Contextual emotion detection in images using deep learning DOI Creative Commons

Fatiha Limami,

Boutaina Hdioud, Rachid Oulad Haj Thami

et al.

Frontiers in Artificial Intelligence, Journal Year: 2024, Volume and Issue: 7

Published: June 17, 2024

Introduction Computerized sentiment detection, based on artificial intelligence and computer vision, has become essential in recent years. Thanks to developments deep neural networks, this technology can now account for environmental, social, cultural factors, as well facial expressions. We aim create more empathetic systems various purposes, from medicine interpreting emotional interactions social media. Methods To develop technology, we combined authentic images databases, including EMOTIC (ADE20K, MSCOCO), EMODB_SMALL, FRAMESDB, train our models. developed two sophisticated algorithms learning techniques, DCNN VGG19. By optimizing the hyperparameters of models, analyze context body language improve understanding human emotions images. merge 26 discrete categories with three continuous dimensions identify context. The proposed pipeline is completed by fusing Results adjusted parameters outperform previous methods capturing different contexts. Our study showed that Sentiment_recognition_model VGG19_contexte increased mAP 42.81% 44.12%, respectively, surpassing results studies. Discussion This groundbreaking research could significantly contextual emotion recognition implications these promising are far-reaching, extending diverse fields such robotics, affective computing, human-machine interaction, human-robot communication.

Language: Английский

Real-Time Deep Learning-Based Drowsiness Detection: Leveraging Computer-Vision and Eye-Blink Analyses for Enhanced Road Safety DOI Creative Commons
Furkat Safarov, Farkhod Akhmedov, Akmalbek Abdusalomov

et al.

Sensors, Journal Year: 2023, Volume and Issue: 23(14), P. 6459 - 6459

Published: July 17, 2023

Drowsy driving can significantly affect performance and overall road safety. Statistically, the main causes are decreased alertness attention of drivers. The combination deep learning computer-vision algorithm applications has been proven to be one most effective approaches for detection drowsiness. Robust accurate drowsiness systems developed by leveraging learn complex coordinate patterns using visual data. Deep algorithms have emerged as powerful techniques because their ability automatically from given inputs feature extractions raw Eye-blinking-based was applied in this study, which utilized analysis eye-blink patterns. In we used custom data model training experimental results were obtained different candidates. blinking eye mouth region coordinates applying landmarks. rate eye-blinking changes shape analyzed measuring landmarks with real-time fluctuation representations. An performed real time proved existence a correlation between yawning closed eyes, classified drowsy. 95.8% accuracy drowsy-eye detection, 97% open-eye 0.84% 0.98% right-sided falling, 100% left-sided falling. Furthermore, proposed method allowed analysis, where threshold served separator into two classes, “Open” “Closed” states.

Language: Английский

Citations

41

Exploring contactless techniques in multimodal emotion recognition: insights into diverse applications, challenges, solutions, and prospects DOI Creative Commons
Umair Ali Khan,

Qianru Xu,

Yang Liu

et al.

Multimedia Systems, Journal Year: 2024, Volume and Issue: 30(3)

Published: April 6, 2024

Abstract In recent years, emotion recognition has received significant attention, presenting a plethora of opportunities for application in diverse fields such as human–computer interaction, psychology, and neuroscience, to name few. Although unimodal methods offer certain benefits, they have limited ability encompass the full spectrum human emotional expression. contrast, Multimodal Emotion Recognition (MER) delivers more holistic detailed insight into an individual's state. However, existing multimodal data collection approaches utilizing contact-based devices hinder effective deployment this technology. We address issue by examining potential contactless techniques MER. our tertiary review study, we highlight unaddressed gaps body literature on Through rigorous analysis MER studies, identify modalities, specific cues, open datasets with unique modality combinations. This further leads us formulation comparative schema mapping requirements given scenario combination. Subsequently, discuss implementation Contactless (CMER) systems use cases help which serves evaluation blueprint. Furthermore, paper also explores ethical privacy considerations concerning employment proposes key principles addressing concerns. The investigates current challenges future prospects field, offering recommendations research development CMER. Our study resource researchers practitioners field recognition, well those intrigued broader outcomes rapidly progressing

Language: Английский

Citations

12

Fire Detection and Notification Method in Ship Areas Using Deep Learning and Computer Vision Approaches DOI Creative Commons

Kuldoshbay Avazov,

Muhammad Kafeel Jamil, Bahodir Muminov

et al.

Sensors, Journal Year: 2023, Volume and Issue: 23(16), P. 7078 - 7078

Published: Aug. 10, 2023

Fire incidents occurring onboard ships cause significant consequences that result in substantial effects. Fires on can have extensive and severe wide-ranging impacts matters such as the safety of crew, cargo, environment, finances, reputation, etc. Therefore, timely detection fires is essential for quick responses powerful mitigation. The study this research paper presents a fire technique based YOLOv7 (You Only Look Once version 7), incorporating improved deep learning algorithms. architecture, with an E-ELAN (extended efficient layer aggregation network) its backbone, serves basis our system. Its enhanced feature fusion makes it superior to all predecessors. To train model, we collected 4622 images various ship scenarios performed data augmentation techniques rotation, horizontal vertical flips, scaling. Our through rigorous evaluation, showcases capabilities recognition improve maritime safety. proposed strategy successfully achieves accuracy 93% detecting minimize catastrophic incidents. Objects having visual similarities may lead false prediction by but be controlled expanding dataset. However, model utilized real-time detector challenging environments small-object detection. Advancements models hold potential enhance measures, exhibits potential. Experimental results proved method used protection monitoring port areas. Finally, compared performance those recently reported fire-detection approaches employing widely matrices test classification achieved.

Language: Английский

Citations

24

Multimodal Emotion Recognition via Convolutional Neural Networks: Comparison of different strategies on two multimodal datasets DOI Creative Commons
Umberto Bilotti, Carmen Bisogni, Maria De Marsico

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2023, Volume and Issue: 130, P. 107708 - 107708

Published: Dec. 14, 2023

The aim of this paper is to investigate emotion recognition using a multimodal approach that exploits convolutional neural networks (CNNs) with multiple input. Multimodal approaches allow different modalities cooperate in order achieve generally better performances because features are extracted from pieces information. In work, the facial frames, optical flow computed consecutive and Mel Spectrograms (from word melody) videos combined together ways understand which modality combination works better. Several experiments run on models by first considering one at time so good accuracy results found each modality. Afterward, concatenated create final model allows inputs. For datasets used BAUM-1 ((Bahçeşehir University Affective Database - 1) RAVDESS (Ryerson Audio–Visual Emotional Speech Song), both collect two distinguished sets based intensity expression, acted/strong or spontaneous/normal, providing representations following emotional states will be taken into consideration: angry, disgust, fearful, happy sad. proposed shown through some confusion matrices, demonstrating than compared proposals literature. best achieved dataset about 95%, while it 95.5%.

Language: Английский

Citations

18

Digitalized therapy and the unresolved gap between artificial and human empathy DOI Creative Commons

Roshini Salil,

Binny Jose,

Jaya Cherian

et al.

Frontiers in Psychiatry, Journal Year: 2025, Volume and Issue: 15

Published: Jan. 7, 2025

Empathy is a cornerstone in psychotherapy for building trust, connection, and understanding between therapist client. Studies meta-analyses continue to support that empathy significantly correlates with positive therapeutic outcomes (Elliott et al., 2018;Garfield & Bergin, 1971;Watson 2014). However, not the sole pathway psychological change. Constructs such as validation, autonomy support, attunement, authentic curiosity also contribute recovery mental well-being (Soto, 2017). There are recent development importance of some non-interpersonal methods, including training mindfulness, expressive writing, focusing, computer-aided cognitive bias modification; these, too have produced changes favorable outcome. (Schnur Montgomery, 2010).Given this multi-psychological framework, how essential core construct from which interventions take part remains moot debate. The role powerful influential but only whole net mechanisms (Voutilainen 2018). This paper discusses special significance change, its limitations, risks associated misrepresentations by AI. It postulates AI's strengths may be better utilized enhancement non-empathic pathways hence provides an alternative focus AI health care.Empathy has traditionally been regarded backbone relationship. multicomponent concept involving emotional resonance or sharing feelings, perspectivetaking another's viewpoint, compassionate action taking steps alleviate distress (Jordan, 2000). These dimensions enable offer environment noncritical safe. there emerging body research questions whether determinant Instead, other factors equally, if more, important (Garrote-Caparrós 2023;Schnur 2010). For example, validation confirms client's feelings experiences effort establish sense trust reduce isolation. Similarly, promoting support-for instance, encouraging clients responsibility their own healing process-promotes long-term aligns modern models centered around client (Steiger therapist's attunement-approach, he himself state, improves rapport. conveyed interest exploratory promote self-reflection insight (Feiner-Homer, 2016;Seikkula 2015).Beyond interpersonal mechanisms, very empathy-free An example mindfulness-based interventions: MBSR proved successful reducing stress enhancing regulation mood (Ghawadra 2019).Experiences writing about events active processing consequences (Mordechay 2019). On hand, even spots corrects negative thinking so address symptoms anxiety depression (Hallion Ruscio, 2011). Gendlin's focusing training, emphasizes awareness processing, tested found effective intervention (Hinterkopf, 1983). underpin, together, multifaceted nature change emphasize needs augment rather try replace pathways.Artificial feature AI, whereby it able recognize then simulate empathic responses based on data text, tone, facial expressions (Asada, 2015). While indeed great achievement technology, lacks depth, intentionality, cultural sensitivity, ingredients (Tubadji Huang, 2023;Zhang 2024). limitations appear most manifestly three areas: First, struggles contextual since cannot holistic individual's life experiences, because unable meaning context, would first limit faces. second one insensitivity, algorithms emotion recognition quick misinterpret simplify cues across different contexts. Finally, resonance, draw lived service deeper connections clients. relying emulating care.Despite these setbacks, argued through simulation empathy, democratizes care insofar increases access services (Balasubramanian 2023). systems can provide immediate serve entry points those who feel uneasy traditional therapy (Lopes Poorly aligned over-and-over robotic could alienate destroy any might needed relationship (McParlin 2022). Given risks, perhaps should shift than trying emulate by, giving real-time, feedback generating personalized insights human therapists.Future priorities must addressed securing position developing responsible health. Development multi-modal combine evidence speech, expressions, physiological signals approach go emotions holistically (Mamieva With effectiveness, empirical study hybrid assessed regarding impacts satisfaction will immensely useful trusting informing user-friendly system designs while perceptions therapy. Furthermore, refinement ethical guidelines, requirement challenges privacy, transparency, consent (Alfano Lastly, roles well investigated include monitoring progress, personalization treatment plans, supporting mindfulness potential extend utility minimizing risks.While psychotherapy, neither nor irreplaceable Evidence underlines effective, training. risk misinterpreting focused models. Coupled developments, enhance delivery without losing human-centered approach. In future, envisaged act substitute ally solving rapidly increasing demand services.

Language: Английский

Citations

1

Explainable Lightweight Block Attention Module Framework for Network-Based IoT Attack Detection DOI Creative Commons
Furkat Safarov,

Mainak Basak,

Rashid Nasimov

et al.

Future Internet, Journal Year: 2023, Volume and Issue: 15(9), P. 297 - 297

Published: Sept. 1, 2023

In the rapidly evolving landscape of internet usage, ensuring robust cybersecurity measures has become a paramount concern across diverse fields. Among numerous cyber threats, denial service (DoS) and distributed (DDoS) attacks pose significant risks, as they can render websites servers inaccessible to their intended users. Conventional intrusion detection methods encounter substantial challenges in effectively identifying mitigating these due widespread nature, intricate patterns, computational complexities. However, by harnessing power deep learning-based techniques, our proposed dense channel-spatial attention model exhibits exceptional accuracy detecting classifying DoS DDoS attacks. The successful implementation framework addresses posed imbalanced data its potential for real-world applications. By leveraging mechanism, precisely identify classify attacks, bolstering defenses servers. high rates achieved different datasets reinforce robustness approach, underscoring efficacy enhancing capabilities. As result, holds promise scenarios, contributing ongoing efforts safeguard against threats an increasingly interconnected digital landscape. Comparative analysis with current reveals superior performance model. We 99.38%, 99.26%, 99.43% Bot-IoT, CICIDS2017, UNSW_NB15 datasets, respectively. These remarkable results demonstrate capability approach accurately detect various types assaults. inherent strengths learning, such pattern recognition feature extraction, overcomes limitations traditional methods, efficiency systems.

Language: Английский

Citations

11

Enhancing Speech Emotion Recognition Using Dual Feature Extraction Encoders DOI Creative Commons

Ilkhomjon Pulatov,

Rashid Oteniyazov,

Fazliddin Makhmudov

et al.

Sensors, Journal Year: 2023, Volume and Issue: 23(14), P. 6640 - 6640

Published: July 24, 2023

Understanding and identifying emotional cues in human speech is a crucial aspect of human-computer communication. The application computer technology dissecting deciphering emotions, along with the extraction relevant characteristics from speech, forms significant part this process. objective study was to architect an innovative framework for emotion recognition predicated on spectrograms semantic feature transcribers, aiming bolster performance precision by acknowledging conspicuous inadequacies extant methodologies rectifying them. To procure invaluable attributes detection, investigation leveraged two divergent strategies. Primarily, wholly convolutional neural network model engaged transcribe spectrograms. Subsequently, cutting-edge Mel-frequency cepstral coefficient abstraction approach adopted integrated Speech2Vec encoding. These dual underwent individual processing before they were channeled into long short-term memory comprehensive connected layer supplementary representation. By doing so, we aimed sophistication efficacy our detection model, thereby enhancing its potential accurately recognize interpret speech. proposed mechanism rigorous evaluation process employing distinct databases: RAVDESS EMO-DB. outcome displayed predominant when juxtaposed established models, registering impressive accuracy 94.8% dataset commendable 94.0% EMO-DB dataset. This superior underscores system realm recognition, as it outperforms current frameworks metrics.

Language: Английский

Citations

10

Emotion Fusion-Sense (Emo Fu-Sense) – A novel multimodal emotion classification technique DOI
Muhammad Umair, Nasir Rashid, Umar Shahbaz Khan

et al.

Biomedical Signal Processing and Control, Journal Year: 2024, Volume and Issue: 94, P. 106224 - 106224

Published: March 28, 2024

Language: Английский

Citations

4

Enhancing Multimodal Emotion Recognition through Attention Mechanisms in BERT and CNN Architectures DOI Creative Commons

Fazliddin Makhmudov,

Alpamis Kultimuratov,

Young Im Cho

et al.

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(10), P. 4199 - 4199

Published: May 15, 2024

Emotion detection holds significant importance in facilitating human–computer interaction, enhancing the depth of engagement. By integrating this capability, we pave way for forthcoming AI technologies to possess a blend cognitive and emotional understanding, bridging divide between machine functionality human complexity. This progress has potential reshape how machines perceive respond emotions, ushering an era empathetic intuitive artificial systems. The primary research challenge involves developing models that can accurately interpret analyze emotions from both auditory textual data, whereby data require optimizing CNNs detect subtle intense fluctuations speech, necessitate access large, diverse datasets effectively capture nuanced cues written language. paper introduces novel approach multimodal emotion recognition, seamlessly speech text modalities infer states. Employing CNNs, meticulously using Mel spectrograms, while BERT-based model processes component, leveraging its bidirectional layers enable profound semantic comprehension. outputs are combined attention-based fusion mechanism optimally weighs their contributions. proposed method here undergoes meticulous testing on two distinct datasets: Carnegie Mellon University’s Multimodal Opinion Sentiment Intensity (CMU-MOSEI) dataset Lines Dataset (MELD). results demonstrate superior efficacy compared existing frameworks, achieving accuracy 88.4% F1-score 87.9% CMU-MOSEI dataset, notable weighted (WA) 67.81% F1 (WF1) score 66.32% MELD dataset. comprehensive system offers precise several advancements field.

Language: Английский

Citations

4

Evolving Feature Selection: Synergistic Backward and Forward Deletion Method Utilizing Global Feature Importance DOI Creative Commons
Takafumi Nakanishi, Ponlawat Chophuk, Krisana Chinnasarn

et al.

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 88696 - 88714

Published: Jan. 1, 2024

Language: Английский

Citations

4