RESUMEN

Based on the air quality data and conventional meteorological data of the Nanjing Region from January 2015 to December 2016, to analyze the characteristics of O3 concentration changes in the Nanjing Region, a light gradient boosting machine (LightGBM) model was established to predict O3 concentration. The model was compared with three machine learning methods that are commonly used in air quality prediction, including support vector machine, recurrent neural network, and random forest methods, to verify its effectiveness and feasibility. Finally, the performance of the prediction model was analyzed under different meteorological conditions. The results showed that the variation in O3 concentration in Nanjing had significant seasonal differences and was affected by a combination of its pre-concentration, meteorological factors, and other air pollutant concentrations. The LightGBM model predicted the ground-level O3 concentration in the Nanjing area more precisely to a large extent (R2=0.92), and the model outperformed other models in prediction accuracy and computational efficiency. In particular, the model showed a significantly higher prediction accuracy and stability than that of other models under a high-temperature condition that was more likely prone to ozone pollution. The LightGBM model was characterized by its high prediction accuracy, good stability, satisfactory generalization ability, and short operation time, which broaden its application prospect in O3 concentration prediction.

RESUMEN

In recent years, there has been a significant surge in discussions surrounding artificial intelligence (AI), along with a corresponding increase in its practical applications in various facets of everyday life, including the medical industry. Notably, even in the highly specialized realm of neurosurgery, AI has been utilized for differential diagnosis, pre-operative evaluation, and improving surgical precision. Many of these applications have begun to mitigate risks of intraoperative and postoperative complications and post-operative care. This article aims to present an overview of the principal published papers on the significant themes of tumor, spine, epilepsy, and vascular issues, wherein AI has been applied to assess its potential applications within neurosurgery. The method involved identifying high-cited seminal papers using PubMed and Google Scholar, conducting a comprehensive review of various study types, and summarizing machine learning applications to enhance understanding among clinicians for future utilization. Recent studies demonstrate that machine learning (ML) holds significant potential in neuro-oncological care, spine surgery, epilepsy management, and other neurosurgical applications. ML techniques have proven effective in tumor identification, surgical outcomes prediction, seizure outcome prediction, aneurysm prediction, and more, highlighting its broad impact and potential in improving patient management and outcomes in neurosurgery. This review will encompass the current state of research, as well as predictions for the future of AI within neurosurgery.

RESUMEN

Human activity recognition (HAR) is an important research problem in computer vision. This problem is widely applied to building applications in human-machine interactions, monitoring, etc. Especially, HAR based on the human skeleton creates intuitive applications. Therefore, determining the current results of these studies is very important in selecting solutions and developing commercial products. In this paper, we perform a full survey on using deep learning to recognize human activity based on three-dimensional (3D) human skeleton data as input. Our research is based on four types of deep learning networks for activity recognition based on extracted feature vectors: Recurrent Neural Network (RNN) using extracted activity sequence features; Convolutional Neural Network (CNN) uses feature vectors extracted based on the projection of the skeleton into the image space; Graph Convolution Network (GCN) uses features extracted from the skeleton graph and the temporal-spatial function of the skeleton; Hybrid Deep Neural Network (Hybrid-DNN) uses many other types of features in combination. Our survey research is fully implemented from models, databases, metrics, and results from 2019 to March 2023, and they are presented in ascending order of time. In particular, we also carried out a comparative study on HAR based on a 3D human skeleton on the KLHA3D 102 and KLYOGA3D datasets. At the same time, we performed analysis and discussed the obtained results when applying CNN-based, GCN-based, and Hybrid-DNN-based deep learning networks.

Asunto(s)

RESUMEN

There is a strong interest in the development of microsomal prostaglandin E2 synthase-1 (mPGES-1) inhibitors of their potential to safely and effectively treat inflammation. Herein, 70 QSAR models were built on the dataset (735 mPGES-1 inhibitors) characterized with RDKit descriptors by multiple linear regression (MLR), support vector machine (SVM), random forest (RF), deep neural networks (DNN), and eXtreme Gradient Boosting (XGBoost). The other three regression models on the dataset are represented by SMILES using self-attention recurrent neural networks (RNN) and Graph Convolutional Networks (GCN). For the best model (Model C2), which was developed by SVM with RDKit descriptors, the coefficient of determination (R2 ) of 0.861 and root mean squared error (RMSE) of 0.235 were achieved for the test set. Additionally, R2 of 0.692 and RMSE of 0.383 were obtained on the external test set. We investigated the applicability domain (AD) of Model C2 with the rivality index (RI), the prediction of Model C2 on 78.92% of molecules in the test set, and 78.33% of molecules in the external test set were reliable. After dissecting the RDKit descriptors of Model C2, we found important physicochemical properties of highly active mPGES-1 inhibitors. Besides, by analyzing the attention weight of each atom of each inhibitor from the attention layer, we found that the benzamide group and the trifluoromethyl cyclohexane group are favorable substructures for mPGES-1 inhibitors.

Asunto(s)

RESUMEN

Recently, interest in e-learning has increased rapidly owing to the lockdowns imposed by COVID-19. A major disadvantage of e-learning is the difficulty in maintaining concentration because of the limited interaction between teachers and students. The objective of this paper is to develop a methodology to predict e-learners' concentration by applying recurrent neural network models to eye gaze and facial landmark data extracted from e-learners' video data. One hundred eighty-four video data of ninety-two e-learners were obtained, and their frame data were extracted using the OpenFace 2.0 toolkit. Recurrent neural networks, long short-term memory, and gated recurrent units were utilized to predict the concentration of e-learners. A set of comparative experiments was conducted. As a result, gated recurrent units exhibited the best performance. The main contribution of this paper is to present a methodology to predict e-learners' concentration in a natural e-learning environment.

RESUMEN

The usage of the internet as a fast medium for spreading fake news reinforces the requirement of computational utensils in order to fight for it. Fake videos also called deep fakes that create great intimidation in society in an assortment of social and political behaviour. It can also be utilized for malevolent intentions. Owing to the availability of deep fake generation algorithms at cheap computation power in cloud platforms, realistic fake videos or images are created. However, it is more critical to detect fake content because of the increased complexity of leveraging various approaches to smudge the tampering. Therefore, this work proposes a novel framework to detect fake videos through the utilization of transfer learning in autoencoders and a hybrid model of convolutional neural networks (CNN) and Recurrent neural networks (RNN). Unseen test input data are investigated to check the generalizability of the model. Also, the effect of residual image input on accuracy of the model is analyzed. Results are presented for both, with and without transfer learning to validate the effectiveness of transfer learning.

RESUMEN

In the current pandemic situation where the coronavirus is spreading very fast that can jump from one human to another. Along with this, there are millions of viruses for example Ebola, SARS, etc. that can spread as fast as the coronavirus due to the mobilization and globalization of the population and are equally deadly. Earlier identification of these viruses can prevent the outbreaks that we are facing currently as well as can help in the earlier designing of drugs. Identification of disease at a prior stage can be achieved through DNA sequence classification as DNA carries most of the genetic information about organisms. This is the reason why the classification of DNA sequences plays an important role in computational biology. This paper has presented a solution in which samples collected from NCBI are used for the classification of DNA sequences. DNA sequence classification will in turn gives the pattern of various diseases; these patterns are then compared with the samples of a newly infected person and can help in the earlier identification of disease. However, feature extraction always remains a big issue. In this paper, a machine learning-based classifier and a new technique for extracting features from DNA sequences based on a hot vector matrix have been proposed. In the hot vector representation of the DNA sequence, each pair of the word is represented using a binary matrix which represents the position of each nucleotide in the DNA sequence. The resultant matrix is then given as an input to the traditional CNN for feature extraction. The results of the proposed method have been compared with 5 well-known classifiers namely Convolution neural network (CNN), Support Vector Machines (SVM), K-Nearest Neighbor (KNN) algorithm, Decision Trees, Recurrent Neural Networks (RNN) on several parameters including precision rate and accuracy and the result shows that the proposed method gives an accuracy of 93.9%, which is highest compared to other classifiers.

RESUMEN

Recurrent neural networks (RNNs) have been proved very successful at modeling sequential data such as language or motions. However, these successes rely on the use of the backpropagation through time (BPTT) algorithm, batch training, and the hypothesis that all the training data are available at the same time. In contrast, the field of developmental robotics aims at uncovering lifelong learning mechanisms that could allow embodied machines to learn and stabilize knowledge in continuously evolving environments. In this article, we investigate different RNN designs and learning methods, that we evaluate in a continual learning setting. The generative modeling task consists in learning to generate 20 continuous trajectories that are presented sequentially to the learning algorithms. Each method is evaluated according to the average prediction error over the 20 trajectories obtained after complete training. This study focuses on learning algorithms with low memory requirements, that do not need to store past information to update their parameters. Our experiments identify two approaches especially fit for this task: conceptors and predictive coding. We suggest combining these two mechanisms into a new proposed model that we label PC-Conceptors that outperforms the other methods presented in this study.

RESUMEN

Time series forecasting of uni-variant rainfall data is done using a hybrid genetic algorithm integrated with optimized long-short term memory (GA-OLSTM) model. The parameters included for the valuation of the efficiency of the considered model, were mean square error (MSE), root mean square error (RMSE), cosine similarity (CS) and correlation coefficient (r). With various epochs like 5, 10, 15 and 20, the optimal window size and the number of units were observed using the GA search algorithm which was found to be (49, 9), (12, 8), (40, 8), and (36, 2) respectively. The computed MSE, RMSE, CS and r for 10 epochs were found to be 0.006, 0.078, 0.910 and 0.858 respectively for the LSTM model, whereas the same parameters were computed using the Hybrid GA-OLSTM model was 0.004, 0.063, 0.947 and 0.917 respectively. The experimental results expressed that the Hybrid GA-OLSTM model gave significantly better results comparing the LSTM model for 10 epochs has been discussed in this research article.

RESUMEN

The coronavirus disease that outbreak in 2019 has caused various health issues. According to the WHO, the first positive case was detected in Bangladesh on 7th March 2020, but while writing this paper in June 2021, the total confirmed, recovered, and death cases were 826922, 766266 and 13118, respectively. Due to the emergence of COVID-19 in Bangladesh, the country is facing a major public health crisis. Unfortunately, the country does not have a comprehensive health policy to address this issue. This makes it hard to predict how the pandemic will affect the population. Machine learning techniques can help us detect the disease's spread. To predict the trend, parameters, risks, and to take preventive measure in Bangladesh; this work utilized the Recurrent Neural Networks based Deep Learning methodologies like LongShort-Term Memory. Here, we aim to predict the epidemic's progression for a period of more than a year under various scenarios in Bangladesh. We extracted the data for daily confirmed, recovered, and death cases from March 2020 to August 2021. The obtained Root Mean Square Error (RMSE) values of confirmed, recovered, and death cases indicates that our result is more accurate than other contemporary techniques. This study indicates that the LSTM model could be used effectively in predicting contagious diseases. The obtained results could help in explaining the seriousness of the situation, also mayhelp the authorities to take precautionary steps to control the situation.

RESUMEN

The enrichment of polyhydroxyalkanoates (PHA) accumulating bacteria (PAB) in mixed microbial cultures (MMC) is extremely difficult to be predicted and optimized. Here we demonstrate that mechanistic and deep learning models can be integrated innovatively to accurately predict the dynamic enrichment of PAB. Well-calibrated activated sludge models (ASM) of the PAB enrichment process provide time-dependent data under different operating conditions. Recurrent neural network (RNN) models are trained and tested based on the time-dependent dataset generated by ASM. The accurate prediction performance is achieved (R2 > 0.991) for three different PAB enrichment datasets by the optimized RNN model. The optimized RNN model can also predict the equilibrium concentration of PAB (R2 = 0.944) and corresponding time, which represents the end of the PAB enrichment process. This study demonstrates the strength of integrating mechanistic and deep learning models to predict long-term variations of specific microbes, helping to optimize their selection process for PHA production.

Asunto(s)

RESUMEN

The rapid development of computational methods and the increasing volume of chemical and biological data have contributed to an immense growth in chemical research. This field of study is known as "chemoinformatics," which is a discipline that uses machine-learning techniques to extract, process, and extrapolate data from chemical structures. One of the significant lines of research in chemoinformatics is the study of blood-brain barrier (BBB) permeability, which aims to identify drug penetration into the central nervous system (CNS). In this research, we attempt to solve the problem of BBB permeability by predicting compounds penetration to the CNS. To accomplish this goal: (i) First, an overview is provided to the field of chemoinformatics, its definition, applications, and challenges, (ii) Second, a broad view is taken to investigate previous machine-learning and deep-learning computational models to solve BBB permeability. Based on the analysis of previous models, three main challenges that collectively affect the classifier performance are identified, which we define as "the triple constraints"; subsequently, we map each constraint to a proposed solution, (iii) Finally, we conclude this endeavor by proposing a deep learning based Recurrent Neural Network model, to predict BBB permeability (RNN-BBB model). Our model outperformed other studies from the literature by scoring an overall accuracy of 96.53%, and a specificity score of 98.08%. The obtained results confirm that addressing the triple constraints substantially improves the classification model capability specifically when predicting compounds with low penetration.

Asunto(s)

RESUMEN

Retrieval of unintelligible speech is a basic need for speech impaired and is under research for several decades. But retrieval of random words from thoughts needs a substantial and consistent approach. This work focuses on the preliminary steps of retrieving vowels from Electroencephalography (EEG) signals acquired while speaking and imagining of speaking a consonant-vowel-consonant (CVC) word. The process, referred to as Speech imagery is imagining of speaking to oneself silently in the mind. Speech imagery is a form of mental imagery. Brain connectivity estimators such as EEG coherence, Partial Directed Coherence, Directed Transfer Function and Transfer Entropy have been used to estimate the concurrency and causal dependence (direction and strength) between different brain regions. From brain connectivity results it has been observed that the left frontal and left temporal electrodes were activated for speech and speech imagery processes. These brain connectivity estimators have been used for training Recurrent Neural Networks (RNN) and Deep Belief Networks (DBN) for identifying the vowel from the subject's thought. Though the accuracy level was found to be varying for each vowel while speaking and imagining of speaking the CVC word, the overall classification accuracy was found to be 72% while using RNN whereas a classification accuracy of 80% was observed while using DBN. DBN was found to outperform RNN in both the speech and speech imagery processes. Thus, the combination of brain connectivity estimators and deep learning techniques appear to be effective in identifying the vowel from EEG signals of subjects' thought.

RESUMEN

Technological advances have lead to the creation of large epigenetic datasets, including information about DNA binding proteins and DNA spatial structure. Hi-C experiments have revealed that chromosomes are subdivided into sets of self-interacting domains called Topologically Associating Domains (TADs). TADs are involved in the regulation of gene expression activity, but the mechanisms of their formation are not yet fully understood. Here, we focus on machine learning methods to characterize DNA folding patterns in Drosophila based on chromatin marks across three cell lines. We present linear regression models with four types of regularization, gradient boosting, and recurrent neural networks (RNN) as tools to study chromatin folding characteristics associated with TADs given epigenetic chromatin immunoprecipitation data. The bidirectional long short-term memory RNN architecture produced the best prediction scores and identified biologically relevant features. Distribution of protein Chriz (Chromator) and histone modification H3K4me3 were selected as the most informative features for the prediction of TADs characteristics. This approach may be adapted to any similar biological dataset of chromatin features across various cell lines and species. The code for the implemented pipeline, Hi-ChiP-ML, is publicly available: https://github.com/MichalRozenwald/Hi-ChIP-ML.

RESUMEN

Infantile onset Pompe disease (IOPD) is a rare and lethal genetic disorder caused by the deletion of the acid alpha-glucosidase (GAA) gene. This gene encodes an essential lysosomal enzyme that converts glycogen to glucose. While enzyme replacement therapy helps some, our understanding of disease pathophysiology is limited. In this project we develop computer simulated stem cells (aiPSC) and differentiated skeletal muscle cells (aiSkMC) to empower IOPD research and drug discovery. Our Artificial Intelligence (AI) platform, DeepNEU v3.6 was used to generate aiPSC and aiSkMC simulations with and without GAA expression. These simulations were validated using peer reviewed results from the recent literature. Once the aiSkMC simulations (IOPD and WT) were validated they were used to evaluate calcium homeostasis and mitochondrial function in IOPD. Lastly, we used aiSkMC IOPD simulations to identify known and novel biomarkers and potential therapeutic targets. The aiSkMC simulations of IOPD correctly predicted genotypic and phenotypic features that were reported in recent literature. The probability that these features were accurately predicted by chance alone using the binomial test is 0.0025. The aiSkMC IOPD simulation correctly identified L-type calcium channels (VDCC) as a biomarker and confirmed the positive effects of calcium channel blockade (CCB) on calcium homeostasis and mitochondrial function. These published data were extended by the aiSkMC simulations to identify calpain(s) as a novel potential biomarker and therapeutic target for IOPD. This is the first time that computer simulations of iPSC and differentiated skeletal muscle cells have been used to study IOPD. The simulations are robust and accurate based on available published literature. We also demonstrated that the IOPD simulations can be used for potential biomarker identification leading to targeted drug discovery. We will continue to explore the potential for calpain inhibitors with and without CCB as effective therapy for IOPD.

RESUMEN

Attention deficit and hyperactivity disorder (ADHD) is a neurodevelopmental condition that affects, among other things, the movement patterns of children suffering it. Inattention, hyperactivity and impulsive behaviors, major symptoms characterizing ADHD, result not only in differences in the activity levels but also in the activity patterns themselves. This paper proposes and trains a Recurrent Neural Network (RNN) to characterize the moment patterns for normally developing children and uses the trained RNN in order to assess differences in the movement patterns from children with ADHD. Each child is monitored for 24 consecutive hours, in a normal school day, wearing 4 tri-axial accelerometers (one at each wrist and ankle). The results for both medicated and non-medicated children with ADHD, and for different activity levels are presented. While the movement patterns for non-medicated ADHD diagnosed participants showed higher differences as compared to those of normally developing participants, those differences were only statistically significant for medium intensity movements. On the other hand, the medicated ADHD participants showed statistically different behavior for low intensity movements.

Asunto(s)