Search results for: hierarchical text classification models

Authors: Nurvadi Albekov

Abstract:

Communicative situation is a basis, which designates potential models of ‘constructed forms’, a motivated basis of a text, for a text can be assumed as a product of the communicative situation. It is within the field of emergence the models of text, that can be potentially prognosticated in a certain communicative situation, are designated. Every text can be assumed as conceptual system structured on the base of certain communicative situation. However in the process of ‘structuring’ of a certain model of ‘conceptual system’ consciousness of a recipient is able act only within the border of the field of emergence for going out of this border indicates misunderstanding of the communicative situation. On the base of communicative situation we can witness the increment of meaning where the synergizing of the informative model of communication, formed by using of the invariant units of a language system, is a result of verbalization of the communicative situation. The potential of the models of a text, prognosticated within the field of emergence, also depends on the communicative situation. The conception ‘the field of emergence’ is interpreted as a unit of the language system, having poly-directed universal structure, implying the presence of the core, the center and the periphery, including different levels of means of a functioning system of language, both in terms of linguistic resources, and in terms of extra linguistic factors interaction of which results increment of a text. The conception ‘field of emergence’ is considered as the most promising in the analysis of texts: oral, written, printed and electronic. As a unit of the language system field of emergence has several properties that predict its use during the study of a text in different levels. This work is an attempt analysis of entropy in a text in the aspect of lingua-cultural code, prognosticated within the model of the field of emergence. The article describes the problem of entropy in the field of emergence, caused by influence of the extra-linguistic factors. The increasing of entropy is caused not only by the fact of intrusion of the language resources but by influence of the alien culture in a whole, and by appearance of non-typical for this very culture symbols in the field of emergence. The borrowing of alien lingua-cultural symbols into the lingua-culture of the author is a reason of increasing the entropy when constructing a text both in meaning and in structuring level. It is nothing but artificial formatting of lexical units that violate stylistic unity of a phrase. It is marked that one of the important characteristics descending the entropy in the field of emergence is a typical similarity of lexical and semantic resources of the different lingua-cultures in aspects of extra linguistic factors.

Keywords: communicative situation, field of emergence, lingua-culture, entropy

Procedia PDF Downloads 362

Authors: Bowen Ding, Yihao Kuang

Abstract:

In recent years, large-scale pre-trained language models have achieved state-of-the-art performance on a variety of natural language processing tasks. The word vectors produced by these language models can be viewed as dense encoded presentations of natural language that in text form. However, it is unknown how much linguistic information is encoded and how. In this paper, we construct several corresponding probing tasks for multiple linguistic information to clarify the encoding capabilities of different language models and performed a visual display. We firstly obtain word presentations in vector form from different language models, including BERT, ELMo, RoBERTa and GPT. Classifiers with a small scale of parameters and unsupervised tasks are then applied on these word vectors to discriminate their capability to encode corresponding linguistic information. The constructed probe tasks contain both semantic and syntactic aspects. The semantic aspect includes the ability of the model to understand semantic entities such as numbers, time, and characters, and the grammatical aspect includes the ability of the language model to understand grammatical structures such as dependency relationships and reference relationships. We also compare encoding capabilities of different layers in the same language model to infer how linguistic information is encoded in the model.

Keywords: language models, probing task, text presentation, linguistic information

Procedia PDF Downloads 110

Authors: Faisal Muhibuddin, Ani Dijah Rahajoe

Abstract:

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

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

Procedia PDF Downloads 64

Authors: Xudong He, Jian Wang, Jiqiang Liu, Lei Han, Yang Yu, Shaohua Lv

Abstract:

Nowadays, the threats of the internet are enormous and increasing; however, the classification of huge alert messages generated in this environment is relatively monotonous. It affects the accuracy of the network situation assessment, and also brings inconvenience to the security managers to deal with the emergency. In order to deal with potential network threats effectively and provide more effective data to improve the network situation awareness. It is essential to build a hierarchical filtering method to prevent the threats. In this paper, it establishes a model for data monitoring, which can filter systematically from the original data to get the grade of threats and be stored for using again. Firstly, it filters the vulnerable resources, open ports of host devices and services. Then use the entropy theory to calculate the performance changes of the host devices at the time of the threat occurring and filter again. At last, sort the changes of the performance value at the time of threat occurring. Use the alerts and performance data collected in the real network environment to evaluate and analyze. The comparative experimental analysis shows that the threat filtering method can effectively filter the threat alerts effectively.

Keywords: correlation analysis, hierarchical filtering, multisource data, network security

Procedia PDF Downloads 201

Authors: Queen Suraajini Rajendran, Sai Hung Cheung

Abstract:

Statistical down scaling models are required to connect the global climate model outputs and the local weather variables for climate change impact prediction. For reliable climate change impact studies, the uncertainty associated with the model including natural variability, uncertainty in the climate model(s), down scaling model, model inadequacy and in the predicted results should be quantified appropriately. In this work, a new approach is developed by the authors for statistical classification, statistical down scaling and uncertainty assessment and is applied to Singapore rainfall. It is a robust Bayesian uncertainty analysis methodology and tools based on coupling dependent modeling error with classification and statistical down scaling models in a way that the dependency among modeling errors will impact the results of both classification and statistical down scaling model calibration and uncertainty analysis for future prediction. Singapore data are considered here and the uncertainty and prediction results are obtained. From the results obtained, directions of research for improvement are briefly presented.

Keywords: statistical downscaling, global climate model, climate change, uncertainty

Procedia PDF Downloads 368

Authors: Hassan Masoumi, Ahad Salimi, Nazanin Barhemmat, Babak Gholami

Abstract:

Artificial neural networks have gained a lot of interest as empirical models for their powerful representational capacity, multi input and output mapping characteristics. In fact, most feed-forward networks with nonlinear nodal functions have been proved to be universal approximates. In this paper, we propose a new supervised method for color image classification based on self organizing feature maps (SOFM). This algorithm is based on competitive learning. The method partitions the input space using self-organizing feature maps to introduce the concept of local neighborhoods. Our image classification system entered into RGB image. Experiments with simulated data showed that separability of classes increased when increasing training time. In additional, the result shows proposed algorithms are effective for color image classification.

Keywords: classification, SOFM algorithm, neural network, neighborhood, RGB image

Procedia PDF Downloads 478

Authors: S. Tehsin, S. Kausar

Abstract:

The ultimate aim of machine intelligence is to explore and materialize the human capabilities, one of which is the ability to detect various text objects within one or more images displayed on any canvas including prints, videos or electronic displays. Multimedia data has increased rapidly in past years. Textual information present in multimedia contains important information about the image/video content. However, it needs to technologically testify the commonly used human intelligence of detecting and differentiating the text within an image, for computers. Hence in this paper feature set based on anatomical study of human text detection system is proposed. Subsequent examination bears testimony to the fact that the features extracted proved instrumental to text detection.

Keywords: biologically inspired vision, content based retrieval, document analysis, text extraction

Procedia PDF Downloads 444

Authors: Arian Hosseini, Mahmudul Hasan

Abstract:

To address the increasing need for efficient and accurate content moderation, we propose an efficient and lightweight deep classification ensemble structure. Our approach is based on a combination of simple visual features, designed for high-accuracy classification of violent content with low false positives. Our ensemble architecture utilizes a set of lightweight models with narrowed-down color features, and we apply it to both images and videos. We evaluated our approach using a large dataset of explosion and blast contents and compared its performance to popular deep learning models such as ResNet-50. Our evaluation results demonstrate significant improvements in prediction accuracy, while benefiting from 7.64x faster inference and lower computation cost. While our approach is tailored to explosion detection, it can be applied to other similar content moderation and violence detection use cases as well. Based on our experiments, we propose a "think small, think many" philosophy in classification scenarios. We argue that transforming a single, large, monolithic deep model into a verification-based step model ensemble of multiple small, simple, and lightweight models with narrowed-down visual features can possibly lead to predictions with higher accuracy.

Keywords: deep classification, content moderation, ensemble learning, explosion detection, video processing

Procedia PDF Downloads 54

Authors: Prajwal Prakash Vasisht, Sharath Rajamurthy, Nishanth Dara

Abstract:

In a supervised machine learning approach, metrics such as precision, accuracy, and coverage can be calculated using ground truth labels to help in model tuning, evaluation, and selection. In an unsupervised setting, however, where the data has no ground truth, there are few interpretable metrics that can guide us to do the same. Our approach creates a framework to adapt the Intersection over Union metric, referred to as Adapted IoU, usually used to evaluate supervised learning models, into the unsupervised domain, which solves the problem by factoring in subject matter expertise and intuition about the ideal output from the model. This metric essentially provides a scale that allows us to compare the performance across numerous unsupervised models or tune hyper-parameters and compare different versions of the same model.

Keywords: general metric, unsupervised learning, classification, intersection over union

Procedia PDF Downloads 47

Authors: Vesile Evrim, Aliyu Awwal

Abstract:

By the evolvement in technology, the way of expressing opinions switched the direction to the digital world. The domain of politics as one of the hottest topics of opinion mining research merged together with the behavior analysis for affiliation determination in text which constitutes the subject of this paper. This study aims to classify the text in news/blogs either as Republican or Democrat with the minimum number of features. As an initial set, 68 features which 64 are constituted by Linguistic Inquiry and Word Count (LIWC) features are tested against 14 benchmark classification algorithms. In the later experiments, the dimensions of the feature vector reduced based on the 7 feature selection algorithms. The results show that Decision Tree, Rule Induction and M5 Rule classifiers when used with SVM and IGR feature selection algorithms performed the best up to 82.5% accuracy on a given dataset. Further tests on a single feature and the linguistic based feature sets showed the similar results. The feature “function” as an aggregate feature of the linguistic category, is obtained as the most differentiating feature among the 68 features with 81% accuracy by itself in classifying articles either as Republican or Democrat.

Keywords: feature selection, LIWC, machine learning, politics

Procedia PDF Downloads 382

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. 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. 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: gendered grammar, misogynistic language, natural language processing, neural networks

Procedia PDF Downloads 120

Authors: Karim Abouelmehdi, Loubna Dali, Elmoutaoukkil Abdelmajid, Hoda Elsayed, Eladnani Fatiha, Benihssane Abderahim

Abstract:

The security of cloud services is the concern of cloud service providers. In this paper, we will mention different classifications of cloud attacks referred by specialized organizations. Each agency has its classification of well-defined properties. The purpose is to present a high-level classification of current research in cloud computing security. This classification is organized around attack strategies and corresponding defenses.

Keywords: cloud computing, classification, risk, security

Procedia PDF Downloads 548

Authors: Lei Zhang

Abstract:

The carbon cycle greatly influences global change, and the land cover changes contribute to the status and rate of the carbon budget in ecosystems. This paper proposes a land cover classification system for mapping land cover, the national ecological environment assessment, and estimating carbon storage in ecosystems. The classification system consists of basic land cover classes at levels Ⅰ and Ⅱ and auxiliary features at level III. The basic 38 classes characterizing land cover features are derived from 19 criteria referring to composition, structure, pattern, phenology, etc. The basic classes reflect the status of carbon storage in ecosystems. The auxiliary classes at level III complement the attributes of higher levels by 9 criteria. The 5 environmental criteria of temperature, moisture, landform, aspect and slope mainly reflect the potential and intensity of carbon storage in ecosystems. The disturbance of vegetation succession caused by land use type influences the vegetation carbon budget. The other 3 vegetation cover criteria, growth period, and species characteristics further refine the vegetation types. The hierarchical structure of the land cover map (the classes of levels Ⅰ and Ⅱ) is independent of the products of level III, which is helpful for land cover product management and applications. The classification system has been adopted in the Chinese national land cover database for the carbon budget in ecosystems at a 30 m scale.

Keywords: classification system, land cover, ecosystem, carbon storage, object based

Procedia PDF Downloads 70

Authors: Nadya Inda Syartanti

Abstract:

This research aims to identify, classify, and analyze descriptively the aspects of grammatical and lexical cohesion in the speech text of Japan’s Prime Minister Shinzo Abe entitled Nihon wa Modotte kimashita delivered in Washington DC, the United States on February 23, 2013, as a research data source. The method used is qualitative research, which uses descriptions through words that are applied by analyzing aspects of grammatical and lexical cohesion proposed by Halliday and Hasan (1976). The aspects of grammatical cohesion consist of references (personal, demonstrative, interrogative pronouns), substitution, ellipsis, and conjunction. In contrast, lexical cohesion consists of reiteration (repetition, synonym, antonym, hyponym, meronym) and collocation. Data classification is based on the 6 aspects of the cohesion. Through some aspects of cohesion, this research tries to find out the frequency of using grammatical and lexical cohesion in Shinzo Abe's speech text entitled Nihon wa Modotte kimashita. The results of this research are expected to help overcome the difficulty of understanding speech texts in Japanese. Therefore, this research can be a reference for learners, researchers, and anyone who is interested in the field of discourse analysis.

Keywords: cohesion, grammatical cohesion, lexical cohesion, speech text, Shinzo Abe

Procedia PDF Downloads 162

Authors: Ceren Kaya, Okan Erkaymaz, Orhan Ayar, Mahmut Özer

Abstract:

Diabetes Mellitus (Diabetes) is a disease based on insulin hormone disorders and causes high blood glucose. Clinical findings determine that diabetes can be diagnosed by electrophysiological signals obtained from the vital organs. 'Diabetic Retinopathy' is one of the most common eye diseases resulting on diabetes and it is the leading cause of vision loss due to structural alteration of the retinal layer vessels. In this study, features of horizontal and vertical Video-Oculography (VOG) signals have been used to classify non-proliferative and proliferative diabetic retinopathy disease. Twenty-five features are acquired by using discrete wavelet transform with VOG signals which are taken from 21 subjects. Two models, based on multi-layer perceptron and radial basis function, are recommended in the diagnosis of Diabetic Retinopathy. The proposed models also can detect level of the disease. We show comparative classification performance of the proposed models. Our results show that proposed the RBF model (100%) results in better classification performance than the MLP model (94%).

Keywords: diabetic retinopathy, discrete wavelet transform, multi-layer perceptron, radial basis function, video-oculography (VOG)

Procedia PDF Downloads 259

Authors: Ghada A. Alfattni

Abstract:

Analysing unbalanced datasets is one of the challenges that practitioners in machine learning field face. However, many researches have been carried out to determine the effectiveness of the use of the synthetic minority over-sampling technique (SMOTE) to address this issue. The aim of this study was therefore to compare the effectiveness of the SMOTE over different models on unbalanced datasets. Three classification models (Logistic Regression, Support Vector Machine and Nearest Neighbour) were tested with multiple datasets, then the same datasets were oversampled by using SMOTE and applied again to the three models to compare the differences in the performances. Results of experiments show that the highest number of nearest neighbours gives lower values of error rates. 

Keywords: imbalanced datasets, SMOTE, machine learning, logistic regression, support vector machine, nearest neighbour

Procedia PDF Downloads 350

Authors: Jia Xin Low, Keng Wah Choo

Abstract:

This paper presents an automatic normal and abnormal heart sound classification model developed based on deep learning algorithm. MITHSDB heart sounds datasets obtained from the 2016 PhysioNet/Computing in Cardiology Challenge database were used in this research with the assumption that the electrocardiograms (ECG) were recorded simultaneously with the heart sounds (phonocardiogram, PCG). The PCG time series are segmented per heart beat, and each sub-segment is converted to form a square intensity matrix, and classified using convolutional neural network (CNN) models. This approach removes the need to provide classification features for the supervised machine learning algorithm. Instead, the features are determined automatically through training, from the time series provided. The result proves that the prediction model is able to provide reasonable and comparable classification accuracy despite simple implementation. This approach can be used for real-time classification of heart sounds in Internet of Medical Things (IoMT), e.g. remote monitoring applications of PCG signal.

Keywords: convolutional neural network, discrete wavelet transform, deep learning, heart sound classification

Procedia PDF Downloads 348

Authors: Mouheb Mehdoui, Amel Fraisse, Mounir Zrigui

Abstract:

This paper explores the potential of short texts through semantic enrichment and disambiguation techniques. By employing context fusion, we aim to enhance the comprehension and utility of concise textual information. The methodologies utilized are grounded in recent advancements in natural language processing, which allow for a deeper understanding of semantics within limited text formats. Specifically, topic classification is employed to understand the context of the sentence and assess the relevance of added expressions. Additionally, word sense disambiguation is used to clarify unclear words, replacing them with more precise terms. The implications of this research extend to various applications, including information retrieval and knowledge representation. Ultimately, this work highlights the importance of refining short text processing techniques to unlock their full potential in real-world applications.

Keywords: information traffic, text summarization, word-sense disambiguation, semantic enrichment, ambiguity resolution, short text enhancement, information retrieval, contextual understanding, natural language processing, ambiguity

Procedia PDF Downloads 8

Authors: Gautier Viaud, Paul-Henry Cournède

Abstract:

Plant growth models have been used extensively for the prediction of the phenotypic performance of plants. However, they remain most often calibrated for a given genotype and therefore do not take into account genotype by environment interactions. One way of achieving such an objective is to consider Bayesian hierarchical models. Three levels can be identified in such models: The first level describes how a given growth model describes the phenotype of the plant as a function of individual parameters, the second level describes how these individual parameters are distributed within a plant population, the third level corresponds to the attribution of priors on population parameters. Thanks to the Bayesian framework, choosing appropriate priors for the population parameters permits to derive analytical expressions for the full conditional distributions of these population parameters. As plant growth models are of a nonlinear nature, individual parameters cannot be sampled explicitly, and a Metropolis step must be performed. This allows for the use of a hybrid Gibbs--Metropolis sampler. A generic approach was devised for the implementation of both general state space models and estimation algorithms within a programming platform. It was designed using the Julia language, which combines an elegant syntax, metaprogramming capabilities and exhibits high efficiency. Results were obtained for Arabidopsis thaliana on both simulated and real data. An organ-scale Greenlab model for the latter is thus presented, where the surface areas of each individual leaf can be simulated. It is assumed that the error made on the measurement of leaf areas is proportional to the leaf area itself; multiplicative normal noises for the observations are therefore used. Real data were obtained via image analysis of zenithal images of Arabidopsis thaliana over a period of 21 days using a two-step segmentation and tracking algorithm which notably takes advantage of the Arabidopsis thaliana phyllotaxy. Since the model formulation is rather flexible, there is no need that the data for a single individual be available at all times, nor that the times at which data is available be the same for all the different individuals. This allows to discard data from image analysis when it is not considered reliable enough, thereby providing low-biased data in large quantity for leaf areas. The proposed model precisely reproduces the dynamics of Arabidopsis thaliana’s growth while accounting for the variability between genotypes. In addition to the estimation of the population parameters, the level of variability is an interesting indicator of the genotypic stability of model parameters. A promising perspective is to test whether some of the latter should be considered as fixed effects.

Keywords: bayesian, genotypic differentiation, hierarchical models, plant growth models

Procedia PDF Downloads 303

Authors: Mina Samizadeh

Abstract:

In the past few decades, there has been an explosion in the amount of available data produced from various sources with different topics. The availability of this enormous data necessitates us to adopt effective computational tools to explore the data. This leads to an intense growing interest in the research community to develop computational methods focused on processing this text data. A line of study focused on condensing the text so that we are able to get a higher level of understanding in a shorter time. The two important tasks to do this are keyword extraction and text summarization. In keyword extraction, we are interested in finding the key important words from a text. This makes us familiar with the general topic of a text. In text summarization, we are interested in producing a short-length text which includes important information about the document. The TextRank algorithm, an unsupervised learning method that is an extension of the PageRank (algorithm which is the base algorithm of Google search engine for searching pages and ranking them), has shown its efficacy in large-scale text mining, especially for text summarization and keyword extraction. This algorithm can automatically extract the important parts of a text (keywords or sentences) and declare them as a result. However, this algorithm neglects the semantic similarity between the different parts. In this work, we improved the results of the TextRank algorithm by incorporating the semantic similarity between parts of the text. Aside from keyword extraction and text summarization, we develop a topic clustering algorithm based on our framework, which can be used individually or as a part of generating the summary to overcome coverage problems.

Keywords: keyword extraction, n-gram extraction, text summarization, topic clustering, semantic analysis

Procedia PDF Downloads 70

Authors: Bryan Crompton, Daniel Giger, Tanay Mehta, Apurva Mody

Abstract:

The task of classifying radio frequency (RF) signals has seen recent success in employing deep neural network models. In this work, we present a combined signal processing and machine learning approach to signal classification for cochannel anomalous signals. The power spectral density and cyclostationary signal processing features of a captured signal are computed and fed into a neural net to produce a classification decision. Our combined signal preprocessing and machine learning approach allows for simpler neural networks with fast training times and small computational resource requirements for inference with longer preprocessing time.

Keywords: signal processing, machine learning, cyclostationary signal processing, signal classification

Procedia PDF Downloads 107

Authors: Shajida M., Sakthiyadharshini N. P., Kamalesh S., Aswitha B.

Abstract:

Natural Language Processing (NLP) continues to play a strategic part in complaint discovery and medicine discovery during the current epidemic. This abstract provides an overview of performance analysis with a combination of visualization and classification techniques of NLP for a medical chatbot. Sentiment analysis is an important aspect of NLP that is used to determine the emotional tone behind a piece of text. This technique has been applied to various domains, including medical chatbots. In this, we have compared the combination of the decision tree with heatmap and Naïve Bayes with Word Cloud. The performance of the chatbot was evaluated using accuracy, and the results indicate that the combination of visualization and classification techniques significantly improves the chatbot's performance.

Keywords: sentimental analysis, NLP, medical chatbot, decision tree, heatmap, naïve bayes, word cloud

Procedia PDF Downloads 72

Authors: N. Fuad, M. N. Taib, R. Jailani, M. E. Marwan

Abstract:

In this paper, the comparison between k-Nearest Neighbor (kNN) algorithms for classifying the 3D EEG model in brain balancing is presented. The EEG signal recording was conducted on 51 healthy subjects. Development of 3D EEG models involves pre-processing of raw EEG signals and construction of spectrogram images. Then, maximum PSD values were extracted as features from the model. There are three indexes for the balanced brain; index 3, index 4 and index 5. There are significant different of the EEG signals due to the brain balancing index (BBI). Alpha-α (8–13 Hz) and beta-β (13–30 Hz) were used as input signals for the classification model. The k-NN classification result is 88.46% accuracy. These results proved that k-NN can be used in order to predict the brain balancing application.

Keywords: power spectral density, 3D EEG model, brain balancing, kNN

Procedia PDF Downloads 486

Authors: Mohamed Lotfy, Ghada Soliman

Abstract:

Recognizing Arabic dot-matrix digits is a challenging problem due to the unique characteristics of dot-matrix fonts, such as irregular dot spacing and varying dot sizes. This paper presents an approach for recognizing Arabic digits printed in dot matrix format. The proposed model is based on Convolutional Neural Networks (CNN) that take the dot matrix as input and generate embeddings that are rounded to generate binary representations of the digits. The binary embeddings are then used to perform Optical Character Recognition (OCR) on the digit images. To overcome the challenge of the limited availability of dotted Arabic expiration date images, we developed a True Type Font (TTF) for generating synthetic images of Arabic dot-matrix characters. The model was trained on a synthetic dataset of 3287 images and 658 synthetic images for testing, representing realistic expiration dates from 2019 to 2027 in the format of yyyy/mm/dd. Our model achieved an accuracy of 98.94% on the expiry date recognition with Arabic dot matrix format using fewer parameters and less computational resources than traditional CNN-based models. By investigating and presenting our findings comprehensively, we aim to contribute substantially to the field of OCR and pave the way for advancements in Arabic dot-matrix character recognition. Our proposed approach is not limited to Arabic dot matrix digit recognition but can also be extended to text recognition tasks, such as text classification and sentiment analysis.

Keywords: computer vision, pattern recognition, optical character recognition, deep learning

Procedia PDF Downloads 93

Authors: Jessica Lopez Espejel, Mahaman Sanoussi Yahaya Alassan, Walid Dahhane, El Hassane Ettifouri

Abstract:

Pretrained transformer-based models have shown high performance in natural language generation tasks. However, a new wave of interest has surged: automatic programming language code generation. This task consists of translating natural language instructions to a source code. Despite the fact that well-known pre-trained models on language generation have achieved good performance in learning programming languages, effort is still needed in automatic code generation. In this paper, we introduce JaCoText, a model based on Transformer neural network. It aims to generate java source code from natural language text. JaCoText leverages the advantages of both natural language and code generation models. More specifically, we study some findings from state of the art and use them to (1) initialize our model from powerful pre-trained models, (2) explore additional pretraining on our java dataset, (3) lead experiments combining the unimodal and bimodal data in training, and (4) scale the input and output length during the fine-tuning of the model. Conducted experiments on CONCODE dataset show that JaCoText achieves new state-of-the-art results.

Keywords: java code generation, natural language processing, sequence-to-sequence models, transformer neural networks

Procedia PDF Downloads 284

Authors: R. Nandhini, Gaurab Mudbhari

Abstract:

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

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

Procedia PDF Downloads 7

Authors: Tapan Jain, Davender Singh Saini

Abstract:

Clustering is a useful mechanism in wireless sensor networks which helps to cope with scalability and data transmission problems. The basic aim of our research work is to provide efficient clustering using Hierarchical agglomerative clustering (HAC). If the distance between the sensing nodes is calculated using their location then it’s quantitative HAC. This paper compares the various agglomerative clustering techniques applied in a wireless sensor network using the quantitative data. The simulations are done in MATLAB and the comparisons are made between the different protocols using dendrograms.

Keywords: routing, hierarchical clustering, agglomerative, quantitative, wireless sensor network

Procedia PDF Downloads 615

Authors: A. M. John-Otumu, M. M. Rahman, O. C. Nwokonkwo, M. C. Onuoha

Abstract:

Online social media networks have long served as a primary arena for group conversations, gossip, text-based information sharing and distribution. The use of natural language processing techniques for text classification and unbiased decision-making has not been far-fetched. Proper classification of this textual information in a given context has also been very difficult. As a result, we decided to conduct a systematic review of previous literature on sentiment classification and AI-based techniques that have been used in order to gain a better understanding of the process of designing and developing a robust and more accurate sentiment classifier that can correctly classify social media textual information of a given context between hate speech and inverted compliments with a high level of accuracy by assessing different artificial intelligence techniques. We evaluated over 250 articles from digital sources like ScienceDirect, ACM, Google Scholar, and IEEE Xplore and whittled down the number of research to 31. Findings revealed that Deep learning approaches such as CNN, RNN, BERT, and LSTM outperformed various machine learning techniques in terms of performance accuracy. A large dataset is also necessary for developing a robust sentiment classifier and can be obtained from places like Twitter, movie reviews, Kaggle, SST, and SemEval Task4. Hybrid Deep Learning techniques like CNN+LSTM, CNN+GRU, CNN+BERT outperformed single Deep Learning techniques and machine learning techniques. Python programming language outperformed Java programming language in terms of sentiment analyzer development due to its simplicity and AI-based library functionalities. Based on some of the important findings from this study, we made a recommendation for future research.

Keywords: artificial intelligence, natural language processing, sentiment analysis, social network, text

Procedia PDF Downloads 115

Authors: Awatef Boubakri, Khaled Jebahi

Abstract:

Using Text World Theory (TWT), we attempted to understand how mental representations (text worlds) and perceptions can be construed by readers of Quranic texts. To this end, Surah Al-Kahf was purposefully selected given the fact that while each of its stories is narrated, different levels of discourse intervene, which might result in a confused reader who might find it hard to keep track of which discourse he or she is processing. This surah was studied using specifically-designed text-world diagrams. The findings suggest that TWT can be used to help solve problems of ambiguity at the level of discourse in Quranic texts and to help construct a thinking reader whose cognitive constructs (text worlds / mental representations) are built through reflecting on the various and often changing components of discourse world, text world, and sub-worlds.

Keywords: Al-Kahf, Surah, cognitive, processing, discourse

Procedia PDF Downloads 88

Authors: Liane Marcia Freitas Silva, Fernando Augusto Silva Marins, Maria Silene Alexandre Leite

Abstract:

The adoption of a network structure, like in the supply chains, favors the increase of dependence between companies and, by consequence, their vulnerability. Environment disasters, sociopolitical and economical events, and the dynamics of supply chains elevate the uncertainty of their operation, favoring the occurrence of events that can generate break up in the operations and other undesired consequences. Thus, supply chains are exposed to various risks that can influence the profitability of companies involved, and there are several previous studies that have proposed risk classification models in order to categorize the risks and to manage them. The objective of this paper is to analyze and discuss thirty of these risk classification models by means a theoretical survey. The research method adopted for analyzing and discussion includes three phases: The identification of the types of risks proposed in each one of the thirty models, the grouping of them considering equivalent concepts associated to their definitions, and, the analysis of these risks groups, evaluating their similarities and differences. After these analyses, it was possible to conclude that, in fact, there is more than thirty risks types identified in the literature of Supply Chains, but some of them are identical despite of be used distinct terms to characterize them, because different criteria for risk classification are adopted by researchers. In short, it is observed that some types of risks are identified as risk source for supply chains, such as, demand risk, environmental risk and safety risk. On the other hand, other types of risks are identified by the consequences that they can generate for the supply chains, such as, the reputation risk, the asset depreciation risk and the competitive risk. These results are consequence of the disagreements between researchers on risk classification, mainly about what is risk event and about what is the consequence of risk occurrence. An additional study is in developing in order to clarify how the risks can be generated, and which are the characteristics of the components in a Supply Chain that leads to occurrence of risk.

Keywords: sisks classification, survey, supply chain management, theoretical discussion

Procedia PDF Downloads 632