Explore the vast range of titles available.

Mental health is essential for well-being, but poorly managed emotions can lead to depression and anxiety. Early emotion recognition systems support timely intervention. While physiological signals like ECG and EEG are accurate, they are invasive for everyday use. This study uses Facial Landmark Trajectories, namely EMO features, from the ASCERTAIN dataset, a non-invasive method tracking facial movements to capture authentic emotions. In contrast to the original dataset, in our work these emotions are classified into four valence-arousal quadrants: High Arousal High Valence (HAHV), High Arousal Low Valence (HALV), Low Arousal High Valence (LAHV), and Low Arousal Low Valence (LALV). To address the inherent class imbalance in this 4-class problem, the SMOTE, GAN, and CTGAN techniques are utilized to generate synthetic data for balanced classes. Four machine learning models, namely, KNN, SVM, Decision Tree, and Random Forest are tested on the augmented datasets, evaluated via confusion matrices and density plots for identifying overfitting. Experimental results demonstrate that CTGAN shows the least overfitting, with synthetic data closely matching the original and Random Forest achieving the highest accuracy (75%) and balanced true positive rates (>40% for all classes), demonstrating the potential utility of using Facial Landmark Trajectories for the development of an efficient automated emotion recognition system.

The misclassification of human activity information by IoT-based smart, health monitoring devices raises concerns about their reliability. For instance, the identification of walking activity by wrist-worn, hand-held, or pocketed devices is often error-prone because tracking of actual leg movement is necessary for proper identification of a walk. In contrast, wearable systems on the waist recognize the bodily movement as a whole and not limb-specific movement. In this paper, we consider the novel problem of distinguishing the walking activity defined as a sequence of repeated leg-swing actions from repetitive leg-swing activities in sitting state. For this purpose, a heterogeneous sensor system is implemented that acquires novel multi-modal data from low-cost leg-worn IMU sensors (m-module) and finger-tip based pulse sensors (p-module). This dataset is then processed to extract features for a supervised learning framework. A 1-D Deep Convolutional Neural Network (DCNN) model is used for system performance evaluation, that prevents misclassification of walking activity with an average accuracy of 97% and maximum accuracy of 99%. With the fusion of features, the DCNN model performs with 2% more accuracy than the performance of the system using only IMU data. For performance comparison with the DCNN model, 4 other supervised learning algorithms have been used, namely Support Vector Machine (SVM), k-Nearest Neighbors (kNN), Decision Tree (DT), and Gaussian Naive Bayes (GNB). The proposed DCNN model outperforms these algorithms by using the m-module features individually and in unison with the p-module features. The performance is also comparable to the state-of-the-art works on intelligent walking activity detection.

The user-generated Twitter data are a rich source of study and research that reflects the various social, economic, political, and other issues affecting people across the world. Analysis of the social interactions among users, who express themselves online, reveals different internal dynamics and provides detailed insights into real-world phenomena. In this paper, the structure and dynamics of the state assembly election-based tweet-reply network have been studied, as generated by Twitter users across the country of India for a period of 6-weeks. We study the flow of Twitter activity pertaining to the West Bengal assembly elections, along with the identification of the hashtags used by the three main political contenders. This information is used to identify the cluster-level dominance in the Twitter network over the 6-weeks of study. It is observed that this information is representative of the actual outcome of the elections, and can be effectively used as a forecasting tool. The collected tweets are used for lexicon-based emotion detection and further analysis. This highlights the reaction of the social media users in response to the events related to the election. It is observed that fear is the dominant emotion, while happiness is scarce in the opinions expressed during the studied duration. Next, the study and analysis of the complete reply-based social networks during weeks 1, 4, and 6 are undertaken. Important political and media actors are identified with standard network-level measures toward determining the efforts put in by the different clusters and individual actors involved in the election to control the network dominance.

Efficient DNA double strand break (DSB) repair is necessary for genomic stability and determines efficacy of DNA damaging cancer therapeutics. Spatiotemporal dynamics and post-translational modifications of repair proteins at DSBs dictate repair efficacy. Here, we identified a non-canonical function of GCN5 in regulating both HR and NHEJ repair post genotoxic stress. Mechanistically, genotoxic stress induced GCN5 recruitment to DSBs. GCN5 PARylation by PARP1 was essential for its recruitment, acetyltransferase activity and DSB repair function. Liquid chromatography-mass spectrometry (LC–MS) identified DNA-PKcs as part of GCN5 interactome. In-vitro acetyltransferase assays revealed that GCN5 acetylates DNA-PKcs at K3241 residue, a prerequisite for DNA-PKcs S2056 phosphorylation and DSB recruitment. Alongside, ChIP-qPCR revealed GCN5 mediates transcription of PRKDC via H3K27Ac acetylation in its promoter region (− 710 to − 554). Genetic perturbation of GCN5 also decreased CHEK1, NBN1, TP53BP1, POL-L transcription and abrogated ATM, BRCA1 activation. Accordingly, GCN5 loss led to persistent ɣ-H2AX foci formation, compromised in-vivo HR-NHEJ and caused GBM radio-sensitization. Importantly, PARP1 inhibition phenocopied GCN5 loss. Together, this study identifies an untraversed DSB repair function of GCN5 and provides mechanistic insights into transcriptional as well as post-translational regulation of pivotal HR-NHEJ factors. Alongside, it highlights the translational importance of PARP1-GCN5 axis in mediating GBM radio-resistance.

Recognizing human activities non-intrusively has prevailed as a challenging and active area of research. In real life, it is a major requirement for human-centric applications like assisted living for elderly care, health-care and creating a smart home environment etc. Considering that people spend more than 90% (Klepeis et al. in J Exposure Sci Environ Epidemiol 11(3):231, 2001 ) of their time indoors, a proper indoor activity monitoring system will be helpful to monitor the abnormal behavior of the occupants. Existing approaches have implemented intrusive or invasive methods such as a camera or wearable devices. In this work, we present a non-invasive, non-intrusive sensing technique using an array of heterogeneous ultrasonic sensors for human activity monitoring. The ultrasonic sensors are placed in two separate deployments as sensor grids and in different positions of the door-frame. The proposed system senses a stream of events as the occupants perform different activities categorized as primary, postural and group activities. The primary activities considered are sitting, standing and fall. The postural activities are intermediate transitional states in the primary activities. These activities when performed in groups, are considered as a group activity. Other than activities it can identify different indoor movements, count room occupancy and identify occupants. Based on the collected data, the results show that the proposed system achieves an accuracy of more than 90% for detection of different activities and shows improvement over existing works. The final outcome of this work can be seen as developing the current prototype into smart ceiling panels that can be easily used in the indoor environment for human activity monitoring.

Identification of human activity considering social interactions and group dynamics non-intrusively has been one of the fundamental problems and a challenging area of research. In real life, it is required for designing human-centric applications like assisted living, health care, and creating a smart home environment. As human beings spend 90% of time indoors, such a system will be helpful to monitor the behavioral anomalies of the inhabitants. Existing approaches have used intrusive or invasive methods like camera or wearable devices. In this work, we present a device-free, non-invasive, and non-intrusive sensing framework called HumanSense using an array of heterogeneous sensor grid for human activity monitoring. The sensor grids, comprising the ultrasonic and sound sensors, have been deployed for collective sensing combining a person’s physical activity and verbal interaction information. The proposed system senses a stream of events when the occupant(s) perform different physical activities categorized as atomic and group activities like sitting, standing, and walking. Simultaneously, it also tracks person-person verbal interactions such as monologue and discussion. Both information are then integrated into a single framework to understand the overall behavioral scenario of the indoor environment. The experimental results have shown that HumanSense can detect different activities with accuracy more than 90% and also improves overall identification accuracy compared to existing works. Our developed system can be further evolved into ready-to-deploy smart sensing panels which can be effective for human activity monitoring in an indoor environment.

The actual Fig. 13 has been missing and in place of Fig. 13, Fig. 14 has been shown.

Emotion recognition has become a popular area of research in recent years, as emotions play a significant role in our social lives. There are many internal and external factors that trigger emotional changes, making it important to develop effective methods for identifying and managing emotional states. One such method is the use of physiological signals, which has revolutionized the treatment and diagnosis of mental health conditions. In this work, the authors focus on using electroencephalogram (EEG) and electrocardiogram (ECG) signals collected from a standard dataset to classify four emotional states based on the Arousal–Valence plane. The states considered are High Arousal and Low Valence (HALV), Low Arousal and Low Valence (LALV), High Arousal and High Valence (HAHV), and Low Arousal and High Valence (LAHV). The signals were collected non-invasively using sensors, and different standard machine intelligence algorithms were used to classify the emotional states. The experiments were conducted in two phases, and the results showed that the k-Nearest Neighbors algorithm was effective in handling class-imbalanced data, while the Logistic Regression algorithm outperformed other algorithms with an F1 score of 53.5% when trained with class-balanced data. This study presents a novel approach to emotion recognition and provides important insights into the use of physiological signals for identifying emotional states.

Large Language Models (LLMs) have demonstrated impressive capabilities as intelligent agents capable of solving complex problems. However, effective planning in scenarios involving dependencies between API or tool calls-particularly in multi-turn conversations-remains a significant challenge. To address this, we introduce T1, a tool-augmented, multi-domain, multi-turn conversational dataset specifically designed to capture and manage inter-tool dependencies across diverse domains. T1 enables rigorous evaluation of agents' ability to coordinate tool use across nine distinct domains (4 single domain and 5 multi-domain) with the help of an integrated caching mechanism for both short- and long-term memory, while supporting dynamic replanning-such as deciding whether to recompute or reuse cached results. Beyond facilitating research on tool use and planning, T1 also serves as a benchmark for evaluating the performance of open-weight and proprietary large language models. We present results powered by T1-Agent, highlighting their ability to plan and reason in complex, tool-dependent scenarios.