Deep spatial–temporal structure learning for rumor detection on Twitter

The relative importance of spatial versus temporal structure in the perception of biological motion: An event-related potential study

Evaluation of multispectral imaging for freeze damage assessment in strawberries using AI-based computer vision technology

Infrared small target tracking algorithm based on temporal-spatial structure sparse Bayesian estimation

Most of the existing hyperspectral image change detection methods based on deep learning utilize convolutional neural networks (CNN), recurrent neural networks (RNN), and long-short-term memory (LSTM). However, CNNs primarily focus on extracting spatial information from hyperspectral images, thereby failing to fully utilize channel and temporal information. In this paper, we propose a network called STSTNet that can jointly extract spatial, spectral, and temporal feature information. To achieve a richer feature representation space, we employ a spatial attention module to extract spatial feature information from feature maps, and a spectral transformer encoder structure to extract abundant spectral sequence information. Specifically, we design two temporal information extraction structures after each spatial information extraction structure or spectral information extraction structure to capture correlations and interactions within the hyperspectral images. Extensive experiments have been conducted on three hyperspectral datasets, and the experimental results demonstrate the network’s excellent performance.

DyHDGE: Dynamic heterogeneous transaction graph embedding for safety-centric fraud detection in financial scenarios

Evaluating neurological disorders such as Parkinson's disease (PD) is a challenging task that requires the assessment of several motor and non-motor functions. In this paper, we present an end-to-end deep learning framework to measure PD severity in two important components, hand movement and gait, of the Unified Parkinson's Disease Rating Scale (UPDRS). Our method leverages on an Inflated 3D CNN trained by a temporal segment framework to learn spatial and long temporal structure in video data. We also deploy a temporal attention mechanism to boost the performance of our model. Further, motion boundaries are explored as an extra input modality to assist in obfuscating the effects of camera motion for better movement assessment. We ablate the effects of different data modalities on the accuracy of the proposed network and compare with other popular architectures. We evaluate our proposed method on a dataset of 25 PD patients, obtaining 72.3% and 77.1% top-1 accuracy on hand movement and gait tasks respectively.

Functional behavior of the brain can be captured using functional Magnetic Resonance Imaging (fMRI). Even though fMRI signals have temporal and spatial structures, most studies have neglected the temporal structure when inferring mental states (brain decoding). This has two main side effects: 1. Degradation in brain decoding performance due to lack of temporal information in the model, 2. Inability to provide temporal interpretability. Few studies have targeted this issue but have had less success due to the burdening challenges related to high feature-to-instance ratio. In this study, a novel model for incorporating temporal information while maintaining a low feature-to-instance ratio, is proposed. Experimental results show the effectiveness of the model compared to recent state of the art approaches.

This article investigates the identification of hate speech on social media using machine learning and deep learning techniques. The research uses metrics such as F-measure, AUC-ROC, precision, accuracy, and recall assessing the effectiveness of various tactics. The findings indicate that deep learning models, particularly the bidirectional long short-term memory (BiLSTM) architecture, consistently outperform other methods in categorization tasks. The research emphasizes the importance of sophisticated neural network designs in identifying the intricacies of hostile and offensive content online. The study offers insights for promoting early identification and prevention of cyberbullying, improving secure and inclusive online environments. Future research may explore real-time detection systems, hybrid approaches, or the integration of complementary components to enhance and improve innovative technology in tackling this significant social issue. A sample tweet was annotated by specialists who categorize tweets as hate speech, offensive language, or neutral. The researchers applied shallow learning methodologies and integrated word embeddings like Word2Vec and GloVe to enhance the efficacy of deep learning models. The results indicate that BiLSTM surpasses shallow learning methods in detecting hate speech on Twitter, highlighting the efficacy of deep learning approaches in recognizing and tracking hate speech on social media platforms. When comparing different deep learning and machine learning models on different datasets, the results reveal that deep learning techniques are usually more effective. A reasonably high level of accuracy is achieved by KNN and SVM among classical algorithms, whereas Naïve Bayes performs the poorest. While deep learning approaches provide better results, tree-based models such as Random Forest and Decision Trees offer more consistent accuracy. Models based on neural networks, such as LSTM, CNN, and BI-LSTM, perform well, with LSTM-based methods excelling in particular. The most successful strategy for classification problems is the model presented, which obtains the greatest accuracy, precision, recall, F1-score of 95%. The research aids in the development of advanced tools and methodologies to mitigate hate speech on social media and foster positive online interactions. Future research may investigate alternative deep learning architectures, such as transformers, to enhance hate speech detection efficacy. The advancement of interpretable AI methodologies for identifying hate speech and delivering transparent forecasts might enhance user confidence and facilitate better content moderation decisions.

Social media platforms provide valuable insights into mental health trends by capturing user-generated discussions on conditions such as depression, anxiety, and suicidal ideation. Machine learning (ML) and deep learning (DL) models have been increasingly applied to classify mental health conditions from textual data, but selecting the most effective model involves trade-offs in accuracy, interpretability, and computational efficiency. This study evaluates multiple ML models, including logistic regression, random forest, and LightGBM, alongside DL architectures such as ALBERT and Gated Recurrent Units (GRUs), for both binary and multi-class classification of mental health conditions. Our findings indicate that ML and DL models achieve comparable classification performance on medium-sized datasets, with ML models offering greater interpretability through variable importance scores, while DL models are more robust to complex linguistic patterns. Additionally, ML models require explicit feature engineering, whereas DL models learn hierarchical representations directly from text. Logistic regression provides the advantage of capturing both positive and negative associations between features and mental health conditions, whereas tree-based models prioritize decision-making power through split-based feature selection. This study offers empirical insights into the advantages and limitations of different modeling approaches and provides recommendations for selecting appropriate methods based on dataset size, interpretability needs, and computational constraints.

Traditional action recognition approaches use pre-defined rigid areas to process the space-time information, e.g. spatial pyramids, cuboids. However, most action categories happen in an unconstrained manner, that is, the same action in different videos can happen at different places. Thus we need a better video representation to deal with the space-time variations. In this paper, we introduce the idea of mining spatial temporal saliency. To better handle the uniqueness of each video, we use a space-time over-segmentation approach, e.g. supervoxel. We choose three different saliency measures that take not only the appearance cues, but also the motion cues into consideration. Furthermore, we design a category-specific mining process to find the discriminative power in each action category. Experiments on action recognition datasets such as UCF11 and HMDB51 show that the proposed spatial temporal saliency video representation can match or surpass some of the state-of-the-art alternatives in the task of action recognition.

An Adaptive Measurement Scheme (AMS) is investigated with Compressed Sensing (CS) theory in Cognitive Wireless Sensor Network (C-WSN). Local sensing information is collected via energy detection with Analog-to-Information Converter (AIC) at massive cognitive sensors, and sparse representation is considered with the exploration of spatial temporal correlation structure of detected signals. Adaptive measurement matrix is designed in AMS, which is based on maximum energy subset selection. Energy subset is calculated with sparse transformation of sensing information, and maximum energy subset is selected as the row vector of adaptive measurement matrix. In addition, the measurement matrix is constructed by orthogonalization of those selected row vectors, which also satisfies the Restricted Isometry Property (RIP) in CS theory. Orthogonal Matching Pursuit (OMP) reconstruction algorithm is implemented at sink node to recover original information. Simulation results are performed with the comparison of Random Measurement Scheme (RMS). It is revealed that, signal reconstruction effect based on AMS is superior to conventional RMS Gaussian measurement. Moreover, AMS has better detection performance than RMS at lower compression rate region, and it is suitable for large-scale C-WSN wideband spectrum sensing.

Finite-Differences Time-Domain (FDTD) algorithms are well established tools of computational electromagnetism. Because of their practical implementation as computer codes, they are affected by many numerical artefact and noise. In order to obtain better results we propose using Principal Component Analysis (PCA) based on multivariate statistical techniques. The PCA has been successfully used for the analysis of noise and spatial temporal structure in a sequence of images. It allows a straightforward discrimination between the numerical noise and the actual electromagnetic variables, and the quantitative estimation of their respective contributions. Besides, The GDTD results can be filtered to clean the effect of the noise. In this contribution we will show how the method can be applied to several FDTD simulations: the propagation of a pulse in vacuum, the analysis of two-dimensional photonic crystals. In this last case, PCA has revealed hidden electromagnetic structures related to actual modes of the photonic crystal.

Over the recent years, people are heavily getting involved in the virtual world to express their opinions and feelings. Each second, hundreds of thousands of data are being gathered in the social media sites. Extraction of information from these data and finding their sentiments is known as a sentiment analysis. Sentiment analysis (SA) is an autonomous text summarization and analysis system. It is one of the most active research areas in the field of NLP and also widely studied in data mining, web mining and text mining. The significance of sentiment analysis is picking up day by day due to its direct impact on various businesses. However, it is not so straightforward to extract the sentiments when it comes to the Bangla language because of its complex grammatical structure. In this paper, a deep learning model was developed to train with Bangla language and mine the underlying sentiments. A critical analysis was performed to compare with a different deep learning model across different representation of words. The main idea is to represent Bangla sentence based on characters and extract information from the characters using a Recurrent Neural Network (RNN). These extracted information are decoded as positive, negative and neutral sentiment.

Fake news is a growing problem on social media and can have significant negative consequences for individuals and society owing to its accessibility, low cost, and quick distribution. It is difficult to automatically identify bogus news that defies the current content-based analysis techniques. One of the key reasons is that current NLP algorithms still lack common sense, which is frequently necessary for understanding how to read the news. Recent research has demonstrated that the propagation patterns of true and fake news differ on social media. With the potential for automatic fake news detection, this study investigates the use of Deep Learning (DL) models to detect fake news on social media. A Neural Network (NN) model was developed using Natural Language Toolkit (NLTK), TensorFlow, and Natural Language Processing (NLP) for textual analysis. The model was trained on a dataset of fake and real news articles, and was able to achieve high accuracy in identifying fake news. The results of this study suggest that DL models can be valuable tools for detecting fake news on social media.

PurposeComputational text mining methods are proposed as a useful methodological innovation in Intimate Partner Violence (IPV) research. Text mining can offer researchers access to existing or new datasets, sourced from social media or from IPV-related organisations, that would be too large to analyse manually. This article aims to give an overview of current work applying text mining methodologies in the study of IPV, as a starting point for researchers wanting to use such methods in their own work.MethodsThis article reports the results of a systematic review of academic research using computational text mining to research IPV. A review protocol was developed according to PRISMA guidelines, and a literature search of 8 databases was conducted, identifying 22 unique studies that were included in the review.ResultsThe included studies cover a wide range of methodologies and outcomes. Supervised and unsupervised approaches are represented, including rule-based classification (n = 3), traditional Machine Learning (n = 8), Deep Learning (n = 6) and topic modelling (n = 4) methods. Datasets are mostly sourced from social media (n = 15), with other data being sourced from police forces (n = 3), health or social care providers (n = 3), or litigation texts (n = 1). Evaluation methods mostly used a held-out, labelled test set, or k-fold Cross Validation, with Accuracy and F1 metrics reported. Only a few studies commented on the ethics of computational IPV research.ConclusionsText mining methodologies offer promising data collection and analysis techniques for IPV research. Future work in this space must consider ethical implications of computational approaches.