Short-term electricity load forecasting is critical and challenging for scheduling operations and production planning in modern power management systems due to stochastic characteristics of electricity load data. Current forecasting models mainly focus on adapting to various load data to improve the accuracy of the forecasting. However, these models ignore the noise and nonstationarity of the load data, resulting in forecasting uncertainty. To address this issue, a short-term load forecasting system is proposed by combining a modified information processing technique, an advanced meta-heuristics algorithm and deep neural networks. The information processing technique utilizes a sliding fuzzy granulation method to remove noise and obtain uncertainty information from load data. Deep neural networks can capture the nonlinear characteristics of load data to obtain forecasting performance gains due to the powerful mapping capability. A novel meta-heuristics algorithm is used to optimize the weighting coefficients to reduce the contingency and improve the stability of the forecasting. Both point forecasting and interval forecasting are utilized for comprehensive forecasting evaluation of future electricity load. Several experiments demonstrate the superiority, effectiveness and stability of the proposed system by comprehensively considering multiple evaluation metrics.

Machine learning has greatly influenced many fields, including science. However, despite of the tremendous accomplishments of machine learning, one of the key limitations of most existing machine learning approaches is their reliance on large labeled sets, and thus, data with limited labeled samples remains a challenge. Moreover, the performance of machine learning methods often severely hindered in case of diverse data, usually associated with smaller data sets or data associated with areas of study where the size of the data sets is constrained by high experimental cost and/or ethics. These challenges call for innovative strategies for dealing with these types of data. In this work, the aforementioned challenges are addressed by integrating graph-based frameworks, semi-supervised techniques, multiscale structures, and modified and adapted optimization procedures. This results in two innovative multiscale Laplacian learning (MLL) approaches for machine learning tasks, such as data classification, and for tackling data with limited samples, diverse data, and small data sets. The first approach, multikernel manifold learning (MML), integrates manifold learning with multikernel information and incorporates a warped kernel regularizer using multiscale graph Laplacians. The second approach, the multiscale MBO (MMBO) method, introduces multiscale Laplacians to the modification of the famous classical Merriman-Bence-Osher (MBO) scheme, and makes use of fast solvers. We demonstrate the performance of our algorithms experimentally on a variety of benchmark data sets, and compare them favorably to the state-of-art approaches.

In machine learning, multiple instance learning is a method evolved from supervised learning algorithms, which defines a "bag" as a collection of multiple examples with a wide range of applications. In this paper, we propose a novel deep multiple instance learning model for medical image analysis, called triple-kernel gated attention-based multiple instance learning with contrastive learning. It can be used to overcome the limitations of the existing multiple instance learning approaches to medical image analysis. Our model consists of four steps. i) Extracting the representations by a simple convolutional neural network using contrastive learning for training. ii) Using three different kernel functions to obtain the importance of each instance from the entire image and forming an attention map. iii) Based on the attention map, aggregating the entire image together by attention-based MIL pooling. iv) Feeding the results into the classifier for prediction. The results on different datasets demonstrate that the proposed model outperforms state-of-the-art methods on binary and weakly supervised classification tasks. It can provide more efficient classification results for various disease models and additional explanatory information.

Sanitizing railway stations is a relevant issue, primarily due to the recent evolution of the Covid-19 pandemic. In this work, we propose a multi-robot approach to sanitize railway stations based on a distributed Deep Q-Learning technique. The proposed framework relies on anonymous data from existing WiFi networks to dynamically estimate crowded areas within the station and to develop a heatmap of prioritized areas to be sanitized. Such heatmap is then provided to a team of cleaning robots - each endowed with a robot-specific convolutional neural network - that learn how to effectively cooperate and sanitize the station's areas according to the associated priorities. The proposed approach is evaluated in a realistic simulation scenario provided by the Italian largest railways station: Roma Termini. In this setting, we consider different case studies to assess how the approach scales with the number of robots and how the trained system performs with a real dataset retrieved from a one-day data recording of the station's WiFi network.

Spreading malicious rumors on social networks such as Facebook, Twitter, and WeChat can trigger political conflicts, sway public opinion, and cause social disruption. A rumor can spread rapidly across a network and can be difficult to control once it has gained traction.Rumor influence minimization (RIM) is a central problem in information diffusion and network theory that involves finding ways to minimize rumor spread within a social network. Existing research on the RIM problem has focused on blocking the actions of influential users who can drive rumor propagation. These traditional static solutions do not adequately capture the dynamics and characteristics of rumor evolution from a global perspective. A deep reinforcement learning strategy that takes into account a wide range of factors may be an effective way of addressing the RIM challenge. This study introduces the dynamic rumor influence minimization (DRIM) problem, a step-by-step discrete time optimization method for controlling rumors. In addition, we provide a dynamic rumor-blocking approach, namely RLDB, based on deep reinforcement learning. First, a static rumor propagation model (SRPM) and a dynamic rumor propagation model (DRPM) based on of independent cascade patterns are presented. The primary benefit of the DPRM is that it can dynamically adjust the probability matrix according to the number of individuals affected by rumors in a social network, thereby improving the accuracy of rumor propagation simulation. Second, the RLDB strategy identifies the users to block in order to minimize rumor influence by observing the dynamics of user states and social network architectures. Finally, we assess the blocking model using four real-world datasets with different sizes. The experimental results demonstrate the superiority of the proposed approach on heuristics such as out-degree(OD), betweenness centrality(BC), and PageRank(PR).

Long time exposure to indoor air pollution environments can increase the risk of cardiovascular and respiratory system damage. Most previous studies focus on outdoor air quality, while few studies on indoor air quality. Current neural network-based methods for indoor air quality prediction ignore the optimization of input variables, process input features serially, and still suffer from loss of information during model training, which may lead to the problems of memory-intensive, time-consuming and low-precision. We present a novel concurrent indoor PM prediction model based on the fusion model of Least Absolute Shrinkage and Selection Operator (LASSO) and an Attention Temporal Convolutional Network (ATCN), together called LATCN. First, a LASSO regression algorithm is used to select features from PM1, PM2.5, PM10 and PM (>10) datasets and environmental factors to optimize the inputs for indoor PM prediction model. Then an Attention Mechanism (AM) is applied to reduce the redundant temporal information to extract key features in inputs. Finally, a TCN is used to forecast indoor particulate concentration in parallel with inputting the extracted features, and it reduces information loss by residual connections. The results show that the main environmental factors affecting indoor PM concentration are the indoor heat index, indoor wind chill, wet bulb temperature and relative humidity. Comparing with Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) approaches, LATCN systematically reduced the prediction error rate (19.7% ~ 28.1% for the NAE, and 16.4% ~ 21.5% for the RMSE) and improved the model running speed (30.4% ~ 81.2%) over these classical sequence prediction models. Our study can inform the active prevention of indoor air pollution, and provides a theoretical basis for indoor environmental standards, while laying the foundations for developing novel air pollution prevention equipment in the future.

Deep learning has been widely considered in medical image segmentation. However, the difficulty of acquiring medical images and labels can affect the accuracy of the segmentation results for deep learning methods. In this paper, an automatic segmentation method is proposed by devising a multicomponent neighborhood extreme learning machine to improve the boundary attention region of the preliminary segmentation results. The neighborhood features are acquired by training U-Nets with the multicomponent small dataset, which consists of original thyroid ultrasound images, Sobel edge images and superpixel images. Afterward, the neighborhood features are selected by min-redundancy and max-relevance filter in the designed extreme learning machine, and the selected features are used to train the extreme learning machine to obtain supplementary segmentation results. Finally, the accuracy of the segmentation results is improved by adjusting the boundary attention region of the preliminary segmentation results with the supplementary segmentation results. This method combines the advantages of deep learning and traditional machine learning, boosting the accuracy of thyroid segmentation accuracy with a small dataset in a multigroup test.

Sentiment Analysis is a method to identify, extract, and quantify people's feelings, opinions, or attitudes. The wealth of online data motivates organizations to keep tabs on customers' opinions and feelings by turning to sentiment analysis tasks. Along with the sentiment analysis, the emotion analysis of written reviews is also essential to improve customer satisfaction with restaurant service. Due to the availability of massive online data, various computerized methods are proposed in the literature to decipher text sentiments. The majority of current methods rely on machine learning, which necessitates the pre-training of large datasets and incurs substantial space and time complexity. To address this issue, we propose a novel unsupervised sentiment classification model. This study presents an unsupervised mathematical optimization framework to perform sentiment and emotion analysis of reviews. The proposed model performs two tasks. First, it identifies a review's positive and negative sentiment polarities, and second, it determines customer satisfaction as either satisfactory or unsatisfactory based on a review. The framework consists of two stages. In the first stage, each review's context, rating, and emotion scores are combined to generate performance scores. In the second stage, we apply a non-cooperative game on performance scores and achieve Nash Equilibrium. The output from this step is the deduced sentiment of the review and the customer's satisfaction feedback. The experiments were performed on two restaurant review datasets and achieved state-of-the-art results. We validated and established the significance of the results through statistical analysis. The proposed model is domain and language-independent. The proposed model ensures rational and consistent results.

According to the World Health Organization, millions of infections and a lot of deaths have been recorded worldwide since the emergence of the coronavirus disease (COVID-19). Since 2020, a lot of computer science researchers have used convolutional neural networks (CNNs) to develop interesting frameworks to detect this disease. However, poor feature extraction from the chest X-ray images and the high computational cost of the available models introduce difficulties for an accurate and fast COVID-19 detection framework. Moreover, poor feature extraction has caused the issue of 'the curse of dimensionality', which will negatively affect the performance of the model. Feature selection is typically considered as a preprocessing mechanism to find an optimal subset of features from a given set of all features in the data mining process. Thus, the major purpose of this study is to offer an accurate and efficient approach for extracting COVID-19 features from chest X-rays that is also less computationally expensive than earlier approaches. To achieve the specified goal, we design a mechanism for feature extraction based on shallow conventional neural network (SCNN) and used an effective method for selecting features by utilizing the newly developed optimization algorithm, Q-Learning Embedded Sine Cosine Algorithm (QLESCA). Support vector machines (SVMs) are used as a classifier. Five publicly available chest X-ray image datasets, consisting of 4848 COVID-19 images and 8669 non-COVID-19 images, are used to train and evaluate the proposed model. The performance of the QLESCA is evaluated against nine recent optimization algorithms. The proposed method is able to achieve the highest accuracy of 97.8086% while reducing the number of features from 100 to 38. Experiments prove that the accuracy of the model improves with the usage of the QLESCA as the dimensionality reduction technique by selecting relevant features.

Software Fault Prediction (SFP) is an important process to detect the faulty components of the software to detect faulty classes or faulty modules early in the software development life cycle. In this paper, a machine learning framework is proposed for SFP. Initially, pre-processing and re-sampling techniques are applied to make the SFP datasets ready to be used by ML techniques. Thereafter seven classifiers are compared, namely K-Nearest Neighbors (KNN), Naive Bayes (NB), Linear Discriminant Analysis (LDA), Linear Regression (LR), Decision Tree (DT), Support Vector Machine (SVM), and Random Forest (RF). The RF classifier outperforms all other classifiers in terms of eliminating irrelevant/redundant features. The performance of RF is improved further using a dimensionality reduction method called binary whale optimization algorithm (BWOA) to eliminate the irrelevant/redundant features. Finally, the performance of BWOA is enhanced by hybridizing the exploration strategies of the grey wolf optimizer (GWO) and harris hawks optimization (HHO) algorithms. The proposed method is called SBEWOA. The SFP datasets utilized are selected from the PROMISE repository using sixteen datasets for software projects with different sizes and complexity. The comparative evaluation against nine well-established feature selection methods proves that the proposed SBEWOA is able to significantly produce competitively superior results for several instances of the evaluated dataset. The algorithms' performance is compared in terms of accuracy, the number of features, and fitness function. This is also proved by the 2-tailed P-values of the Wilcoxon signed ranks statistical test used. In conclusion, the proposed method is an efficient alternative ML method for SFP that can be used for similar problems in the software engineering domain.

The classification of time series is essential in many real-world applications like healthcare. The class of a time series is usually labeled at the final time, but more and more time-sensitive applications require classifying time series continuously. For example, the outcome of a critical patient is only determined at the end, but he should be diagnosed at all times for timely treatment. For this demand, we propose a new concept, Continuous Classification of Time Series (CCTS). Different from the existing single-shot classification, the key of CCTS is to model multiple distributions simultaneously due to the dynamic evolution of time series. But the deep learning model will encounter intertwined problems of catastrophic forgetting and over-fitting when learning multi-distribution. In this work, we found that the well-designed distribution division and replay strategies in the model training process can help to solve the problems. We propose a novel Adaptive model training strategy for CCTS (ACCTS). Its adaptability represents two aspects: (1) Adaptive multi-distribution extraction policy. Instead of the fixed rules and the prior knowledge, ACCTS extracts data distributions adaptive to the time series evolution and the model change; (2) Adaptive importance-based replay policy. Instead of reviewing all old distributions, ACCTS only replays important samples adaptive to their contribution to the model. Experiments on four real-world datasets show that our method outperforms all baselines.

Although the Internet and social media provide people with a range of opportunities and benefits in a variety of ways, the proliferation of fake news has negatively affected society and individuals. Many efforts have been invested to detect the fake news. However, to learn the representation of fake news by context information, it has brought many challenges for fake news detection due to the feature sparsity and ineffectively capturing the non-consecutive and long-range context. In this paper, we have proposed Intra-graph and Inter-graph Joint Information Propagation Network (abbreviated as IIJIPN) with Third-order Text Graph Tensor for fake news detection. Specifically, data augmentation is firstly utilized to solve the data imbalance and strengthen the small corpus. In the stage of feature extraction, Third-order Text Graph Tensor with sequential, syntactic, and semantic features is proposed to describe contextual information at different language properties. After constructing the text graphs for each text feature, Intra-graph and Inter-graph Joint Information Propagation is used for encoding the text: intra-graph information propagation is performed in each graph to realize homogeneous information interaction, and high-order homogeneous information interaction in each graph can be achieved by stacking propagation layer; inter-graph information propagation is performed among text graphs to realize heterogeneous information interaction by connecting the nodes across the graphs. Finally, news representations are generated by attention mechanism consisting of graph-level attention and node-level attention mechanism, and then news representations are fed into a fake news classifier. The experimental results on four public datasets indicate that our model has outperformed state-of-the-art methods. Our source code is available at https://github.com/cuibenkuan/IIJIPN.

In the rapid development of public transportation led, the traffic flow prediction has become one of the most crucial issues, especially estimating the number of passengers using the Mass Rapid Transit (MRT) system. In general, predicting the passenger flow of traffic is a time-series problem that requires external information to improve accuracy. Because many MRT passengers take cars or buses to MRT stations, this study used external information from vehicle detection (VD) devices to improve the prediction of passenger flow. This study proposed a deep learning architecture, called a multiple-attention deep neural network (MADNN) model, based on historical MRT passenger flow and the flow from surrounding VD devices that estimates the weights of the vehicle detection devices. The model consists of (1) an MRT attention layer (MRT-AL) that generate hidden features for MRT stations, (2) a surrounding VD (SVD) attention layer (SVD-AL) that generate hidden features for SVD devices, and (3) an MRT-SVD attention layer (MRT-SVD-AL) that generate attention weights for each VD device in an MRT station. The results of the investigation indicated that the MADNN model outperformed the models without multiple-attention mechanisms in predicting the passenger flow of MRT traffic.

Nowadays, the hectic work life of people has led to sleep deprivation. This may further result in sleep-related disorders and adverse physiological conditions. Therefore, sleep study has become an active research area. Sleep scoring is crucial for detecting sleep-related disorders like sleep apnea, insomnia, narcolepsy, periodic leg movement (PLM), and restless leg syndrome (RLS). Sleep is conventionally monitored in a sleep laboratory using polysomnography (PSG) which is the recording of various physiological signals. The traditional sleep stage scoring (SSG) done by professional sleep scorers is a tedious, strenuous, and time-consuming process as it is manual. Hence, developing a machine-learning model for automatic SSG is essential. In this study, we propose an automated SSG approach based on the biorthogonal wavelet filter bank's (BWFB) novel least squares (LS) design. We have utilized a huge Wisconsin sleep cohort (WSC) database in this study. The proposed study is a pioneering work on automatic sleep stage classification using the WSC database, which includes good sleepers and patients suffering from various sleep-related disorders, including apnea, insomnia, hypertension, diabetes, and asthma. To investigate the generalization of the proposed system, we evaluated the proposed model with the following publicly available databases: cyclic alternating pattern (CAP), sleep EDF, ISRUC, MIT-BIH, and the sleep apnea database from St. Vincent's University. This study uses only two unipolar EEG channels, namely O1-M2 and C3-M2, for the scoring. The Hjorth parameters (HP) are extracted from the wavelet subbands (SBS) that are obtained from the optimal BWFB. To classify sleep stages, the HP features are fed to several supervised machine learning classifiers. 12 different datasets have been created to develop a robust model. A total of 12 classification tasks (CT) have been conducted employing various classification algorithms. Our developed model achieved the best accuracy of 83.2% and Cohen's Kappa of 0.7345 to reliably distinguish five sleep stages, using an ensemble bagged tree classifier with 10-fold cross-validation using WSC data. We also observed that our system is either better or competitive with existing state-of-art systems when we tested with the above-mentioned five databases other than WSC. This method yielded promising results using only two EEG channels using a huge WSC database. Our approach is simple and hence, the developed model can be installed in home-based clinical systems and wearable devices for sleep scoring.

This paper proposes a method to assist patients in finding the most appropriate doctor for online medical consultation. To do that, it constructs an online doctor selection decision-making method that considers the correlation attributes, in which the measure of attribute correlation is derived from the history real decision data. To combine public and personal preference with correlated attributes, it proposes a Choquet integral based comprehensive online doctor ranking method. In detail, a two stage classification model based on BERT (Bidirectional Encoder Representations from Transformers) is used to extract service features from unstructured text reviews. Then, 2-additive fuzzy measure is adopted to represent the patient public group aggregated attribute preference. Next, a novel optimization model is proposed to combine the public preference and personal preference. Finally, a case study of dxy.com is carried out to illustrate the procedure of the method. The comparison result between proposed method and other traditional MADM (multi-attribute decision-making) methods prove its rationality.

Sepsis is a life-threatening medical condition that is characterized by the dysregulated immune system response to infections, having both high morbidity and mortality rates. Early prediction of sepsis is critical to the decrease of mortality. This paper presents a novel early warning model called Double Fusion Sepsis Predictor (DFSP) for sepsis onset. DFSP is a double fusion framework that combines the benefits of early and late fusion strategies. First, a hybrid deep learning model that combines both the convolutional and recurrent neural networks to extract deep features is proposed. Second, deep features and handcrafted features, such as clinical scores, are concatenated to build the joint feature representation (early fusion). Third, several tree-based models based on joint feature representation are developed to generate the risk scores of sepsis onset that are combined with an End-to-End neural network for final sepsis detection (late fusion). To evaluate DFSP, a retrospective study was conducted, which included patients admitted to the ICUs of a hospital in Shanghai China. The results demonstrate that the DFSP outperforms state-of-the-art approaches in early sepsis prediction.

Cross-collection topic models extend previous single-collection topic models, such as Latent Dirichlet Allocation (LDA), to multiple collections. The purpose of cross-collection topic modeling is to model document-topic representations and reveal similarities between each topic and differences among groups. However, the restriction of Dirichlet prior and the significant privacy risk have hampered those models' performance and utility. Training those cross-collection topic models may, in particular, leak sensitive information from the training dataset. To address the two issues mentioned above, we propose a novel model, cross-collection latent Beta-Liouville allocation (ccLBLA), which operates a more powerful prior, Beta-Liouville distribution with a more general covariance structure that enhances topic correlation analysis. To provide privacy protection for the ccLBLA model, we leverage the inherent differential privacy guarantee of the Collapsed Gibbs Sampling (CGS) inference scheme and then propose a hybrid privacy protection algorithm for the ccLBLA model (HPP-ccLBLA) that prevents inferring data from intermediate statistics during the CGS training process without sacrificing its utility. More crucially, our technique is the first attempt to use the cross-collection topic model in image classification applications and investigate the cross-collection topic model's capabilities beyond text analysis. The experimental results for comparative text mining and image classification will show the merits of our proposed approach.

The network, with some or all characteristics of scale-free, self-similarity, self-organization, attractor and small world, is defined as a complex network. The identification of significant spreaders is an indispensable research direction in complex networks, which aims to discover nodes that play a crucial role in the structure and function of the network. Since influencers are essential for studying the security of the network and controlling the propagation process of the network, their assessment methods are of great significance and practical value to solve many problems. However, how to effectively combine global information with local information is still an open problem. To solve this problem, the generalized mechanics model is further improved in this paper. A generalized mechanics model based on information entropy is proposed to discover crucial spreaders in complex networks. The influence of each neighbor node on local information is quantified by information entropy, and the interaction between each node on global information is considered by calculating the shortest distance. Extensive tests on eleven real networks indicate the proposed approach is much faster and more precise than traditional ways and state-of-the-art benchmarks. At the same time, it is effective to use our approach to identify influencers in complex networks.

Domain adaptation (DA) is a popular strategy for pattern recognition and classification tasks. It leverages a large amount of data from the source domain to help train the model applied in the target domain. Supervised domain adaptation (SDA) approaches are desirable when only few labeled samples from the target domain are available. They can be easily adopted in many real-world applications where data collection is expensive. In this study, we propose a new supervision signal, namely center transfer loss (CTL), to efficiently align features under the SDA setting in the deep learning (DL) field. Unlike most previous SDA methods that rely on pairing up training samples, the proposed loss is trainable only using one-stream input based on the mini-batch strategy. The CTL exhibits two main functionalities in training to increase the performance of DL models, i.e., domain alignment and increasing the feature's discriminative power. The hyper-parameter to balance these two functionalities is waived in CTL, which is the second improvement from the previous approaches. Extensive experiments completed on well-known public datasets show that the proposed method performs better than recent state-of-the-art approaches.

is the task of discerning the intended goal that an agent aims to achieve, given a set of goal hypotheses, a domain model, and a sequence of observations (i.e., a sample of the plan executed in the environment). Existing approaches assume that goal hypotheses comprise a single conjunctive formula over a single final state and that the environment dynamics are deterministic, preventing the recognition of temporally extended goals in more complex settings. In this paper, we expand goal recognition to in (fond) planning domain models, focusing on goals on finite traces expressed in (ltl) and (ppltl). We develop the first approach capable of recognizing goals in such settings and evaluate it using different ltl and ppltl goals over six fond planning domain models. Empirical results show that our approach is accurate in recognizing temporally extended goals in different recognition settings.

Interval-valued data is an effective way to represent complex information where uncertainty, inaccuracy etc. are involved in the data space and they are worthy of taking into account. Interval analysis together with neural network has proven to work well on Euclidean data. However, in real-life scenarios, data follows a much more complex structure and is often represented as graphs, which is non-Euclidean in nature. Graph Neural Network is a powerful tool to handle graph like data with countable feature space. So, there is a research gap between the interval-valued data handling approaches and existing GNN model. No model in GNN literature can handle a graph with interval-valued features and, on the other hand, Multi Layer Perceptron (MLP) based on interval mathematics can not process the same due to non-Euclidean structure behind the graph. This article proposes an Interval-Valued Graph Neural Network, a novel GNN model where, for the first time, we relax the restriction of the feature space being countable without compromising the time complexity of the best performing GNN model in the literature. Our model is much more general than existing models as any countable set is always a subset of the universal set , which is uncountable. Here, to deal with interval-valued feature vectors, we propose a new aggregation scheme of intervals and show its expressive power to capture different interval structures. We validate our theoretical findings about our model for graph classification task by comparing its performance with those of the state-of-the-art models on several benchmark and synthetic network datasets.