Search

Background/Aims: The purpose of the current study was to examine the anti-inflammatory effects of CKD-506, a novel histone deacetylase 6 inhibitor, on human peripheral blood mononuclear cells (PBMCs) and CD4+ T cells and to explore the relationship between CKD-506 and gut epithelial barrier function. Methods: Lipopolysaccharide-stimulated human PBMCs from inflammatory bowel disease (IBD) patients were treated with CKD-506, and tumor necrosis factor (TNF)-α expression was measured using an enzyme-linked immunosorbent assay. The proliferation of CD4+ T cells from IBD patients was evaluated using flow cytometric analysis. The effects of CKD-506 on gut barrier function in a cell line and colon organoids, based on examinations of mRNA production, goblet cell differentiation, and E-cadherin recovery, were investigated using quantitative reverse transcription polymerase chain reaction, immunofluorescence, and a fluorescein isothiocyanate-dextran permeability assay. Results: Secretion of TNF-α, a pivotal pro-inflammatory mediator in IBD, by lipopolysaccharide-triggered PBMCs was markedly decreased by CKD-506 treatment in a dose-dependent manner and to a greater extent than by tofacitinib or tubastatin A treatment. E-cadherin mRNA expression and goblet cell differentiation increased significantly and dose-dependently in HT-29 cells in response to CKD-506, and inhibition of E-cadherin loss after TNF-α stimulation was significantly reduced both in HT-29 cells and gut organoids. Caco-2 cells treated with CKD-506 showed a significant reduction in barrier permeability in a dose-dependent manner. Conclusions: The present study demonstrated that CKD-506 has anti-inflammatory effects on PBMCs and CD4 T cells and improves gut barrier function, suggesting its potential as a small-molecule therapeutic option for IBD.

Video action recognition based on skeleton nodes is a highlighted issue in the computer vision field. In real application scenarios, the large number of skeleton nodes and behavior occlusion problems between individuals seriously affect recognition speed and accuracy. Therefore, we proposed a lightweight multi-stream feature cross-fusion (L-MSFCF) model to recognize abnormal behaviors such as fighting, vicious kicking, climbing over the wall, et al., which could obviously improve recognition speed based on lightweight skeleton node calculation, and improve recognition accuracy based on occluded skeleton node prediction analysis in order to effectively solve the behavior occlusion problem. The experiments show that our proposed All-MSFCF model has a video action recognition average accuracy rate of 92.7% for eight kinds of abnormal behavior recognition. Although our proposed lightweight L-MSFCF model has an 87.3% average accuracy rate, its average recognition speed is 62.7% higher than the full-skeleton recognition model, which is more suitable for solving real-time tracing problems. Moreover, our proposed Trajectory Prediction Tracking (TPT) model could real-time predict the moving positions based on the dynamically selected core skeleton node calculation, especially for the short-term prediction within 15 frames and 30 frames that have lower average loss errors.

Any bearing faults are a leading cause of motor damage and bring economic losses. Fast and accurate identification of bearing faults is valuable for preventing damaging the whole equipment and continuously running industrial processes without interruption. Vibration signals from a running motor can be utilized to diagnose a bearing health condition. This study proposes a detection method for bearing faults based on two types of neural networks from motor vibration data. The proposed method uses an autoencoder neural network for constructing a new motor vibration feature and a feed-forward neural network for the final detection. The constructed signal feature enhances the prediction performance by focusing more on a fault type that is difficult to detect. We conducted experiments on the CWRU bearing datasets. The experimental study shows that the proposed method improves the performance of the feed-forward neural network and outperforms the other machine learning algorithms.

For the classification task, neural network-based approaches attempt to distinguish between two distributions by determining the joint distribution of input variables for each class. However, the most challenging task is still to classify the observations in the overlapping region of two classes. In this work, we propose a new discrimination neural network (DiscNN) architecture to address this issue. Our DiscNN learns to embed the initial input into more informative representations with better discriminability between the two distributions based on the cosine embedding loss. We also train our proposed model using the few-shot learning method to extract better-generalized representations from the initial input. We applied the DiscNN model to 35 tabular datasets from the OpenML-CC18 benchmark for a binary classification task. Our model showed superior performances on 28 datasets of them. In addition, we also performed experiments on 95 imbalanced datasets from the KEEL repository. The experiment results showed that the DiscNN outperformed the state-of-the-art models, including CatBoost, LightGBM, TabNet, VIME and Scarf, by around 0.23% AUC, 0.20% G-mean, and 1.06% F1 score.

The rapid development of natural language processing technology and improvements in computer performance in recent years have resulted in the wide-scale development and adoption of human–machine dialogue systems. In this study, the Icc_dialogue model is proposed to enhance the semantic awareness of moods for emotional interactive robots. Equipped with a voice interaction module, emotion calculation is conducted based on model responses, and rules for calculating users’ degree of interest are formulated. By evaluating the degree of interest, the system can determine whether it should transition to a new topic to maintain the user’s interest. This model can also address issues such as overly purposeful responses and rigid emotional expressions in generated replies. Simultaneously, this study explores topic continuation after answering a question, the construction of dialogue rounds, keyword counting, and the creation of a target text similarity matrix for each text in the dialogue dataset. The matrix is normalized, weights are assigned, and the final text score is calculated. In the text with the highest score, the content of dialogue continuation is determined by calculating a subsequent sentence with the highest similarity. This resolves the issue in which the conversational bot fails to continue dialogue on a topic after answering a question, instead waiting for the user to voluntarily provide more information, resulting in topic interruption. As described in the experimental section, both automatic and manual evaluations were conducted to validate the significant improvement in the mood semantic awareness model’s performance in terms of dialogue quality and user experience.

A variety of technologies that could enhance driving safety are being actively explored, with the aim of reducing traffic accidents by accurately recognizing the driver’s state. In this field, three mainstream detection methods have been widely applied, namely visual monitoring, physiological indicator monitoring and vehicle behavior analysis. In order to achieve more accurate driver state recognition, we adopted a multi-sensor fusion approach. We monitored driver physiological signals, electroencephalogram (EEG) signals and electrocardiogram (ECG) signals to determine fatigue state, while an in-vehicle camera observed driver behavior and provided more information for driver state assessment. In addition, an outside camera was used to monitor vehicle position to determine whether there were any driving deviations due to distraction or fatigue. After a series of experimental validations, our research results showed that our multi-sensor approach exhibited good performance for driver state recognition. This study could provide a solid foundation and development direction for future in-depth driver state recognition research, which is expected to further improve road safety.

The task of accurately identifying medical entities and extracting entity relationships from large-scale medical text data has become a hot topic in recent years, aiming to mine potential rules and knowledge. How to conduct in-depth context analysis from biomedical texts, such as medical procedures, diseases, therapeutic drugs, and disease characteristics, and identify valuable knowledge in the medical field is our main research content. Through the process of knowledge mining, a deeper understanding of the complex relationships between various factors in diseases can be gained, which holds significant guiding implications for clinical research. An approach based on context semantic analysis is proposed to realize medical entity recognition and entity relationship extraction. In addition, we build a medical knowledge base related to coronary heart disease and combine the NCBI disease dataset and the medical lexicon dataset extracted from the text as the test data of the experiment. Experimental results show that this model can effectively identify entities in medical text data; the WBC model achieved an F1 score of 89.2% in the experiment, while the CSR model achieved an F1 score of 83.4%, and the result is better than other methods.

Explaining dynamic relationships between input and output variables is one of the most important issues in time dependent domains such as economic, finance and so on. In this work, we propose a novel locally adaptive interpretable deep learning architecture that is augmented by recurrent neural networks to provide model explainability and high predictive accuracy for time-series data. The proposed model relies on two key aspects. First, the base model should be a simple interpretable model. In this step, we obtain our base model using a simple linear regression and statistical test. Second, we use recurrent neural networks to re-parameterize our base model to make the regression coefficients adaptable for each time step. Our experimental results on public benchmark datasets showed that our model not only achieves better predictive performance than the state-of-the-art baselines, but also discovers the dynamic relationship between input and output variables.

The rapid rise of non-communicable diseases (NCDs) becomes one of the serious health issues and the leading cause of death worldwide. In recent years, artificial intelligence-based systems have been developed to assist clinicians in decision-making to reduce morbidity and mortality. However, a common drawback of these modern studies is related to explanations of their output. In other words, understanding the inner logic behind the predictions is hidden to the end-user. Thus, clinicians struggle to interpret these models because of their black-box nature, and hence they are not acceptable in the medical practice. To address this problem, we have proposed a Deep Shapley Additive Explanations (DeepSHAP) based deep neural network framework equipped with a feature selection technique for NCDs prediction and explanation among the population in the United States. Our proposed framework comprises three components: First, representative features are done based on the elastic net-based embedded feature selection technique; second a deep neural network classifier is tuned with the hyper-parameters and used to train the model with the selected feature subset; third, two kinds of model explanation are provided by the DeepSHAP approach. Herein, (I) explaining the risk factors that affected the model’s prediction from the population-based perspective; (II) aiming to explain a single instance from the human-centered perspective. The experimental results indicated that the proposed model outperforms various state-of-the-art models. In addition, the proposed model can improve the medical understanding of NCDs diagnosis by providing general insights into the changes in disease risk at the global and local levels. Consequently, DeepSHAP based explainable deep learning framework contributes not only to the medical decision support systems but also can provide to real-world needs in other domains.

This study proposes an efficient prediction method for coronary heart disease risk based on two deep neural networks trained on well-ordered training datasets. Most real datasets include an irregular subset with higher variance than most data, and predictive models do not learn well from these datasets. While most existing prediction models learned from the whole or randomly sampled training datasets, our suggested method draws up training datasets by separating regular and highly biased subsets to build accurate prediction models. We use a two-step approach to prepare the training dataset: (1) divide the initial training dataset into two groups, commonly distributed and highly biased using Principal Component Analysis, (2) enrich the highly biased group by Variational Autoencoders. Then, two deep neural network classifiers learn from the isolated training groups separately. The well-organized training groups enable a chance to build more accurate prediction models. When predicting the risk of coronary heart disease from the given input, only one appropriate model is selected based on the reconstruction error on the Principal Component Analysis model. Dataset used in this study was collected from the Korean National Health and Nutritional Examination Survey. We have conducted two types of experiments on the dataset. The first one proved how Principal Component Analysis and Variational Autoencoder models of the proposed method improves the performance of a single deep neural network. The second experiment compared the proposed method with existing machine learning algorithms, including Naïve Bayes, Random Forest, K-Nearest Neighbor, Decision Tree, Support Vector Machine, and Adaptive Boosting. The experimental results show that the proposed method outperformed conventional machine learning algorithms by giving the accuracy of 0.892, specificity of 0.840, precision of 0.911, recall of 0.920, f-measure of 0.915, and AUC of 0.882.

Protein-protein interaction (PPI) prediction is meaningful work for deciphering cellular behaviors. Although many kinds of data and machine learning algorithms have been used in PPI prediction, the performance still needs to be improved. In this paper, we propose InferSentPPI, a sentence embedding based text mining method with gene ontology (GO) information for PPI prediction. First, we design a novel weighting GO term-based protein sentence representation method to generate protein sentences including multi-semantic information in the preprocessing. Gene ontology annotation (GOA) provides the reliability of relationships between proteins and GO terms for PPI prediction. Thus, GO term-based protein sentence can help to improve the prediction performance. Then we also propose an InferSent_PN algorithm based on the protein sentences and InferSent algorithm to extract relations between proteins. In the experiments, we evaluate the effectiveness of InferSentPPI with several benchmarking datasets. The result shows our proposed method has performed better than the state-of-the-art methods for a large PPI dataset.

Proper demand forecasting for postal delivery service can be used for optimal logistic management, staff scheduling and topology planning. More especially, during special holidays, such as the Lunar New Year and the Chuseok (Mid-autumn day), the demand for delivery service increases sharply in South Korea. It makes a challenge to forecast demand to provide a normal delivery schedule for the Korean mail center. To address this problem, we propose a novel deep learning model equipped with selection and update layers (MLP-SUL) to achieve high predictive performance. The proposed model consists of three main parts: the first part of the model learns to generate context-dependent weights to decide which input feed to the next layer; the second part updates the weighted input to prepare encoded input, and the third part is a prediction layer that consists of a linear layer. A linear layer takes encoded input for forecasting demand. We also introduce a special data preprocessing step for our task that requires long-term forecasting. The experimental results show that our proposed deep learning model outperforms state-of-the-art baselines on Korean mail center datasets.

Developing lifelong learning algorithms are mandatory for computational systems biology. Recently, many studies have shown how to extract biologically relevant information from high-dimensional data to understand the complexity of cancer by taking the benefit of deep learning (DL). Unfortunately, new cancer growing up into the hundred types that make systems difficult to classify them efficiently. In contrast, the current state-of-the-art continual learning (CL) methods are not designed for the dynamic characteristics of high-dimensional data. And data security and privacy are some of the main issues in the biomedical field. This article addresses three practical challenges for class-incremental learning (Class-IL) such as data privacy, high-dimensionality, and incremental learning problems. To solve this, we propose a novel continual learning approach, called Deep Generative Feature Replay (DGFR), for cancer classification tasks. DGFR consists of an incremental feature selection (IFS) and a scholar network (SN). IFS is used for selecting the most significant CpG sites from high-dimensional data. We investigate different dimensions to find an optimal number of selected CpG sites. SN employs a deep generative model for generating pseudo data without accessing past samples and a neural network classifier for predicting cancer types. We use a variational autoencoder (VAE), which has been successfully applied to this research field in previous works. All networks are sequentially trained on multiple tasks in the Class-IL setting. We evaluated the proposed method on the publicly available DNA methylation data. The experimental results show that the proposed DGFR achieves a significantly superior quality of cancer classification tasks with various state-of-the-art methods in terms of accuracy.

With the rapid increase of publishable research articles and manuscripts, the pressure to find reviewers often overwhelms the journal editors. This paper incorporates the major entity level metrics found in the heterogeneous publication networks into a pattern mining process in order to recommend academic reviewers and potential research collaborators. In essence, the paper integrates authors' h-index and papers' citation count and proposes a quantification to account for the author diversity into one formula duped impact to measure the real influence of a scientific paper. Thereafter, this paper formulates two kinds of target patterns and mines them harnessing the high-utility itemset mining (HUIM) framework. The first pattern, researcher-general topic patterns (RGP), is a pattern that includes only researchers; whereas, the researcher-specific topic patterns (RSP) is comprised of combinations of researchers and keywords that summarize their niche of expertise. The HUI algorithms of Two Phase, IHUP, UP-Growth, FHM, FHN, HUINIV-Mine, D2HUP, and EFIM were compared on two real-world citation datasets related to Deep Learning and HUIM, in addition to the open source mushroom dataset. The EFIM algorithm showed good performance in terms of run time and memory usage. Consequently, it was then used to mine the patterns within the proposed framework. The discovered patterns of RGP and RSP showed high coverage, proving the efficiency of the proposed framework.

A multivariate time series forecasting is critical in many applications, such as signal processing, finance, air quality forecasting, and pattern recognition. In particular, determining the most relevant variables and proper lag length from multivariate time series is challenging. This paper proposes an end-to-end recurrent neural network framework equipped with an adaptive input selection mechanism to improve the prediction performance for multivariate time series forecasting. The proposed model, named AIS-RNN, consists of two main components: the first neural network learns to generate context-dependent importance weights to dynamically select the input. The selected input is then fed into the second module for predicting the target variable. The experimental results show that our proposed end-to-end approach outperforms machine learning-based baselines on several public benchmark datasets. The AIS-LSTM model achieves higher performance on a public M3 dataset than the M3-specialized models. Furthermore, the AIS-RNN gives a beneficial advantage to interpret variable importance.

An accurate exchange rate forecasting and its decision-making to buy or sell are critical issues in the Forex market. Short-term currency rate forecasting is a challenging task due to its inherent characteristics, which include high volatility, trend, noise, and market shocks. We propose a novel deep learning architecture consisting of an adaptive activation function selection mechanism to achieve higher predictive accuracy. The proposed architecture is composed of seven neural networks that have different activation functions as well as softmax layer and multiplication layer with a skip connection, which are used to generate the dynamic importance weights that decide which activation function is preferred. In addition, we introduce an extended Min-Max smoothing technique to further normalize financial time series that have non-stationary properties. In our experimental evaluation, the results showed that our proposed model not only outperforms deep neural network baselines but also other classic machine learning approaches. The extended Min-Max smoothing technique is step towards forecasting non-stationary financial time series with deep neural networks.

Emotion detection and recognition from text is a recent essential research area in Natural Language Processing (NLP) which may reveal some valuable input to a variety of purposes. Nowadays, writings take many forms of social media posts, micro-blogs, news articles, customer review, etc., and the content of these short-texts can be a useful resource for text mining to discover an unhide various aspects, including emotions. The previously presented models mainly adopted word embedding vectors that represent rich semantic/syntactic information and those models cannot capture the emotional relationship between words. Recently, some emotional word embeddings are proposed but it requires semantic and syntactic information vice versa. To address this issue, we proposed a novel neural network architecture, called SENN (Semantic-Emotion Neural Network) which can utilize both semantic/syntactic and emotional information by adopting pre-trained word representations. SENN model has mainly two sub-networks, the first sub-network uses bidirectional Long-Short Term Memory (BiLSTM) to capture contextual information and focuses on semantic relationship, the second sub-network uses the convolutional neural network (CNN) to extract emotional features and focuses on the emotional relationship between words from the text. We conducted a comprehensive performance evaluation for the proposed model using standard real-world datasets. We adopted the notion of Ekman's six basic emotions. The experimental results show that the proposed model achieves a significantly superior quality of emotion recognition with various state-of-the-art approaches and further can be improved by other emotional word embeddings.

Abstract We report a phase I pharmacological study of an oral formulation of CKD‐516, a vascular‐disrupting agent, in patients with refractory solid tumors. Twenty‐seven patients (16 in the dose‐escalation cohort and 11 in the expansion cohort) received a single daily dose (5‐25 mg) of CKD‐516 five days per week. Nausea (67%) and diarrhea (63%) were the most common treatment‐related adverse events. The recommended phase II dose of oral CKD‐516 was 20 mg/d (15 mg/d with a body surface area (BSA)

Vast quantities of data are generated by social networks in seconds. The information generated in a social network is transformed into a flow by the subjects who produce, transmit, and consume it. This flow can be represented in a very complicated directional graph where each subject is represented as a node, and the flow of information is represented as a directed edge. In this paper, we introduce a method of dividing this complex directional graph by user and quantifying the flow of information between and among users based on information flow vectors. We propose a system that can monitor the flow of information in social networks using information flow vectors extracted from social media data. We also introduce an improved skyline algorithm that can respond quickly to a user's various queries.

Caladium bicolor is one of the most popular plants in Thailand. The original species of Caladium bicolor was found a hundred years ago. Until now, there are more than 500 species through multiplication. The classification of Caladium bicolor can be done by using its color and shape. This study aims to develop a model to classify Caladium bicolor using a transfer learning technique. This work also presents a proof of concept, GUI design, and web application deployment using the user-design-center method. We also evaluated the performance of the following pre-trained models in this work, and the results are as follow: 87.29% for AlexNet, 90.68% for GoogleNet, 93.59% for XceptionNet, 93.22% for MobileNetV2, 89.83% for RestNet18, 88.98% for RestNet50, 97.46% for RestNet101, and 94.92% for InceptionResNetV2. This work was implemented using MATLAB R2023a. [ABSTRACT FROM AUTHOR]

Investors aim to increase their profitability by investing in the stock market. An adroit strategy for minimizing related risk lies through diversifying portfolio operationalization. In this paper, we propose a six-step stocks portfolio selection model. This model is based on data mining clustering techniques that reflect the ensuing impact of the political, economic, legal, and corporate governance in Mongolia. As a dataset, we have selected stock exchange trading price, financial statements, and operational reports of top-20 highly capitalized stocks that were traded at the Mongolian Stock Exchange from 2013 to 2017. In order to cluster the stock returns and risks, we have used k-means clustering techniques. We have combined both k-means clustering with Markowitz's portfolio theory to create an optimal and efficient portfolio. We constructed an efficient frontier, creating 15 portfolios, and computed the weight of stocks in each portfolio. From these portfolio options, the investor is given a choice to choose any one option. [ABSTRACT FROM AUTHOR]