Search

CeXO2 (X: Fe, Mn) nanoparticles, synthesized using the coprecipitation route, were investigated for their structural, morphological, magnetic, and electrochemical properties using X-ray diffraction (XRD), field emission transmission electron microscopy (FE-TEM), dc magnetization, and cyclic voltammetry methods. The single-phase formation of CeO2 nanoparticles with FCC fluorite structure was confirmed by the Rietveld refinement, indicating the successful incorporation of Fe and Mn in the CeO2 matrix with the reduced dimensions and band gap values. The Raman analysis supported the lowest band gap of Fe-doped CeO2 on account of oxygen non-stoichiometry. The samples exhibited weak room temperature ferromagnetism, which was found to be enhanced in the Fe doped CeO2. The NEXAFS analysis supported the results by revealing the oxidation state of Fe to be Fe2+/Fe3+ in Fe-doped CeO2 nanoparticles. Further, the room temperature electrochemical performance of CeXO2 (X: Fe, Mn) nanoparticles was measured with a scan rate of 10 mV s−1 using 1 M KCL electrolyte, which showed that the Ce0.95Fe0.05O2 electrode revealed excellent performance with a specific capacitance of 945 Fּ·g−1 for the application in energy storage devices.

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 phenomenon of hydrogen embrittlement (HE) in metals and alloys, which determines the performance of components in hydrogen environments, has recently been drawing considerable attention. This study explores the interplay between strain rates and solute hydrogen in inducing HE of Ti6Al4V alloy. For the hydrogen-charged sample, as the strain rate was decreased from 10−2/s to 10−5/s, the ductility decreased significantly, but the HE effect on mechanical strength was negligible. The low strain rate (LSR) conditions facilitated the development of high-angle grain boundaries, providing more pathways for hydrogen diffusion and accumulation. The presence of solute hydrogen intensified the formation of nano/micro-voids and intergranular cracking tendencies, with micro-crack occurrences observed exclusively in the LSR conditions. These factors expanded the brittle hydrogen-damaged region more deeply into the interior of the lattice. This, in turn, accelerated both crack initiation and intergranular crack propagation, finally resulting in a considerable HE effect and a reduction in ductility at the LSR. The current study underscores the influence of strain rate on HE, enhancing the predictability of longevity and improving the reliability of components operating in hydrogen-rich environments under various loading conditions.

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.

Magnetic nanoparticles of NiFe2O4 were successfully prepared by utilizing the sol–gel techniques. The prepared samples were investigated through various techniques such as X-ray diffraction (XRD), transmission electron microscopy (TEM), dielectric spectroscopy, DC magnetization and electrochemical measurements. XRD data analysed using Rietveld refinement procedure inferred that NiFe2O4 nanoparticles displayed a single-phase nature with face-centred cubic crystallinity with space group Fd-3m. Average crystallite size estimated using the XRD patterns was observed to be ~10 nm. The ring pattern observed in the selected area electron diffraction pattern (SAED) also confirmed the single-phase formation in NiFe2O4 nanoparticles. TEM micrographs confirmed the uniformly distributed nanoparticles with spherical shape and an average particle size of 9.7 nm. Raman spectroscopy showed characteristic bands corresponding to NiFe2O4 with a shift of the A1g mode, which may be due to possible development of oxygen vacancies. Dielectric constant, measured at different temperatures, increased with temperature and decreased with increase in frequency at all temperatures. The Havrilliak–Negami model used to study the dielectric spectroscopy indicated that a NiFe2O4 nanoparticles display non-Debye type relaxation. Jonscher’s power law was utilized for the calculation of the exponent and DC conductivity. The exponent values clearly demonstrated the non-ohmic behaviour of NiFe2O4 nanoparticles. The dielectric constant of the nanoparticles was found to be >300, showing a normal dispersive behaviour. AC conductivity showed an increase with the rise in temperature with the highest value of 3.4 × 10−9 S/cm at 323 K. The M-H curves revealed the ferromagnetic behaviour of a NiFe2O4 nanoparticle. The ZFC and FC studies suggested a blocking temperature of ~64 K. The saturation of magnetization determined using the law of approach to saturation was ~61.4 emu/g at 10 K, corresponding to the magnetic anisotropy ~2.9 × 104 erg/cm3. Electrochemical studies showed that a specific capacitance of ~600 F g−1 was observed from the cyclic voltammetry and galvanostatic charge–discharge, which suggested its utilization as a potential electrode for supercapacitor applications.

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.

The color filter required for manufacturing a CMOS image sensor was redeveloped to optimize its optical uniformity. An in-depth study of the three-dimensional (3D) coating process and how it gives rise to various radial-shaped striation patterns was conducted. These radial-shaped striation patterns were systematically investigated with reference to two types of patterns: the orthogonal type found only at the orthogonal edges of the wafer and the diagonal type found mostly at the corner of each quadrant. The formation of the orthogonal pattern was based on the wide standing wave created by the incident force of the spreading color photoresist (PR) and the reflective force from the bump pads acting as coating barriers. The diagonal pattern was found to be generated by the turbulent wakes created behind the bump pads by the drag force, which interfered with the coating flow. An in-depth study using Ansys CFX software and an in-line inspection tool revealed that lowering the viscosity of the color PR material is a key factor for improving the phenomenon whereby the 3D striation patterns of the orthogonal and diagonal types are formed. Based on this finding, it was possible to drastically reduce the formation of the 3D striation patterns by decreasing the viscosity of the material comprising each color PR. This study provides not only an empirical and theoretical understanding of the 3D color PR coating mechanism, but also guidelines for future color filter processes.

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.

BiFe1−xCrxO3, (0 ≤ x ≤ 10) nanoparticles were prepared through the sol–gel technique. The synthesized nanoparticles were characterized using various techniques, viz., X-ray diffraction, high-resolution field emission scanning electron microscopy (HRFESEM), energy dispersive spectroscopy (EDS), UV–Vis absorption spectroscopy, photoluminescence (PL), dc magnetization, near-edge X-ray absorption spectroscopy (NEXAFS) and cyclic voltammetry (CV) measurements, to investigate the structural, morphological, optical, magnetic and electrochemical properties. The structural analysis showed the formation of BiFeO3 with rhombohedral (R3c) as the primary phase and Bi25FeO39 as the secondary phase. The secondary phase percentage was found to reduce with increasing Cr content, along with reductions in crystallite sizes, lattice parameters and enhancement in strain. Nearly spherical shape morphology was observed via HRFESEM with Bi, Fe, Cr and O as the major contributing elements. The bandgap reduced from 1.91 to 1.74 eV with the increase in Cr concentration, and PL spectra revealed emissions in violet, blue and green regions. The investigation of magnetic field (H)-dependent magnetization (M) indicated a significant effect of Cr substitution on the magnetic properties of the nanoparticles. The ferromagnetic character of the samples was found to increase with the increase in the Cr concentration and the increase in the saturation magnetization. The Fe (+3/+4) was dissolved in mixed-valence states, as found through NEXAFS analysis. Electrochemical studies showed that 5%-Cr-doped BFO electrode demonstrated outstanding performance for supercapacitors through a specific capacitance of 421 F g−1 measured with a scan rate of 10 mV s−1. It also demonstrated remarkable cyclic stability through capacitance retention of >78% for 2000 cycles.

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.