Search results for: hierarchical text classification models

Authors: Sarah Beaver, Renee Bryce

Abstract:

Audiograms detect hearing impairment, but missing values pose problems. This work explores imputations in an attempt to improve accuracy. This work implements Linear Regression, Lasso, Linear Support Vector Regression, Bayesian Ridge, K Nearest Neighbors (KNN), and Random Forest machine learning techniques to impute audiogram frequencies ranging from 125Hz to 8000Hz. The data contains patients who had or were candidates for cochlear implants. Accuracy is compared across two different Nested Cross-Validation k values. Over 4000 audiograms were used from 800 unique patients. Additionally, training on data combines and compares left and right ear audiograms versus single ear side audiograms. The accuracy achieved using Root Mean Square Error (RMSE) values for the best models for Random Forest ranges from 4.74 to 6.37. The R\textsuperscript{2} values for the best models for Random Forest ranges from .91 to .96. The accuracy achieved using RMSE values for the best models for KNN ranges from 5.00 to 7.72. The R\textsuperscript{2} values for the best models for KNN ranges from .89 to .95. The best imputation models received R\textsuperscript{2} between .89 to .96 and RMSE values less than 8dB. We also show that the accuracy of classification predictive models performed better with our best imputation models versus constant imputations by a two percent increase.

Keywords: machine learning, audiograms, data imputations, single imputations

Procedia PDF Downloads 82

Authors: Mohammad Sarchami, Mohsen Zeinalkhani

Abstract:

Always, financial reporting system faces some problems to win public ear. The increase in the number of fraud and representation, often combined with the bankruptcy of large companies, has raised concerns about the quality of financial statements. So, investors, legislators, managers, and auditors have focused on significant fraud detection or prevention in financial statements. This article aims to investigate the Sugeno fuzzy classification to consider fraud detection in financial reporting of accepted firms by Tehran stock exchange. The hypothesis is: Sugeno fuzzy classification may detect fraud in financial reporting by financial ratio. Hypothesis was tested using Matlab software. Accuracy average was 81/80 in Sugeno fuzzy classification; so the hypothesis was confirmed.

Keywords: fraud, financial reporting, Sugeno fuzzy classification, firm

Procedia PDF Downloads 248

Authors: Pavan K. Rallabandi, Kailash C. Patidar

Abstract:

In this paper, we present an optimization technique or a learning algorithm using the hybrid architecture by combining the most popular sequence recognition models such as Recurrent Neural Networks (RNNs) and Hidden Markov models (HMMs). In order to improve the sequence or pattern recognition/ classification performance by applying a hybrid/neural symbolic approach, a gradient descent learning algorithm is developed using the Real Time Recurrent Learning of Recurrent Neural Network for processing the knowledge represented in trained Hidden Markov Models. The developed hybrid algorithm is implemented on automata theory as a sample test beds and the performance of the designed algorithm is demonstrated and evaluated on learning the deterministic finite state automata.

Keywords: hybrid systems, hidden markov models, recurrent neural networks, deterministic finite state automata

Procedia PDF Downloads 388

Authors: Vesile Evrim, Aliyu Awwal

Abstract:

Today as in the other domains, there are an enormous number of political transcripts available in the Web which is waiting to be mined and used for various purposes such as statistics and recommendations. Therefore, automatically determining the political orientation on these transcripts becomes crucial. The methodologies used by machine learning algorithms to do the automatic classification are based on different features such as Linguistic. Considering the ideology differences between Liberals and Conservatives, in this paper, the effect of Personality Traits on political orientation classification is studied. This is done by considering the correlation between LIWC features and the BIG Five Personality Traits. Several experiments are conducted on Convote U.S. Congressional-Speech dataset with seven benchmark classification algorithms. The different methodologies are applied on selecting different feature sets that constituted by 8 to 64 varying number of features. While Neuroticism is obtained to be the most differentiating personality trait on classification of political polarity, when its top 10 representative features are combined with several classification algorithms, it outperformed the results presented in previous research.

Keywords: politics, personality traits, LIWC, machine learning

Procedia PDF Downloads 495

Authors: Teklu Urgessa, Wookjae Maeng, Joong Seek Lee

Abstract:

Application of five implementations of three data mining classification techniques was experimented for extracting important insights from tourism data. The aim was to find out the best performing algorithm among the compared ones for tourism knowledge discovery. Knowledge discovery process from data was used as a process model. 10-fold cross validation method is used for testing purpose. Various data preprocessing activities were performed to get the final dataset for model building. Classification models of the selected algorithms were built with different scenarios on the preprocessed dataset. The outperformed algorithm tourism dataset was Random Forest (76%) before applying information gain based attribute selection and J48 (C4.5) (75%) after selection of top relevant attributes to the class (target) attribute. In terms of time for model building, attribute selection improves the efficiency of all algorithms. Artificial Neural Network (multilayer perceptron) showed the highest improvement (90%). The rules extracted from the decision tree model are presented, which showed intricate, non-trivial knowledge/insight that would otherwise not be discovered by simple statistical analysis with mediocre accuracy of the machine using classification algorithms.

Keywords: classification algorithms, data mining, knowledge discovery, tourism

Procedia PDF Downloads 295

Authors: Yin Yuanling

Abstract:

A Deep Feedback Recurrent Neural Network (DFRNN) and Bidirectional Long Short-Term Memory (BiLSTM) are designed to address the problem of low accuracy of traditional relationship extraction models. This method combines a deep feedback-based recurrent neural network (DFRNN) with a bi-directional long short-term memory (BiLSTM) approach. The method combines DFRNN, which extracts local features of text based on deep feedback recurrent mechanism, BiLSTM, which better extracts global features of text, and Self-Attention, which extracts semantic information. Experiments show that the method achieves an F1 value of 76.69% on the CEC dataset, which is 0.0652 better than the BiLSTM+Self-ATT model, thus optimizing the performance of the deep learning method in the event relationship extraction task.

Keywords: event relations, deep learning, DFRNN models, bi-directional long and short-term memory networks

Procedia PDF Downloads 144

Authors: Jonah Kenei, Elisha Opiyo

Abstract:

Electronic health records, as a repository of patient information, is nowadays the most commonly used technology to record, store and review patient clinical records and perform other clinical tasks. However, the accurate identification and retrieval of relevant information from clinical records is a difficult task due to the unstructured nature of clinical documents, characterized in particular by a lack of clear structure. Therefore, medical practice is facing a challenge thanks to the rapid growth of health information in electronic health records (EHRs), mostly in narrative text form. As a result, it's becoming important to effectively manage the growing amount of data for a single patient. As a result, there is currently a requirement to visualize electronic health records (EHRs) in a way that aids physicians in clinical tasks and medical decision-making. Leveraging text visualization techniques to unstructured clinical narrative texts is a new area of research that aims to provide better information extraction and retrieval to support clinical decision support in scenarios where data generated continues to grow. Clinical datasets in electronic health records (EHR) offer a lot of potential for training accurate statistical models to classify facets of information which can then be used to improve patient care and outcomes. However, in many clinical note datasets, the unstructured nature of clinical texts is a common problem. This paper examines the very issue of getting raw clinical texts and mapping them into meaningful structures that can support healthcare professionals utilizing narrative texts. Our work is the result of a collaborative design process that was aided by empirical data collected through formal usability testing.

Keywords: classification, electronic health records, narrative texts, visualization

Procedia PDF Downloads 118

Authors: Filiz Ersoz, Taner Ersoz, Tugrul Bayraktar

Abstract:

Renewable energy is referred to as "clean energy" and common popular support for the use of renewable energy (RE) is to provide electricity with zero carbon dioxide emissions. This study provides useful insight into the European Union (EU) RE, especially, into electricity generation obtained from renewables, and their targets. The objective of this study is to identify groups of European countries, using multivariate statistical analysis and selected indicators. The hierarchical clustering method is used to decide the number of clusters for EU countries. The conducted statistical hierarchical cluster analysis is based on the Ward’s clustering method and squared Euclidean distances. Hierarchical cluster analysis identified eight distinct clusters of European countries. Then, non-hierarchical clustering (k-means) method was applied. Discriminant analysis was used to determine the validity of the results with data normalized by Z score transformation. To explore the relationship between the selected indicators, correlation coefficients were computed. The results of the study reveal the current situation of RE in European Union Member States.

Keywords: share of electricity generation, k-means clustering, discriminant, CO2 emission

Procedia PDF Downloads 415

Authors: Mustafa Alhamdi

Abstract:

Industrial application to classify gamma rays and neutron events is investigated in this study using deep machine learning. The identification using a convolutional neural network and recursive neural network showed a significant improvement in predication accuracy in a variety of applications. The ability to identify the isotope type and activity from spectral information depends on feature extraction methods, followed by classification. The features extracted from the spectrum profiles try to find patterns and relationships to present the actual spectrum energy in low dimensional space. Increasing the level of separation between classes in feature space improves the possibility to enhance classification accuracy. The nonlinear nature to extract features by neural network contains a variety of transformation and mathematical optimization, while principal component analysis depends on linear transformations to extract features and subsequently improve the classification accuracy. In this paper, the isotope spectrum information has been preprocessed by finding the frequencies components relative to time and using them as a training dataset. Fourier transform implementation to extract frequencies component has been optimized by a suitable windowing function. Training and validation samples of different isotope profiles interacted with CdTe crystal have been simulated using Geant4. The readout electronic noise has been simulated by optimizing the mean and variance of normal distribution. Ensemble learning by combing voting of many models managed to improve the classification accuracy of neural networks. The ability to discriminate gamma and neutron events in a single predication approach using deep machine learning has shown high accuracy using deep learning. The paper findings show the ability to improve the classification accuracy by applying the spectrogram preprocessing stage to the gamma and neutron spectrums of different isotopes. Tuning deep machine learning models by hyperparameter optimization of neural network models enhanced the separation in the latent space and provided the ability to extend the number of detected isotopes in the training database. Ensemble learning contributed significantly to improve the final prediction.

Keywords: machine learning, nuclear physics, Monte Carlo simulation, noise estimation, feature extraction, classification

Procedia PDF Downloads 150

Authors: Chiung-Hui Chen

Abstract:

The Internet of Things (IoT) was designed for widespread convenience. With the smart tag and the sensing network, a large quantity of dynamic information is immediately presented in the IoT. Through the internal communication and interaction, meaningful objects provide real-time services for users. Therefore, the service with appropriate decision-making has become an essential issue. Based on the science of human behavior, this study employed the environment model to record the time sequences and locations of different behaviors and adopted the probability module of the hierarchical Hidden Markov Model for the inference. The statistical analysis was conducted to achieve the following objectives: First, define user behaviors and predict the user behavior routes with the environment model to analyze user purposes. Second, construct the hierarchical Hidden Markov Model according to the logic framework, and establish the sequential intensity among behaviors to get acquainted with the use and activity fabric of the intelligent environment. Third, establish the intensity of the relation between the probability of objects’ being used and the objects. The indicator can describe the possible limitations of the mechanism. As the process is recorded in the information of the system created in this study, these data can be reused to adjust the procedure of intelligent design services.

Keywords: behavior, big data, hierarchical hidden Markov model, intelligent object

Procedia PDF Downloads 233

Authors: Min Chen, Rubi Gupta

Abstract:

Understanding and predicting stock market movements is a challenging problem. It is believed stock markets are partially driven by public sentiments, which leads to numerous research efforts to predict stock market trend using public sentiments expressed on social media such as Twitter but with limited success. Recently a microblogging website StockTwits is becoming increasingly popular for users to share their discussions and sentiments about stocks and financial market. In this project, we analyze the text content of StockTwits tweets and extract financial sentiment using text featurization and machine learning algorithms. StockTwits tweets are first pre-processed using techniques including stopword removal, special character removal, and case normalization to remove noise. Features are extracted from these preprocessed tweets through text featurization process using bags of words, N-gram models, TF-IDF (term frequency-inverse document frequency), and latent semantic analysis. Machine learning models are then trained to classify the tweets' sentiment as positive (bullish) or negative (bearish). The correlation between the aggregated daily sentiment and daily stock price movement is then investigated using Pearson’s correlation coefficient. Finally, the sentiment information is applied together with time series stock data to predict stock price movement. The experiments on five companies (Apple, Amazon, General Electric, Microsoft, and Target) in a duration of nine months demonstrate the effectiveness of our study in improving the prediction accuracy.

Keywords: machine learning, sentiment analysis, stock price prediction, tweet processing

Procedia PDF Downloads 156

Authors: Nor Diana Ahmad, Eric Atwell, Brandon Bennett

Abstract:

Text processing techniques for English have been developed for several decades. But for the Malay language, text processing methods are still far behind. Moreover, there are limited resources, tools for computational linguistic analysis available for the Malay language. Therefore, this research presents the use of natural language processing (NLP) in processing Malay translated Qur’an text. As the result, a new language resource for Malay translated Qur’an was created. This resource will help other researchers to build the necessary processing tools for the Malay language. This research also develops a simple question-answer prototype to demonstrate the use of the Malay Qur’an resource for text processing. This prototype has been developed using Python. The prototype pre-processes the Malay Qur’an and an input query using a stemming algorithm and then searches for occurrences of the query word stem. The result produced shows improved matching likelihood between user query and its answer. A POS-tagging algorithm has also been produced. The stemming and tagging algorithms can be used as tools for research related to other Malay texts and can be used to support applications such as information retrieval, question answering systems, ontology-based search and other text analysis tasks.

Keywords: language resource, Malay translated Qur'an, natural language processing (NLP), text processing

Procedia PDF Downloads 318

Authors: Victor N. Anisimov, Lyubov A. Boyko, Yazgul R. Almukhametova, Natalia V. Galkina, Alexander V. Latanov

Abstract:

Modern commercials presented on billboards, TV and on the Internet contain a lot of information about the product or service in text form. However, this information cannot always be perceived and understood by consumers. Typical sociological focus group studies often cannot reveal important features of the interpretation and understanding information that has been read in text messages. In addition, there is no reliable method to determine the degree of understanding of the information contained in a text. Only the fact of viewing a text does not mean that consumer has perceived and understood the meaning of this text. At the same time, the tools based on marketing analysis allow only to indirectly estimate the process of reading and understanding a text. Therefore, the aim of this work is to develop a valid method of recording objective indicators in real time for assessing the fact of reading and the degree of text comprehension. Psychophysiological parameters recorded during text reading can form the basis for this objective method. We studied the relationship between multimodal psychophysiological parameters and the process of text comprehension during reading using the method of correlation analysis. We used eye-tracking technology to record eye movements parameters to estimate visual attention, electroencephalography (EEG) to assess cognitive load and polygraphic indicators (skin-galvanic reaction, SGR) that reflect the emotional state of the respondent during text reading. We revealed reliable interrelations between perceiving the information and the dynamics of psychophysiological parameters during reading the text in commercials. Eye movement parameters reflected the difficulties arising in respondents during perceiving ambiguous parts of text. EEG dynamics in rate of alpha band were related with cumulative effect of cognitive load. SGR dynamics were related with emotional state of the respondent and with the meaning of text and type of commercial. EEG and polygraph parameters together also reflected the mental difficulties of respondents in understanding text and showed significant differences in cases of low and high text comprehension. We also revealed differences in psychophysiological parameters for different type of commercials (static vs. video, financial vs. cinema vs. pharmaceutics vs. mobile communication, etc.). Conclusions: Our methodology allows to perform multimodal evaluation of text perusal and the quality of text reading in commercials. In general, our results indicate the possibility of designing an integral model to estimate the comprehension of reading the commercial text in percent scale based on all noticed markers.

Keywords: reading, commercials, eye movements, EEG, polygraphic indicators

Procedia PDF Downloads 165

Authors: Lu Song Ma Li Zhi

Abstract:

With the rapid advancement of artificial intelligence technology, large language models (LLMs) have become a milestone in the field of natural language processing, demonstrating remarkable capabilities in semantic understanding, intelligent question answering, and text generation. These models are gradually penetrating various industries, particularly showcasing significant application potential in the data analysis domain. However, retraining or fine-tuning these models requires substantial computational resources and ample downstream task datasets, which poses a significant challenge for many enterprises and research institutions. Without modifying the internal parameters of the large models, prompt engineering techniques can rapidly adapt these models to new domains. This paper proposes a prompt design strategy aimed at leveraging the capabilities of large language models to automate the generation of data analysis code. By carefully designing prompts, data analysis requirements can be described in natural language, which the large language model can then understand and convert into executable data analysis code, thereby greatly enhancing the efficiency and convenience of data analysis. This strategy not only lowers the threshold for using large models but also significantly improves the accuracy and efficiency of data analysis. Our approach includes requirements for the precision of natural language descriptions, coverage of diverse data analysis needs, and mechanisms for immediate feedback and adjustment. Experimental results show that with this prompt design strategy, large language models perform exceptionally well in multiple data analysis tasks, generating high-quality code and significantly shortening the data analysis cycle. This method provides an efficient and convenient tool for the data analysis field and demonstrates the enormous potential of large language models in practical applications.

Keywords: large language models, prompt design, data analysis, code generation

Procedia PDF Downloads 38

Authors: Chad Goldsworthy, B. Rajeswari Matam

Abstract:

The use of deep learning for species identification in camera trap images has revolutionised our ability to study, conserve and monitor species in a highly efficient and unobtrusive manner, with state-of-the-art models achieving accuracies surpassing the accuracy of manual human classification. The high imbalance of camera trap datasets, however, results in poor accuracies for minority (rare or endangered) species due to their relative insignificance to the overall model accuracy. This paper investigates the use of Focal Loss, in comparison to the traditional Cross Entropy Loss function, to improve the identification of minority species in the “255 Bird Species” dataset from Kaggle. The results show that, although Focal Loss slightly decreased the accuracy of the majority species, it was able to increase the F1-score by 0.06 and improve the identification of the bottom two, five and ten (minority) species by 37.5%, 15.7% and 10.8%, respectively, as well as resulting in an improved overall accuracy of 2.96%.

Keywords: convolutional neural networks, data imbalance, deep learning, focal loss, species classification, wildlife conservation

Procedia PDF Downloads 190

Authors: Zayar Phyo, Ei Chaw Htoon

Abstract:

In a New-LSB based Steganography method, the Fisher-Yates algorithm is used to permute an existing array randomly. However, that algorithm performance became slower and occurred memory overflow problem while processing the large dimension of images. Therefore, the Text-Based Shuffling algorithm aimed to select only necessary pixels as hiding characters at the specific position of an image according to the length of the input text. In this paper, the enhanced text-based shuffling algorithm is presented with the powered of GPU to improve more excellent performance. The proposed algorithm employs the OpenCL Aparapi framework, along with XORShift Kernel including the Pseudo-Random Number Generator (PRNG) Kernel. PRNG is applied to produce random numbers inside the kernel of OpenCL. The experiment of the proposed algorithm is carried out by practicing GPU that it can perform faster-processing speed and better efficiency without getting the disruption of unnecessary operating system tasks.

Keywords: LSB based steganography, Fisher-Yates algorithm, text-based shuffling algorithm, OpenCL, XORShiftKernel

Procedia PDF Downloads 149

Authors: Bingchun Liu, Pei-Chann Chang, Natasha Huang, Dun Li

Abstract:

Machine Learning and Data Mining are the two important tools for extracting useful information and knowledge from large datasets. In machine learning, classification is a wildly used technique to predict qualitative variables and is generally preferred over regression from an operational point of view. Due to the enormous increase in air pollution in various countries especially China, Air Quality Classification has become one of the most important topics in air quality research and modelling. This study aims at introducing a hybrid classification model based on information theory and Support Vector Machine (SVM) using the air quality data of four cities in China namely Beijing, Guangzhou, Shanghai and Tianjin from Jan 1, 2014 to April 30, 2016. China's Ministry of Environmental Protection has classified the daily air quality into 6 levels namely Serious Pollution, Severe Pollution, Moderate Pollution, Light Pollution, Good and Excellent based on their respective Air Quality Index (AQI) values. Using the information theory, information gain (IG) is calculated and feature selection is done for both categorical features and continuous numeric features. Then SVM Machine Learning algorithm is implemented on the selected features with cross-validation. The final evaluation reveals that the IG and SVM hybrid model performs better than SVM (alone), Artificial Neural Network (ANN) and K-Nearest Neighbours (KNN) models in terms of accuracy as well as complexity.

Keywords: machine learning, air quality classification, air quality index, information gain, support vector machine, cross-validation

Procedia PDF Downloads 235

Authors: M.R Asghari Bejestani, Gh. R. Mohammad Khani, V.R. Nafisi

Abstract:

Imagined speech recognition is one of the most interesting approaches to BCI development and a lot of works have been done in this area. Many different experiments have been designed and hundreds of combinations of feature extraction methods and classifiers have been examined. Reported classification accuracies range from the chance level to more than 90%. Based on non-stationary nature of brain signals, we have introduced 3 classification modes according to time difference in inter and intra-class samples. The modes can explain the diversity of reported results and predict the range of expected classification accuracies from the brain signal accusation procedure. In this paper, a few samples are illustrated by inspecting results of some previous works.

Keywords: brain computer interface, silent talk, imagined speech, classification, signal processing

Procedia PDF Downloads 153

Authors: Sidi Yang, Haiyi Zhang

Abstract:

Twitter is a microblogging platform, where millions of users daily share their attitudes, views, and opinions. Using a probabilistic Latent Dirichlet Allocation (LDA) topic model to discern the most popular topics in the Twitter data is an effective way to analyze a large set of tweets to find a set of topics in a computationally efficient manner. Sentiment analysis provides an effective method to show the emotions and sentiments found in each tweet and an efficient way to summarize the results in a manner that is clearly understood. The primary goal of this paper is to explore text mining, extract and analyze useful information from unstructured text using two approaches: LDA topic modelling and sentiment analysis by examining Twitter plain text data in English. These two methods allow people to dig data more effectively and efficiently. LDA topic model and sentiment analysis can also be applied to provide insight views in business and scientific fields.

Keywords: text mining, Twitter, topic model, sentiment analysis

Procedia PDF Downloads 179

Authors: Liang Wang, Beste F. Yuksel, David Guy Brizan

Abstract:

A computational model of affect that can distinguish between spontaneous and posed smiles with no errors on a large, popular data set using deep learning techniques is presented in this paper. A Long Short-Term Memory (LSTM) classifier, a type of Recurrent Neural Network, is utilized and compared to human classification. Results showed that while human classification (mean of 0.7133) was above chance, the LSTM model was more accurate than human classification and other comparable state-of-the-art systems. Additionally, a high accuracy rate was maintained with small amounts of training videos (70 instances). The derivation of important features to further understand the success of our computational model were analyzed, and it was inferred that thousands of pairs of points within the eyes and mouth are important throughout all time segments in a smile. This suggests that distinguishing between a posed and spontaneous smile is a complex task, one which may account for the difficulty and lower accuracy of human classification compared to machine learning models.

Keywords: affective computing, affect detection, computer vision, deep learning, human-computer interaction, machine learning, posed smile detection, spontaneous smile detection

Procedia PDF Downloads 125

Authors: Alper Taner, Yesim Benal Oztekin, Huseyin Duran

Abstract:

In this study, an Artificial Neural Network (ANN) was developed in order to classify barley varieties. For this purpose, physical properties of barley varieties were determined and ANN techniques were used. The physical properties of 8 barley varieties grown in Turkey, namely thousand kernel weight, geometric mean diameter, sphericity, kernel volume, surface area, bulk density, true density, porosity and colour parameters of grain, were determined and it was found that these properties were statistically significant with respect to varieties. As ANN model, three models, N-l, N-2 and N-3 were constructed. The performances of these models were compared. It was determined that the best-fit model was N-1. In the N-1 model, the structure of the model was designed to be 11 input layers, 2 hidden layers and 1 output layer. Thousand kernel weight, geometric mean diameter, sphericity, kernel volume, surface area, bulk density, true density, porosity and colour parameters of grain were used as input parameter; and varieties as output parameter. R2, Root Mean Square Error and Mean Error for the N-l model were found as 99.99%, 0.00074 and 0.009%, respectively. All results obtained by the N-l model were observed to have been quite consistent with real data. By this model, it would be possible to construct automation systems for classification and cleaning in flourmills.

Keywords: physical properties, artificial neural networks, barley, classification

Procedia PDF Downloads 178

Authors: Ren Moses, Jaqueline Masaki

Abstract:

This paper addresses the need for accurate and updated vehicle classification system through a thorough evaluation of vehicle class categories to identify errors arising from the existing system and proposing modifications. The data collected from two permanent traffic monitoring sites in Florida were used to evaluate the performance of the existing vehicle classification table. The vehicle data were collected and classified by the automatic vehicle classifier (AVC), and a video camera was used to obtain ground truth data. The Federal Highway Administration (FHWA) vehicle classification definitions were used to define vehicle classes from the video and compare them to the data generated by AVC in order to identify the sources of misclassification. Six types of errors were identified. Modifications were made in the classification table to improve the classification accuracy. The results of this study include the development of updated vehicle classification table with a reduction in total error by 5.1%, a step by step procedure to use for evaluation of vehicle classification studies and recommendations to improve FHWA 13-category rule set. The recommendations for the FHWA 13-category rule set indicate the need for the vehicle classification definitions in this scheme to be updated to reflect the distribution of current traffic. The presented results will be of interest to States’ transportation departments and consultants, researchers, engineers, designers, and planners who require accurate vehicle classification information for planning, designing and maintenance of transportation infrastructures.

Keywords: vehicle classification, traffic monitoring, pavement design, highway traffic

Procedia PDF Downloads 180

Authors: Aliya Grig, Konstantin Sokolov, Igor Shatalin

Abstract:

The report describes the methodology for collecting data and building an ML model for determining the personality psychotype using profiling and personality traits methods based on several short messages of a user communicating on an arbitrary topic with a chitchat bot. In the course of the experiments, the minimum amount of text was revealed to confidently determine aspects of personality. Model accuracy - 85%. Users' language of communication is English. AI for a personalized communication with a user based on his mood, personality, and current emotional state. Features investigated during the research: personalized communication; providing empathy; adaptation to a user; predictive analytics. In the report, we describe the processes that captures both structured and unstructured data pertaining to a user in large quantities and diverse forms. This data is then effectively processed through ML tools to construct a knowledge graph and draw inferences regarding users of text messages in a comprehensive manner. Specifically, the system analyzes users' behavioral patterns and predicts future scenarios based on this analysis. As a result of the experiments, we provide for further research on training AI models to be empathetic, creating personalized communication for a user

Keywords: AI, empathetic, chatbot, AI models

Procedia PDF Downloads 92

Authors: Beier Zhu, Rui Zhang, Qi Song

Abstract:

Text contained within fixed-layout documents can be of great semantic value and so requires a high localization accuracy, such as ID cards, invoices, cheques, and passports. Recently, algorithms based on deep convolutional networks achieve high performance on text detection tasks. However, for text localization in fixed-layout documents, such algorithms detect word bounding boxes individually, which ignores the layout information. This paper presents a novel architecture built on convolutional neural networks (CNNs). A global text localization network and a regional bounding-box regression network are introduced to tackle the problem in a coarse-to-fine manner. The text localization network simultaneously locates word bounding points, which takes the layout information into account. The bounding-box regression network inputs the features pooled from arbitrarily sized RoIs and refine the localizations. These two networks share their convolutional features and are trained jointly. A typical type of fixed-layout documents: ID cards, is selected to evaluate the effectiveness of the proposed system. These networks are trained on data cropped from nature scene images, and synthetic data produced by a synthetic text generation engine. Experiments show that our approach locates high accuracy word bounding boxes and achieves state-of-the-art performance.

Keywords: bounding box regression, convolutional networks, fixed-layout documents, text localization

Procedia PDF Downloads 194

Authors: Shelby Simpson, William Stanley, Namir Naba, Xiaodi Wang

Abstract:

Both t-SNE and UMAP are brand new state of art tools to predominantly preserve the local structure that is to group neighboring data points together, which indeed provides a very informative visualization of heterogeneity in our data. In this research, we develop a t-SNE and UMAP base neural network image classification algorithm to embed the original dataset to a corresponding low dimensional dataset as a preprocessing step, then use this embedded database as input to our specially designed neural network classifier for image classification. We use the fashion MNIST data set, which is a labeled data set of images of clothing objects in our experiments. t-SNE and UMAP are used for dimensionality reduction of the data set and thus produce low dimensional embeddings. Furthermore, we use the embeddings from t-SNE and UMAP to feed into two neural networks. The accuracy of the models from the two neural networks is then compared to a dense neural network that does not use embedding as an input to show which model can classify the images of clothing objects more accurately.

Keywords: t-SNE, UMAP, fashion MNIST, neural networks

Procedia PDF Downloads 198

Authors: Shreyansh Singh, Afroz Ahmed

Abstract:

Sentiment Analysis intends to naturally reveal the hidden mentality that we hold towards an entity. The total of this assumption over a populace addresses sentiment surveying and has various applications. Current text-based sentiment analysis depends on the development of word embeddings and Machine Learning models that take in conclusion from enormous text corpora. Sentiment Analysis from text is presently generally utilized for consumer loyalty appraisal and brand insight investigation. With the expansion of online media, multimodal assessment investigation is set to carry new freedoms with the appearance of integral information streams for improving and going past text-based feeling examination using the new transforms methods. Since supposition can be distinguished through compelling follows it leaves, like facial and vocal presentations, multimodal opinion investigation offers good roads for examining facial and vocal articulations notwithstanding the record or printed content. These methodologies use the Recurrent Neural Networks (RNNs) with the LSTM modes to increase their performance. In this study, we characterize feeling and the issue of multimodal assessment investigation and audit ongoing advancements in multimodal notion examination in various spaces, including spoken surveys, pictures, video websites, human-machine, and human-human connections. Difficulties and chances of this arising field are additionally examined, promoting our theory that multimodal feeling investigation holds critical undiscovered potential.

Keywords: sentiment analysis, RNN, LSTM, word embeddings

Procedia PDF Downloads 119

Authors: Christian Neunzig, Simon Fahle, Jürgen Schulz, Matthias Möller, Bernd Kuhlenkötter

Abstract:

Due to increasing cost pressure in global markets, artificial intelligence is becoming a technology that is decisive for competition. Predictive quality enables machinery and plant manufacturers to ensure product quality by using data-driven forecasts via machine learning models as a decision-making basis for test results. The use of cross-process Bosch production data along the value chain of hydraulic valves is a promising approach to classifying the quality characteristics of workpieces.

Keywords: predictive quality, hydraulics, machine learning, classification, supervised learning

Procedia PDF Downloads 230

Authors: Dewi Juliah Ratnaningsih, Imas Sukaesih Sitanggang

Abstract:

Classification is one of data mining techniques that aims to discover a model from training data that distinguishes records into the appropriate category or class. Data mining classification methods can be applied in education, for example, to determine the classification of non-active students in Indonesia Open University. This paper presents a comparison of three methods of classification: Naïve Bayes, Bagging, and C.45. The criteria used to evaluate the performance of three methods of classification are stratified cross-validation, confusion matrix, the value of the area under the ROC Curve (AUC), Recall, Precision, and F-measure. The data used for this paper are from the non-active Indonesia Open University students in registration period of 2004.1 to 2012.2. Target analysis requires that non-active students were divided into 3 groups: C1, C2, and C3. Data analyzed are as many as 4173 students. Results of the study show: (1) Bagging method gave a high degree of classification accuracy than Naïve Bayes and C.45, (2) the Bagging classification accuracy rate is 82.99 %, while the Naïve Bayes and C.45 are 80.04 % and 82.74 % respectively, (3) the result of Bagging classification tree method has a large number of nodes, so it is quite difficult in decision making, (4) classification of non-active Indonesia Open University student characteristics uses algorithms C.45, (5) based on the algorithm C.45, there are 5 interesting rules which can describe the characteristics of non-active Indonesia Open University students.

Keywords: comparative analysis, data mining, clasiffication, Bagging, Naïve Bayes, C.45, non-active students, Indonesia Open University

Procedia PDF Downloads 315

Authors: Rita Chattopadhyay, Vivek Anand Thoutam

Abstract:

Speech is the most acceptable means of communication where we can quickly exchange our feelings and thoughts. Quite often, people can communicate orally but cannot interact or work with computers or devices. It’s easy and quick to give speech commands than typing commands to computers. In the same way, it’s easy listening to audio played from a device than extract output from computers or devices. Especially with Robotics being an emerging market with applications in warehouses, the hospitality industry, consumer electronics, assistive technology, etc., speech-based human-machine interaction is emerging as a lucrative feature for robot manufacturers. Considering this factor, the objective of this paper is to design the “Audio-Visual Co-Data Processing Pipeline.” This pipeline is an integrated version of Automatic speech recognition, a Natural language model for text understanding, object detection, and text-to-speech modules. There are many Deep Learning models for each type of the modules mentioned above, but OpenVINO Model Zoo models are used because the OpenVINO toolkit covers both computer vision and non-computer vision workloads across Intel hardware and maximizes performance, and accelerates application development. A speech command is given as input that has information about target objects to be detected and start and end times to extract the required interval from the video. Speech is converted to text using the Automatic speech recognition QuartzNet model. The summary is extracted from text using a natural language model Generative Pre-Trained Transformer-3 (GPT-3). Based on the summary, essential frames from the video are extracted, and the You Only Look Once (YOLO) object detection model detects You Only Look Once (YOLO) objects on these extracted frames. Frame numbers that have target objects (specified objects in the speech command) are saved as text. Finally, this text (frame numbers) is converted to speech using text to speech model and will be played from the device. This project is developed for 80 You Only Look Once (YOLO) labels, and the user can extract frames based on only one or two target labels. This pipeline can be extended for more than two target labels easily by making appropriate changes in the object detection module. This project is developed for four different speech command formats by including sample examples in the prompt used by Generative Pre-Trained Transformer-3 (GPT-3) model. Based on user preference, one can come up with a new speech command format by including some examples of the respective format in the prompt used by the Generative Pre-Trained Transformer-3 (GPT-3) model. This pipeline can be used in many projects like human-machine interface, human-robot interaction, and surveillance through speech commands. All object detection projects can be upgraded using this pipeline so that one can give speech commands and output is played from the device.

Keywords: OpenVINO, automatic speech recognition, natural language processing, object detection, text to speech

Procedia PDF Downloads 80

Authors: JaeYoon Lee, Gi-Hoon Yang, JongHan Ha, MyungGu Yeo, SeungHyun Ahn, Hyeongjin Lee, HoJun Jeon, YongBok Kim, Minseong Kim, GeunHyung Kim

Abstract:

One of the important factors in tissue engineering is to design optimal biomedical scaffolds, which can be governed by topographical surface characteristics, such as size, shape, and direction. Of these properties, we focused on the effects of nano- to micro-sized hierarchical surface. To fabricate the hierarchical surface structure on poly(ε-caprolactone) (PCL) film, we employed a micro-casting technique by pressing the mold and nano-etching technique using a modified plasma process. The micro-sized topography of PCL film was controlled by sizes of the micro structures on lotus leaf. Also, the nano-sized topography and hydrophilicity of PCL film were controlled by a modified plasma process. After the plasma treatment, the hydrophobic property of the PCL film was significantly changed into hydrophilic property, and the nano-sized structure was well developed. The surface properties of the modified PCL film were investigated in terms of initial cell morphology, attachment, and proliferation using osteoblast-like-cells (MG63). In particular, initial cell attachment, proliferation and osteogenic differentiation in the hierarchical structure were enhanced dramatically compared to those of the smooth surface. We believe that these results are because of a synergistic effect between the hierarchical structure and the reactive functional groups due to the plasma process. Based on the results presented here, we propose a new biomimetic surface model that maybe useful for effectively regenerating hard tissues.

Keywords: hierarchical surface, lotus leaf, nano-etching, plasma treatment

Procedia PDF Downloads 375