:

This paper aims to analyze the ability of 2d point clouds features to classify different models of helicopters using radars. This method does not need to estimate the blade length, the number of blades of helicopters, and the period of their micro-Doppler signatures. It is also not necessary to generate spectrograms (or any other image based on time and frequency domain). This work transforms a radar return signal into a 2D point cloud and extracts features of it. Three classifiers are used to distinguish 9 different helicopter models in order to analyze the performance of the features used in this work. The high accuracy obtained with each of the classifiers demonstrates that the 2D point clouds features are very useful for classifying helicopters from radar signal.

Keywords: helicopter classification, point clouds features, radar, supervised classifiers

Procedia PDF Downloads 227

Authors: Esther Chiramal, Kelvin Soh Boon Kai

Abstract:

Explainable AI is a strong strategy implemented to understand complex black-box model predictions in a human-interpretable language. It provides the evidence required to execute the use of trustworthy and reliable AI systems. On the other hand, however, it also opens the door to locating possible vulnerabilities in an AI model. Traditional adversarial text attack uses word substitution, data augmentation techniques, and gradient-based attacks on powerful pre-trained Bidirectional Encoder Representations from Transformers (BERT) variants to generate adversarial sentences. These attacks are generally white-box in nature and not practical as they can be easily detected by humans e.g., Changing the word from “Poor” to “Rich”. We proposed a simple yet effective Grey-box cum Black-box approach that does not require the knowledge of the model while using a set of surrogate Transformer/BERT models to perform the attack using Explainable AI techniques. As Transformers are the current state-of-the-art models for almost all Natural Language Processing (NLP) tasks, an attack generated from BERT1 is transferable to BERT2. This transferability is made possible due to the attention mechanism in the transformer that allows the model to capture long-range dependencies in a sequence. Using the power of BERT generalisation via attention, we attempt to exploit how transformers learn by attacking a few surrogate transformer variants which are all based on a different architecture. We demonstrate that this approach is highly effective to generate semantically good sentences by changing as little as one word that is not detectable by humans while still fooling other BERT models.

Keywords: BERT, explainable AI, Grey-box text attack, transformer

Procedia PDF Downloads 136

Authors: Hamed Sarbazy, Zohre Gholipour Haftkhani, Ali Safari, Pejman Hosseiniun

Abstract:

Scientific and industrial progress in the past two decades has resulted in energy distribution systems based on power electronics, as an enabling technology in various industries and building management systems can be considered. Grading and standardization module power electronics systems and its use in a distributed control system, a strategy for overcoming the limitations of using this system. The purpose of this paper is to investigate strategies for scheduling and control structure of standard modules is a power electronic systems. This paper introduces the classical control methods and disadvantages of these methods will be discussed, The hierarchical control as a mechanism for distributed control structure of the classification module explains. The different levels of control and communication between these levels are fully introduced. Also continue to standardize software distribution system control structure is discussed. Finally, as an example, the control structure will be presented in a DC distribution system.

Keywords: application management, hardware management, power electronics, building blocks

Procedia PDF Downloads 521

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: Tao Youjun, Zhao Younan

Abstract:

The separation effect of fine coal can be improved by the process of pre-desliming. It was significantly enhanced when the fine coal was processed using Falcon concentrator with the removal of -45um coal slime. Ultrafine classification tests using Krebs classification cyclone with annular rinse water showed that increasing feeding pressure can effectively avoid the phenomena of heavy particles passing into overflow and light particles slipping into underflow. The increase of rinse water pressure could reduce the content of fine-grained particles while increasing the classification size. The increase in feeding concentration had a negative effect on the efficiency of classification, meanwhile increased the classification size due to the enhanced hindered settling caused by high underflow concentration. As a result of optimization experiments with response indicator of classification efficiency which based on orthogonal design using Design-Expert software indicated that the optimal classification efficiency reached 91.32% with the feeding pressure of 0.03MPa, the rinse water pressure of 0.02MPa and the feeding concentration of 12.5%. Meanwhile, the classification size was 49.99 μm which had a good agreement with the predicted value.

Keywords: hydrocyclone, ultrafine classification, slime, classification efficiency, classification size

Procedia PDF Downloads 167

Authors: Bowen Ding, Yihao Kuang

Abstract:

In recent years, with the development of large-scale pre-trained lan-guage models, building vector representations of text through deep neural network models has become a standard practice for natural language processing tasks. From the performance on downstream tasks, we can know that the text representation constructed by these models contains linguistic information, but its encoding mode and extent are unclear. In this work, a structural probe is proposed to detect whether the vector representation produced by a deep neural network is embedded with a syntax tree. The probe is trained with the deep metric learning method, so that the distance between word vectors in the metric space it defines encodes the distance of words on the syntax tree, and the norm of word vectors encodes the depth of words on the syntax tree. The experiment results on ELMo and BERT show that the syntax tree is encoded in their parameters and the word representations they produce.

Keywords: deep metric learning, syntax tree probing, natural language processing, word representations

Procedia PDF Downloads 67

Authors: Irene Yi

Abstract:

Machine learning, natural language processing, and neural network models of language are becoming more and more prevalent in the fields of technology and linguistics today. Training data for machines are at best, large corpora of human literature and at worst, a reflection of the ugliness in society. Computational linguistics is a growing field dealing with such issues of data collection for technological development. Machines have been trained on millions of human books, only to find that in the course of human history, derogatory and sexist adjectives are used significantly more frequently when describing females in history and literature than when describing males. This is extremely problematic, both as training data, and as the outcome of natural language processing. As machines start to handle more responsibilities, it is crucial to ensure that they do not take with them historical sexist and misogynistic notions. This paper gathers data and algorithms from neural network models of language having to deal with syntax, semantics, sociolinguistics, and text classification. Computational analysis on such linguistic data is used to find patterns of misogyny. Results are significant in showing the existing intentional and unintentional misogynistic notions used to train machines, as well as in developing better technologies that take into account the semantics and syntax of text to be more mindful and reflect gender equality. Further, this paper deals with the idea of non-binary gender pronouns and how machines can process these pronouns correctly, given its semantic and syntactic context. This paper also delves into the implications of gendered grammar and its effect, cross-linguistically, on natural language processing. Languages such as French or Spanish not only have rigid gendered grammar rules, but also historically patriarchal societies. The progression of society comes hand in hand with not only its language, but how machines process those natural languages. These ideas are all extremely vital to the development of natural language models in technology, and they must be taken into account immediately.

Keywords: computational analysis, gendered grammar, misogynistic language, neural networks

Procedia PDF Downloads 119

Authors: Zhidong Zhang

Abstract:

This study established a mixed method model in assessing statistics learning with Bayesian network models. There are three variants in exploratory sequential designs. There are three linked steps in one of the designs: qualitative data collection and analysis, quantitative measure, instrument, intervention, and quantitative data collection analysis. The study used a scoring model of analysis of variance (ANOVA) as a content domain. The research study is to examine students’ learning in both semantic and performance aspects at fine grain level. The ANOVA score model, y = α+ βx1 + γx1+ ε, as a cognitive task to collect data during the student learning process. When the learning processes were decomposed into multiple steps in both semantic and performance aspects, a hierarchical Bayesian network was established. This is a theory-driven process. The hierarchical structure was gained based on qualitative cognitive analysis. The data from students’ ANOVA score model learning was used to give evidence to the hierarchical Bayesian network model from the evidential variables. Finally, the assessment results of students’ ANOVA score model learning were reported. Briefly, this was a mixed method research design applied to statistics learning assessment. The mixed methods designs expanded more possibilities for researchers to establish advanced quantitative models initially with a theory-driven qualitative mode.

Keywords: exploratory sequential design, ANOVA score model, Bayesian network model, mixed methods research design, cognitive analysis

Procedia PDF Downloads 178

Authors: Aadityaa Singla

Abstract:

The big five personality traits are as follows: openness, conscientiousness, extraversion, agreeableness, and neuroticism. In order to get an insight into their personality, many flocks to these categories, which each have different meanings/characteristics. This information is important not only to individuals but also to career professionals and psychologists who can use this information for candidate assessment or job recruitment. The links between AI and psychology have been well studied in cognitive science, but it is still a rather novel development. It is possible for various AI classification models to accurately predict a personality question via ten input questions. This would contrast with the hundred questions that normal humans have to answer to gain a complete picture of their five personality traits. In order to approach this problem, various AI classification models were used on a dataset to predict what a user may answer. From there, the model's prediction was compared to its actual response. Normally, there are five answer choices (a 20% chance of correct guess), and the models exceed that value to different degrees, proving their significance. By utilizing an MLP classifier, decision tree, linear model, and K-nearest neighbors, they were able to obtain a test accuracy of 86.643, 54.625, 47.875, and 52.125, respectively. These approaches display that there is potential in the future for more nuanced predictions to be made regarding personality.

Keywords: machine learning, personally, big five personality traits, cognitive science

Procedia PDF Downloads 145

Authors: Thiago Spilborghs Bueno Meyer, Plinio Thomaz Aquino Junior

Abstract:

Through speech, which privileges the functional and interactive nature of the text, it is possible to ascertain the spatiotemporal circumstances, the conditions of production and reception of the discourse, the explicit purposes such as informing, explaining, convincing, etc. These conditions allow bringing the interaction between humans closer to the human-robot interaction, making it natural and sensitive to information. However, it is not enough to understand what is said; it is necessary to recognize emotions for the desired interaction. The validity of the use of neural networks for feature selection and emotion recognition was verified. For this purpose, it is proposed the use of neural networks and comparison of models, such as recurrent neural networks and deep neural networks, in order to carry out the classification of emotions through speech signals to verify the quality of recognition. It is expected to enable the implementation of robots in a domestic environment, such as the HERA robot from the RoboFEI@Home team, which focuses on autonomous service robots for the domestic environment. Tests were performed using only the Mel-Frequency Cepstral Coefficients, as well as tests with several characteristics of Delta-MFCC, spectral contrast, and the Mel spectrogram. To carry out the training, validation and testing of the neural networks, the eNTERFACE’05 database was used, which has 42 speakers from 14 different nationalities speaking the English language. The data from the chosen database are videos that, for use in neural networks, were converted into audios. It was found as a result, a classification of 51,969% of correct answers when using the deep neural network, when the use of the recurrent neural network was verified, with the classification with accuracy equal to 44.09%. The results are more accurate when only the Mel-Frequency Cepstral Coefficients are used for the classification, using the classifier with the deep neural network, and in only one case, it is possible to observe a greater accuracy by the recurrent neural network, which occurs in the use of various features and setting 73 for batch size and 100 training epochs.

Keywords: emotion recognition, speech, deep learning, human-robot interaction, neural networks

Procedia PDF Downloads 170

Authors: Usoro Anthony E., Udoh Emediong

Abstract:

Diagonal Vector Autoregressive Models are special classes of the general vector autoregressive models identified under certain conditions, where parameters are restricted to the diagonal elements in the coefficient matrices. Variance, autocovariance, and autocorrelation properties of the upper and lower diagonal VAR models are derived. The new set of VAR models is verified with empirical data and is found to perform favourably with the general VAR models. The advantage of the diagonal models over the existing models is that the new models are parsimonious, given the reduction in the interactive coefficients of the general VAR models.

Keywords: VAR models, diagonal VAR models, variance, autocovariance, autocorrelations

Procedia PDF Downloads 116

Authors: Yung-Chung Chuang

Abstract:

The cultural layers of archaeological sites are mainly affected by surface land use, land cover, and root system of surface vegetation. For this reason, continuous monitoring of land use and land cover change is important for archaeological sites protection and management. However, in actual operation, on-site investigation and orthogonal photograph interpretation require a lot of time and manpower. For this reason, it is necessary to perform a good alternative for surface vegetation survey in an automated or semi-automated manner. In this study, we applied semi-automatic digital aerial survey technology and canopy characters classification with very high-resolution aerial photographs for surface vegetation interpretation of archaeological sites. The main idea is based on different landscape or forest type can easily be distinguished with canopy characters (e.g., specific texture distribution, shadow effects and gap characters) extracted by semi-automatic image classification. A novel methodology to classify the shape of canopy characters using landscape indices and multivariate statistics was also proposed. Non-hierarchical cluster analysis was used to assess the optimal number of canopy character clusters and canonical discriminant analysis was used to generate the discriminant functions for canopy character classification (seven categories). Therefore, people could easily predict the forest type and vegetation land cover by corresponding to the specific canopy character category. The results showed that the semi-automatic classification could effectively extract the canopy characters of forest and vegetation land cover. As for forest type and vegetation type prediction, the average prediction accuracy reached 80.3%~91.7% with different sizes of test frame. It represented this technology is useful for archaeological site survey, and can improve the classification efficiency and data update rate.

Keywords: digital aerial survey, canopy characters classification, archaeological sites, multivariate statistics

Procedia PDF Downloads 141

Authors: Dina Ahmed Selim, Eman Shawky Anwar, Rasha Mohamed Abu El-Khair

Abstract:

A rapid, simple and efficient method with minimal sample treatment was developed for authentication of Garcinia cambogia fruit peel powder, along with determining undeclared active pharmaceutical ingredients (APIs) in its herbal slimming dietary supplements using near infrared spectroscopy combined with chemometrics. Five featured adulterants, including sibutramine, metformin, orlistat, ephedrine, and theophylline are selected as target compounds. The Near infrared spectral data matrix of authentic Garcinia cambogia fruit peel and specimens degraded by intentional contamination with the five selected APIs was subjected to hierarchical clustering analysis to investigate their bundling figure. SIMCA models were established to ensure the genuiness of Garcinia cambogia fruit peel which resulted in perfect classification of all tested specimens. Adulterated samples were utilized for construction of PLSR models based on different APIs contents at minute levels of fraud practices (LOQ < 0.2% w/w).The suggested approach can be applied to enhance and guarantee the safety and quality of Garcinia fruit peel powder as raw material and in dietary supplements.

Keywords: Garcinia cambogia, Quality control, NIR spectroscopy, Chemometrics

Procedia PDF Downloads 77