Table 1.

Summary of existing studies comprising methods, datasets, and key findings.

Reference Number	Objective	Method	Dataset	Measures
Islam et al.11	To explore how ML and sensor technologies enhance emotion perception and activity recognition.	Multimodal Sensor Data, DL, Temporal–Spatial Behaviour Modelling, Cognitive and Affective Computing	AAL or Smart Home Sensor Dataset	Quality of Life, Emotion Recognition Accuracy, Activity Detection
Romero and Armenta12	To develop a real-time model for detecting and classifying seven facial emotions in children.	Camera input, CNN on Raspberry Pi 3b+, Trained CNN model	FER‑2013	Facial Emotion Identification Rate
Asha et al.13	To develop a modular, voice-controlled AI assistant for seamless human–machine interaction.	NLP, Voice Commands	Pre-Trained Models	Real-Time Performance, Interaction Accuracy
Pavithra et al.14	To develop a DL-based SER system for accurate and reliable emotion detection from speech.	Audio Feature Extraction, DL, RNN	Labelled Emotional Speech Samples	Accuracy, Reliability
Brilli et al.15	To develop AIris, an AI-powered wearable device for visually impaired users.	Object Recognition, Scene Interpretation, NLP, Real-Time Auditory Feedback	Real-World Visual Data	Accuracy, Usability
Bertacchini et al.16	To explore the use of a Pepper robot integrated with ChatGPT.	Pepper–ChatGPT Integration, Simulated Interaction Scenarios, Social Robotics Dialogue	Simulated ASD Interaction Scenarios	Feasibility, Acceptability, Effectiveness
Reddy et al.17	To develop an assistive system to support individuals with paralyzed hands.	HGR, Real-time Voice Output, Sensor-based Input Processing	Custom Gesture Dataset	Accuracy, Responsiveness
Begum et al.18	To develop an end-to-end system to aid communication for hearing-impaired individuals.	Quantized YOLOv4-Tiny Detection, Character to Text Generation, LSTM-based Text Model	BdSL 49 Dataset	mAP, Accuracy
Kandula et al.19	To bridge communication gaps and memorize complex sign systems.	Webcam hand gesture capture, Gesture recording pipeline, Model training and testing	Custom Webcam Gesture Data	Accuracy
Di Luzio, Rosato, and Panella20	To enhance emotion classification via video by optimizing facial landmark inputs.	Facial Landmarks Detection, Binary DNN, Improved Integrated Gradient	Facial Video Dataset	Higher Accuracy, Reduced Cost
Slade et al.21	To enhance SER accuracy and robustness.	AST with CSO, Optimizable 1D‑CNN, BiLSTM, CNN‑BiLSTM with Attention, NTKM	EMO‑DB, SAVEE, TESS	Accuracy, mAP
Neeraja et al.22	To develop an accurate and real-time system for detecting driver somnolence, thereby improving road safety.	CV, Physiological Signal Monitoring, ML	Driver Drowsiness Datasets	Accuracy, Real-Time Performance
Ali and Hughes23	To develop a model for emotion recognition using self-supervised pretraining techniques.	UBVMT, Self-supervised pretraining, masked autoencoding, contrastive modelling, transformer architecture	CMU-MOSEI, Public Biosensor Datasets	Accuracy, Memory Efficiency
Paul et al.24	To develop a real-time attendance system for enhanced accuracy and practical deployment.	ResNet-50 Face Recognition, ViT Emotion Detection, Dual-Path Architecture, Web Integration	Custom Real-Time Dataset	Accuracy, AUC-ROC Score
Choi, Zhang, and Watkins25	To enhance audio classification for improved performance.	SSAST, Multi-Layer Feature Fusion, Patch-Wise Pooling, Self-Supervised Learning, Dual Representation	CREMA-D, TESS, RAVDESS, Speech Emotion Classification, Isolated Urban Events, CornellBirdCall	Accuracy Rates
Wang and Chai26	To optimize personalized learning paths and learning efficiency.	LSTM Behaviour Capture, Transformer Self-Attention, DL Integration	Learner Behaviour Sequences	Knowledge Mastery, Learning Time, Satisfaction
Ramani et al.27	To accurately detect human emotions without manual feature engineering.	Deep Bidirectional LSTM, Multimodal Sensor Fusion, Iterative DL	On-Body, Ambient, Geographical Sensors	Accuracy, Effectiveness
Prithi and Tamizharasi28	To enhance CRM for accurate emotion analysis.	FFDMLC, Feature Fusion, DL, COOT	CK+, FER2013	Recognition Rate, Accuracy
Selvaraju et al.29	To develop a real-time ISL gesture-to-text subtitle system for individuals with hearing and speaking impairments.	CNN, YOLOv5, HMM, WebRTC	ISL Gesture Video Dataset	Accuracy, Latency, Usability
Ghadami, Taheri, and Meghdari30	To develop a transformer-based DL system for improved communication and learning.	Early And Late Fusion Transformers, GS, Keypoint Feature Extraction, Multi-Task Learning	101 Iranian Sign Language Words	Accuracy, Real-Time Feedback
Khanum et al.31	To develop an IoT-based wearable device to enhance women’s safety, including offline functionality for evidence preservation.	IoT Wearable Device, Real-Time Audio Tracking, Location Tracking, Emergency Alert System	Not Specified/Real-Time User Data	Response Time, Alert Accuracy
Siju and Selvam32	To develop a system for accurate and efficient SLR compatible with edge devices.	Google Mediapipe Landmarks, DNN, Tensorflow Training, Live Webcam Testing	Hand Gesture Images (Peace, Okay, Stop)	Accuracy, Latency
Naik et al.33	To develop a robust multimodal real-time emotion recognition system.	Text: BERT + TF-IDF, Audio: CNN + Augmentation, Video: CNN + OpenCV	Four Kaggle Datasets (audio, video, text)	Audio and Video Accuracy of 99.44% and 97.66%, Audio and Video Validation of 94.71% and 65.38%
Liu et al.34	To enhance sentiment analysis accuracy for short texts.	TF-IDF, CSO, SVM, AdaBoost Soft Voting	Six Real Polar Sentiment Analysis Datasets	Accuracy Improvement: >4.5%
Filahi et al.35	To improve e-commerce decision-making using IoT data and ML models.	LR, NB, SVM, RF, AdaBoosting, GRU, LSTM	Customer Behaviour and Preference Data Collected Via IoT Devices	Accuracy of 88%, F1-Score of 0.927, Precision of 0.908, Recall-0 of 0.569 and Recall-1 of 0.947
Sandulescu et al.36	To develop an AI-driven healthcare platform.	IoMT Sensor Integration, AI Predictive Models, Emotion Detection Algorithm	Patient Sensor Data and Voice Recordings	Early Symptom Detection, Disease Progression Tracking
Muhammad et al.37	To enhance emotion detection accuracy on imbalanced and limited data.	DeBERTa-v3-large + CNN, Electra + CNN, XLNet-base, RoBERTa + CNN, T5-base, Synonym Replacement Augmentation	ISEAR	Accuracy (best) of 94.94%, Accuracy (others) of 93%/69%, Improved Precision & Recall
Thiab, Alawneh, and Mohammad38	To evaluate and enhance emotion classification in textual conversations.	RNN and Transformer-based Models, Ensemble via Majority Voting	SemEval 2019 Task 3 (EmotionX)	Transformer F1-Score of 75.55%, RNN F1-Score of 67.03%, Ensemble F1-Score of 77.07%
Kumar, Khan, and Choi39	To develop an accurate mental health detection model from social media text.	RoBERTa + Adapter Layers, BiLSTM, AM	Filtered GoEmotions Dataset	Accuracy (binary): 92%, Accuracy (multiclass): 88%
Geethanjali and Valarmathi40	To improve multimodal sentiment analysis during the COVID-19 pandemic.	CNN, LSTM, IChOA, Feature Fusion Strategy	GeoCoV19 Dataset	Accuracy of 97.8%
Arbaizar et al.41	To enable real-time, objective monitoring and prediction of psychiatric patients’ emotional states.	HMM, Transformer DNN, Time-Series Forecasting, Classification Algorithms	Passive and Self-Reported Data from the Evidence-Based Behaviour (eB2) App	Emotional state accuracy: 0.93, ROC AUC (valence): 0.98, ROC AUC (1-day prediction): 0.87, Accuracy (suicidal ideation): 0.9, ROC AUC (suicidal ideation): 0.77
Kohneh Shahri, Afshar Kazemi, and Pourebrahimi42	To develop and evaluate a comprehensive sentiment analysis model for improved accuracy and speed.	Image, Sound and text processing, CV, NLP	Social Network Multimedia Data	Accuracy (High), Speed (Fast)