Search

The confluence of high performance computing algorithms and large scale high-quality data has led to the availability of cutting edge tools in computational linguistics. However, these state-of-the-art tools are available only for the major languages of the world. The preparation of large scale high-quality corpora for low-resource language such as Urdu is a challenging task as it requires huge computational and human resources. In this paper, we build and analyze a large scale Urdu language Twitter corpus Anbar. For this purpose, we collect 106.9 million Urdu tweets posted by 1.69 million users during one year (September 2018-August 2019). Our corpus consists of tweets with a rich vocabulary of 3.8 million unique tokens along with 58K hashtags and 62K URLs. Moreover, it contains 75.9 million (71.0%) retweets and 847K geotagged tweets. Furthermore, we examine Anbar using a variety of metrics like temporal frequency of tweets, vocabulary size, geo-location, user characteristics, and entities distribution. To the best of our knowledge, this is the largest repository of Urdu language tweets for the NLP research community which can be used for Natural Language Understanding (NLU), social analytics, and fake news detection. [ABSTRACT FROM AUTHOR]

The aim of this article is to contextualize and describe the gathering and annotation of a conventual Hispanic and Novo Hispanic texts corpus for emotions identification. Such corpus will be the dataset for an emotions identification model based on machine learning ∖ deep learning techniques. Furthermore, this document describes several exploratory experiments carried out on the corpus. Within these experiments, it is described how the corpus is also used to obtain a lexicon mapped to polarities and emotions, and how some of the documents are hand-labeled by experts for the evaluation of the Machine Learning ∖ Deep learning -based emotion classification model. Finally, the future uses and experiments with said corpus are described. [ABSTRACT FROM AUTHOR]

The rise of digital communication systems provides an almost infinite source of information that can be useful to feed classification algorithms, so it makes use of an already categorized collection of opinions of the social network Twitter for the formation and generation of a model of classification of short texts; which aims to categorize the emotional tone found in an author's Spanish-language digital text. In addition, linguistic, lexicographic and opinion mining computational tools are used to implement a series of methods that allow to automatically finding coincidences or orientations that allow determining the polarity of sentences and categorize them as positive, negative or neutral considering their lemmas. The results obtained from the analysis of emotions and polarity of this project, on the test phrases allow to observe a direct relationship between the categorized emotional tone and it is positive, negative or neutral classification, which allows to provide additional information to know the intention that the author had when he created the sentence. Determining these characteristics can be useful as a consistent information objective that can be leveraged by sectors where the prevalence of a product or service depends on user opinion, product rating or turns with satisfaction metrics. [ABSTRACT FROM AUTHOR]

On YouTube, billions of videos are watched online and millions of short messages are posted each day. YouTube along with other social networking sites are used by individuals and extremist groups for spreading hatred among users. In this paper, we consider religion as the most targeted domain for spreading hate speech among people of different religions. We present a methodology for the detection of religion-based hate videos on YouTube. Messages posted on YouTube videos generally express the opinions of users' related to that video. We provide a novel dataset for religious hate speech detection on Youtube comments. The proposed methodology applies data mining techniques on extracted comments from religious videos in order to filter religion-oriented messages and detect those videos which are used for spreading hate. The supervised learning algorithms: Support Vector Machine (SVM), Logistic Regression (LR), and k-Nearest Neighbor (k-NN) are used for baseline results. [ABSTRACT FROM AUTHOR]

Language translation is essential to bring the world closer and plays a significant part in building a community among people of different linguistic backgrounds. Machine translation dramatically helps in removing the language barrier and allows easier communication among linguistically diverse communities. Due to the unavailability of resources, major languages of the world are accounted as low-resource languages. This leads to a challenging task of automating translation among various such languages to benefit indigenous speakers. This article investigates neural machine translation for the English–Assamese resource-poor language pair by tackling insufficient data and out-of-vocabulary problems. We have also proposed an approach of data augmentation-based NMT, which exploits synthetic parallel data and shows significantly improved translation accuracy for English-to-Assamese and Assamese-to-English translation and obtained state-of-the-art results. [ABSTRACT FROM AUTHOR]

Frequent pattern mining (FIM) identifies the most important patterns in data sets. However, due to the huge and high-dimensional nature of transactional data, classical pattern mining techniques suffer from the limitations of dimensions and data annotations. Recently, data mining while preserving privacy is considered as an important research area. Information privacy is a tradeoff that must be considered when using data. Through many years, privacy-preserving data mining (PPDM) made use of methods that are mostly based on heuristics. The operation of deletion was used to hide the sensitive information in PPDM. In this study, we used deep active learning to protect private and sensitive information. This paper combines entropy-based active learning with an attention-based approach to effectively hide sensitive patterns. The constructed models are then validated using high-dimensional transactional data with attention-based and active learning methods in a reinforcement environment. The results show that the proposed model can support and improve the effectiveness of decision-making by increasing the number of training instances through the use of a pooling technique and an entropy uncertainty measure. The proposed paradigm can achieve data sanitization by the hiding sensitive items and avoiding to hide the non-sensitive items. The model outperforms greedy, genetic, and particle swarm optimization approaches. [ABSTRACT FROM AUTHOR]

Neurodegenerative diseases affect a large part of the population in the world and also in Mexico, deteriorating gradually the quality of patients' life. Therefore, it is important to diagnose them with a high degree of reliability. In order to solve it, various computational methods have been applied in the analysis of biomarkers of human gait. In this study, we propose employing the automatic model selection and hyperparameter optimization method that has not been addressed before for this problem. Our results showed highly competitive percentages of correctly classified instances when discriminating binary and multiclass sets of neurodegenerative diseases: Parkinson's disease, Huntington's disease, and Spinocerebellar ataxias. [ABSTRACT FROM AUTHOR]

We present a novel algorithm based on combinatorial operations on lists for computing the number of models on two conjunctive normal form Boolean formulas whose restricted graph is represented by a grid graph Gm,n. We show that our algorithm is correct and its time complexity is O (t · 1. 618 t + 2 + t · 1. 618 2 t + 4) , where t = n · m is the total number of vertices in the graph. For this class of formulas, we show that our proposal improves the asymptotic behavior of the time-complexity with respect of the current leader algorithm for counting models on two conjunctive form formulas of this kind. [ABSTRACT FROM AUTHOR]

Artificial music tutors are needed for assisting a performer during his/her practice time whenever a human tutor is not available. But for these artificial tutors to be intelligent and fulfill the role of a music tutor, they have to be able to identify errors made by the performer while playing a musical sequence. This task is not a trivial one, since all musical activities are considered as open-ended domains. Therefore, not only there is no unique correct way of performing a musical sequence, but also the analysis made by the tutor has to consider the development level of the performer, the difficulty level of the performed musical sequence, and many other variables. This paper describes an ongoing research that uses cascading connected layers of symbolic processing as the core of a human-performed error identification and characterization module able to overcome the complexity of the studied open-ended domain. [ABSTRACT FROM AUTHOR]

A current challenge for autonomous vehicles is the detection of irregularities on road surfaces in order to prevent accidents; in particular, speed bump detection is an important task for safe and comfortable autonomous navigation. There are some techniques that have achieved acceptable speed bump detection under optimal road surface conditions, especially when signs are well-marked. However, in developing countries it is very common to find unmarked speed bumps and existing techniques fail. In this paper a methodology to detect both marked and unmarked speed bumps is proposed, for clearly painted speed bumps we apply local binary patterns technique to extract features from an image dataset. For unmarked speed bump detection, we apply stereo vision where point clouds obtained by the 3D reconstruction are converted to triangular meshes by applying Delaunay triangulation. A selection and extraction of the most relevant features is made to speed bump elevation on surfaces meshes. Results obtained have an important contribution and improve some of the existing techniques since the reconstruction of three-dimensional meshes provides relevant information for the detection of speed bumps by elevations on surfaces even though they are not marked. [ABSTRACT FROM AUTHOR]

This paper presents the technical proposal of a novel approach based on Ant Colony Optimization (ACO) to recommend personalized microlearning paths considering the learning needs of the learner. In this study, the information of the learner was considered from a disciplinary ICT perspective, since the characteristics of our learner correspond to those of a professor with variable characteristics, such as the level of knowledge and their learning status. The recommendation problem is approached as an instance of the Traveling Salesman Problem (TSP), the educational pills represent the cities, the paths are the relationships between educational pills, the cost of going from one pill to another can be estimated by their degree of difficulty as well as the performance of the learner during the individual test. The results prove the approach proposal capacity to suggest microlearning path personalized recommendation according to the different levels of knowledge of the learners. The higher the number of learners, the behavior of the algorithm benefits in terms of stability. [ABSTRACT FROM AUTHOR]

In the last few years, text analysis has grown as a keystone in several domains for solving many real-world problems, such as machine translation, spam detection, and question answering, to mention a few. Many of these tasks can be approached by means of machine learning algorithms. Most of these algorithms take as input a transformation of the text in the form of feature vectors containing an abstraction of the content. Most of recent vector representations focus on the semantic component of text, however, we consider that also taking into account the lexical and syntactic components the abstraction of content could be beneficial for learning tasks. In this work, we propose a content spectral-based text representation applicable to machine learning algorithms for text analysis. This representation integrates the spectra from the lexical, syntactic, and semantic components of text producing an abstract image, which can also be treated by both, text and image learning algorithms. These components came from feature vectors of text. For demonstrating the goodness of our proposal, this was tested on text classification and complexity reading score prediction tasks obtaining promising results. [ABSTRACT FROM AUTHOR]

Breast cancer is a very important health concern around the world. Early detection of such a disease increases the chances of survival. Among the available screening tools, there is the Electro-Impedance Mammography (EIM), which is a novel and less invasive method that captures the potential difference stored in breast tissues under the assumption that electrical properties among normal and pathologically altered tissues are different. In this paper, we address breast cancer detection as a multi-class problem aiming to determine the corresponding label in terms of the Breast Imaging Electrical Impedance classification system, the standard used by physicians for interpreting an EIM mammogram. For experimental purposes, for the first time in the literature, we took advantage of a dataset comprising EIM of Mexican patients. Aiming to establish a baseline for this task, traditional supervised learning methods were used together with two different feature extraction techniques: raw pixel data and transfer learning. Besides, data augmentation was exploited for compensating data imbalance. Different experimental settings were evaluated reaching classification rates over 0.85 in F-score. KNN emerges as a very promising classifier for addressing this task. The obtained results allow us to validate the usefulness of traditional methods for classifying electro-impedance mammograms. [ABSTRACT FROM AUTHOR]

Probabilistic approaches are frequently used to describe irregular activity data to assist the design and development of devices. Unfortunately, useful estimations are not always feasible due to the large noise in the data modeled, as it occurs when estimating the sea waves potential for electricity generation. In this work we propose a simple methodology based on the use of joint probability models that allow discriminating extreme values, collected from measurements as pairs of independent points, while allowing the preservation of the essential statistics of the measurements. The outcome of the proposed methodology is an equivalent data series where large-amplitude fluctuations are suppressed and, therefore, can be used for design purposes. For the evaluation of the proposed method, we used year-long databases of hourly-collected measurements of the wave's height and period, performed at maritime buoys located in the Gulf of Mexico. These measurements are used to obtain a fluctuations-reduced representation of the energy potential of the waves that can be useful, for instance, for the design of electric generators. [ABSTRACT FROM AUTHOR]

The cornerstone to achieve the development of autonomous ground driving with the lowest possible risk of collision in real traffic environments is the movement estimation obstacle. Predicting trajectories of multiple obstacles in dynamic traffic scenarios is a major challenge, especially when different types of obstacles such as vehicles and pedestrians are involved. According to the issues mentioned, in this work a novel method based on Bayesian dynamic networks is proposed to infer the paths of interest objects (IO). Environmental information is obtained through stereo video, the direction vectors of multiple obstacles are computed and the trajectories with the highest probability of occurrence and the possibility of collision are highlighted. The proposed approach was evaluated using test environments considering different road layouts and multiple obstacles in real-world traffic scenarios. A comparison of the results obtained against the ground truth of the paths taken by each detected IO is performed. According to experimental results, the proposed method obtains a prediction rate of 75% for the change of direction taking into consideration the risk of collision. The importance of the proposal is that it does not obviate the risk of collision in contrast with related work. [ABSTRACT FROM AUTHOR]

The present paper proposes a fuzzy inference system for query-focused multi-document text summarization (MTS). The overall scheme is based on Mamdani Inferencing scheme which helps in designing Fuzzy Rule base for inferencing about the decision variable from a set of antecedent variables. The antecedent variables chosen for the task are from linguistic and positional heuristics, and similarity of the documents with the user-defined query. The decision variable is the rank of the sentences as decided by the rules. The final summary is generated by solving an Integer Linear Programming problem. For abstraction coreference resolution is applied on the input sentences in the pre-processing step. Although designed on the basis of a small set of antecedent variables the results are very promising. [ABSTRACT FROM AUTHOR]

In the medical area, the detection of invasive ductal carcinoma is the most common sub-type of all breast cancers; about 80% of all breast cancers are invasive ductal carcinomas. Detection of this type of cancer shows a great challenge for specialist doctors since the digital images of the sample must be analyzed by sections because the spatial dimensions of this kind of image are above 50k × 50k pixels; doing this operation manually takes long time to determine if the patient suffers this type of cancer. Time is essential for the patient because this cancer can invade quickly other parts of the body. Its name reaffirms this characteristic, with the term "invasive" forming part of its name. With the purpose of solving this task, we propose an automatic methodology consisting in improving the performance of a convolutional neural network that classifies images containing invasive ductal carcinoma cells by highlighting cancer cells using several preprocessing methods such as histogram stretching and contrast enhancement. In this way, characteristics of the sub-images are extracted from the panoramic sample and it is possible to learn to classify them in a better way. [ABSTRACT FROM AUTHOR]

The traditional end-to-end Neural Question Generation (NQG) models tend to generate generic and bland questions, as there are two obscure points: 1) the modifications of the answer in the context can be used as the clues to the answer mentioned in the question, while they are generally not unique and can be used independently for generating diverse questions; 2) the same question content can also be asked in diverse ways, which depends on personal preference in practice. The above-mentioned two points are indeed two variables to conduct question generation, but they are not annotated in the original dataset and are thus ignored by the traditional end-to-end models. In this paper we propose a framework that clarifies those two points through two sub-modules to better conduct question generation. We take experiments based on the GPT-2 model and the SQuAD dataset, and prove that our framework can improve the performance measured by similarity metrics, while it also provides appropriate alternatives for controllable diversity enhancement. [ABSTRACT FROM AUTHOR]

The paper presents a classifier for fake news spreaders detection in social media. Detecting fake news spreaders is an important task because this kind of disinformation aims to change the reader's opinion about a relevant topic for the society. This work presents a classifier that can compete with the ones that are found in the state-of-the-art. In addition, this work applies Explainable Artificial Intelligence (XIA) methods in order to understand the corpora used and how the model estimates results. The work focuses on the corpora developed by members of the PAN@CLEF 2020 competition. The score obtained surpasses the state-of-the-art with a mean accuracy score of 0.7825. The solution uses XIA methods for the feature selection process, since they present more stability to the selection than most of traditional feature selection methods. Also, this work concludes that the detection done by the solution approach is generally based on the topic of the text. [ABSTRACT FROM AUTHOR]

This paper presents a novel methodology to identify the dynamic parameters of a real robot with a convolutional neural network (CNN). Conventional identification methodologies use continuous motion signals. However, these signals are quantized in their amplitude and are discrete in time. Therefore, the time required to identify the parameters of a robot with a limited measurement system is related to an optimized motion trajectory performed by the robot. The proposed methodology consists of an algorithm that uses a trained CNN with the data created by the dynamical model of the case study robot. A processing technique is proposed to transform the position, velocity, acceleration, and torque robot signals into an image whose characteristics are extracted by the CNN to determine their dynamic parameters. The proposed algorithm does not require any optimal trajectory to find the dynamic parameters. A proposed time-spectral evaluation metric is used to validate the robot data and the identification data. The validation results show that the proposed methodology identifies the parameters of a Cartesian robot in less than 1 second, exceeding 90% of the proposed evaluation metric and 98% for the simulation results. [ABSTRACT FROM AUTHOR]

Covid-19 braces serious mental health crisis across the world. Since a vast majority of the population exploit social media platforms such as twitter to exchange information, rapid collecting and analyzing social media data to understand personal well-being and subsequently adopting adequate measures could avoid severe socio-economic damage. Sentiment analysis on twitter data is very useful to understand and identify the mental health issues. In this research, we proposed a unified deep neuro-fuzzy approach for Covid-19 twitter sentiment classification. Fuzzy logic has been a very powerful tool for twitter data analysis where approximate semantic and syntactic analysis is more relevant because correcting spelling and grammar in tweets are merely obnoxious. We conducted the experiment on three challenging COVID-19 twitter sentiment datasets. Experimental results demonstrate that fuzzy Sugeno integral based ensembled classifiers succeed over individual base classifiers. [ABSTRACT FROM AUTHOR]

Distant Supervision is an approach that allows automatic labeling of instances. This approach has been used in Relation Extraction. Still, the main challenge of this task is handling instances with noisy labels (e.g., when two entities in a sentence are automatically labeled with an invalid relation). The approaches reported in the literature addressed this problem by employing noise-tolerant classifiers. However, if a noise reduction stage is introduced before the classification step, this increases the macro precision values. This paper proposes an Adversarial Autoencoders-based approach for obtaining a new representation that allows noise reduction in Distant Supervision. The representation obtained using Adversarial Autoencoders minimize the intra-cluster distance concerning pre-trained embeddings and classic Autoencoders. Experiments demonstrated that in the noise-reduced datasets, the macro precision values obtained over the original dataset are similar using fewer instances considering the same classifier. For example, in one of the noise-reduced datasets, the macro precision was improved approximately 2.32% using 77% of the original instances. This suggests the validity of using Adversarial Autoencoders to obtain well-suited representations for noise reduction. Also, the proposed approach maintains the macro precision values concerning the original dataset and reduces the total instances needed for classification. [ABSTRACT FROM AUTHOR]

The general population increasingly uses digital services, meaning services which are delivered over the internet or an electronic network, and events such as pandemics have accelerated the need of using new digital services. Governments have also increased their number of digital services, however, these digital services still lack of sufficient information security, particularly integrity. Blockchain uses cryptographic techniques that allow decentralization and increase the integrity of the information it handles, but it still has disadvantages in terms of efficiency, making it incapable of implementing some digital services where a high rate of transactions are required. In order to increase its efficient, a multi-layer proposal based on blockchain is presented. It has four layers, where each layer specializes in a different type of information and uses properties of public blockchain and private blockchain. An statistical analysis is performed and the proposal is modeled showing that it maintains and even increases the integrity of the information while preserving the efficiency of transactions. Besides, the proposal can be flexible and adapt to different types of digital services. It also considers that voluntary nodes participate in the decentralization of information making it more secure, verifiable, transparent and reliable. [ABSTRACT FROM AUTHOR]