Search

• MLP, GRU, CNN and MSCNN for landslide susceptibility mapping were compared. • CNN combined with multi-scale technique can improve feature utilization. • The joint evaluation method of ROC curve and PR curve for LSM was proposed. Landslide susceptibility mapping (LSM) can be used to determine the spatial probability of landslide occurrence. There are many methods for LSM, including statistical methods, traditional machine learning methods and deep learning methods, etc. However, the difference comparison of these methods has been not perfect, especially the comparison of different neural network models for LSM and their application prospects were rarely studied. In this paper, the classical neural net-work multi-layer perceptron (MLP), convolutional neural network (CNN), gated recurrent unit (GRU) and multi-scale convolutional neural network (MSCNN) four models are selected for comparison. Taking Lanzhou city, Gansu Province, China as an example, eight landslide-related influencing factors and historical landslide and non-landslide locations were selected, and the training set and validation set were divided according to 7:3. Through training the four models, four landslide susceptibility maps were generated. The experimental results were verified and compared by the confusion matrix, Kappa coefficient, F1-score and other statistical indicators. The receiver operating characteristic (ROC) curve and Precision-Recall (PR) curve were plotted to evaluate the classification effect and generalization capability of four models. The results show that the constructed MSCNN is the optimal model, which has the best performance both in the training process and in the mapping results. MSCNN model has the highest value of Recall (99.93%), Kappa (0.96) and F1-score (0.98) in the confusion matrix. In addition, ROC curve and PR curve of MSCNN model maintain the maximum area under curve (AUC) on different data sets. In the comparison, MLP and GRU accept sequence features, while CNN and MSCNN accept neighborhood features. In general, the prediction model considering neighborhood features contains more information in the limited input data and is better than the prediction model considering sequence features in all evaluation indicators. Therefore, we think that the neighborhood features can better represent the landslide occurrence characteristics. In the future model design process for LSM, more attention should be paid to the neighborhood features of landslide influencing factors. [ABSTRACT FROM AUTHOR]

This paper presents a deep artificial neural network approach based currency market volatility based recommendation engine. Since deep learning classification needs labeled data set that we don't have, an approach is designed specially for that point in order to generate labeled data set from non labeled one. This is a major innovative aspect in this contribution in addition to the recommendation service. It is based on Gaussian kernel density and Monte Carlo simulation. The main goal of the proposed approach is to predict - for each hour of the day - the volatility behaviour of the selected currency pair. The proposed model has a range of applications in financial market specially the algorithmic trading. Deep neural network was trained and evaluated and testing process gave good convergence rate. [ABSTRACT FROM AUTHOR]

The problem addressed in this paper is automatic house price determination using multiple regression models and machine learning. In the practice of real estate appraisal, discussions about automated valuation (AVM) are increasingly common. Resistance to modern machine learning methods stems from a low level of knowledge about these methods and, as a result, an unawareness to what extent and where they can support the classical process of estimating property value. The problem is much broader, because it affects many aspects of the use of machine learning (including neural networks) in the broader real estate market. The process of real estate management at each stage generates huge information resources, which are used at different levels and to different extents by entities operating in the real estate market. One of such professional groups are real estate appraisers, for whom intelligent systems for monitoring the market and providing necessary data are becoming increasingly common and sought after. In this context, a comparative study of two models: multiple regression and neural networks has been carried out. Both methods were used to determine house prices, based on the same set of input data, and in the next step the effects of using these models for an additional group of objects with known characteristics and transaction prices were compared. The multivariate regression model obtained in the study was of medium quality, but sufficient for the purpose of comparative analysis. In the case of neural networks, the highest quality model was not obtained for the study sample, despite normalizing the variables to the required interval (0;1). In both models, the prices for the control sample were overestimated in most cases. However, this does not deny the relevance of further research and attempts to teach neural networks using larger data sets, especially in the case of properties other than typical residential units or land for residential development. Machine learning methods can be extremely useful especially in the processes of general valuation. In these processes, large sets of properties are estimated in a short period of time and with the same methods. [ABSTRACT FROM AUTHOR]

A continuing outbreak of pneumonia-related disease novel, Coronavirus has been recorded worldwide and has become a global health problem. This research aims to generate a constructive training data set for a neural network to detect COVID-19 from X-ray images. The creation of medical images is an issue in the field of deep learning. Medical image datasets are frequently unbalanced; using such datasets to train a deep neural network model to correctly classify medical conditions typically leads to over-fitting the data on majority class samples. Data augmentation is commonly used in training data to expand the dataset. Data augmentation may not be beneficial in medical domains with limited data. This paper proposed a data generation model using a Deep Convolutional Generative adversarial network (DCGAN), which generates fake instances with comparable properties to the original data. The model's Fréchet Distance of Inception (FID) was 23.78, close to the original data. Deep transfer learning-based models VGG-16, Inceptionv3 and MobilNet, were chosen as the backbone for COVID-19 detection. The present study aims to increase the dataset using the DCGAN data augmentation technique to improve classifier performance. [ABSTRACT FROM AUTHOR]

Researchers and practitioners have attempted to predict the financial market by analyzing textual (e.g., news articles and social media) and numeric data (e.g., hourly stock prices, and moving averages). Among textual data, while many papers have been published that analyze social media, news content has gained limited attention in predicting the stock market. Acknowledging that news is critical in predicting the stock market, the focus of this systematic review is on papers investigating machine learning and text mining techniques to predict the stock market using news. Using Kitchenham's methodology, we present a systematic review of the literature on intelligent financial market prediction, examining data mining and machine learning approaches and the employed datasets. From five digital libraries, we identified 61 studies from 2015–2022 for synthesis and interpretation. We present notable gaps and barriers to predicting financial markets, then recommend future research scopes. Various input data, including numerical (stock prices and technical indicators) and textual data (news text and sentiment), have been employed for news-based stock market prediction. News data collection can be costly and time-consuming: most studies have used custom crawlers to gather news articles; however, there are financial news databases available that could significantly facilitate news collection. Furthermore, although most datasets have covered fewer than 100K records, deep learning and more sophisticated artificial neural networks can process enormous datasets faster, improving future model performance. There is a growing trend toward using artificial neural networks, particularly recurrent neural networks and deep learning models, from 2018 to 2021. Furthermore, regression and gradient-boosting models have been developed for stock market prediction during the last four years. Although word embedding approaches for feature representation have been employed recently with good accuracy, emerging language models may be a focus for future research. Advanced natural language processing methods like transformers have undeniably contributed to intelligent stock market prediction. However, stock market prediction has not yet taken full advantage of them. • Emerging articles (2015–2021) on news-based stock market prediction are reviewed. • There is a growing trend toward using news headlines for stock market prediction. • Recurrent neural networks are advantageous models for stock market prediction. • Stock market prediction not fully took advantage of Natural language processing yet. • Quarterly and annual reports of companies are authorized credible data sources. [ABSTRACT FROM AUTHOR]

Predicting the location of parking is a long-lasting problem that has ultimate importance in our daily life. In this paper, artificial neural networks are used to predict the parking location that will be helpful for drivers to settle on a reasonable area for stopping. This approach eventually adds to the familiarity and wellbeing of traffic on the roads which results in a decrease in turbulence. By using the approach of Deep Extreme Learning Machine (DELM), reliability can be achieved with a marginal error rate thus reducing the skeptical inclination. In this article, the Proposed Car Parking Space Prediction (CPSP) to elaborate on the dilemma of parking space for vehicles, we have used deep learning neural networks in contrast with feedforward and backward propagation. When the results were taken into consideration, it was unveiled that extreme deep machine learning neural network bears the highest accuracy rate with 60% of training (21431 samples), 40% of test and validation (14287 examples). It has been observed that the proposed DELM has the highest precision rate of 91.25%. Simulation results validate the prediction effectiveness of the proposed DELM strategy. [ABSTRACT FROM AUTHOR]

In view of most current studies on text sentiment classification focus on the deep learning model to obtain the sentimental characteristics of English text. Chinese text sentiment analysis is rarely involved, and only the context information of the statement is considered, but the syntax information of the statement is rarely considered. In this paper, a novel sentiment classification model is proposed (Dependency Tree Graph Convolutional Network, DTGCN) combined Chinese syntactically dependent tree with graph convolution. Firstly, the Bi-GRU (Bi-directional Gated Recurrent Unit) model is used to learn the contextual feature representation of a given text. Secondly, the syntax-dependent tree structure of a given text is constructed, then obtain its adjacency matrix according to the syntax-dependent tree, with the initial features extracted from the bidirectional gate control network, input into the graph convolutional neural network (GCN) to extract the sentimental features of the text; the obtained sentimental characteristics are then input into the classifier SoftMax for text sentimental polarity classification. Finally, the data set is compared with the mainstream neural network model. The experimental results show that the accuracy of the proposed DTGCN model proposed on the data set is 90.51% and the recall rate is 90.34%. Compared with the benchmark models (LSTM, CNN, TextCNN and Bi-GRU), the proposed DTGCN model shows a 4.45% advantage in accuracy. It shows that the proposed DTGCN model can effectively use the grammatical information of Chinese text to mine the hidden relationship in statements, it can improve the accuracy of Chinese text sentiment classification. In addition, the proposed DTGCN model not only improves the performance of sentiment classification in the essay, it also provides a new research method for social network public opinion identification. [ABSTRACT FROM AUTHOR]

Surface reconstruction is a fundamental problem in 3D graphics. In this paper, we propose a learning-based approach for implicit surface reconstruction from raw point clouds without normals. Our method is inspired by Gauss Lemma in potential energy theory, which gives an explicit integral formula for the indicator functions. We design a novel deep neural network to perform surface integral and learn the modified indicator functions from un-oriented and noisy point clouds. We concatenate features with different scales for accurate point-wise contributions to the integral. Moreover, we propose a novel Surface Element Feature Extractor to learn local shape properties. Experiments show that our method generates smooth surfaces with high normal consistency from point clouds with different noise scales and achieves state-of-the-art reconstruction performance compared with current data-driven and non-data-driven approaches. [Display omitted] • A learning-based approach for surface reconstruction from raw point clouds. • A novel Surface Element Feature Extractor to learn local shape properties. • Aggregating the point-wise contributions of Gauss Lemma in the network. • Generating smooth surfaces with high normal consistency. [ABSTRACT FROM AUTHOR]

Network representation learning based on graph auto-encoder has been the mainstream technique for learning embeddings in low-dimensional space. Graph auto-encoders learn the network representations by minimizing the loss between the generated and actual samples. However, limited information on the contextual structure of nodes is captured during the generation of samples. Furthermore, the dimensionality of the features is altered in the process of feature aggregation, resulting in impaired feature information in the network. In order to solve these two problems, normalized auto-encoder based on biased walk for network representation learning is proposed. This model can combine the advantages of shallow neural network and deep neural network to solve these two problems, and contains two key design components. One is the biased walk regularization module, a regularization term of shallow neural network, which captured broader and deeper context structure information of nodes. The other is the normalized regularization module of features, a regularization term of deep neural network, which smoothed the feature difference of nodes, and thus improved the feature information aggregation capability of convolution layer. This paper conducted experiments on three datasets Cora, CiteSeer and PubMed and compared them with other state-of-the-art network representation learning models. The results show that the proposed model can improve the link prediction results by 0.7% on AUC and 0.9% on AP to the state-of-the-art algorithms. In addition, the ablation experiments are conducted for two key design components, which can demonstrate the necessity of the proposed two regularization terms. [Display omitted] • A novel network representation learning model on graph auto-encoder is proposed. • The biased walk regularization module learns a wider range of contextual structural information. • The normalized regularization module improves the feature information aggregation capability. [ABSTRACT FROM AUTHOR]

• Soil reflectance composites were generated with Sentinel-2 L2A data. • A multi-channel CNN learning framework for soil organic carbon prediction is proposed. • A dual input deep learning architecture improves the predictions. • The framework produced results that can be interpreted. The Copernicus Sentinel-2 multispectral imagery data may be aggregated to extract large-scale, bare soil, reflectance composites, which enable soil mapping applications. In this paper, this approach was tested in the German federal state of Bavaria, to provide estimations for soil organic carbon (SOC). Different temporal ranges were considered for the generation of the composites, including multi-annual and seasonal ranges. A novel multi-channel convolutional neural network (CNN) is proposed. By leveraging the advantages of deep learning techniques, it utilizes complementary information from different spectral pre-treatment techniques. The SOC predictions indicated little dissimilarity amongst the different composites, with the best performance attained for the six-year composite containing only spring months (RMSE = 12.03 g C · kg−1, R2 = 0.64, RPIQ = 0.89). It has been demonstrated that these outcomes outperform other well-known machine learning techniques. An ablation analysis was accordingly performed to evaluate the interplay of the CNN's different components to disentangle the advantages of each aspect of the proposed framework. Finally, a DUal inPut deep LearnIng architecture, named DUPLICITE, is proposed, which concatenates deep spectral features derived from the CNN mentioned earlier, as well as topographical and environmental covariates through an artificial neural network (ANN) to exploit their complementarity. The proposed approach was demonstrated to provide an improvement in the overall prediction performance (RMSE = 11.60 gC · kg−1, R2 = 0.67, RPIQ = 0.92). [ABSTRACT FROM AUTHOR]

Accurate forecasting of regional solar photovoltaic power (SPVP) generation is essential for efficient energy management and planning. Existing approaches have shown the effectiveness of decomposing the time series to model the stochastic variability in SPVP data. However, these approaches have limitations in extracting and exploiting both spatial and temporal information from complex and high-dimensional data from multiple sources with intricate relationships, which can impact the accuracy of predictions. In this paper, we propose a novel approach called multilevel data fusion and neural basis expansion analysis (MF-NBEA) for forecasting aggregated regional-level SPVP generation. MF-NBEA integrates exogenous data at multiple levels, uses supervised and unsupervised encoders to provide compact data representation, and enhances model learning from complex data by incorporating spatial information. It also includes a sequence analyser module based on a neural network decomposition mechanism to learn the variability in data and incorporates a residuals learner module to improve overall predictions. We evaluate MF-NBEA using two real-world datasets and find that it outperforms state-of-the-art deep learning methods in terms of forecast accuracy. Furthermore, MF-NBEA facilitates information fusion and knowledge extraction to provide interpretable predictions regarding trend, seasonality, and residual components. The insights gained from our approach inform decision-making for energy management and planning, and can lead to more efficient and sustainable resource utilisation. • MF-NBEA for multivariate solar power time series forecasting. • A 3D autoencoder encodes spatial and temporal information from heterogeneous sources. • Interpretable forecasting in terms of trend, seasonality, and residuals. [ABSTRACT FROM AUTHOR]

This paper presents an effective and accurate method to analyze the network traffic risk of enterprise public cloud financial system by using deep learning algorithm. To build the analytical model, the collected data is preprocessed to extract relevant features that contribute to risk analysis. The pre-processed data is used to train the deep learning model. The model is designed to learn patterns and relationships in network traffic data. The network traffic risk analysis module is constructed by combining the deep learning model with the system architecture of the enterprise public cloud financial system. Through a trained deep learning model, the module is able to accurately identify abnormal behavior in network traffic and provide corresponding risk assessments. The results show that the proposed system module can accurately identify abnormal behavior in network traffic and provide risk assessment. [ABSTRACT FROM AUTHOR]

The rapid growth of online music education has led to increased security risks from cyber intrusions. This paper proposes public cloud networks oriented deep neural networks for effective intrusion detection in online music education environments. Specifically, a novel intrusion detection framework is developed, comprising fuzzy logic based feature selection, chronological salp swarm algorithm optimized deep belief networks, and gated recurrent unit integrated convolutional neural networks. Detailed methodologies are presented for the fuzzy logic system, chronological salp optimization, deep belief network architecture, and convolutional neural networks. Comprehensive experiments are conducted on the NSL-KDD and CICIDS2017 datasets. Various deep neural networks are evaluated and compared, including multi-layer perceptrons, convolutional neural networks, deep belief networks, recurrent neural networks, and the proposed models. Experimental results demonstrate that the proposed fuzzy feature selection and chronological salp swarm algorithm optimized deep belief network achieves a test accuracy of 97.33 %, outperforming other peer models. The gated recurrent unit integrated convolutional neural network obtains a test accuracy of 98.46 %, superior to state-of-the-art methods. While the experiments on the newly created dataset for intrusion detection in cloud-based online music education demonstrate that the proposed models outperform the benchmarks. The experiments verify the effectiveness of the proposed deep learning frameworks for intrusion detection in online music education cloud networks. [ABSTRACT FROM AUTHOR]

The enhanced answer evaluation system is a cutting-edge automated tool that evaluates subjective answers in various contexts, such as educational assessments, surveys, and feedback forms. The proposed system leverages Natural Language Processing (NLP) and deep learning techniques to analyse subjective answers and provide evaluation scores with precision. Students' answers are evaluated based on various criteria, such as keywords, context, relevance, coherence, and similarity. This paper introduces an architecture for a subjective answer evaluator using three main aspects: detection of keywords, similarity matrix, and presence of named entities. It combines the three aspects and provides a final score. It provides a standardized mechanism to score a given user answer compared to the particular model answer without human prejudice. This research aims to transcend traditional methodologies that predominantly utilize keyword or keyphrase scoring (text-based similarity) to determine the final score of an answer without delving into its technical intricacies. The semantic similarity (vector-based) employs vector data representations for score calculation. This approach necessitates partitioning data into multiple vectors for a comprehensive analysis. While text similarity is effective for short answers, its efficacy diminishes as the length of the answer increases. Therefore, this study emphasizes the critical role of similarity scoring and Named Entity Recognition (NER) scoring in evaluating more extended responses based on the stsb-en-main dataset (short answers) and a custom dataset with 190 records. This research reveals its remarkable performance, which excels through a dynamic three-pronged approach: keyword scoring, semantic similarity, and NER scoring with models like Yet Another Keyword Extractor (YAKE), SimCSE and Camembert. These three independent components synergize to produce unmatched results, establishing a new standard in the field. This enhancement led to Root Mean Square Error (RMSE) scores of 0.031 (optimized error rate) and an impressive 71%+ accuracy for our comprehensive system. This achievement surpasses existing works, which typically reached accuracies ranging between 40%–60% for long answers. • Evaluation using a three-pronged approach of Keyword, Semantic & NER scoring. • Semantic scores enhance similarity matrix grading and impact evaluation. • NER scores address proper noun issues. • Deep Neural Network predicts actual marks effectively. • The best-performing LLM models are YAKE, SimCSE and Camembert. [ABSTRACT FROM AUTHOR]

The state-of-the-art performance on entity disambiguation has been reached by deep neural networks. However, the task remains very challenging due to the complexity of natural language. Moreover, the target data distribution is often different from that of training data. In this paper, we address the limitation of deep entity disambiguation from the perspective of misprediction risk. We propose a knowledge-based approach of risk analysis for entity disambiguation, and leverage it to enable adaptive deep learning. The proposed approach generates risk features by extracting evidences from the knowledge base, and then models them as a linearly-weighted random vector where an attention mechanism is used to focus on the most significant components. Finally, it estimates misprediction risk of the aggregated probability distribution via the Conditional Value-at-Risk metric. Furthermore, we demonstrate how to utilize risk analysis results in adaptive deep learning via two-phase training, the first phase fits on labeled training data while the second one minimizes misprediction risk on unlabeled target data. We evaluate the performance of the proposed approach on benchmark datasets through a comparative study. Our thorough experiments demonstrate that it can detect mispredictions more accurately than existing alternatives and can substantially improve the performance of deep learning models. [ABSTRACT FROM AUTHOR]

Simulation-driven structural health monitoring (SHM) is crucial for enhancing the safety and reliability of structures. Its primary aim is to utilize numerical simulations to design efficient SHM systems, reducing costs while maintaining effectiveness. However, challenges arise due to disparities between simulations and physical measurements, stemming from uncertainties, noise, and simplifications. These challenges also extend to SHM methods using machine learning, particularly deep neural networks (DNNs). This paper bridges the gap between DNNs trained on simulated data and real-world experiments by investigating three transfer learning (TL) techniques: feature augmentation, direct fine-tuning, and boosting-based fine-tuning. The focus is on guided wave damage interaction coefficients (WDICs) as damage-sensitive features, modeled by DNNs for damage identification in thin plates, commonly found in aerospace structures like aircraft fuselages. This classification task compares measured and predicted WDICs in a common guided wave SHM configuration with one actuator and three sensors. Training and extensive testing datasets are generated using advanced finite element simulations and laser Doppler vibrometer experiments. The study demonstrates that TL techniques significantly enhance DNN prediction accuracy and improve damage identification performance for untrained scenarios compared to purely simulation-based DNNs. Among the TL approaches explored, feature augmentation with appropriate activation functions and boosting-based fine-tuning yield the most promising results. Using four out of twelve TL datasets, feature augmentation reduces the simulation-based mean absolute percentage error from 46.80% to 35.98% and increases coefficient of determination R 2 values from 0.02 to 0.72. With six TL datasets and a boosting-based fine tuning, the mean absolute percentage error decreases from 47.42% to 35.20%, maintaining similar R 2 values. While TL substantially enhances prediction accuracy, its impact on damage identification is slightly less pronounced, with improvements in relative classification accuracy by approximately 5% compared to simulation-based DNNs. These findings highlight the efficacy of TL techniques for damage identification in thin plates using WDICs and DNNs, emphasizing the influence of TL training and DNN model variations. Furthermore, they showcase the potential of TL methods to enhance DNN performance in future SHM applications, particularly emphasizing the promise of feature augmentation and boosting. • Novel simulation-driven structural health monitoring technique using guided waves. • Deep neural network modeling to predict wave damage interaction coefficients. • Bridging disparity between simulations and experiments through transfer learning. • Study of transfer learning techniques based on feature augmentation and fine tuning. • Demonstrated significant enhancement in simulation-based neural network performance. [ABSTRACT FROM AUTHOR]

Accurate and automatic segmentation of individual cell instances in microscopy images is a vital step for quantifying the cellular attributes, which can subsequently lead to new discoveries in biomedical research. In recent years, data-driven deep learning techniques have shown promising results in this task. Despite the success of these techniques, many fail to accurately segment cells in microscopy images with high cell density and low signal-to-noise ratio. In this paper, we propose a novel 3D cell segmentation approach DeepSeeded, a cascaded deep learning architecture that estimates seeds for a classical seeded watershed segmentation. The cascaded architecture enhances the cell interior and border information using Euclidean distance transforms and detects the cell seeds by performing voxel-wise classification. The data-driven seed estimation process proposed here allows segmenting touching cell instances from a dense, intensity-inhomogeneous microscopy image volume. We demonstrate the performance of the proposed method in segmenting 3D microscopy images of a particularly dense cell population called bacterial biofilms. Experimental results on synthetic and two real biofilm datasets suggest that the proposed method leads to superior segmentation results when compared to state-of-the-art deep learning methods and a classical method. • Data-driven seed estimation of a classical seeded watershed for 3D dense cell segmentation. • Enhancement of cell interior and border voxels by predicting Euclidean distance transforms using deep learning. • Multi-scale structural similarity index measure (MS-SSIM) loss for image-to- image mapping with better quality output. • Localization of cell seeds by performing voxel-wise classification using a deep network. [ABSTRACT FROM AUTHOR]

Hardware Trojans (HT) are the most malicious components attacking modern integrated circuits (ICs). Information leakage, incorrect functionality, and overheating are the major effects of HT insertion. Due to the outsourcing of multi-stage digital circuit design and fabrication, HTs can be inserted by rogues at every stage. The types of HTs and insertion methods evolve continuously and their detection becomes more complex. Consequently, designing integrated circuits robust to HT insertion seems efficient. A prerequisite for such a strategy is the evaluation of integrated circuit vulnerability to HT insertion. There are several factors involved in the vulnerability of fabricated integrated circuits such as the distribution of white spaces in the IC layout, the ratio of unutilized routing resources, the amount of activity of the circuit's nodes, the geometrical properties of the circuit's gates, the delay of various paths, and etc. The interrelation of these diverse factors makes IC vulnerability modeling a challenging problem. In this paper, a deep neural network (DNN) based approach is developed to combine all the effective factors in IC vulnerability analysis. Firstly, we generate a comprehensive dataset containing various types and sizes of hardware Trojans inserted into benchmark circuits. The benchmark circuits used in this study are ISCAS 85, ISCAS 89, and ITC 99. Then using the transfer learning concept seven state-of-the-art deep convolutional neural networks are trained and verified using the constructed dataset to classify every integrated circuit into three vulnerability levels (low, moderate, and highly vulnerable classes). Simulation results show that our proposed method achieves almost 95 % accuracy in the most successful case (VGG16). The lowest accuracy belongs to Inception V3 (∼87.65 %) which is much better than the most successful previous studies (72 %). This is mainly because the DNN-based method handles shortcomings (such as incomplete modeling of vulnerability-related factors) in the previous state-of-the-art methods efficiently. [ABSTRACT FROM AUTHOR]

Most image inpainting algorithms have problems such as fuzzy images, texture distortion and semantic inaccuracy, and the image inpainting effect is limited when processing photos with large missing sections and resolution levels. The paper proposes an effective image inpainting algorithm via partial multi-scale channel attention mechanism and deep neural networks to address the above phenomenon that existing image inpainting methods using deep learning modules have insufficient perception and representation capabilities for multi-scale features with high proportion of irregular defects. Initially, we used the Res-U-Net module as a generator. The U-Net-like backbone network topology can achieve the encoding and decoding stages of damaged images. Secondly, the residual network structure was built in the encoder and decoder to improve the ability of the proposed network to extract and display the features of the damaged images. Finally, the partial multi-scale channel attention module was inserted in the skip connection with the decoder to increase the efficiency of using the low-level features of the original images. The experimental results of the research can show that the proposed method outperforms state-of-the-art methods in terms of subjective visual perception and objective evaluation indicators on the CelebA , Places2 and Paris Street View datasets. • The model has improved the ability to extract and express multi-scale features. • The method had included partial multi-scale channel attention and residual network. • The backbone network structure can realize encoding and decoding stage. • The structure of residual networks had constructed to enhance the abilities. [ABSTRACT FROM AUTHOR]

Online social networks can be used for mental healthcare monitoring using Artificial Intelligence and Machine Learning techniques for detecting various mental health disorders and corresponding risk assessment. Recent research in this domain has primarily been focused on leveraging deep neural networks and various Transformer based Large Language Models, which have now become state-of-the-art for most natural language processing and computational linguistic tasks due to their unmatched prediction accuracy. Unlike conventional machine learning algorithms, these deep neural networks are black box architectures, where it is difficult to interpret and explain their predicted outcome. However, a black box classification outcome is insufficient for healthcare applications. Such systems will not be widely adopted and trusted by healthcare practitioners if they are not able to understand and explain the reasoning behind the predicted decisions made by an AI and ML based healthcare diagnostic system. The key objective of our research is to demonstrate the applications of model agnostic, post hoc surrogate XAI techniques for providing explainability to classification decisions of pretrained LLMs (Transformers) based mental healthcare diagnostic systems fine-tuned (or trained) to detect depressive and suicidal behavior using UGC from online social networks. For this, we have used the two most recent and popular techniques, SHAP and LIME. We have conducted extensive and in-depth experiments with four datasets and six pretrained LLMs, three of which have already been domain-adapted using mental health related datasets. We have also performed Few Shot Learning experiments with these three pretrained mental health domain-adapted LLMs. The results of qualitative and descriptive data analysis in this paper demonstrate that in order to build a comprehensive understanding of a person's psychological state, emotion, and behavior and to discover the causes, symptoms, and triggers of mental health issues, it is essential to utilize e X pl AI nable (XAI) techniques with Transformer based LLMs (supervised). Alternatively, Transformer based unsupervised topic modeling technique BERTopic may be used for mental health risk monitoring and cause or symptom extraction when supervised training of LLMs is not feasible due to dataset annotation or availability challenges. [ABSTRACT FROM AUTHOR]

This paper presents a plan for preparing for changes in the business environment by analyzing and predicting business district data in Seoul. The COVID-19 pandemic and economic crisis caused by inflation have led to an increase in store closures and a decrease in sales, which has had a significant impact on commercial districts. The number of stores and sales are critical factors that directly affect the business environment and can help prepare for changes. This study conducted correlation analysis to extract factors related to the commercial district's environment in Seoul and estimated the number of stores and sales based on these factors. Using the Kendaltau correlation coefficient, the study found that existing population and working population were the most influential factors. Linear regression, tensor decomposition, Factorization Machine, and deep neural network models were used to estimate the number of stores and sales, with the deep neural network model showing the best performance in RMSE and evaluation indicators. This study also predicted the number of stores and sales of the service industry in a specific area using the population prediction results of the neural prophet model. The study's findings can help identify commercial district information and predict the number of stores and sales based on location, industry, and influencing factors, contributing to the revitalization of commercial districts. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs) can result in suboptimal monitoring performance due to nonlinearity, dynamics, and local characteristics in modern complex industrial processes. To surmount these limitations, this paper first proposes a novel data construction method to model the short-term autocorrelation and spatial correlations as a three-dimensional matrix and then reorder the elements of it to better encode the local and temporal structures. Subsequently, we design a new structure called Long-range Discriminative Attention (LDA) based on the self-attention mechanism to enlarge the receptive field of the original convolutional neural networks (CNNs) to extract global features. Finally, we propose a monitoring model named Long-range Discriminative Attention Autoencoder (LDCA) based on LDA to extract structural features between long-range and local variables from the constructed matrix. The effectiveness of the method in fault detection is verified by numerical examples and a three-phase flow process. • Model the spatiotemporal correlation into a three-dimensional tensor. • Reorder elements in data tensor to present the meaning of images. • Long-range discriminative attention mechanism for feature extraction. [ABSTRACT FROM AUTHOR]

Multimodal learning has gained significant attention in recent years for combining information from different modalities using Deep Neural Networks (DNNs). However, existing approaches often overlook the varying importance of modalities and neglect uncertainty estimation, leading to limited generalization and unreliable predictions. In this paper, we propose a novel algorithm, Dual-level Deep Evidential Fusion (DDEF), to address these challenges by integrating multimodal information at both the Basic Belief Assignment (BBA) level and multimodal level, for enhancing accuracy, robustness, and reliability. The proposed DDEF approach utilizes the Dirichlet framework and BBA methods to connect neural network outputs with Dirichlet distribution parameters, enabling effective uncertainty estimation, and the Dempster-Shafer Theory (DST) is used for dual-level fusion, facilitating the fusion of evidence from two BBA methods and multiple modalities. It has been validated by two experiments on synthetic digit classification, and real-world medical prognosis after brain–computer interface (BCI) treatment, and by demonstrating superior performance compared to existing methods. Our findings emphasize the importance of considering multimodal integration and uncertainty estimation for reliable decision-making in deep learning. • We propose a novel dual-level fused evidential deep learning model. • The dual levels encompass basic belief assignment and multimodal aspects. • The model adeptly employs the Dempster–Shafer theory for information integration. • Our approach demonstrates enhanced accuracy and reliability in decision-making. • Evidence stems from theoretical analysis, numerical instances, and empirical experiments. [ABSTRACT FROM AUTHOR]

Robustness has become an important consideration in deep learning. With the help of explainable AI, mismatches between an explained model's decision strategy and the user's domain knowledge (e.g. Clever Hans effects) have been identified as a starting point for improving faulty models. However, it is less clear what to do when the user and the explanation agree. In this paper, we demonstrate that acceptance of explanations by the user is not a guarantee for a machine learning model to be robust against Clever Hans effects, which may remain undetected. Such hidden flaws of the model can nevertheless be mitigated, and we demonstrate this by contributing a new method, Explanation-Guided Exposure Minimization (EGEM), that preemptively prunes variations in the ML model that have not been the subject of positive explanation feedback. Experiments demonstrate that our approach leads to models that strongly reduce their reliance on hidden Clever Hans strategies, and consequently achieve higher accuracy on new data. • Explainable AI may not detect all Clever Hans effects in practical ML scenarios. • Hidden Clever Hans effects can be mitigated using Exposure Minimization. • We propose a solution in the form of a soft-pruning scheme on network activations. • We demonstrate the practical benefits of our approach on image and text data. [ABSTRACT FROM AUTHOR]

[Display omitted] • The proposed system solves a high-dimensional problem by reconstructing a 3D domain in a series of timesteps. • Average stiffness properties of the predicted 3D unit cell were within 10% error margin. • Different neural network architectures were explored demonstrating the validity of the proposed approach. • The variety of possible neural networks makes the proposed approach available to setups with lesser computational resources. • The prediction speed was higher in comparison with conventional approaches allowing to explore various weaving architectures. In this paper, a deep learning approach to 3D textile geometry simulations is presented. Two different network architectures with convolutional and recurrent properties are explored. The deep neural networks were trained to generate a fully compacted 3D textile unit cell based on the weave initial architecture. The AI training was conducted on a set of precomputed weaving case studies generated by digital element based weaving simulation software. The proposed strategy demonstrated effectiveness in estimation of 3D textile architectures. The designed system was able to operate within 10% error for stiffness properties prediction. The main benefit of the proposed approach over conventional modelling is its computational efficiency. Rapid weaving simulations provide an opportunity to explore the effects of different yarn architectures, matrix materials, and manufacturing techniques on the mechanical properties of woven composites, leading to a better understanding of their behaviour and their potential for use in new applications. [ABSTRACT FROM AUTHOR]

Digital whole slides images contain an enormous amount of information providing a strong motivation for the development of automated image analysis tools. Particularly deep neural networks show high potential with respect to various tasks in the field of digital pathology. However, a limitation is given by the fact that typical deep learning algorithms require (manual) annotations in addition to the large amounts of image data, to enable effective training. Multiple instance learning exhibits a powerful tool for training deep neural networks in a scenario without fully annotated data. These methods are particularly effective in the domain of digital pathology, due to the fact that labels for whole slide images are often captured routinely, whereas labels for patches, regions, or pixels are not. This potential resulted in a considerable number of publications, with the vast majority published in the last four years. Besides the availability of digitized data and a high motivation from the medical perspective, the availability of powerful graphics processing units exhibits an accelerator in this field. In this paper, we provide an overview of widely and effectively used concepts of (deep) multiple instance learning approaches and recent advancements. We also critically discuss remaining challenges as well as future potential. • A review of publications on multiple instance learning in digital pathology. • Due to a strong increase since 2019, we strongly focus on the last three years. • We structured according to the technically innovative building blocks. • We provide a discussion including future potential and limitations. [ABSTRACT FROM AUTHOR]

Modern-day digitalization has a profound impact on business and society, revolutionizing logistics. Supply chain digitalization improves transparency, speed, and cost-effectiveness, increasing tech adoption—transportation benefits from IoT-driven shipment tracking and web data storage. However, cyber threats target IoT data by exploiting cyber vulnerabilities. Although ML/DL approaches have showed potential in finding IoT vulnerabilities, the difficulty of selecting appropriate features remains. Existing research has produced surprising outcomes, and deep neural networks have been utilised to extract characteristics without taking sequence information into account. To address this, the paper presents a unique approach for accurate IoT vulnerability identification that combines deep learning and better feature selection. On the BoT-IoT dataset, the LSTM + CNN model achieved 95.73 % accuracy. This approach has the ability to successfully anticipate IoT based vulnerabilities by leveraging benchmark data, selecting relevant features, and enhancing overall system performance. [ABSTRACT FROM AUTHOR]

Traditional high-dimensional electroencephalography (EEG) features (spectral or temporal) may not always attain satisfactory results in cognitive workload estimation. In contrast, deep representation learning (DRL) transforms high-dimensional data into cluster-friendly low-dimensional feature space. Therefore, this paper proposes an Integrated Spatio-Temporal Deep Clustering (ISTDC) model that uses DRL followed by a clustering method to achieve better clustering performance. The proposed model is illustrated using four Algorithms and Variational Bayesian Gaussian Mixture Model (VBGMM) clustering method. Temporal and spatial Variational Auto Encoder (VAE) models (mentioned in Algorithm 2 and Algorithm 3) learn temporal and spatial latent features from sequence-wise EEG signals and scalp topographical maps using the Long short-term memory and Convolutional Neural Network models. The concatenated spatio-temporal latent feature (mentioned in Algorithm 4) is passed to the VBGMM clustering method to efficiently estimate workload levels of n -back task. For the 0-back vs. 2-back task, the proposed model achieves the maximum mean clustering accuracy of 98.0%, and it improves by 11.0% over the state-of-the-art method. The results also indicate that the proposed multimodal approach outperforms temporal and spatial latent feature-based unimodal models in workload assessment. [ABSTRACT FROM AUTHOR]

The camera traps have revolutionized the image and video capture in ecology and are often used to monitor and record animal presence. With miniaturization of low power electronic devices, better battery technologies, and software advancements, it has become possible to use the edge devices, such as Raspberry Pi as camera traps that can not only capture images and videos, but can also enable sophisticated image processing, and off-site communications. These developments can help to provide near real-time insights and reduce the manual processing of images. The on-board image classification and visualization is facilitated by the advancements in the Deep Neural Networks (DNN), transfer learning approaches, and software libraries. This paper provides an investigation of image classification with transfer learning approaches using pre-trained DNN models, and visualizations with Explainable Artificial Intelligence (XAI) techniques on Raspberry Pi Zero (RPi-Z) edge device. The MobileNetV2 model was used for image classification on the Florida-Part1 dataset obtaining the results for precision, recall, and F1-score as 0.95, 0.96, and 0.95 respectively. We also compared the model performance of MobileNetV2, EfficientNetV2B0, and MobileViT models for classification on the Extinction dataset with the best results for precision, recall, and F1-score as 0.97, 0.96, and 0.96 respectively, obtained with the EfficientNetV2B0 model. Two XAI techniques, Gradient-weighted-Class Activation Mapping (Grad-CAM) and Occlusion Sensitivity were used for visualization through heatmaps, to highlight the relative importance of the image areas contributing to the DNN model's prediction, that can also help to understand the model's performance and bias. The results provide practical use case scenarios for utilizing the transfer learning approaches, model optimization and deployment to edge devices, and model visualizations in ecological research. • Animal image classification with fine tuning of the Deep Neural Network (DNN) models. • Visualization of the classification results with Explainable Artificial Intelligence (XAI) techniques. • Prototype design and testing of a solar-powered camera trap with on-board image classification and visualization. • Performance comparison of state-of-the-art models with hyperparameter tuning. [ABSTRACT FROM AUTHOR]

Classification of ECG signals plays an important role in the field of medical diagnosis. Despite that much progress has been made in ECG classification in recent years, most of them focus on single-lead cardiac feature extraction. In this paper, we propose a new classification method based on twelve-lead surface ECG signal by fusing improved hand-crafted ECG features and deep learning classifiers for paroxysmal atrial fibrillation (PAF) detection. Three-dimensional dominated components are extracted without ECG signal segmentation operations, and continuous wavelet transform (CWT) is adopted for time–frequency representation to reflect essential characteristics of multi-resolution frequency domain at different scales. This kind of time–frequency representation has high discriminative power to detect PAF even before pathologic changes in surface twelve-lead ECG signals. Five pre-trained deep neural networks models are used to perform transfer learning and feature fusion. ECG signals are finally classified by using a feature fusion method based on multiple deep networks. • Hand-crafted ECG features and deep learning techniques are combined. • New time–frequency representation is proposed to detect PAF. • The proposed method can detect PAF before pathologic changes in ECGs. • Five pre-trained deep models are used to perform transfer learning. [ABSTRACT FROM AUTHOR]

Driver behavior is an essential factor affecting traffic safety, and driver behavior monitoring systems (DMSs) are widely exploited in intelligent transportation systems to reduce the risk of traffic accidents. However, understanding driver behavior is challenging because of the uncertainty of real driving scenarios. Most of the existing methods use deterministic models, which suffer from data uncertainty, for recognizing driver behaviors. In this paper, the fuzzy deep attention network (FDAN) method is proposed to improve driver behavior recognition. FDAN integrates fuzzy logic and an attention mechanism into deep neural networks, which enhances the representation ability of the model and reduces the uncertainty of the data. The attention mechanism with a lightweight squeeze-and-excitation block is embedded in the deep learning model for adaptively refining features. A DMS is designed, and the distracted driver dataset from the real scene is built. Experimental results confirm the proposed method performs better than the existing methods. [ABSTRACT FROM AUTHOR]

Establishing reliable correspondences by a deep neural network is an important task in computer vision, and it generally requires permutation-equivariant architecture and rich contextual information. In this paper, we design a Permutation-Equivariant Split Attention Network (called PESA-Net), to gather rich contextual information for the feature matching task. Specifically, we propose a novel "Split–Squeeze–Excitation–Union" (SSEU) module. The SSEU module not only generates multiple paths to exploit the geometrical context of putative correspondences from different aspects, but also adaptively captures channel-wise global information by explicitly modeling the interdependencies between the channels of features. In addition, we further construct a block by fusing the SSEU module, Multi-Layer Perceptron and some normalizations. The proposed PESA-Net is able to effectively infer the probabilities of correspondences being inliers or outliers and simultaneously recover the relative pose by essential matrix. Experimental results demonstrate that the proposed PESA-Net relative surpasses state-of-the-art approaches for pose estimation and outlier rejection on both outdoor scenes and indoor scenes (i.e., YFCC100M and SUN3D). Source codes: https://github.com/x-gb/PESA-Net. • We propose an iterative network to establish reliable correspondences. • We develop an attention mechanism to capture rich contextual information. • We construct a novel block to exploit the global context of unordered data. • The proposed network achieves the state-of-the-art performance. [ABSTRACT FROM AUTHOR]

Modern day computer vision tasks requires efficient solution to problems such as image recognition, natural language processing, object detection, object segmentation and language translation. Symbolic Artificial Intelligence with its hard coding rules is incapable of solving these complex problems resulting in the introduction of Deep Learning (DL) models such as Recurrent Neural Networks and Convolutional Neural Networks (CNN). However, CNNs require lots of training data and are incapable of recognizing pose and deformation of objects leading to the introduction of Capsule Networks. Capsule Networks are the new sensation in Deep Learning. They have lived to this expectation as their performance in relation to the above problems has been better than Convolutional Neural Networks. Even with this promise in performance, lack of architectural knowledge and inner workings of Capsules serves as a hindrance for researchers to take full advantage of this breakthrough. In this paper, we provide a comprehensive review of the state of the art architectures, tools and methodologies in existing implementations of capsule networks. We highlight the successes, failures and opportunities for further research to serve as a motivation to researchers and industry players to exploit the full potential of this new field. The main contribution of this survey article is that it explains and summarizes significant current state of the art Capsule Network architectures and implementations. [ABSTRACT FROM AUTHOR]

This paper describes the implementation of fast state-dependent Riccati equation (SDRE) control algorithms through the use of shallow and deep artificial neural networks (ANN). Several ANNs are trained to replicate an SDRE controller developed for a satellite attitude dynamics simulator (SADS) to display the technique's efficacy. The neural controllers have reduced computational complexity compared with the original SDRE controller, allowing its execution at a significantly higher rate. One of the neural controllers was validated using the SADS in a practical experiment. The experimental results indicate that the training error is sufficiently small for the neural controller to perform equivalently to the original SDRE controller. • A real-time SDRE controller is designed using shallow and deep neural networks. • A significant reduction in computation is achieved using the neural controllers. • Deep denoising autoencoders were trained as deep neural controllers. • The neural controller is validated through simulations and a practical experiment. • Results show that the neural controller retains its high performance. [ABSTRACT FROM AUTHOR]

Modern complex chemical process operations produce a large amount of process monitoring and control time series data, which are potentially useful to extract valuable operating experiences and manipulating rules to improve the intelligence of process operations. Previous researches show that time series clustering is an effective method to mine historical control sequences. However, the actual working conditions often deviate from the historical data, making it difficult to reconstruct accurate process regulation manipulating strategies. In response to this problem, this paper proposes a manipulation strategies reconstruction method using a convolutional neural network model (MSR-CNN). Therein, the time series are hierarchically clustered according to the Levenshtein distance to obtain different classes of process disturbance states, and the corresponding manipulated sequences fragments obtained are treated with a symbolic aggregation approximation. Then the improved convolutional neural network is used for deep learning and manipulation strategies reconstruction of the process disturbance states and the corresponding manipulating sequences strings. Finally, applying to a numerical example and an ethanol–water distillation tower unit, the proposed method is proved to be effective. Compared with traditional supervisory control methods, our contributions can help well construct complex chemical process control strategies less dependent on human operators' operating experiences. • Agglomerative hierarchical time series clustering based on levenshtein distance. • Fragmentation of effective manipulation sequences. • Deep learning and reconstruction of manipulation strategies with convolutional neural networks. • Favorable comparison with the supervisory control method. [ABSTRACT FROM AUTHOR]

Several breakthroughs have appeared in different applications due to deep learning which can be applied in Bridge Weigh-In-Motion (BWIM) systems as well. Therefore, deep learning applications should be examined in BWIM systems. However, some deep learning-based solutions have already been proposed in the international literature, they cannot be compared to static methods because available datasets are not appropriate to train and test artificial neural networks. In addition, numerous other aspects have been already considered during tests. In the current paper, a numerically simulated and validated comprehensive dataset is provided. It is designed to meet requirements of incremental development. This dataset makes it possible to benchmark static algorithms and deep learning-based methods on the same dataset. In the second part of the paper, a deep learning-based solution is proposed. The developed solution shows promising results on the provided dataset and also demonstrates the applicability of the dataset. • Deep learning-based algorithm is developed for Bridge Weigh-In-Motion system. • Validated FEA-based influence surfaces and strain gauge data are used as input. • BME-Simulated 1 (BME-S1) dataset with more than 100000 vehicle models is provided. • A BWIM system is developed with class B+ in accordance with COST 323 standard. [ABSTRACT FROM AUTHOR]

Nowadays, Artificial intelligence (AI), combined with the digitalization of healthcare, can lead to substantial improvements in Patient Care, Disease Management, Hospital Administration, and supply chain effectiveness. Among predictive analytics tools, time series forecasting represents a central task to support healthcare management in terms of bookings and medical services predictions. In this context, the development of flexible frameworks to provide robust and reliable predictions became a central point in this healthcare innovation process. This paper presents and discusses a multi-source time series fusion and forecasting framework relying on Deep Learning. By combining weather, air-quality and medical bookings time series through a feature compression stage which preserves temporal patterns, the prediction is provided through a flexible ensemble technique based on machine learning models and a hybrid neural network. The proposed system is able to predict the number of bookings related to a specific medical examination for a 7-days horizon period. To assess the proposed approach's effectiveness, we rely on time series extracted from a real dataset of administrative e-health records provided by the Campania Region health department, in Italy. • We propose a multi-source time-series fusion methodology relying on Deep Learning. • We design a robust framework for daily 7-days-horizon predictions. • We assess the proposed approach on a real medical bookings dataset. [ABSTRACT FROM AUTHOR]

This paper proposes a novel sequence-to-sequence recurrent neural network model to predict re-entry trajectories of uncontrolled space objects. The epoch and altitude information of the objects from two-line element data were interpolated to equally spaced data and were used as inputs to the model. More than 200 datasets from five different objects with already known re-entry times were used as the training set for the model. Test datasets being not used for training, were chosen to validate the model's performance. To assess the performance, the model predictions were compared with the ground-truth data of the test objects and with predictions from the Inter-Agency Space Debris Coordination re-entry campaign, in which space agencies from various countries had participated. The results indicate that the proposed approach is highly suitable for re-entry prediction compared to classical dynamics-based approaches, despite the small quantity of training data. [ABSTRACT FROM AUTHOR]

As growing complexity of digital VLSI circuits, fault detection and correction processes have been the most crucial phases during IC design. Many CAD tools and formal approaches have been used for debugging and localizing different kinds of design bugs. However, the search space explosion problem remains the main problem for IC designers. Recently, Artificial intelligence and machine learning models have been expanded in feature extraction and reduction models. In this paper, we introduce a new fault detection model based on deep learning for extracting features and detecting faults from large-sized digital circuits. The main goal of the proposed model is to avoid the search space using stacked sparse autoencoder, a specific type of artificial neural network. The model consists of three phases: test pattern generation using ATALANTA software, feature reduction using SSAE and classification for fault detection. Test vectors are utilized in SSAE as a training data for unsupervised learning phase. The performance of feature extraction is tested by changing the architecture of SSAE network and sparsity constraint. The proposed algorithm has been implemented using eight combinational digital circuits from ISCAS'85. From experimental results, the maximum fault coverage using ATALANTA tool delivers around 99.2% using ISCAS'85. In addition, the maximum validation accuracy of proposed SSAE model delivers around 99.7% in feature reduction phase. [ABSTRACT FROM AUTHOR]

The rapid increase in urbanization has resulted in a significant rise in electricity consumption, which resulted in a wide gap between the amount of electricity generated and the consumer's demand. Literature shows that 40% of the generated electricity is consumed by building sectors. To address the gap between demand and supply, there is a need to develop novel prediction models that adopt automated techniques, to dynamically predict buildings energy consumption. An efficient load forecast can assist in efficient power generation and distribution among users. Different Machine Learning techniques have been applied in future electricity consumption forecasts with the need for a more ideal solution. This paper reviews methods for building energy consumption forecasts that use Machine Learning algorithms like Artificial Neural Network, Deep Belief Network, Recurrent Neural Network, Elman Neural Network, Deep Recurrent Neural Network, Convolutional Neural Network and Nonlinear Autoregressive Network. The review explores existing research gaps and research directions for future work. Finally, a novel Deep Learning framework was suggested for future work on enhancing prediction performance and reliability using occupancy profile and distinct climatic scenarios based on Transfer Learning and LSTM algorithms (Trans-LSTM) for medium to long term electricity consumption forecast. [ABSTRACT FROM AUTHOR]

Accurate time transfer by time of flight measurements via diffuse reflections on passive orbiting space debris targets requires a selection of suitable objects out of a large catalogue of debris items. In this paper, we report on our development of an automatic classification system of space objects based on photometric observations of sun illuminated satellite and debris items from the Mini–Mega TORTORA (MMT) system observation data base by a deep learning algorithm. A deep neural network model based on a convolutional long short-term memory network has been designed to identify four different object categories with a test accuracy of over 85%. The method is also suitable for an automated analysis of the temporal evolution of the orbit motion of specific space objects. • Neural networks exploit a single observable to classify many space objects. • Reliable space object classification is achieved where rule based systems fail. • Satellite or space debris orbit anomalies are automatically detected. • A body of thousands of different objects can be monitored continuously. [ABSTRACT FROM AUTHOR]