Search

Augmented reality (AR) has been shown to improve productivity in industry, but its adverse effects (e.g., headaches, eye strain, nausea, and mental workload) on users warrant further investigation. The objective of this study is to investigate the effects of different instruction methods (i.e., HoloLens AR-based and paper-based instructions) and task complexity (low and high-demanding tasks) on cognitive workloads and performance. Twenty-eight healthy males with a mean age of 32.12 (SD 2.45) years were recruited in this study and were randomly divided into two groups. The first group performed the experiment using AR-based instruction, and the second group used paper-based instruction. Performance was measured using total task time (TTT). The cognitive workload was measured using the power of electroencephalograph (EEG) features and the NASA task load index (NASA TLX). The results showed that using AR instructions resulted in a reduction in maintenance times and an increase in mental workload compared to paper instructions, particularly for the more demanding tasks. With AR instruction, 0.45% and 14.94% less time was spent on low- and high-demand tasks, respectively, as compared to paper instructions. According to the EEG features, employing AR to guide employees during highly demanding maintenance tasks increased information processing, which could be linked with an increased germane cognitive load. Increased germane cognitive load means participants can better facilitate long-term knowledge and skill acquisition. These results suggested that AR is superior and recommended for highly demanding maintenance tasks since it speeds up maintenance times and increases the possibility that information is stored in long-term memory and encrypted for recalls. [ABSTRACT FROM AUTHOR]

Fruit fly species classification is a fine-grained task as there is a small gap between species. In order to effectively identify and improve the recognition of fruit flies, a fine-grained image-recognition method based on a multi-channel self-attention mechanism was studied and a network framework for fine-grained image recognition based on deep learning was designed in this paper. In this framework, long-term and short-term memory networks are used to extract the underlying features in fruit fly fine-grained images. By inputting the underlying features in the multi-channel self-attention mechanism module, the global and local attention feature maps can be obtained.The weighted attention feature map can also be obtained by multiplying the weight of each channel and the attention feature map. The fine-grained image features of fruit flies were obtained by summing the weighted attention feature map. A softmax classifier was used to process the features and complete the recognition of the fruit fly fine-grained images. Two fine-grained image datasets of fruit flies were applied as experimental objects. Dataset 1 and Dataset 2 contain 11,778 images and 20,580 images from 46 different categories of fruit flies, respectively. The Kappa coefficient was used as the evaluation index to identify fruit fly images with different targets using the method proposed herein. The experimental results showed that, as the number of attention channels increased, the Kappa coefficient gradually increased, suggesting an improvement in the accuracy of fine-grained image recognition. The fine-grained image features extracted by introducing a multi-channel self-attention mechanism exhibited more distinct boundaries with a small amount of overlap, demonstrating strong feature extraction capabilities. When dealing with fine-grained images with either simple or complex backgrounds, the method proposed in this paper has good performance and generalization ability. Even if the target is small and varied in shape, it can still achieve highly accurate recognition. [ABSTRACT FROM AUTHOR]

Adaptation of handover parameters in ultra-dense networks has always been one of the key issues in optimizing network performance. Aiming at the optimization goal of effective handover ratio, this paper proposes a deep Q-learning (DQN) method that dynamically selects handover parameters according to wireless signal fading conditions. This approach seeks good backward compatibility. In order to enhance the efficiency and performance of the DQN method, Long Short Term Memory (LSTM) is used to build a digital twin and assist the DQN algorithm to achieve a more efficient search. Simulation experiments prove that the enhanced method has a faster convergence speed than the ordinary DQN method, and at the same time, achieves an average effective handover ratio increase of 2.7%. Moreover, in different wireless signal fading intervals, the method proposed in this paper has achieved better performance. [ABSTRACT FROM AUTHOR]

With the rapid development of smart grids, the number of various types of power IoT terminal devices has grown by leaps and bounds. An attack on either of the difficult-to-protect end devices or any node in a large and complex network can put the grid at risk. The traffic generated by Distributed Denial of Service (DDoS) attacks is characterised by short bursts of time, making it difficult to apply existing centralised detection methods that rely on manual setting of attack characteristics to changing attack scenarios. In this paper, a DDoS attack detection model based on Bidirectional Long Short-Term Memory (BiLSTM) is proposed by constructing an edge detection framework, which achieves bi-directional contextual information extraction of the network environment using the BiLSTM network and automatically learns the temporal characteristics of the attack traffic in the original data traffic. This paper takes the DDoS attack in the power Internet of Things as the research object. Simulation results show that the model outperforms traditional advanced models such as Recurrent Neural Network (RNN) and Long Short Term Memory (LSTM) in terms of accuracy, false detection rate, and time delay. It plays an auxiliary role in the security protection of the power Internet of Things and effectively improves the reliability of the power grid. [ABSTRACT FROM AUTHOR]

Recently, interest in the Cyber-Physical System (CPS) has been increasing in the manufacturing industry environment. Various manufacturing intelligence studies are being conducted to enable faster decision-making through various reliable indicators collected from the manufacturing process. Artificial intelligence (AI) and Machine Learning (ML) have advanced enough to give various possibilities of predicting manufacturing time, which can help implement CPS in manufacturing environments, but it is difficult to secure reliability because it is difficult to understand how AI works, and although it can offer good results, it is often not applied to industries. In this paper, Bidirectional Long Short Term Memory (BI-LSTM) is used to predict process execution time, which is an indicator that can be used as a basis for CPS in the manufacturing process, and the Shapley Additive Explanations (SHAP) algorithm is used to explain how artificial intelligence works. The experimental results of this paper, applying manufacturing data, prove that the results derived from SHAP are effective for workers and AI to collaborate. [ABSTRACT FROM AUTHOR]

Entity relation extraction mainly extracts relations from text, which is one of the important tasks of natural language processing. At present, some special fields have insufficient data; for example, agriculture, the metallurgical industry, etc. There is a lack of an effective model for entity relationship recognition under the condition of insufficient data. Inspired by this, we constructed a suitable small balanced data set and proposed a multi-neural network collaborative model (RBF, Roberta–Bidirectional Gated Recurrent Unit–Fully Connected). In addition, we also optimized the proposed model. This model uses the Roberta model as the coding layer, which is used to extract the word-level features of the text. This model uses BiGRU (Bidirectional Gated Recurrent Unit)–FC (Fully Connected) as the decoding layer, which is used to obtain the optimal relationship of the text. To further improve the effect, the input layer is optimized by feature fusion, and the learning rate is optimized by the cosine annealing algorithm. The experimental results show that, using the small balanced data set, the F1 value of the RBF model proposed in the paper is 25.9% higher than the traditional Word2vec–BiGRU–FC model. It is 18.6% higher than the recent Bert–BiLSTM (Bidirectional Long Short Term Memory)–FC model. The experimental results show that our model is effective. [ABSTRACT FROM AUTHOR]

The current research into decision-making strategies for air combat focuses on the performance of algorithms, while the selection of actions is often ignored, and the actions are often fixed in amplitude and limited in number in order to improve the convergence efficiency, making the strategy unable to give full play to the maneuverability of the aircraft. In this paper, a decision-making strategy for close-range air combat based on reinforcement learning with variable-scale actions is proposed; the actions are the variable-scale virtual pursuit angles and speeds. Firstly, a trajectory prediction method consisting of a real-time prediction, correction, and judgment of errors is proposed. The back propagation (BP) neural network and the long and short term memory (LSTM) neural network are used as base prediction network and correction prediction network, respectively. Secondly, the past, current, and future positions of the target aircraft are used as virtual pursuit points, and they are converted into virtual pursuit angles as the track angle commands using angle guidance law. Then, the proximity policy optimization (PPO) algorithm is applied to train the agent. The simulation results show that the attacking aircraft that uses the strategy proposed in this paper has a higher win rate during air combat and the attacking aircraft's maneuverability is fully utilized. [ABSTRACT FROM AUTHOR]

Healthcare cost is an issue of concern right now. While many complex machine learning algorithms have been proposed to analyze healthcare cost and address the shortcomings of linear regression and reliance on expert analyses, these algorithms do not take into account whether each characteristic variable contained in the healthcare data has a positive effect on predicting healthcare cost. This paper uses hybrid machine learning algorithms to predict healthcare cost. First, network structure learning algorithms (a score-based algorithm, constraint-based algorithm, and hybrid algorithm) for a Conditional Gaussian Bayesian Network (CGBN) are used to learn the isolated characteristic variables in healthcare data without changing the data properties (i.e., discrete or continuous). Then, the isolated characteristic variables are removed from the original data and the remaining data used to train regression algorithms. Two public healthcare datasets are used to test the performance of the proposed hybrid machine learning algorithm model. Experiments show that when compared to popular single machine learning algorithms (Long Short Term Memory, Random Forest, etc.) the proposed scheme can obtain similar or higher prediction accuracy with a reduced amount of data. [ABSTRACT FROM AUTHOR]

Although tsunamis occur less frequently compared to some other natural disasters, they can be extremely devastating in the nearshore environment if they occur. An earthquake of magnitude 6.9 Mw occurred on 30 October 2020 at 12:51 p.m. UTC (2:51 p.m. GMT+03:00) and its epicenter was approximately 23 km south of İzmir province of Turkey, off the Greek island of Samos. The tsunami event triggered by this earthquake is known as the 30 October 2020 İzmir-Samos (Aegean) tsunami, and in this paper, we study the hydrodynamics of this tsunami using some of these artificial intelligence (AI) techniques applied to observational data. More specifically, we use the tsunami time series acquired from the UNESCO data portal at different stations of Bodrum, Syros, Kos, and Kos Marina. Then, we investigate the usage and shortcomings of the Long Short Term Memory (LSTM) DL technique for the prediction of the tsunami time series and its Fourier spectra. More specifically we study the predictability of the offshore water surface elevation dynamics, their spectral frequency and amplitude features, possible prediction success and enhancement of the accurate early prediction time scales. The uses and applicability of our findings and possible research directions are also discussed. [ABSTRACT FROM AUTHOR]

The availability of high spatial and temporal resolution imagery, such as that provided by the Sentinel satellites, allows the use of image time series to classify land cover. Recurrent neural networks (RNNs) are a clear candidate for such an approach; however, the presence of clouds poses a difficulty. In this paper, random forest (RF) and RNNs are used to reconstruct cloud-covered pixels using data from other next in time images instead of pixels in the same image. Additionally, two RNN architectures are tested to classify land cover from the series, treating reflectivities as time series and also treating spectral signatures as time series. The results are compared with an RF classification. The results for cloud removal show a high accuracy with a maximum RMSE of 0.057 for RNN and 0.038 for RF over all images and bands analysed. In terms of classification, the RNN model obtained higher accuracy (over 0.92 in the test data for the best hyperparameter combinations) than the RF model (0.905). However, the temporal–spectral model accuracies did not reach 0.9 in any case. [ABSTRACT FROM AUTHOR]

This paper proposes a new optimization algorithm for backpropagation (BP) neural networks by fusing integer-order differentiation and fractional-order differentiation, while fractional-order differentiation has significant advantages in describing complex phenomena with long-term memory effects and nonlocality, its application in neural networks is often limited by a lack of physical interpretability and inconsistencies with traditional models. To address these challenges, we propose a mixed integer-fractional (MIF) gradient descent algorithm for the training of neural networks. Furthermore, a detailed convergence analysis of the proposed algorithm is provided. Finally, numerical experiments illustrate that the new gradient descent algorithm not only speeds up the convergence of the BP neural networks but also increases their classification accuracy. [ABSTRACT FROM AUTHOR]

Oceanic targets, including ripples, islands, vessels, and coastlines, display distinct sparse characteristics, rendering the ocean a significant arena for sparse Synthetic Aperture Radar (SAR) imaging rooted in sparse signal processing. Deep neural networks (DNNs), a current research emphasis, have, when integrated with sparse SAR, attracted notable attention for their exceptional imaging capabilities and high computational efficiency. Yet, the efficiency of traditional unfolding techniques is impeded by their architecturally inefficient design, which curtails their information transmission capacity and consequently detracts from the quality of reconstruction. This paper unveils a novel Memory-Augmented Deep Unfolding Network (MADUN) for SAR imaging in marine environments. Our methodology harnesses the synergies between deep learning and algorithmic unfolding, enhanced with a memory component, to elevate SAR imaging's computational precision. At the heart of our investigation is the incorporation of High-Throughput Short-Term Memory (HSM) and Cross-Stage Long-Term Memory (CLM) within the MADUN framework, ensuring robust information flow across unfolding stages and solidifying the foundation for deep, long-term informational correlations. Our experimental results demonstrate that our strategy significantly surpasses existing methods in enhancing the reconstruction of sparse marine scenes. [ABSTRACT FROM AUTHOR]

Pu-erh tea, Camellia sinensis is a traditional Chinese tea, one of the black teas, originally produced in China's Yunnan Province, named after its origin and distribution center in Pu-erh, Yunnan. Yunnan Pu-erh tea is protected by geographical Indication and has unique quality characteristics. It is made from Yunnan large-leaf sun-green tea with specific processing techniques. The quality formation of Pu-erh tea is closely related to the soil's environmental conditions. In this paper, time-by-time data of the soil environment of tea plantations during the autumn tea harvesting period in Menghai County, Xishuangbanna, Yunnan Province, China, in 2021 were analyzed. Spearman's correlation analysis was conducted between the inner components of Pu'er tea and the soil environmental factor. The analysis showed that three soil environmental indicators, soil temperature, soil moisture, and soil pH, were highly significantly correlated. The soil environmental quality evaluation method was proposed based on the selected soil environmental characteristics. Meanwhile, a deep learning model of Long Short Term Memory (LSTM) Network for the soil environmental quality of tea plantation was established according to the proposed method, and the soil environmental quality of tea was classified into four classes. In addition, the paper also compares the constructed models based on BP neural network and random forest to evaluate the coefficient of determination (R2), mean absolute error (MAE), mean square error (MSE), mean absolute percentage error (MAPE) and root mean square error (RMSE) of the indicators for comparative analysis. This paper innovatively proposes to introduce the main inclusions of Pu'er tea into the classification and discrimination model of the soil environment in tea plantations, while using machine learning-related algorithms to classify and predict the categories of soil environmental quality, instead of relying solely on statistical data for analysis. This research work makes it possible to quickly and accurately determines the physiological status of tea leaves based on the establishment of a soil environment quality prediction model, which provides effective data for the intelligent management of tea plantations and has the advantage of rapid and low-cost assessment compared with the need to measure the intrinsic quality of Pu-erh tea after harvesting is completed. [ABSTRACT FROM AUTHOR]

This study addressed the issues related to the difficulty of determining the operating status of machine tool spindle bearings due to the high rotational speeds and rapid temperature fluctuations. This paper presents an optimized model that combines Convolutional Neural Networks (CNNs) and Informer to dynamically predict the temperature rise process of bearings. Taking the H7006C angular contact ball bearing as the research object, a combination of experimental data and simulations was used to obtain the training dataset. Next, a model for predicting the temperature rise of the bearing was constructed using CNN + Informer and the structural parameters were optimized. Finally, the model's generalization ability was then verified by predicting the bearing temperature rise process under various working conditions. The results show that the error of the simulation data source model was less than 1 °C at steady state; the temperature error of the bearing temperature rise prediction model was less than 0.5 °C at both the temperature rise and steady-state stages under variable rotational speeds and variable load conditions compared to Informer and Long Short Term Memory (LSTM) models; the maximum prediction error of the operating conditions outside the dataset was less than 0.5 °C, and the temperature rise prediction model has a high accuracy, robustness, and generalization capability. [ABSTRACT FROM AUTHOR]

Viscoelastic damping phenomena are ubiquitous in diverse kinds of wave motions of nonlinear media. This arouses extensive interest in studying the existence, the finite time blow-up phenomenon and various large time behaviors of solutions to viscoelastic wave equations. In this paper, we are concerned with a class of variable coefficient coupled quasi-linear wave equations damped by viscoelasticity with a long-term memory fading at very general rates and possibly damped by friction but provoked by nonlinear interactions. We prove a local existence result for solutions to our concerned coupled model equations by applying the celebrated Faedo-Galerkin scheme. Based on the newly obtained local existence result, we prove that solutions would exist globally in time whenever their initial data satisfy certain conditions. In the end, we provide a criterion to guarantee that some of the global-in-time-existing solutions achieve energy decay at general rates uniquely determined by the fading rates of the memory. Compared with the existing results in the literature, our concerned model coupled wave equations are more general, and therefore our theoretical results have wider applicability. Modified energy functionals (can also be viewed as certain Lyapunov functionals) play key roles in proving our claimed general energy decay result in this paper. [ABSTRACT FROM AUTHOR]

In this paper, the authors investigate the possibility of applying artificial intelligence algorithms to the outputs of a low-cost Kalman filter-based navigation solution in order to achieve performance similar to that of high-end MEMS inertial sensors. To further improve the results of the prototype and simultaneously lighten filter requirements, different AI models are compared in this paper to determine their performance in terms of complexity and accuracy. By overcoming some known limitations (e.g., sensitivity on the dimension of input data from inertial sensors) and starting from Kalman filter applications (whose raw noise parameter estimates were obtained from a simple analysis of sensor specifications), such a solution presents an intermediate behavior compared to the current state of the art. It allows the exploitation of the power of AI models. Different Neural Network models have been taken into account and compared in terms of measurement accuracy and a number of model parameters; in particular, Dense, 1-Dimension Convolutional, and Long Short Term Memory Neural networks. As can be excepted, the higher the NN complexity, the higher the measurement accuracy; the models' performance has been assessed by means of the root-mean-square error (RMSE) between the target and predicted values of all the navigation parameters. [ABSTRACT FROM AUTHOR]

Despite the obvious benefits and growing popularity of Machine Learning (ML) technology, there are still concerns regarding its ability to provide Financial Distress Prediction (FDP). An accurate FDP model is required to avoid financial risk at the lowest possible cost. However, in the Internet era, financial data are exploding, and they are being coupled with other kinds of risk data, making an FDP model challenging to operate. As a result, researchers presented several novel FDP models based on ML and Deep Learning. Time series data is are important to reflect the multi-source and heterogeneous aspects of financial data. This paper gives insight into building a time-series model and forecasting distress far in advance of its occurrence. To build an efficient FDP model, we provide a hybrid model (GALSTM-FDP) that incorporates LSTM and GA. Unlike other previous studies, which established models that predicted distress probability only within one year, our approach predicts distress two years ahead. This research integrates GA with LSTM to find the optimum hyperparameter configuration for LSTM. Using GA, we focus on optimizing architectural aspects for modeling the optimal network based on prediction accuracy. The results showed that our algorithm outperforms other state-of-the-art methods in terms of predictive accuracy. [ABSTRACT FROM AUTHOR]

Fish head cutting is one of the most important processes during fish pre-processing. At present, the identification of cutting positions mainly depends on manual experience, which cannot meet the requirements of large-scale production lines. In this paper, a fast and contactless identification method of cutting position was carried out by using a constructed line laser data acquisition system. The fish surface data were collected by a linear laser scanning sensor, and Principal Component Analysis (PCA) was used to reduce the dimensions of the dorsal and abdominal boundary data. Based on the dimension data, Least Squares Support Vector Machines (LS-SVMs), Particle Swarm Optimization-Back Propagation (PSO-BP) networks, and Long and Short Term Memory (LSTM) neural networks were applied for fish head cutting position identification model establishment. According to the results, the LSTM model was considered to be the best prediction model with a determination coefficient ( R 2 ) value, root mean square error ( R M S E ), mean absolute error ( M A E ), and residual predictive deviation ( R P D ) of 0.9480, 0.2957, 0.1933, and 3.1426, respectively. This study demonstrated the reliability of combining line laser scanning techniques with machine learning using LSTM to identify the fish head cutting position accurately and quickly. It can provide a theoretical reference for the development of intelligent processing and intelligent cutting equipment for fish. [ABSTRACT FROM AUTHOR]

The aim of this paper is to analyse Bitcoin in order to shed some light on its nature and behaviour. We select 9 cryptocurrencies that account for almost 75% of total market capitalisation and compare their evolution with that of a wide variety of traditional assets: commodities with spot and future contracts, treasury bonds, stock indices, and growth and value stocks. Fractal geometry will be applied to carry out a careful statistical analysis of the performance of Bitcoin returns. As a main conclusion, we have detected a high degree of persistence in its prices, which decreases the efficiency but increases its predictability. Moreover, we observe that the underlying technology influences price dynamics, with fully decentralised cryptocurrencies being the only ones to exhibit self-similarity features at any time scale. [ABSTRACT FROM AUTHOR]

This paper provides a pioneering examination and enhancement of generative chat models, with a specific focus on the BlenderBot 3 model. Through meticulous interaction with a diverse set of human participants, we dissected the fundamental components of these models, unveiling several deficiencies, including long-term memory and entity recognition. Leveraging these insights, we engineered refined, streamlined iterations, culminating in a chatbot that transcends the capabilities of all existing models. Our work follows Occam's razor principle and proves that, for tasks with relatively low complexity, using large overparameterized models instead of smaller ones does not bring significant benefits but increases latency, which may result in a lowered overall user experience. In upholding our commitment to transparency and the progression of shared knowledge, we have made our improved model universally accessible through open-source distribution. [ABSTRACT FROM AUTHOR]

This paper investigates the bipolar resistive switching and synaptic characteristics of IZO single-layer and IZO/SiO2 bilayer two-terminal memory devices. The chemical properties and structure of the device with a SiO2 layer are confirmed by x-ray photoemission spectroscopy (XPS) and transmission electron microscopy (TEM) imaging. The device with the SiO2 layer showed better memory characteristics with a low current level, as well as better cell-to-cell and cycle-to-cycle uniformity. Moreover, the neuromorphic applications of the IZO/SiO2 bilayer device are demonstrated by pulse response. Paired pulse facilitation, excitatory postsynaptic current, and pulse-width-dependent conductance changes are conducted by the coexistence of short- and long-term memory characteristics. Moreover, Hebbian rules are emulated to mimic biological synapse function. The result of potentiation, depression, spike-rate-dependent plasticity, and spike-time-dependent plasticity prove their favorable abilities for future applications in neuromorphic computing architecture. [ABSTRACT FROM AUTHOR]

In wireless communication, multiple signals are utilized to receive and send information in the form of signals simultaneously. These signals consume little power and are usually inexpensive, with a high data rate during data transmission. An Multi Input Multi Output (MIMO) system uses numerous antennas to enhance the functionality of the system. Moreover, system intricacy and power utilization are difficult and highly complicated tasks to achieve in an Analog to Digital Converter (ADC) at the receiver side. An infinite number of MIMO channels are used in wireless networks to improve efficiency with Cross Entropy Optimization (CEO). ADC is a serious issue because the data of the accepted signal are completely lost. ADC is used in the MIMO channels to overcome the above issues, but it is very hard to implement and design. So, an efficient way to enhance the estimation of channels in the MIMO system is proposed in this paper with the utilization of the heuristic-based optimization technique. The main task of the implemented channel prediction framework is to predict the channel coefficient of the MIMO system at the transmitter side based on the receiver side error ratio, which is obtained from feedback information using a Hybrid Serial Cascaded Network (HSCN). Then, this multi-scaled cascaded autoencoder is combined with Long Short Term Memory (LSTM) with an attention mechanism. The parameters in the developed Hybrid Serial Cascaded Multi-scale Autoencoder and Attention LSTM are optimized using the developed Hybrid Revised Position-based Wild Horse and Energy Valley Optimizer (RP-WHEVO) algorithm for minimizing the "Root Mean Square Error (RMSE), Bit Error Rate (BER) and Mean Square Error (MSE)" of the estimated channel. Various experiments were carried out to analyze the accomplishment of the developed MIMO model. It was visible from the tests that the developed model enhanced the convergence rate and prediction performance along with a reduction in the computational costs. [ABSTRACT FROM AUTHOR]

Urban rail transit offers advantages such as high safety, energy efficiency, and environmental friendliness. With cities rapidly expanding, travelers are increasingly using rail systems, heightening demands for passenger capacity and efficiency while also pressuring these networks. Passenger flow forecasting is an essential part of transportation systems. Short-term passenger flow forecasting for rail transit can estimate future station volumes, providing valuable data to guide operations management and mitigate congestion. This paper investigates short-term forecasting for Suzhou's Shantang Street station. Shantang Street's high commercial presence and distinct weekday versus weekend ridership patterns make it an interesting test case, making it a representative subway station. Wavelet denoising and Long Short Term Memory (LSTM) were combined to predict short-term flows, comparing the results to those of standalone LSTM, Support Vector Regression (SVR), Artificial Neural Network (ANN), and Autoregressive Integrated Moving Average Model (ARIMA). This study illustrates that the algorithms adopted exhibit good performance for passenger prediction. The LSTM model with wavelet denoising proved most accurate, demonstrating applicability for short-term rail transit forecasting and practical significance. The research findings can provide fundamental recommendations for implementing appropriate passenger flow control measures at stations and offer effective references for predicting passenger flow and mitigating traffic pressure in various cities. [ABSTRACT FROM AUTHOR]

This paper discusses current formulations based on fuzzy-logic control concepts as applied to the removal of impulsive noise from digital images. We also discuss the various principles related to fuzzy-ruled based logic control techniques, aiming at preserving edges and digital image details efficiently. Detailed descriptions of a number of formulations for recently developed fuzzy-rule logic controlled filters are provided, highlighting the merit of each filter. Fuzzy-rule based filtering algorithms may be designed assuming the tailoring of specific functional sub-modules: (a) logical controlled variable selection, (b) the consideration of different methods for the generation of fuzzy rules and membership functions, (c) the integration of the logical rules for detecting and filtering impulse noise from digital images. More specifically, we discuss impulse noise models and window-based filtering using fuzzy inference based on vector directional filters as associated with the filtering of RGB color images and then explain how fuzzy vector fields can be generated using standard operations on fuzzy sets taking into consideration fixed or random valued impulse noise and fuzzy vector partitioning. We also discuss how fuzzy cellular automata may be used for noise removal by adopting a Moore neighbourhood architecture. We also explain the potential merits of adopting a fuzzy rule based deep learning ensemble classifier which is composed of a convolutional neural network (CNN), a recurrent neural networks (RNN), a long short term memory neural network (LSTM) and a gated recurrent unit (GRU) approaches, all within a fuzzy min-max (FMM) ensemble. Fuzzy non-local mean filter approaches are also considered. A comparison of various performance metrics for conventional and fuzzy logic based filters as well as deep learning filters is provided. The algorhitms discussed have the following advantageous properties: high quality of edge preservation, high quality of spatial noise suppression capability especially for complex images, sound properties of noise removal (in cases when both mixed additive and impulse noise are present), and very fast computational implementation. [ABSTRACT FROM AUTHOR]

Determining the types of light curves has been a challenge due to the massive amount of light curves generated by large sky survey programs. In the literature, the light curves classification methods are overly dependent on the imaging quality of the light curves, so the classification results are often poor. In this paper, a new method is proposed to classify the Kepler light curves from Quarter 1, and consists of two parts: feature extraction and classification neural network construction. In the first part, features are extracted from the light curves using three different methods, and then the features are fused (transform domain features, light curve flux statistics features, and Kepler photometry features). In the second part, a classification neural network RLNet, based on Residual Network (ResNet) and Long Short Term Memory (LSTM), is proposed. The experiment involved the classification of approximately 150,000 Kepler light curves into 11 categories. The results show that this new method outperforms seven other methods in all metrics, with an accuracy of 0.987, a minimum recall of 0.968, and a minimum precision of 0.970 under all categories. [ABSTRACT FROM AUTHOR]

Accurate short-term precipitation forecast is extremely important for urban flood warning and natural disaster prevention. In this paper, we present an innovative deep learning model named ISA-PredRNN (improved self-attention PredRNN) for precipitation nowcasting based on radar echoes on the basis of the advanced PredRNN-V2. We introduce the self-attention mechanism and the long-term memory state into the model and design a new set of gating mechanisms. To better capture different intensities of precipitation, the loss function with weights was designed. We further train the model using a combination of reverse scheduled sampling and scheduled sampling to learn the long-term dynamics from the radar echo sequences. Experimental results show that the new model (ISA-PredRNN) can effectively extract the spatiotemporal features of radar echo maps and obtain radar echo prediction results with a small gap from the ground truths. From the comparison with the other six models, the new ISA-PredRNN model has the most accurate prediction results with a critical success index (CSI) of 0.7001, 0.5812 and 0.3052 under the radar echo thresholds of 10 dBZ, 20 dBZ and 30 dBZ, respectively. [ABSTRACT FROM AUTHOR]

This paper introduces a compact SPICE model of a two-terminal memory with a Pd/Ti/IGZO/p+-Si structure. In this paper, short- and long-term components are systematically separated and applied in each model. Such separations are conducted by the applied bias and oxygen flow rate (OFR) during indium gallium zinc oxide (IGZO) deposition. The short- and long-term components in the potentiation and depression curves are modeled by considering the process (OFR of IGZO) and bias conditions. The compact SPICE model with the physical mechanism of SiO2 modulation is introduced, which can be useful for optimizing the specification of memristor devices. [ABSTRACT FROM AUTHOR]

(1) Background: Rolling bearings are important components in mechanical equipment, but they are also components with a high failure rate. Once a malfunction occurs, it will cause mechanical equipment to malfunction and may even affect personnel safety. Therefore, studying the fault diagnosis methods for rolling bearings is of great significance and is also a current research hotspot and frontier. However, the vibration signals of rolling bearings usually exhibit nonlinear and non-stationary characteristics, and are easily affected by industrial environmental noise, making it difficult to accurately diagnose bearing faults. (2) Methods: Therefore, this article proposes a rolling bearing fault diagnosis model based on an improved dung beetle optimizer (DBO) algorithm-optimized variational mode decomposition-convolutional neural network-bidirectional long short-term memory (VMD-CNN-BiLSTM). Firstly, an improved DBO algorithm named CSADBO is proposed by integrating multiple strategies such as chaotic mapping and cooperative search. Secondly, the optimal parameter combination of VMD was adaptively determined through the CSADBO algorithm, and the optimized VMD algorithm was used to perform modal decomposition on the bearing vibration signal. Then, CNN-BiLSTM was used as the model for fault classification, and hyperparameters of the model were optimized using the CSADBO algorithm. (3) Results: Finally, multiple experiments were conducted on the bearing dataset of Case Western Reserve University, and the proposed method achieved an average diagnostic accuracy of 99.6%. (4) Conclusions: Experimental comparisons were made with other models to verify the effectiveness of the proposed model. The experimental results show that the proposed model based on an improved DBO algorithm optimized VMD-CNN-BiLSTM can effectively be used for rolling bearing fault diagnosis, with high diagnostic accuracy, and can provide a theoretical reference for other related fault diagnosis problems. [ABSTRACT FROM AUTHOR]

Changes in the consumption price of aquatic products will affect demand and fishermen's income. The accurate prediction of consumer price index provides important information regarding the aquatic product market. Based on the non-linear and non-smooth characteristics of fishery product price series, this paper innovatively proposes a fishery product price forecasting model that is based on Variational Modal Decomposition and Improved bald eagle search algorithm optimized Long Short Term Memory Network (VMD-IBES-LSTM). Empirical analysis was conducted using fish price data from the Department of Marketing and Informatization of the Ministry of Agriculture and Rural Affairs of China. The proposed model in this study was subsequently compared with common forecasting models such as VMD-LSTM and SSA-LSTM. The research results show that the VMD-IBES-LSTM model that was constructed in this paper has good fitting results and high prediction accuracy, which can better explain the seasonality and trends of the change of China's aquatic product consumer price index, provide a scientific and effective method for relevant management departments and units to predict the aquatic product consumer price, and have a certain reference value for reasonably coping with the fluctuation of China's aquatic product market price. [ABSTRACT FROM AUTHOR]

Many studies indicated that ionospheric total electron content (TEC) prediction is vital for terrestrial and space-based radio-communication systems. In previous TEC prediction schemes based on RNN, they learn TEC representations from previous time steps, and each time-step made an equal contribution to a prediction. To overcome these drawbacks, we propose two improvements in our study: (1) To predict TEC with both past and future time-step, Bidirectional Gate Recurrent Unit (BiGRU) was presented to improve the capabilities. (2) To highlight critical time-step information, attention mechanism was used to provide weights to each time-step. The proposed attentional BiGRU TEC predicting method was evaluated on the publicly available data set from the Centre for Orbit Determination in Europe. We chose three geographical locations in low latitude, middle latitude, and high latitude to verify the performance of our proposed model. Comparative experiments were conducted using Deep Neural Network (DNN), Artificial Neural Network (ANN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Bidirectional Long Short-Term Term memory (BiLSTM), and Gated Recurrent Unit (GRU). Experimental results show that the proposed Attentional BiGRU model is superior to the other models in the selected nine regions. In addition, the paper discussed the effects of latitudes and solar activities on the performance of Attentional BiGRU model. Experimental results show that the higher the latitude, the higher the prediction accuracy of our proposed model. Experimental results also show that in the middle latitude, the prediction accuracy of the model is less affected by solar activity, and in other areas, the model is greatly affected by solar activity. [ABSTRACT FROM AUTHOR]

Sports activities play a crucial role in preserving our health and mind. Due to the rapid growth of sports video repositories, automatized classification has become essential for easy access and retrieval, content-based recommendations, contextual advertising, etc. Traditional Bangladeshi sport is a genre of sports that bears the cultural significance of Bangladesh. Classification of this genre can act as a catalyst in reviving their lost dignity. In this paper, the Deep Learning method is utilized to classify traditional Bangladeshi sports videos by extracting both the spatial and temporal features from the videos. In this regard, a new Traditional Bangladeshi Sports Video (TBSV) dataset is constructed containing five classes: Boli Khela, Kabaddi, Lathi Khela, Kho Kho, and Nouka Baich. A key contribution of this paper is to develop a scratch model by incorporating the two most prominent deep learning algorithms: convolutional neural network (CNN) and long short term memory (LSTM). Moreover, the transfer learning approach with the fine-tuned VGG19 and LSTM is used for TBSV classification. Furthermore, the proposed model is assessed over four challenging datasets: KTH, UCF-11, UCF-101, and UCF Sports. This model outperforms some recent works on these datasets while showing 99% average accuracy on the TBSV dataset. [ABSTRACT FROM AUTHOR]

In this paper, we fabricate an ITO/SiN/TaN memristor device and analyze its electrical characteristics for a neuromorphic system. The device structure and chemical properties are investigated using transmission electron microscopy and X-ray photoelectron spectroscopy. Uniform bipolar switching is achieved through DC sweep under a compliance current of 5 mA. Also, the analog reset phenomenon is observed by modulating the reset voltage for long-term memory. Additionally, short-term memory characteristics are obtained by controlling the strength of the pulse response. Finally, bio-inspired synaptic characteristics are emulated using Hebbian learning rules such as spike-rate-dependent plasticity (SRDP) and spike-timing-dependent plasticity (STDP). As a result, we believe that the coexistence of short-term and long-term memories in the ITO/SiN/TaN device can provide flexibility in device design in future neuromorphic applications. [ABSTRACT FROM AUTHOR]

Question Classification (QC) is the fundamental task for Question Answering Systems (QASs) implementation, and is a vital task, as it helps in identifying the question category. It plays a big role in predicting the answer to a question while building a QAS. However, classifying medical questions is still a challenging task due to the complexity of medical terms. Many researchers have proposed different techniques to solve these problems, but some of these problems remain partially solved or unsolved. With the help of deep learning technology, various text-processing problems have become much easier to solve. In this paper, an improved deep learning-based model for Medical Forum Question Classification (MFQC) is proposed to classify medical questions. In the proposed model, feature representation is performed using Word2Vec, which is a word embedding model. Additionally, the features are extracted from the word embedding layer based on Convolutional Neural Networks (CNNs). Finally, a Bidirectional Long Short Term Memory (BiLSTM) network is used to classify the extracted features. The BiLSTM model analyzes the target information of the representation and then outputs the question category via a SoftMax layer. Our model achieves state-of-the-art performance by effectively capturing semantic and syntactic features from the input questions. We evaluate the proposed CNN-BiLSTM model on two benchmark datasets and compare its performance with existing methods, demonstrating its superiority in accurately categorizing medical forum questions. [ABSTRACT FROM AUTHOR]

The rapid progress of artificial neural networks (ANN) is largely attributed to the development of the rectified linear unit (ReLU) activation function. However, the implementation of software-based ANNs, such as convolutional neural networks (CNN), within the von Neumann architecture faces limitations due to its sequential processing mechanism. To overcome this challenge, research on hardware neuromorphic systems based on spiking neural networks (SNN) has gained significant interest. Artificial synapse, a crucial building block in these systems, has predominantly utilized resistive memory-based memristors. However, the two-terminal structure of memristors presents difficulties in processing feedback signals from the post-synaptic neuron, and without an additional rectifying device it is challenging to prevent sneak current paths. In this paper, we propose a four-terminal synaptic transistor with an asymmetric dual-gate structure as a solution to the limitations of two-terminal memristors. Similar to biological synapses, the proposed device multiplies the presynaptic input signal with stored synaptic weight information and transmits the result to the postsynaptic neuron. Weight modulation is explored through both hot carrier injection (HCI) and Fowler–Nordheim (FN) tunneling. Moreover, we investigate the incorporation of short-term memory properties by adopting polysilicon grain boundaries as temporary storage. It is anticipated that the devised synaptic devices, possessing both short-term and long-term memory characteristics, will enable the implementation of various novel ANN algorithms. [ABSTRACT FROM AUTHOR]

The memristor, characterized by its nano-size, nonvolatility, and continuously adjustable resistance, is a promising candidate for constructing brain-inspired computing. It operates based on ion migration, enabling it to store and retrieve electrical charges. This paper reviews current research on synapses using digital and analog memristors. Synapses based on digital memristors have been utilized to construct positive, zero, and negative weights for artificial neural networks, while synapses based on analog memristors have demonstrated their ability to simulate the essential functions of neural synapses, such as short-term memory (STM), long-term memory (LTM), spike-timing-dependent plasticity (STDP), spike-rate-dependent plasticity (SRDP), and paired-pulse facilitation (PPF). Furthermore, synapses based on analog memristors have shown potential for performing advanced functions such as experiential learning, associative learning, and nonassociative learning. Finally, we highlight some challenges of building large-scale artificial neural networks using memristors. [ABSTRACT FROM AUTHOR]

The amyloid properties of RAD51 imply that aberrant protein-based assemblies could potentially affect DNA lesions, thus providing a possible link between protein-based and DNA-based transmission machineries. The authors highlight the biological functions of amyloids formed by proteins containing -barrel domains and discuss probable pathways of amyloid formation by such proteins. The review critically assesses existing diagnostic techniques and explains how the principles and procedures derived from studying transmissible amyloids could be applied to clinical and pre-clinical detection of amyloids involved in other diseases, such as renal amyloids. While some of cases of amyloid-associated diseases are heritable (that is, derived from DNA mutations), the majority of cases are sporadic, and prion-like transmissibility of protein assemblies has been observed at a cellular level and, in some experimental models, even at the organismal level [[14], [16]]. [Extracted from the article]

This paper introduces a novel technique that uses observation data from GNSS to estimate the ionospheric vertical total electron content (VTEC) using the Kriging–Kalman method. The technique provides a method to validate the accuracy of the Ionospheric VTEC analysis within the Equatorial Ionization anomaly region. The technique developed uses GNSS VTEC alongside solar parameters, such as solar radio flux (F10.7 cm), Disturbance Storm Time (Dst) and other data, and Long Short Term Memory (LSTM) Networks to predict the occurrence time of the ionospheric equatorial anomaly and ionospheric VTEC changes. The LSTM method was applied to GNSS data from Haikou Station. A comparison of this technique with the neural network (NN) model and International Reference Ionosphere model shows that the LSTM outperforms all of them at VTEC estimation and prediction. The results, which are based on the root mean square error (RMSE) between GNSS VTEC and GIM VTEC outside the equatorial anomaly region, was 1.42 TECU, and the results of GNSS VTEC and VTEC from Beidou geostationary orbit satellite, which lies inside the equatorial ionization anomaly region, was 1.92 TECU. The method developed can be used in VTEC prediction and estimation in real time space operations. [ABSTRACT FROM AUTHOR]

Over the last decade, the development of machine-learning models has enabled the design of sophisticated regression models. For this reason, studies have been conducted to design predictive models using machine learning in various industries. In particular, in terms of inventory management, forecasting models predict historical market demand, predict future demand, and enable systematic inventory management. However, in most small and medium enterprise (SMEs), there is no systematic management of data, and because of the lack of data and the volatility of random data, it is difficult for prediction models to work well. Since the predictive model is a core function derived from the management of the enterprise's inventory data, the poor performance of the model causes the company's inventory data-management system to be degraded. Companies that have poor inventory data because of this vicious cycle will continue to have difficulty introducing data-management systems. In this paper, we propose a framework that can reliably predict the inventory data of a firm by modeling the volatility of a firm stochastically. The framework makes the prediction using the point prediction model by means of LSTM(Long Short Term Memory), the 2D kernel density function, and the prediction result reflecting inventory-management cost. Through various experiments, the necessity of interval prediction in demand prediction and the validity of the cost-effective prediction model through the readjustment function were shown. [ABSTRACT FROM AUTHOR]

Edge detection is a highly researched topic in the field of image processing, with numerous methods proposed by previous scholars. Among these, ant colony algorithms have emerged as a promising approach for detecting image edges. These algorithms have demonstrated high efficacy in accurately identifying edges within images. For this paper, due to the long-term memory, nonlocality, and weak singularity of fractional calculus, fractional-order ant colony algorithm combined with fractional differential mask and coefficient of variation (FACAFCV) for image edge detection is proposed. If we set the order of the fractional-order ant colony algorithm and fractional differential mask to v = 0 , the edge detection method we propose becomes an integer-order edge detection method. We conduct experiments on images that are corrupted by multiplicative noise, as well as on an edge detection dataset. Our experimental results demonstrate that our method is able to detect image edges, while also mitigating the impact of multiplicative noise. These results indicate that our method has the potential to be a valuable tool for edge detection in practical applications. [ABSTRACT FROM AUTHOR]

The trend of E-commerce and online shopping is increasing rapidly. However, it is difficult to know about the quality of items from pictures and videos available on the online stores. Therefore, online stores and independent products reviews sites share user reviews about the products for the ease of buyers to find out the best quality products. The proposed work is about measuring and detecting product quality based on consumers' attitude in product reviews. Predicting the quality of a product from customers' reviews is a challenging and novel research area. Natural Language Processing and machine learning methods are popularly employed to identify product quality from customer reviews. Most of the existing research for the product review system has been done using traditional sentiment analysis and opinion mining. Going beyond the constraints of opinion and sentiment, such as a deeper description of the input text, is made possible by utilizing appraisal categories. The main focus of this study is exploiting the quality subcategory of the appraisal framework in order to predict the quality of the product. This paper presents a quality of product-based classification model (named QLeBERT) by combining quality of product-related lexicon, N-grams, Bidirectional Encoder Representations from Transformers (BERT), and Bidirectional Long Short Term Memory (BiLSTM). In the proposed model, the quality of the product-related lexicon, N-grams, and BERT are employed to generate vectors of words from part of the customers' reviews. The main contribution of this work is the preparation of the quality of product-related lexicon dictionary based on an appraisal framework and automatically labelling the data accordingly before using them as the training data in the BiLSTM model. The proposed model is evaluated on an Amazon product reviews dataset. The proposed QLeBERT outperforms the existing state-of-the-art models by achieving an F1macro score of 0.91 in binary classification. [ABSTRACT FROM AUTHOR]

In order to solve the problem of long video dependence and the difficulty of fine-grained feature extraction in the video behavior recognition of personnel sleeping at a security-monitored scene, this paper proposes a time-series convolution-network-based sleeping behavior recognition algorithm suitable for monitoring data. ResNet50 is selected as the backbone network, and the selfattention coding layer is used to extract rich contextual semantic information; then, a segment-level feature fusion module is constructed to enhance the effective transmission of important information in the segment feature sequence on the network, and the long-term memory network is used to model the entire video in the time dimension to improve behavior detection ability. This paper constructs a data set of sleeping behavior under security monitoring, and the two behaviors contain about 2800 single-person target videos. The experimental results show that the detection accuracy of the network model in this paper is significantly improved on the sleeping post data set, up to 6.69% higher than the benchmark network. Compared with other network models, the performance of the algorithm in this paper has improved to different degrees and has good application value. [ABSTRACT FROM AUTHOR]

This paper addresses the problem of achieving lifelong open-ended learning autonomy in robotics, and how different cognitive architectures provide functionalities that support it. To this end, we analyze a set of well-known cognitive architectures in the literature considering the different components they address and how they implement them. Among the main functionalities that are taken as relevant for lifelong open-ended learning autonomy are the fact that architectures must contemplate learning, and the availability of contextual memory systems, motivations or attention. Additionally, we try to establish which of them were actually applied to real robot scenarios. It transpires that in their current form, none of them are completely ready to address this challenge, but some of them do provide some indications on the paths to follow in some of the aspects they contemplate. It can be gleaned that for lifelong open-ended learning autonomy, motivational systems that allow finding domain-dependent goals from general internal drives, contextual long-term memory systems that all allow for associative learning and retrieval of knowledge, and robust learning systems would be the main components required. Nevertheless, other components, such as attention mechanisms or representation management systems, would greatly facilitate operation in complex domains. [ABSTRACT FROM AUTHOR]

Friction is one of important factors that cause contouring errors, and the friction error is difficult to predict because of its nonlinearity. In this paper, a prediction model of the friction error of a servo system is proposed based on the Long Short-Term Memory method (LSTM). Firstly, the transfer function is used to predict the position of the servo system, and then the prediction error of the transfer function is obtained. Secondly, the nonlinear friction error is extracted and predicted by a LSTM network. Finally, the accurate tracking error can be predicted by the proposed combined model. The experimental results show that the proposed model can improve the prediction accuracy of tracking errors dramatically. [ABSTRACT FROM AUTHOR]

Stock price prediction is crucial but also challenging in any trading system in stock markets. Currently, family of recurrent neural networks (RNNs) have been widely used for stock prediction with many successes. However, difficulties still remain to make RNNs more successful in a cluttered stock market. Specifically, RNNs lack power to retrieve discerning features from a clutter of signals in stock information flow. Making it worse, by RNN a single long time cell from the market is often fused into a single feature, losing all the information about time which is essential for temporal stock prediction. To tackle these two issues, we develop in this paper a novel hybrid neural network for price prediction, which is named frequency decomposition induced gate recurrent unit (GRU) transformer, abbreviated to FDGRU-transformer or FDG-trans). Inspired by the success of frequency decomposition, in FDG-transformer we apply empirical model decomposition to decompose the complete ensemble of cluttered data into a trend component plus several informative and independent mode components. Equipped with the decomposition, FDG-transformer has the capacity to extract the discriminative insights from the cluttered signals. To retain the temporal information in the observed cluttered data, FDG-transformer utilizes hybrid neural network of GRU, long short term memory (LSTM) and multi-head attention (MHA) transformers. The integrated transformer network is capable of encoding the impact of different weights from each past time step to the current one, resulting in the establishment of a time series model from a deeper fine-grained level. We appy the developed FDG-transformer model to analyze Limit Order Book data and compare the results with that obtained from other state-of-the-art methods. The comparison shows that our model delivers effective price forecasting. Moreover, an ablation study is conducted to validate the importance and necessity of each component in the proposed model. [ABSTRACT FROM AUTHOR]

Telecommunication networks are growing exponentially due to their significant role in civilization and industry. As a result of this very significant role, diverse applications have been appeared, which require secured links for data transmission. However, Internet-of-Things (IoT) devices are a substantial field that utilizes the wireless communication infrastructure. However, the IoT, besides the diversity of communications, are more vulnerable to attacks due to the physical distribution in real world. Attackers may prevent the services from running or even forward all of the critical data across the network. That is, an Intrusion Detection System (IDS) has to be integrated into the communication networks. In the literature, there are numerous methodologies to implement the IDSs. In this paper, two distinct models are proposed. In the first model, a custom Convolutional Neural Network (CNN) was constructed and combined with Long Short Term Memory (LSTM) deep network layers. The second model was built about the all fully connected layers (dense layers) to construct an Artificial Neural Network (ANN). Thus, the second model, which is a custom of an ANN layers with various dimensions, is proposed. Results were outstanding a compared to the Logistic Regression algorithm (LR), where an accuracy of 97.01% was obtained in the second model and 96.08% in the first model, compared to the LR algorithm, which showed an accuracy of 92.8%. [ABSTRACT FROM AUTHOR]

In recent years, the foreign exchange (FOREX) market has attracted quite a lot of scrutiny from researchers all over the world. Due to its vulnerable characteristics, different types of research have been conducted to accomplish the task of predicting future FOREX currency prices accurately. In this research, we present a comprehensive review of the recent advancements of FOREX currency prediction approaches. Besides, we provide some information about the FOREX market and cryptocurrency market. We wanted to analyze the most recent works in this field and therefore considered only those papers which were published from 2017 to 2019. We used a keyword-based searching technique to filter out popular and relevant research. Moreover, we have applied a selection algorithm to determine which papers to include in this review. Based on our selection criteria, we have reviewed 39 research articles that were published on "Elsevier", "Springer", and "IEEE Xplore" that predicted future FOREX prices within the stipulated time. Our research shows that in recent years, researchers have been interested mostly in neural networks models, pattern-based approaches, and optimization techniques. Our review also shows that many deep learning algorithms, such as gated recurrent unit (GRU) and long short term memory (LSTM), have been fully explored and show huge potential in time series prediction. [ABSTRACT FROM AUTHOR]

For the image super-resolution method from a single channel, it is difficult to achieve both fast convergence and high-quality texture restoration. By mitigating the weaknesses of existing methods, the present paper proposes an image super-resolution algorithm based on dual-channel convolutional neural networks (DCCNN). The novel structure of the network model was divided into a deep channel and a shallow channel. The deep channel was used to extract the detailed texture information from the original image, while the shallow channel was mainly used to recover the overall outline of the original image. Firstly, the residual block was adjusted in the feature extraction stage, and the nonlinear mapping ability of the network was enhanced. The feature mapping dimension was reduced, and the effective features of the image were obtained. In the up-sampling stage, the parameters of the deconvolutional kernel were adjusted, and high-frequency signal loss was decreased. The high-resolution feature space could be rebuilt recursively using long-term and short-term memory blocks during the reconstruction stage, further enhancing the recovery of texture information. Secondly, the convolutional kernel was adjusted in the shallow channel to reduce the parameters, ensuring that the overall outline of the image was restored and that the network converged rapidly. Finally, the dual-channel loss function was jointly optimized to enhance the feature-fitting ability in order to obtain the final high-resolution image output. Using the improved algorithm, the network converged more rapidly, the image edge and texture reconstruction effect were obviously improved, and the Peak Signal-to-Noise Ratio (PSNR) and structural similarity were also superior to those of other solutions. [ABSTRACT FROM AUTHOR]

The air quality prediction is a very important and challenging task, especially PM 2.5 (particles with diameter less than 2.5 μm) concentration prediction. To improve the accuracy of the PM 2.5 concentration prediction, an improved integrated deep neural network method based on attention mechanism is proposed in this paper. Firstly, the influence of exogenous series of other sites on the central site is considered to determine the best relevant site. Secondly, the data of all relevant sites are input into the improved dual-stage two-phase (DSTP) model, then the PM 2.5 prediction result of each site is obtained. Finally, with the PM 2.5 prediction result of each site, the attention-based layer predicts the PM 2.5 concentration at the central site. The experimental results show that the proposed model is superior to most of the latest models. [ABSTRACT FROM AUTHOR]

3D reconstruction is the computer vision task of reconstructing the 3D shape of an object from multiple 2D images. Most existing algorithms for this task are designed for offline settings, producing a single reconstruction from a batch of images taken from diverse viewpoints. Alongside reconstruction accuracy, additional considerations arise when 3D reconstructions are used in real-time processing pipelines for applications such as robot navigation or manipulation. In these cases, an accurate 3D reconstruction is already required while the data gathering is still in progress. In this paper, we demonstrate how existing batch-based reconstruction algorithms lead to suboptimal reconstruction quality when used for online, iterative 3D reconstruction and propose appropriate modifications to the existing Pix2Vox++ architecture. When additional viewpoints become available at a high rate, e.g., from a camera mounted on a drone, selecting the most informative viewpoints is important in order to mitigate long term memory loss and to reduce the computational footprint. We present qualitative and quantitative results on the optimal selection of viewpoints and show that state-of-the-art reconstruction quality is already obtained with elementary selection algorithms. [ABSTRACT FROM AUTHOR]

This paper is concerned with the problem of state estimation of memristor neural networks with model uncertainties. Considering the model uncertainties are composed of time-varying delays, floating parameters and unknown functions, an improved method based on long short term memory neural networks (LSTMs) is used to deal with the model uncertainties. It is proved that the improved LSTMs can approximate any nonlinear model with any error. On this basis, adaptive updating laws of the weights of improved LSTMs are proposed by using Lyapunov method. Furthermore, for the problem of state estimation of memristor neural networks, a new full-order state observer is proposed to achieve the reconstruction of states based on the measurement output of the system. The error of state estimation is proved to be asymptotically stable by using Lyapunov method and linear matrix inequalities. Finally, two numerical examples are given, and simulation results demonstrate the effectiveness of the scheme, especially when the memristor neural networks with model uncertainties. [ABSTRACT FROM AUTHOR]