Federated learning (FL) offers significant advantages in preserving data privacy and enhancing communication efficiency, making it especially suitable for Internet of Things (IoT) networks supported by unmanned aerial vehicles (UAVs). However, most existing FL approaches rely on assumptions of uniformly distributed, well-labeled, and large-scale datasets-conditions that rarely hold in practical UAV-based IoT scenarios. These environments typically feature small-scale, non-independent and identically distributed (non-IID), and dynamically changing data. To address these challenges, we propose a novel self-supervised federated unsupervised learning (FUL) framework tailored for UAV-assisted IoT systems. The proposed framework comprises three key components: (1) a realistic UAV data collection model that considers limited onboard storage and mobility constraints; (2) a robust local training strategy that incorporates self-supervised regularization and a centered kernel alignment (CKA)-based similarity loss to mitigate the effects of data heterogeneity and rapid distribution shifts; and (3) an importance-aware hybrid normalized aggregation method at the global server, which leverages model divergence-based metrics to evaluate local model reliability and integrates both current and historical gradient information for stable model updates. Experimental results demonstrate that our framework achieves classification accuracies of 30.5%, 62.8%, and 70.5% under memory constraints of 500, 1000, and 2000 samples, respectively—outperforming the best baseline by 18.1%, 26.5%, and 9.1% under the same conditions. These results highlight the effectiveness of the proposed FUL framework in handling data heterogeneity and dynamic sample variations inherent in realistic UAV-enabled IoT applications.

Graph Neural Networks (GNN) have gained significant attention for their effectiveness across various domains. This study focuses on applying GNN to process 3D point cloud data for Human Pose Estimation (HPE) and Human Activity Recognition (HAR). We propose novel point cloud feature extraction techniques to capture meaningful information at the point, edge, and graph levels of the point cloud by considering point cloud as a graph. Moreover, we introduce a GNN architecture designed to efficiently process these features. Our approach is evaluated on four most popular publicly available millimeter-wave radar datasets—three for HPE and one for HAR. The results show substantial improvements, with significantly reduced errors in all three HPE benchmarks, and an overall accuracy of 98.8% in mmWave-based HAR, outperforming existing state-of-the-art models. This work demonstrates the great potential of feature extraction incorporated with GNN modeling approach to enhance the precision of point cloud processing.

This work studies subject-independent continuous human activity recognition (HAR) using a modulation-independent multi-radar network. Our method is designed as a practical solution for real-world deployment, with a strong emphasis on robust generalization to unseen subjects, while also preventing abrupt performance drops and ensuring stable operation under varying radar availability. We introduce a Dynamic Local Range–Doppler Map (DL-RDM) that automatically tracks the line-of-sight (LoS) component range to generate subject-centered, short-time range–Doppler patches. These features are fused with micro-Doppler spectrograms via a learned gate, and multiple radar streams are combined using radar-wise attention. To reduce subject dependence, a triplet-loss pretraining stage precedes fine-tuning for frame-wise classification. Evaluations on public 5-node and 3-node HAR datasets show that gated fusion consistently outperforms single-stream models. On the 5-node dataset, fusion raises accuracy from the best single stream’s 85.3% to 87.2%, and to 87.5% with triplet pretraining, while the macro-F1 score increases from 77.2% to 81.2%. On the 3-node dataset, the MD spectrogram baseline reaches 71.9% accuracy; our proposed DL–RDM improves to 85.3%, gated feature fusion achieves 89.3%, and the pretrained gated fusion attains 89.4%. Our method achieves lower inter-subject performance variation, enhancing generalization ability on unseen users. Moreover, performance remains stable as active sensors are removed, preventing abrupt drops and demonstrating robustness under varying radar availability, making it well-suited for practical, real-world deployment.

Conventional multi-unmanned aerial vehicle (UAV) assisted non-orthogonal multiple access (NOMA) wireless caching networks (WCNs) usually operate in a distributed and non-collaborative manner, where each UAV serves users independently without coordination or relay support. When UAVs move beyond the communication range of ground base stations (BSs), backhaul disruption occurs, leading to high user latency and limited system scalability. To address these issues, we propose a multi-layer UAV-assisted NOMA WCN architecture, where a primary UAV (PUAV) communicates with the BS and cooperates with multiple secondary UAVs (SUAVs). The PUAV not only acts as a control and coordination hub but also serves as a relay for content transmission to SUAVs when necessary. To minimize user transmission latency, we propose a joint iterative algorithm that integrates user clustering, user pairing, power allocation, and UAV deployment. First, we develop an Advanced Balanced K-Means++ (ABKM) algorithm to ensure that each cluster contains a balanced number of users and to reduce the distance between users and their serving SUAVs. Next, we derive the NOMA power allocation factor that minimizes user transmission latency, ensuring efficient resource distribution among all paired users. Furthermore, we analyze the impact of PUAV and SUAV placement on user latency and propose a two-stage particle swarm optimization (PSO)-based algorithm to iteratively optimize the deployment of all UAVs. Finally, the user pairs and power allocation are jointly optimized based on the updated deployment of all UAVs to further reduce user latency. Simulation results show that, compared with a single-layer UAV architecture and benchmark schemes, the proposed multi-layer design with joint optimization achieves lower user latency. Additionally, comparisons with the optimal power allocation search method confirm the validity of the derived NOMA power allocation factor.

This paper proposes a novel radar-based framework for non-contact biometric identification through heart signal extraction, targeting secure and privacy-conscious identification scenarios. Traditional biometric methods, such as fingerprint and facial recognition, face challenges including privacy concerns, vulnerability to spoofing, and the requirement for close proximity or direct line-of-sight. Our framework addresses these issues by reconstructing electrocardiogram (ECG) signals from radar-extracted cardiac motion data and implementing an open-set person identification system. Specifically, the framework integrates ECGReconNet, a specialized deep learning model for reconstructing ECG signals from human chest wall displacement, the InceptionTime model enhanced with fixed-Class Anchor Clustering (fixed-CAC) loss for robust feature anchoring, and a hypersphere-based delineation method to differentiate known from unknown individuals. Experimental results on a public dataset demonstrate state-of-the-art performance, achieving 99.61% accuracy in closed-set identification (27 subjects) and 93.97% accuracy under challenging open-set conditions (14 known and 13 unknown subjects). However, the proposed approach exhibits limitations, including sensitivity to abrupt body movements and environmental noise, potential performance degradation under severe cardiac irregularities, and reduced efficacy with increased numbers of unknown identities.

Federated learning (FL) enables decentralized model training without sharing raw data, but its use in wireless sensor networks (WSNs) for natural disaster management remains underexplored. In this paper, we address this gap by proposing a data-aware clustered FL system tailored for disaster scenarios. We introduce the Data-Aware Disk Covering Problem (DA-DCP), a clustering method that leverages central knowledge of data distributions to form balanced clusters. These clusters serve as FL agents, improving both clustering efficiency and model convergence under heterogeneous data conditions. The simulation results highlight the advantages of DA-DCP in accelerating learning and improving robustness for disaster response.

Human activity recognition (HAR) is important for assistive care, enhancing safety and timely assistance. Traditional HAR systems using wearables and non-wearables have limitations, such as intrusiveness, privacy concerns, dependence on environmental conditions, and reliance on a single modality where noise can drastically affect their performance. In this paper, we propose a novel HAR approach using infrared (IR) thermal sensors, which offer a non-intrusive and privacy-preserving solution. Our method addresses key challenges in HAR using IR sensors, including low resolution, sensor noise, and the limitations of single-modal approaches, by integrating multi-modal learning. The proposed deep learning framework combines depth estimation, pose detection, and thermal feature extraction, utilizing a hybrid CNN-LSTM model with an attention mechanism to improve activity classification accuracy. Through extensive experimentation, we demonstrate that our approach significantly outperforms traditional HAR methods which use raw IR sensor data and rely on a single modality, achieving high precision and robustness across diverse environmental conditions. By employing all modalities, our approach reaches an accuracy equal to 98.78%.

Federated Learning (FL) enables collaborative training across distributed edge devices. However, it struggles with statistical heterogeneity in non-IID scenarios, which degrades overall model performance. Clustered FL addresses this issue by grouping clients with similar data distributions, allowing clients within each cluster to the similar data for more personalized training. However, existing clustered FL methods face challenges in accurately identifying data similarities and often introduce significant communication overhead and computational costs. In this paper, we propose a clustered FL framework (ProCFL) that exploits local prototypes during the initialization phase for one-shot identification of client data similarities, guiding subsequent federation. Each client computes a local prototype representing its data distribution using a common model and uploads it to the server. The server employs Singular Value Decomposition (SVD) to extract principal vectors from these prototypes, addressing label misalignment and enabling pairwise angular similarity computation. To achieve better cluster assignments, ProCFL incorporates a hierarchical soft clustering mechanism that forms overlapping cluster sets, promoting knowledge sharing across clusters. We evaluate our method under Label Skew and Feature Skew non-IID scenarios using multiple datasets, including Fashion-MNIST, CIFAR-10, and Digit-5. The results show that ProCFL achieves higher test accuracy than existing methods while reducing communication overhead from 11.71 MB to 0.27 MB and clustering time from 6.07 s to 0.44 s.

Stress has become an increasingly common issue, significantly impacting individuals' health and productivity. Traditional methods for assessing stress levels often rely on physiological signals, such as heart rate and skin conductance. However, these methods can be impractical for continuous, non-invasive monitoring. To address these limitations, we propose a machine learning approach for stress assessment using eye-tracking data. We collected eye-tracking and Electrocardiogram (ECG) data under different stress conditions. From this dataset, we extracted relevant features and conducted preliminary analysis. We further proposed a novel stress index, the Least Absolute Shrinkage and Selection Operator Stress Index (Lasso Stress Index), specifically tailored for stress detection in our dataset. In previous studies, researchers commonly used predefined subjective stress index or Baevsky's Stress Index (BSI) for stress classification. We compared these methods and found that our proposed Lasso Stress Index yielded the highest accuracy, achieving up to 90.6% in stress classification.

This paper proposes a heart rate estimation method using Variational Mode Decomposition (VMD) employing Multiple-Input Multiple-Output (MIMO) Frequency Modulated Continuous Wave (FMCW) radar. The proposed method first estimates the human position within the radar's coverage area, then reduces noise by focusing on the signal from these positions. The signal is decomposed into Intrinsic Mode Function (IMF) signals using VMD, and only the IMF signal related to the heartbeat is retained. Heart rate signal is reconstructed by weighting IMF signals based on their energy within the specific spatial area in which the human is located. The reconstructed signals are utilized for heart rate estimation through peak detection. The estimation is done over consecutive time windows. Until the fourth time window, among the estimated heart rates from the different cells, the selection is based on energy and periodicity. From the fifth time window onwards, the heart rate closest to the average of the previous four estimates is chosen. This approach considers the gradual transition of heart rate estimation over time to mitigate extraneous variations. Validation experiments involved 4 subjects being seated and stationary within the radar coverage area, with heart rate observed via MIMO FMCW radar. Results showed an average Mean Absolute Error (MAE) of 2.54 BPM, with an exclusion rate of 2.12%.

Semantic communication (SC) has emerged as a promising paradigm to address the bandwidth limitations of traditional wireless communication systems by transmitting only the essential meaning of data. This paper investigates an advanced SC framework for vehicular communication, employing diverse feature extraction techniques to encode multi-modal information, such as textual descriptions, object poses, semantic segmentation, and sketches, into compact semantic representations. These semantic encoders are evaluated based on their output size, faithfulness of reconstruction, and resilience to data loss. The proposed system model considers vehicular communication scenarios where vehicles transmit important information extracted from camera-collected data to other vehicles and road users, in bandwidth-constrained environments. Simulation results show the effectiveness of the proposed SC framework, with a reconstruction performance reaching 17.24 in Fréchet Inception distance (FID) and a an RMSE equal to 0.029 between the transmitted image and the reconstructed one. This performance is achieved while the data saving between the size of the original image and the transmitted semantics is equal to$\text{9 2. 2 5 \%}$.

High altitude platform station (HAPS) systems have emerged as a key solution to address the increasing networking demands of the Internet of Things (IoT), providing wide-area coverage, low latency, enhanced network resilience, and cost-effective service delivery, particularly in remote regions. Given that the continuous movement of HAPS and the inherent mobility of user equipments (UEs) often lead to low and unevenly distributed UE throughput, it is crucial for HAPS systems to dynamically control the antenna using beamforming techniques. However, the current reactive approaches to dynamic control fail to effectively minimize the number of low throughput UEs and achieve low time complexity. To overcome these challenges, we propose a clustering-aided particle swarm optimization (PSO) algorithm to determine the antenna parameters, enabling HAPS to configure multiple cells and dynamically control beams based on UE distribution. This algorithm leverages UE clustering information to redefine the search space, reducing the complexity while enhancing the ability to find the global optimum. Specifically, we propose a novel regulated K-means algorithm that groups UEs into appropriately balanced clusters, precisely reducing the search space for global optimization. Simulations using real-world UE distributions demonstrate that our proposed method outperforms conventional approaches in reducing low throughput UEs and providing balanced throughput distribution, while maintaining low computational complexity.

WiFi-based passive noncontact sensing is widely regarded as a leading technology in wireless sensing, owing to its extensive application scope and favorable growth outlook. Nevertheless, although current WiFi-based sensing techniques attain remarkable accuracy in identifying activities within particular scenarios, they need stronger generalization capabilities across different targets and environments, hindering further commercial development. To address this issue, this article uses convolutional neural network (CNN), BLSTM, and attention layers to propose a cross-subject transfer learning method based on the CNN-ABLSTM algorithm model. This method combines widely used transfer learning methods with deep neural network algorithms in cross-domain sensing. Specifically, this method leverages the performance advantages of the CNN-ABLSTM algorithm model in processing time-series data like channel state information (CSI) and utilizes transfer learning to fine-tune the pretrained model from the source domain for application in the target domain with different subjects. This enables faster and more accurate achievement of cross-subject tasks. The simulated results show that the proposed new approach achieves higher recognition accuracy and shorter training times than traditional transfer learning methods for cross-subject tasks. In testing with the dataset used, it achieves up to around 85% performance of activity recognition accuracy in cross-subject tasks.

WiFi-based wireless sensing has emerged as a promising passive sensing technology that is precious for human activity recognition (HAR) across diverse applications. However, achieving robustness across varying scenarios presents a significant challenge, limiting its broader adoption. To address this issue, we propose a robust cross-scenario incremental learning (IL) method for WiFi-based wireless sensing that leverages WiFi channel state information (CSI) and elastic weight consolidation (EWC) loss. Our approach integrates a convolutional neural network and attention-based long short-term memory (CNN-ABLSTM) framework, which effectively captures the spatial and temporal features of CSI data. The IL strategy enhances model adaptability across dynamic environments, while EWC minimizes catastrophic forgetting by preserving critical weights from prior tasks. The method’s integration of a memory set and EWCLoss enables it to balance the retention of learned features with adaptation to new scenarios, effectively mitigating performance degradation across tasks. Experimental results on the MM-Fi dataset demonstrate robust cross-scenario performance: starting with initial training on scene E01, the model achieves incremental recognition in new scenes E02, E03, and E04 with cross-scenario accuracies of 88.01%, 80.16%, and 70.93%, respectively. The proposed approach substantially improves cross-scenario adaptability and test accuracy compared to traditional and cross-domain methods such as transfer learning. This work marks a significant advancement toward robust and scalable WiFi-based wireless sensing for diverse real-world applications.

Activity recognition is essential in computer vision applications, such as smart homes and healthcare services. While RGB images have been widely used in this area, they pose challenges related to privacy invasion and environmental constraints. To address these issues, some research has explored using 3-D light detection and ranging (3-D LiDAR) to collect 3-D point cloud data for activity recognition. However, the high-computational cost and large model parameters required for processing 3-D point clouds remain major limitations. To overcome these challenges, we propose a novel multiclass activity recognition system based on skeleton extraction from depth images collected by 3-D LiDAR. First, we use 3-D LiDAR to collect depth images of ten distinct activities, such as walking, falling, and squatting. Next, we process these depth images using our proposed multiple dynamic nonlinear mapping (MDNLM) method. The MDNLM method enhances the clarity of human body details by adjusting the color distribution of depth values based on the human position, ensuring that more colors are allocated to specific regions of the human body. This enhancement allows a fine-tuned algorithm to extract skeleton joints accurately from the mapped images. Finally, the extracted skeletons are fed into a convolutional neural network combined with a long short-term memory network (CNN+LSTM) for multiclass activity recognition. Our proposed method achieved 100.0% accuracy for a 2-class classification task (fall detection), 99.0% accuracy for a 7-class classification task, and 94.7% accuracy for a 10-class classification task.

The development of a cost-effective digital biomarker for detecting dementia is highly needed. While numerous studies have explored dementia detection through speech and natural language analysis, only a few studies have focused on dementia detection using face video recordings, and more in-depth research is needed. In this paper, we propose a method for detecting dementia and mild cognitive impairment (MCI), a pre-dementia stage, by utilizing four types of facial expression features extracted from recorded videos of participants. These features include Action Units, emotion categories, Valence-Arousal, and face embeddings. From the above features obtained from each video frame, various statistical information was extracted and used as features, and predictions were performed using a decision tree-based model. Our method was evaluated using face video recordings during conversations. The method achieved an area under the receiver operating characteristic curve (AUC) of 0.933 for dementia detection and 0.889 for MCI detection. Statistical analysis of facial expression features revealed that participants with dementia had fewer positive emotions, more negative emotions, and lower valence and arousal than healthy participants. These results indicate that the proposed method could serve as an explainable screening tool for the early detection of dementia and MCI.

Federated Learning (FL) is a machine learning (ML) approach that allows a model to be trained across multiple decentralized devices holding local data samples without exchanging them. In the realm of Wireless Sensor Networks (WSNs), FL has not attracted much attention given that FL is typically meant to train models on data collected by much fewer and decently more powerful devices. However, given the potential of WSNs to collect diverse data in hazardous regions, we aim to explore how to employ FL to collect data in an area of interest where we have a natural disaster. In this paper, we introduce a novel task with regards to FL in the context of WSN for natural disaster management. Given a region where wireless sensors are deployed and data samples are distributed, we aim to cluster the sensors so that each cluster can be treated as a FL agent in a way that accelerates the process of FL.

Currently, the field of wireless sensing is moving towards non-contact and easy-to-deploy passive sensing technologies. Among these, sensing techniques based on WiFi channel state information (CSI) have emerged as highly promising due to their excellent performance and suitability for current sensing needs. However, despite the potential of WiFi CSI-based sensing technologies, there are still pressing issues that need to be addressed. Traditional WiFi CSI-based methods face challenges such as weak generalization ability and poor robustness, especially when the sensing target and environment change, which hinders the further development. To address this problem, this paper introduces the transfer learning method and combines it with the deep neural network to propose a novel cross-subject WiFi sensing method. Specifically, this method utilizes the source domain-target domain partitioning approach in transfer learning. In the source domain, deep neural networks are trained to obtain the source domain feature model, which is then transferred to the target domain. Fine-tuning is performed using techniques such as network freezing, aiming to meet the faster and more accurate sensing task demands of cross-subject. From the final experimental results, the novel cross-subject transfer learning method proposed in this paper achieved higher recognition accuracy and shorter training time. Moreover, the implementation of network freezing further enhanced the performance and efficiency of cross-subject, achieving up to 86% performance on the dataset used in this paper.

MIMO FMCW Radar, a non-contact heart rate (HR) monitoring technology, has emerged as one of the superior alternatives to contact-based sensors, providing precise HR estimation without the drawbacks of discomfort or privacy concerns, and excelling in diverse environmental conditions. Recent HR estimation studies using conventional methods have achieved high accuracy but face challenges with lengthy processing times and sensitivity to experimental conditions, affecting real-time application and robustness. A previous Deep learning (DL)-based approach improves on these aspects but is limited by the range resolution of SISO FMCW Radar and the requirement for close positioning of subjects. Additionally, this method has inability to utilize contextual information from adjacent time windows restricts its effectiveness for time series analysis. Thus, our proposed method combines a Curve-Length (CL) approach with a DL rough-to-fine model, addressing the limitations of previous studies and improving HR estimation accuracy and robustness. This integrated process begins with human location detection through a CL-based approach and is followed by a two-phase rough-to-fine HR estimation. The experimental results show significant improvement over the conventional methods.

This paper presents a radar-based heart rate monitoring and Inter-beat interval (IBI) estimation. Traditional IBI estimation relies on peak detection combined with signal processing techniques. Our approach uses signal reconstruction with a neural network, which significantly improves the accuracy and robustness of IBI estimation compared to conventional methods. By utilizing multi-channel input data, our approach effectively mitigates various sources of noise and interference, resulting in highly accurate and reliable IBI predictions. Instead of relying solely on peak detection, we use the U-net architecture and cross-channel attention mechanism to reconstruct the triangular waveform generated from the ground truth ECG signals. The incorporation of multi-channel input and channel-wise attention mechanism improves our model's ability to discriminate and em-phasize critical features from different input channels, further improving IBI estimation accuracy. To evaluate the accuracy and robustness of our proposed method, we trained our model on the open-source dataset [1], and then performed leave-one-subject-out validation, which ensures our approach to be evaluated only on unseen independent subjects. We have achieved a Root Mean Square Error (RMSE) of 26.7 ms for the IBI of each heart-beat. Our results demonstrate the transformative potential of adopting signal reconstruction methods supported by state-of-the-art deep learning techniques. This shift in perspective promises more accurate and robust heart rate and IBI estimation, opening new avenues for improving the accuracy and reliability of cardiac monitoring systems.11This work was supported by JST ASPIRE Grant Number JPMJAP2326, Japan.

Mental stress is something we experience on a daily basis. However, when it becomes chronic, it has various negative effects on our body. Although stress monitoring methods based on physiological signals are effective, they may not provide a comfortable experience for users, as they require sensors to be worn or attached to the body. As such, the need for non-invasive, non-contact and comfortable methods arises. In this paper, we propose a stress detection method using face-related and emotion-related features, all of which can be acquired by using a camera. Face-related features include action units and face embedding. Emotion related features include valence, arousal and emotion-related labels. Through these features and their fusions we achieved accuracy of 1.000 for stress detection, 0.891 for task recognition and 0.883 for stress level classification, respectively, with the sample sizes of 111, 316, and 319, respectively. These results demonstrate that our proposed method using face-related and emotion-related features and their fusion is effective in stress monitoring and detection.

Electrocardiogram (ECG) measurement is a fundamental diagnostic and monitoring tool in cardiology and healthcare. It plays a crucial role in identifying and managing cardiac conditions, assessing heart function, and improving patient outcomes through timely interventions and treatment adjustments. Conventional approaches for ECG measurement are often unsuitable for everyday use due to their invasiveness, inaccessibility, or limited accuracy. In this context, we introduce ECGDiff, a novel approach based on conditional denoising diffusion models for ECG signals reconstruction from Doppler signals. ECGDiff provides a non-intrusive and accessible method for non-contact ECG measurement. Our method represents a pioneering use of denoising diffusion models for time series trans-lation. In the proposed framework, ECG signals are iteratively reconstructed from random noise using preprocessed signals derived from a Doppler sensor as input conditions. Extensive experiments have been conducted on a dataset comprising 19 healthy individuals, consisting of pairs of synchronized Doppler and ECG signals. Our experimental results demonstrate that the proposed ECGDiff outperforms other state-of-the-art methods by a large margin for the task of ECG signals reconstruction. Specifically, we achieved a DTW score of 8.32, a Frechet distance score of 3.10, and a Pearson correlation coefficient of 0.93. These results highlight the effectiveness of our approach for reconstructing ECG signals from Doppler signals.

Pose estimation and human action recognition (HAR) are pivotal technologies spanning various domains. While the image-based pose estimation and HAR are widely admired for their superior performance, they lack in privacy protection and suboptimal performance in low-light and dark environments. This paper exploits the capabilities of millimeter-wave (mmWave) radar technology for human pose estimation by processing radar data with Graph Neural Network (GNN) architecture, coupled with the attention mechanism. Our goal is to capture the finer details of the radar point cloud to improve the pose estimation performance. To this end, we present a unique feature extraction technique that exploits the full potential of the GNN processing method for pose estimation. Our model mmGAT demonstrates remarkable performance on two publicly available benchmark mmWave datasets and establishes new state of the art results in most scenarios in terms of human pose estimation. Our approach achieves a noteworthy reduction of pose estimation mean per joint position error (MPJPE) by 35.6% and PA-MPJPE by 14.1% from the current state of the art benchmark within this domain.

With the aging of the population, the health of the elderly people has become a concern for many families. Monitoring of elderly people and the detection of their activities have become hot research topics. Several approaches have been proposed in the literature to detect such activity (e.g., falls), but their reliance on RGB cameras poses a serious threat to the privacy of the elderly. Therefore, Light Detection and Ranging (LiDAR) has attracted the attention of researchers. In this paper, we propose a novel method for fall detection using transfer learning and dynamic non-linear mapping to extract the human skeletons from depth images and implement a fall detection method using a Long Short-Term Memory (LSTM) neural network. We collected RGB images and depth images using 3D-LiDAR. The RGB images are used as a ground-truth for annotation and evaluation, whereas depth images are used as input to our proposed method. For fall detection, we achieved 98.5% accuracy, 97.0% precision, 100% recall, and 98.5% F1 score.

Semantic communication plays a crucial role in human interactions, allowing for the exchange of complex ideas and concepts. In this paper, we introduce a novel approach to semantic communication leveraging image generative Artificial Intelligence (AI) models, specifically stable diffusion models. Unlike conventional works, our system enables the transmission of images through a physical channel by transforming them into multi-dimensional semantic representations consisting of text descriptions, low-resolution sketches, and pose information. At the receiver’s end, these semantic representations are used to reconstruct the original image using a trained stable diffusion model. The benefits of our approach include reduced transmission bandwidth requirements, flexibility in reconstruction styles, adaptability to multiple receivers’ preferences, and the ability to omit unwanted image elements. We present preliminary results demonstrating the feasibility and effectiveness of our method. The similarity score between the transmitted images and reconstructed ones reach values ranging between 0.015 and 0.029 in Root Mean Square Error (RMSE) and between 0.993 and 0.998 using a Siamese network.

This paper aims to address the issue of low through-put for users, caused by the random movement of High-Altitude Platform Stations (HAPS) due to winds. The proposed solution involves developing an Equal Clustering (EC) approach that groups users into high-density clusters, ensuring an equal num-ber of users in each cluster while maintaining low complexity. To further enhance the system's throughput performance, we fine-tune the antenna parameters using a Deep Q-Network (DQN) and the results of the EC clustering. To evaluate the effectiveness of the proposed method, we compare it with three Reinforcement Learning (RL)-based approaches and a K-Means clustering-based method. Simulation results indicate that both the EC method and the EC-aided DQN method successfully enhance the Cumulative Distribution Function (CDF) performance of throughput distribution when compared to the RL-based method for both rotation and shift scenarios. Furthermore, the EC-aided DQN method outperforms the K-Means clustering-based method in terms of the CDF of throughput performance.

High Altitude Platform Stations (HAPS) are instrumental in wireless communications, providing enhanced connectivity and extensive coverage by complementing ground-based infrastructure where its expansion is limited. HAPS enhance wireless communications by employing advanced beamforming technology, traditionally based on 2D with free space path loss models. Addressing the inadequacy of these models in different areas, our research introduces a novel beamforming strategy that incorporates detailed 3D geographic and architectural information. This approach models line-of-sight (LOS) and non-line-of-sight (NLOS) conditions with 3D information and optimizes beamforming patterns using Deep Reinforcement Learning (DRL). Our results indicate that by incorporating 3D information, the beamforming performance in terms of average throughput and SINR is markedly enhanced across all user equipments (UEs), compared to traditional 2D approaches. By taking 3D information into account, beamforming in HAPS systems becomes more equitable.

To leverage antenna diversity effectively in Massive Multiple-Input Multiple-Output (MIMO) systems, Channel State Information (CSI) utilization at the base station (BS) is crucial. In Frequency Division Duplexing (FDD) MIMO setups, downlink CSI is acquired by user equipment (UE) and transmitted back to the BS. However, this feedback overhead diminishes communication throughput, necessitating CSI compression technologies. Methods such as traditional compression or more advanced ones such as Transformer-based neural networks which aim to address this issue suffer from low compression rates or high computational cost. In this context, Reformers emerge as a potential solution as they employ Locality-Sensitive Hashing (LSH) attention, offering a comparable accuracy to Transformers but with reduced computational demands. In this paper, we propose a CSI feedback method using Reformer. Specifically, by replacing the multi-head attention of the CSI feedback method using Transformer with the LSH attention of Reformer, we aimed to achieve similar CSI reconstruction accuracy while reducing computational complexity. Computer simulations confirm that the CSI feedback method using Reformer reduces computational complexity by about 12% while achieving comparable CSI reconstruction accuracy compared to the CSI feedback method using Transformer.

The increasing demand for spectral efficiency and system capacity in communication networks has driven the integration of Non-Orthogonal Multiple Access (NOMA) technology with Unmanned Aerial Vehicle (UAV) networks. In this paper, we propose an enhanced user clustering and pairing scheme for NOMA-aided UAV networks. Our study aims to maximize the minimum user throughput by proposing an Advanced Balanced K-Means (ABKM) algorithm, based on the traditional K-Means (KM) and Balanced K-Means (BKM) algorithms. The ABKM algorithm addresses the issue in the BKM algorithm where some users are assigned to sub-optimal clusters, resulting in increased distances to the cluster centroids, while simultaneously ensuring balanced clustering. Through extensive numerical simulations, we demonstrate that the ABKM algorithm significantly outperforms KM and BKM algorithms in terms of the minimum user throughput. The results highlight the potential of the proposed ABKM algorithm to enhance system performance and ensure fair resource allocation in NOMA-aided UAV networks, making it a promising solution for future 6G wireless communication systems.

Belief propagation (BP) detection is a technique for separating and detecting incoming signals with minimal complexity in massive multiple-input multiple-output (MIMO) systems. However, because of the interference and noise that remain in the received signals even after attempting to remove them through conventional techniques, errors manifest in the transmitted messages. Due to the MIMO channel's numerous loops, a message containing mistakes spreads across the factor graph leading to a degradation in the BP's convergence properties and detection performance. In this paper, we propose a BP detection using deep image prior (DIP) with deep neural network (DNN)-trained scaling factor. By applying DIP to the BP detection algorithm, we achieve a reduction in residual interference and noise. Post DIP application, there is a modification in the variance of both interference and noise components. To align it more accurately with its true value and enhance message reliability, we adjust the variance using scaling factors trained through DNN-based damped BP (DNN-dBP). Using computer simulations, we demonstrate that applying DIP helps decrease the power of the residual interference and noise after removing the interference at each iteration in the BP detection. It is also shown that the proposed method improves the detection performance compared to the normal BP detection, BP detection without DIP when training the scaling factors of the variance, and BP detection to which DIP is applied without training the scaling factors of the variance.

Over the past few years, there has been a significant rise in the number of fall accidents occurring among elderly individuals, a problem that has been accentuated with to the aging population. Researchers and developers have focused their efforts on investigating and creating various fall detection methods that utilize an accelerometer. However, conventional fall detection methods typically target specific positions where accelerometers are placed. In addition, they suffer from low accuracy which can be attributed to the fact that the classification algorithms commonly employed, such as the support vector machine (SVM) and the random forest (RF), are not specialized in making predictions based on time series data. In this paper, we propose the fall detection method based on a long short-term memory (LSTM) neural network, using an accelerometer. In the proposed method, four kinds of possession positions are set: (i) in hand, (ii) inside a chest pocket, (iii) inside a waist pocket, and (iv) in a bag. The acceleration data collected are classified using the LSTM classifies into one of four classes: (i) standing, (ii) walking, (iii) falling, and (iv) lying down. The results of the multi-class classification are further reclassified into two classes, i.e., fall and non-fall. The experimental results demonstrate that our approach outperforms the conventional methods in terms of fall detection accuracy.

A key concept in health monitoring systems for elderly people is the continuous and non-intrusive detection of their activities to identify when hazardous events such as sudden falling occur/are about to occur. The existence of obstacles in the environment largely limits the detection performance of existing approaches of activity detection relying on non-contact sensors. A simple, yet effective, approach to address this issue is the use of multiple sensors which collaborate with one another. In this paper, we propose an approach that relies on 2D Light Detection and Ranging (LiDAR) technology for activity detection. We employ multiple 2D LiDARs placed at different locations in a single room with difference obstacles (e.g., furniture) and working in coordination to construct a fuller representation of the activities being performed. Our approach transforms the concatenation of the different LiDAR data into a more comprehensible data format (i.e., images). The generated images are then processed using a Convolutional LSTM Neural Network to perform the classification. For 3 different tasks, namely activity detection, fall detection, and unsteady gate detection, our proposed approach reaches an accuracy equal to 96.10%, 99.13% and 93.13%, respectively.

An Electrocardiograms (ECG) is a recording of the heart's electrical activity. It can help detect problems with one's heart rate or heart rhythm. Traditional methods to measure and collect ECG are not practical for daily use due to their invasive nature and inaccessibility. Thus, a less intrusive and more accessible method is needed. In this paper, we propose a method that uses attention-based Wasserstein Generative Adversarial Networks-Gradient Penalty (aWGAN-GP) to reconstruct ECG signals from ones collected using a Doppler sensor. GANs can capture pertinent features in the Doppler signals to enable such reconstruction. Our approach uses the integrated spectrum of the Doppler signal to identify R-peaks, which are then employed to train the aWGAN-GP to reconstruct the ECG signal. We evaluated this method on 19 healthy subjects and obtained a correlation coefficient of 0.88 between the reconstructed and actual ECG signals, outperforming the conventional CNN-based method which reached only 0.35. Our results demonstrate that it is possible to reconstruct an ECG signal from a heartbeat signal collected via a Doppler sensor using aWGAN-GP.

High Altitude Platform Station (HAPS), functioning as a flying base station (BS) positioned in the stratosphere, has gradually captured more interest in the field of mobile communications. HAPS holds the potential to deliver extensive coverage areas and resilient networks in the face of disasters. Using beamforming techniques, a HAPS can configure multiple cells within its coverage area to serve a large user population. However, the position of HAPS and the distribution of user equipment (UE) changes with time, resulting in changes in the relative position between HAPS and UEs. Consequently, the maximum throughput of UE decreases and some UEs can suffer network outages. A previously proposed method treats this as an optimization problem and tries to maximize throughput based on an objective function. However, the computational complexity is still too high for real-time control. To help beams respond faster to position changes, some AI-based methods are proposed but they cannot guarantee that low throughput UEs are well minimized. In this paper, we propose a K-means clustering-aided particle swarm optimization (PSO) algorithm that can adjust the cell configuration to minimize the number of low throughput UEs. Taking advantage of K-means clustering, this method redefines the search range for each parameter to help PSO quickly converge to the optimum. By running simulations using realistic UE distributions in some cities, we demonstrate the superiority of our proposed method in terms of computational complexity and ability to reduce low throughput UEs.

Depression is a common mental illness and the second leading cause of disability worldwide. Traditional depression diagnosis requires communication with patients and subjective cooperation of patients, which consumes a lot of manpower, material resources, and time costs. With the accumulation of user data in social media and the development of natural language processing, computer-aided diagnosis is realized, better and objective analysis is provided, and a new idea for the diagnosis of depression is provided. We propose a multimodal model based on EmoBERTa and Transformer and a text preprocessing method for a specific pre-trained model and application context. We use user behavior information and past tweets to detect whether a user has depression. Our model achieves state-of-the-art performance on a publicly available multimodal Twitter dataset.

In this paper, we propose a novel data augmentation framework where an attention-based Wasserstein Generative Adversarial Networks-Gradient penalty (aWGAN-GP) is used to augment Doppler radar signals from electrocardiogram (ECG) signals. Besides, we present a new heart rate (HR) range classi-fication algorithm by applying support vector machine (SVM) to classify Doppler radar signals depending on the HR ranges (i.e., into low, normal, and high). Finally, since the class distribution of ECG samples is also imbalanced, a simple augmentation method for ECG signals is proposed to prepare new ECG inputs for the trained generator, which can be used to synthesize Doppler radar signals to balance the training set used by SVM. Our experiments show that the Doppler radar signals generated by aWGAN-GP provide more accurate morphology in terms of root mean squared error (RMSE) and Pearson's correlation coefficient (PCC). In addition, the proposed method achieves the lowest relative Fréchet inception distance (rFID), which shows a better diversity in the generated Doppler radar signals. In regard to HR range classification, the proposed method relieves the data imbalance problem and obtains better classification performance in terms of accuracy, F1-score, and recall.

This paper presents a radar-based, non-contact Blood Pressure (BP) estimation model based on accurate detection of cardiac activities, which enables BP monitoring to be performed in a touch-free and continuous manner. Cardiac movements have been regarded as essential factors for BP estimation. However, accurately obtaining these movements by a radar system remains a challenging problem because these movements are too inconspicuous and could be easily hindered by respiration and random noise. In this paper, we propose a method that mainly focuses on cardiac feature extraction in radar-based BP monitoring. First, we employ an integrated-spectrum waveform. It is derived from short-time Fourier transform (STFT) and is capable of recording and preserving minor cardiac activities. Compared with the pulse-wave signals used in previous works, the integrated-spectrum focuses on energy changes introduced by short and high-frequency vibrations. It can eliminate the interference of respiration and random noise, and cardiac contractile movement can be reserved accurately. Second, we propose a cardiac features estimation method in which a hidden semi-Markov model (HSMM) is applied to the integrated-spectrum for feature extraction. Compared to the pulse wave signal, the Root-Mean-Square Error (RMSE) of the estimated interbeat intervals (IBI), Systolic time, and Diastolic time is reduced by 44.2%, 73.3%, and 76.7% respectively. The estimated accurate cardiac features are further used as inputs for a Random Forest model for BP prediction. Though previous work required the subject to hold one's breath, we achieved a comparable prediction accuracy even when our subject is breathing normally. The Diastolic BP (DBP) error of our model is$4.27\pm 5.84$mmHg (Mean Absolute Difference ± Standard Deviation), and the Systolic BP (SBP) error is$6.63\pm 8.95$mmHg.

In this paper, we propose a Mean Field reinforcement learning (MFRL) method for dynamic antenna control in High-Altitude-Platform-Station (HAPS) communication system with Multi-Cell Configuration. HAPS works at stratospheric altitudes of about 20 km to provide an ultra-wide coverage area. However, the wind pressure caused HAPS movement leads to the degradation of users' throughput. Considering the multi-antenna arrays in the HAPS, to find the optimal antenna parameters of all antenna arrays for reducing the number of low-throughput users, we formulate the antenna control problem into stochastic game equilibrium. Usually, solving the stochastic to find the equilibrium needs very high computation complexity to calculate the transition probability for getting the$\mathcal{Q}$-value under a certain state and action. Therefore, we use the reinforcement learning (RL) named Deep$\mathcal{Q}$-Network (DQN) to learn the transition probability and predict the Q-value according to the reward fed backed from the environment. Besides, we employ the Mean field Game theory in conjunction with RL during the training phase of DQN to reduce the complexity of the interactions among agents. To evaluate the proposed method, we compare the proposed method with a genetic algorithm (GA) named Particle Swarm Optimization (PSO),$\mathcal{Q}$-learning, Fuzzy$\mathcal{Q}$-learning, and conventional DQN under four realistic user distribution scenarios. The simulation results show that the proposed method achieves comparable throughput performance with a high convergence rate.

Twitter has skyrocketed over the past few years and has become a major social media platform. At the same time, the number of social robots on Twitter has also increased significantly. These bot accounts imitate the speeches of normal users to manipulate public opinions, affect the normal communication of users. Therefore, bot account detection came into being. Despite extensive research efforts, bots on Twitter are still evolving to evade detection. Most of the current bot detection methods have a single structure and cannot detect and identify different types of bot accounts well. In this paper, we propose a new system for social robot detection that uses a RoBERTa (Robustly Optimized Bidirectional Encoder Representations from Transformers Pretraining Approach) classifier and a random forest regressor with similarity analysis. In particular, the system considers the similarity of tweets and uses a voting system in addition to a set of features extracted from the user profile information and the tweets themselves. We conduct experiments using the largest dataset of bots available and show that the accuracy of our system is up to 0.8588, which is higher than that of all the other baseline methods.

Non-contact measurement of the heart rate (HR) refers to the usage of wireless sensors (e.g., Doppler sensors) to identify the heart-related faint movements and to reconstruct the R-peaks or estimate the HR. Conventional work in the field requires the chest of the subject being monitored to be in a specific position in front of the sensor. In our previous work, we have proposed to use a Multiple-Input Multiple-Output (MIMO) Doppler Radar to perform the detection of heartbeats even when the Signal-to-Noise Ratio (SNR) is not very high. By exploiting the fact that different beams have different SNR of heartbeat components, our previous method detects heartbeats by aggregating several received signals. In general, it is essential to use beam directions toward the a subject’s chest. However, the chest location estimation is challenging, when there exist several subjects or other moving objects. In the current paper, to deal with this issue, we narrow down the direction of beams to use by using a system composed of a MIMO Doppler sensor and a Light Detection and Ranging (LiDAR) device. By means of transfer learning and automatic annotation of data, the LiDAR is trained to identify the relative chest angle and distance to the subject from the devices, while the MIMO Doppler Radar can adjust the beam towards the identified direction. Throughout experiments, we show the effectiveness of the combination of both the Lidar and radar in detecting the direction and distance to the subject as well as the heartbeat.

In the 5th generation mobile communications (5G) and 5G and beyond (B5G), a high altitude platform station (HAPS) is expected to serve as a flying base station (BS) to provide communications over wide areas. In the HAPS system, a multi-cell configuration with multiple beams is considered to increase system throughput. When the HAPS is subjected to wind pressure, the cell range moves accordingly, causing degradation of received signal power and handover to the user equipment (UE). To suppress such degradation and handover, beam control of HAPS is necessary. However, it is not easy to control the beam because multiple antenna parameters affect each other and determine the cell range. In this paper, we propose a beam control method for HAPS using fuzzy Q-learning in multi-cell configuration. In this type of learning, the variable states are controlled by the use of fuzzy sets, which allows multiple searches to be performed in one setup, thus reducing the cost of search, compared with conventional Q-learning. In the proposed beam control method, antenna parameters are controlled by fuzzy Q-learning so that the number of users having a received signal power larger than a predetermined threshold becomes larger in each cell. We evaluate the proposed method by computer simulation and show that the proposed method can improve the number of users having a received signal power larger than a predefined threshold and thus reduce the number of users with low throughput compared to before learning.

Accessing the accurate downlink channel state information (CSI) is essential to take full advantage of frequency division duplex (FDD) massive multiple-input multiple-output (MIMO) systems due to its weak channel reciprocity. Meanwhile, great computational burdens will happen, which is accompanied by continuous CSI feedback. The existing compressive sensing (CS)-based and deep learning (DL)-based methods try to solve such problems, but do not achieve desired effect to get ideal CSI feedback or decrease the overhead. An adaptive deep neural network (DNN)-based CSI feedback method is proposed in this paper to address this. A classification block of the compression ratio is adopted and modified to apply to a more complex channel model named Clustered-Delay-Line (CDL), which helps decrease the computational overhead of the network. Besides, the reconstruction accuracy of the CSI feedback is further improved by proposing a new structure of the encoder. Quantization and dequantization modules are also applied to make the whole network more robust and effectively minimize the quantization distortion in the real communication scenario, respectively. The simulation results show that the proposed method performs better than the conventional ones on the CSI reconstruction accuracy in terms of normalized mean square error (NMSE), even though the quantization module is added.

In this research, we propose a novel antenna control method for reducing the number of low throughput User Equipments (UEs) caused by the movement and rotation of High-altitude platform station (HAPS). We assume that each HAPS has three antenna arrays for serving one region that consists of three cells and that we know the UE locations in each cell. In the proposed method we first redesign the cell configuration for each HAPS and then divide all UEs into three cells based on the UE locations. Based on the radius and center location information of three new cells, we can mathematically calculate the antenna parameters by the desired coverage model. Thus, each antenna array will be controlled to serve a new cell, respectively. We evaluate the proposed method under 5 different UE distribution scenarios. The simulation results show that, in 5 different UE distribution scenarios, the proposed method can reduce the number of UEs with low throughput. Compared with the conventional method, the proposed method can achieve good throughput performance in all the scenarios.

Activity detection is a key task in the monitoring of elderly people living alone. This is because it helps locate them and identify any accident that might occur to them. In this article, we propose a novel approach that uses 2-D light detection and ranging (LIDAR) and deep learning to perform activity detection. In a first step, our approach processes and interpolates the data collected using the 2-D LIDAR following an algorithm we propose to locate the person and identify the useful data points. In the next steps, the data are transformed into two types of representations: 1) a time-series type and 2) an image type. The time-series data are used to train different long short-term memory (LSTM) networks to identify the person and to recognize his/her activity, while the image type is used to fine-tune a convolutional neural network (CNN) for fall detection. Throughout our experiments, we show that our approach allows for the identification of people from their gait, and the detection of unsteady gait or unstable walk (i.e., when the person is about to fall or feeling dizzy) as well as the detection of up to four activities: 1) walking; 2) standing; 3) sitting; and 4) falling. The results obtained from our experiment show that the proposed method reaches an accuracy equal to 94.1% for multiclass activity detection, 98.6% for fall detection, 93.2% for person identification (for three different people), and 92.5% for unsteady walk detection.

Wi-Fi channel state information (CSI)-based fall detection systems have a great potential compared with other alternatives since they are nonintrusive and nonspace limited. However, in the conventional work on Wi-Fi CSI-based fall detection, a phenomenon is commonly observed: the classification performance degrades when data in different environments are used for learning and testing. Nonetheless, when the signal-to-noise-power ratio (SNR) is small, the conventional methods cannot capture features of motion and cannot segment signals accurately. Therefore, there is a need to address these problems in order to build a robust fall detection system. In this article, we propose a spectrogram-image-based fall detection using Wi-Fi CSI. Unlike the conventional method, CSI is segmented with a certain sliding-time window, and then the classifier detects fall by using the spectrogram image generated from the segmented CSI. We use a pretrained convolutional neural network (CNN) optimized for binary classification of the spectrogram images of the fall and nonfall motions. We carried out experiments to evaluate the classification performance of our proposed method against the conventional one by using motion data in two different rooms for learning and testing. As a result, we confirmed that our proposed method outperforms the conventional one and reaches over 0.92 accuracy. In addition, compared with the conventional method, the fall detection performance of our method does not degrade even when using different environment data for learning and testing.

Accurate localization of devices in 5G cellular networks is of that utmost importance. This is because location information is a key component of a variety of new emerging applications. In particular, collocation (or co-location) refers to the idea of identifying devices that are located within a certain range from one another. In this paper, we propose a novel technique for inter-user distance estimation that uses low-resolution and high-resolution beam energy-based images as location fingerprints. Our approach uses the beam energy-based images generated by different users to estimate the distance between each pair of them. Nevertheless, we explore the idea of using a deep learning technique referred to as super resolution applied on low-resolution beam energy-based images to enhance their resolution, thus identify collocated users with an accuracy comparable to that of higher resolution ones. More specifically, throughout our experiments, we generate images of resolution$4\times 4$and$8\times 8$and use these for distance estimation between users. Afterwards, we apply super resolution on images with size$4\times 4$to improve their resolution, and compare their results to the ones obtained with the original$8\times 8$images. For an area roughly equal to$60\times 30\ \mathrm{m}$, our proposed approach reaches an average mean squared error equal to 0.13 m. We also demonstrate how our proposed approach outperforms the conventional ones that rely on user location detection to measure the inter-user distance.

Monitoring elderly people living alone is of the utmost importance given the amount of risk they are exposed to. Being aware of the activities of the elderly person in real time could help prevent/detect dangerous event that might occur such as falling. In this paper, we propose a method for activity detection using a 2D LIght Detection and Ranging (LIDAR) and deep learning. Unlike conventional work, where an activity refers to moving from one position to another, we use the term “activity” to refer to a set of movements including walking, standing, falling and sitting. Not only does our approach detect these activities, but it also identifies a given person from his gait, and identifies unsteady gait (i.e., when he is about to fall or feeling dizzy). Throughout our experiments, we show that the proposed approach could reach an accuracy equal to 92.3% and 91.3% in activity and unsteady gait detection, respectively. It is also capable of identifying up to 3 people's gait with an accuracy equal to 92.4% using 10 seconds of walking data.

Fall detection system has a great demand for elderly people living alone. Wi-Fi CSI (Channel State Information) based fall detection method can be used to build non-intrusive and nonspace- limited fall detection systems. In the conventional work on Wi-Fi CSI based fall detection, a classification performance degradation has been observed when data in different environments is used for learning and testing data. Also, that method can not capture accurate features of motion due to the signal distortion during the noise reduction, and it can not segment signals accurately when the SNR (Signal to Noise power Ratio) is small. In this paper, we propose a spectrogram image-based fall detection using Wi-Fi CSI. Unlike the conventional method, CSI is segmented with a certain sliding time window, and then the classifier detects fall by using the spectrogram image generated from segmented CSI. We use a CNN (Convolutional Neural Network) for binary classification of the spectrogram images of the fall and non-fall motions. We carried out experiments to evaluate the classification performance of our proposed method against the conventional one by using motion data in two different rooms for learning and testing data. As a result, we confirmed that our proposed method outperformed conventional one and reached 0.90 accuracy.

Twitter is attracting significant interests from the research community in the last few years. Sentiment analysis of tweets is among the hottest topics of research nowadays. State of the art approaches of sentiment analysis present many shortcomings when classifying tweets, in particular when the classification goes beyond the binary or ternary classification. Multi-class sentiment analysis has proven to be a very challenging task. This is mainly for the simple reason that a tweet usually does not contain a single sentiment, but many ones. In this paper, we propose a pattern-based approach for sentiment quantification in Twitter. By quantification, we refer to the detection of the existing sentiments within a tweet and the detection of the weight of these sentiments. In a first step, we classify tweets into positive, negative, or neutral. Our approach reaches an accuracy of 81%. We then perform the sentiment quantification on the sentimental tweets (i.e., positive and negative ones) to extract the sentiments within them: we define 5 positive sentiment sub-classes 5 negative ones and detect which exist in each tweet. We define 2 metrics to measure the correctness of sentiment detection, and prove that sentiment quantification can be a more meaningful task than the regular multi-class classification.

Most of the state of the art works and researches on the automatic sentiment analysis and opinion mining of texts collected from social networks and microblogging websites are oriented towards the classification of texts into positive and negative. In this paper, we propose a pattern-based approach that goes deeper in the classification of texts collected from Twitter (i.e., tweets). We classify the tweets into 7 different classes; however the approach can be run to classify into more classes. Experiments show that our approach reaches an accuracy of classification equal to 56.9% and a precision level of sentimental tweets (other than neutral and sarcastic) equal to 72.58%. Nevertheless, the approach proves to be very accurate in binary classification (i.e., classification into “positive” and “negative”) and ternary classification (i.e., classification into “positive”, “negative” and “neutral”): in the former case, we reach an accuracy of 87.5% for the same dataset used after removing neutral tweets, and in the latter case, we reached an accuracy of classification of 83.0%.

Opinion mining and sentiment analysis refer to the identification and the aggregation of attitudes or opinions expressed by internet users towards a specific topic. However, due to the limitation in terms of characters (i.e. 140 characters per tweet) and the use of informal language, the state-of-the-art approaches of sentiment analysis present lower performances in Twitter than that when they are applied on longer texts. Moreover, presence of sarcasm makes the task even more challenging. Sarcasm is when a person conveys implicit information, usually the opposite of what is said, within the message he transmits. In this paper we propose a method that makes use of a minimal set of features, yet, efficiently classifies tweets regardless of their topic. We also study the importance of detecting sarcastic tweets automatically, and demonstrate how the accuracy of sentiment analysis can be enhanced knowing which tweets are sarcastic and which are not.

Sarcasm is a special form of irony by which the person conveys implicit information, usually the opposite of what is said, within the message he transmits. Sarcasm is largely used in social networks and microblogging websites, where people mock or criticize in a way that makes it difficult even for humans to tell if what is said is what is meant. Recognizing sarcastic statements can be very useful when it comes to improving automatic sentiment analysis of data collected from social networks. It helps also enhance the efficiency of after-sales services or consumer assistance through understanding the intentions and real opinions of consumers when browsing their feedbacks or complaints. In this paper we propose a method to detect sarcasm in Twitter that makes use of the different components of the tweet. We propose four sets of features that cover different types of sarcasm we defined, and that will be used to classify tweets into sarcastic and non-sarcastic. We evaluate the performances of our approach. We study the importance of each of the proposed sets of features and evaluate its added value to the classification.