Cristiane Neri Nobre

Applying Artificial Neural Networks to prediction of stock price and improvement of the directional prediction index – Case study of PETR4, Petrobras, Brazil

Abstract Predicting the direction of stock price changes is an important factor, as it contributes to the development of effective strategies for stock exchange transactions and attracts much interest in incorporating variables historical series into the mathematical models or computer algorithms in order to produce estimations of expected price fluctuations. The purpose of this study is to build a neural model for the financial market, allowing predictions of stocks closing prices future behavior negotiated in BM&FBOVESPA in the short term, using the economic and financial theory, combining technical analysis, fundamental analysis and analysis of time series, to predict price behavior, addressing the percentage of correct predictions of price series direction (POCID or Prediction of Change in Direction). The aim of this work is to understand the information available in the financial market and identify the variables that drive stock prices. The methodology presented may be adapted to other companies and their stock. Petrobras stock PETR4, traded in BM&FBOVESPA, was used as a case study. As part of this effort, configurations with different window sizes were designed, and the best performance was achieved with a window size of 3, which the POCID index of correct direction predictions was 93.62% for the test set and 87.50% for a validation set.

Parallel and distributed kmeans to identify the translation initiation site of proteins

Prediction of the translation initiation site is of vital importance in bioinformatics since through this process it is possible to understand the organic formation and metabolic behavior of living organisms. Sequential algorithms are not always a viable solution due to the fact that mRNA databases are normally very large, resulting in long processing times. Applying parallel and distributed computing resources to such databases could help reduce this time. The objective of this article is to present a class balancing solution for the translation initiation site process using parallel and distributed computing resources in a hybrid model. The results reveal a speedup of up to 23 times compared to sequential methods and performance rates for accuracy, precision, sensitivity, specificity and adjusted accuracy of 91.15%, 39.83%, 89.11%, 88.93% and 89.02%, respectively, for the Homo sapiens database. For the Drosophila melanogaster database, the speedup was 18.33 times and accuracy, precision, sensitivity, specificity and adjusted accuracy were 95.22%, 43.01%, 90.83%, 90.47% and 90.64%, respectively. Both sets of results are considered important. Thus, the solution presented in this article demonstrated itself viable for the problem in question.

The usage of Artificial Neural Networks in the classification and forecast of potable water consumption

This study aimed at identifying the main factors that influence potable water consumption. It was used a neural representation structure to model its consumption, applying geographic and socio-economic variables, as well as Trepan (TREes Parroting Networks), a special tool to to obtain knowledge from trained Artificial Neural Networks. The model was applied to a database of the State of Paraná - Brazil.

A revision and analysis of the comprehensiveness of the main longitudinal studies of human aging for data mining research

Human aging is a global problem that will have a large socioeconomic impact. A better understanding of aging can direct public policies that minimize its negative effects in the future. Over many years, several longitudinal studies of human aging have been conducted aiming to comprehend the phenomenon, and various factors influencing human aging are under analysis. In this review, we categorize the main aspects affecting human aging into a taxonomy for assisting data mining (DM) research on this topic. We also present tables summarizing the main characteristics of 64 research articles using data from aging‐related longitudinal studies, in terms of the aging‐related aspects analyzed, the main data analysis techniques used, and the specific longitudinal database mined in each article. Finally, we analyze the comprehensiveness of the main databases of longitudinal studies of human aging worldwide, regarding which proportion of the proposed taxonomys aspects are covered by each longitudinal database. We observed that most articles analyzing such data use classical (parametric, linear) statistical techniques, with little use of more modern (nonparametric, nonlinear) DM methods for analyzing longitudinal databases of human aging. We hope that this article will contribute to DM research in two ways: first, by drawing attention to the important problem of global aging and the free availability of several longitudinal databases of human aging; second, by providing useful information to make research design choices about mining such data, e.g., which longitudinal study and which types of aging‐related aspects should be analyzed, depending on the researchs goals. WIREs Data Mining Knowl Discov 2017, 7:e1202. doi: 10.1002/widm.1202

Transductive learning as an alternative to translation initiation site identification

BackgroundThe correct protein coding region identification is an important and latent problem in the molecular biology field. This problem becomes a challenge due to the lack of deep knowledge about the biological systems and unfamiliarity of conservative characteristics in the messenger RNA (mRNA). Therefore, it is fundamental to research for computational methods aiming to help the patterns discovery for identification of the Translation Initiation Sites (TIS). In the field of Bioinformatics, machine learning methods have been widely applied based on the inductive inference, as Inductive Support Vector Machine (ISVM). On the other hand, not so much attention has been given to transductive inference-based machine learning methods such as Transductive Support Vector Machine (TSVM). The transductive inference performs well for problems in which the amount of unlabeled sequences is considerably greater than the labeled ones. Similarly, the problem of predicting the TIS may take advantage of transductive methods due to the fact that the amount of new sequences grows rapidly with the progress of Genome Project that allows the study of new organisms. Consequently, this work aims to investigate the transductive learning towards TIS identification and compare the results with those obtained in inductive method.ResultsThe transductive inference presents better results both in F-measure and in sensitivity in comparison with the inductive method for predicting the TIS. Additionally, it presents the least failure rate for identifying the TIS, presenting a smaller number of False Negatives (FN) than the ISVM. The ISVM and TSVM methods were validated with the molecules from the most representative organisms contained in the RefSeq database: Rattus norvegicus, Mus musculus, Homo sapiens, Drosophila melanogaster and Arabidopsis thaliana. The transductive method presented F-measure and sensitivity higher than 90% and also higher than the results obtained with ISVM. The ISVM and TSVM approaches were implemented in the TransduTIS tool, TransduTIS-I and TransduTIS-T respectively, available in a web interface. These approaches were compared with the TISHunter, TIS Miner, NetStart tools, presenting satisfactory results.ConclusionsIn relation to precision, the results are similar for the ISVM and TSVM classifiers. However, the results show that the application of TSVM approach ensured an improvement, specially for F-measure and sensitivity. Moreover, it was possible to identify a potential for the application of TSVM, which is for organisms in the initial study phase with few identified sequences in the databases.

A Genetic Algorithm for the Selection of Features Used in the Prediction of Protein Function

Proteins are macromolecules that have a high molecular weight, and make up, along with water, most of the composition of cells. The functions they perform are extremely important, such as the catalysis of biochemical reactions, cytoskeleton formation, and the transportation and storage of substances. With the completion of genome sequencing, protein discovery has been growing exponentially, and the laboratory methods for determining their functions have not been able to keep up with this growth. Due to this fact, it is necessary to develop methods to aid in this function discovery process. Thus, this work proposes a physical-chemical feature selection methodology calculated by means of the structures that compose the proteins. This stage has the goal of choosing a feature subset from all available features. A feature is considered relevant if it can be used by the machine to create a separation capability between the different protein classes. To select this subset, we proposed the use of a simple genetic algorithm. The results obtained with the proposed methodology were superior to those found in the literature, reaching a precision of 71% and a sensitivity of 68%.

Evaluation of inductive and transductive inference in the context of translation initiation site

The prediction of Translation Initiation Site (TIS) from a mRNA (Ribonucleic Acid Messenger) is a relevant and latent problem of molecular biology, which has benefited from the evolution of computational techniques of machine learning (ML). There are some machine learning scenarios where the dataset either does not have enough classified sequences to train a precise model, or it does not have an upstream region, such as Caenorhabditis elegans. In this article, we compare the inductive and transductive approaches for TIS prediction, using a methodology that disregards the upstream region. With the proposed methodology, we achieved 95% training accuracy, using only 2.5% of sequences belonging to the Caenorhabditis elegans class, which has many available sequences but does not have the upstream region, and 75% for the Rattus norvegicus class, which has fewer sequences available, using a transductive approach. Our results demonstrate the viability of the transductive approach for scenarios with fewer sequences, a common situation for organisms with incomplete gene sequencing.

Emotionally Oriented Analysis of the Experiences of Visually Impaired People on Facebook

With technological advancements, there has been a vast increase in the number of companies that fight over their market share. In search of a differentiating factor, companies are investing more and more in their products’ emotional designs. This researched work has evaluated the affects that are caused in visually impaired people when using Facebooks features and then compared them with the experiences of sighted users. To do that, these two types of Facebook users were subjected to a questionnaire that was based on the PANAS affect scale. Once the information was collected, statistics were employed so as to evaluate both users’ feelings. The results have shown that there were significant statistical differences between the sighted and the visually impaired users when the “affects” were evaluated by using the PANAS tool. The five “negative affects” that were selected (Irritability, Uselessness, Frustration, Sadness, and Confusion) were largely more relevant for the blind people in most of the evaluated features. This has indicated some serious accessibility problems. However, a high frequency of the five “positive affects” that were considered (Satisfaction, Pleasantness, Surprise, Excitement, Interest, and Determination) were additionally observed for both of these two groups. These results were interpreted as feelings of both social inclusion and social exclusion, indicating the possibility of exploring technological devices that were unavailable not long ago. After analyzing their experiences in their usage of the Facebook features, the findings have also highlighted the many differing emotions that are felt by the visually impaired and the sighted users. The resulting outcomes have indicated that there are some issues that are still open to problems and difficulties. Moreover, these issues involve human-computer interactions. Nevertheless, fortunately, there is light at the end of the tunnel, as will be revealed.

Extraction of Conservative Rules for Translation Initiation Site Prediction using Formal Concept Analysis.

The search for conservative features that define the translation and transcription processes used by cells to interpret and express their genetic information is one of the great challenges in the molecular biology. Each transcribed mRNA sequence has only one part translated into proteins, called Coding Sequence . The detection of this region is what motivates the search for conservative characteristics in an mRNA sequence. In eukaryotes, this region usually begins with the first occurrence of the sequence of three nucleotides, being Adenine, Uracil and Guanine, the nucleotide set that it is called Translation Initiation Site. One way to look for conservative rules that define this region is to use the formal concept analysis that can have implications that indicate a coexistence between the positions of the sequence with the presence of the translation start site. This paper analyze the use of this technique to extract conservative rules to predict the translation initiation

Persuasion strategies in mobile systems: a case study of Facebook application

The use of mobile devices has grown more and more. To retain customers and stay in the market, companies need to innovate and adapt to a new model: mobile persuasive technology. With social networks this is no different. Currently, Facebook is the most used social network. Knowing this, this work made a survey of the persuasive principles applied to computational systems, more specifically to mobile systems, since they are considered a source of influence that is with the user all the time. As a case study, the persuasive strategies adopted by Facebook in its mobile application are identified. The results of this research contribute to the design area of persuasive social networks, collaborating to the development of applications with greater probability of success.