Methods for detecting emotions that employ many modalities at the same time have been found to be more accurate and resilient than those that rely on a single sense. This is due to the fact that sentiments may be conveyed in a wide range of modalities, each of which offers a different and complementary window into the thoughts and emotions of the speaker. In this way, a more complete picture of a person’s emotional state may emerge through the fusion and analysis of data from several modalities. The research suggests a new attention-based approach to multimodal emotion recognition. This technique integrates facial and speech features that have been extracted by independent encoders in order to pick the aspects that are the most informative. It increases the system’s accuracy by processing speech and facial features of various sizes and focuses on the most useful bits of input. A more comprehensive representation of facial expressions is extracted by the use of both low- and high-level facial features. These modalities are combined using a fusion network to create a multimodal feature vector which is then fed to a classification layer for emotion recognition. The developed system is evaluated on two datasets, IEMOCAP and CMU-MOSEI, and shows superior performance compared to existing models, achieving a weighted accuracy WA of 74.6% and an F1 score of 66.1% on the IEMOCAP dataset and a WA of 80.7% and F1 score of 73.7% on the CMU-MOSEI dataset.

Commercial e-learning platforms have to overcome the challenge of resource overload and find the most suitable material for educators using a recommendation system (RS) when an exponential increase occurs in the amount of available online educational resources. Therefore, we propose a novel DNN method that combines synchronous sequences and heterogeneous features to more accurately generate candidates in e-learning platforms that face an exponential increase in the number of available online educational courses and learners. Mitigating the learners’ cold-start problem was also taken into consideration during the modeling. Grouping learners in the first phase, and combining sequence and heterogeneous data as embeddings into recommendations using deep neural networks, are the main concepts of the proposed approach. Empirical results confirmed the proposed solution’s potential. In particular, the precision rates were equal to 0.626 and 0.492 in the cases of Top-1 and Top-5 courses, respectively. Learners’ cold-start errors were 0.618 and 0.697 for 25 and 50 new learners.

This study describes an applied and enhanced real-time vehicle-counting system that is an integral part of intelligent transportation systems. The primary objective of this study was to develop an accurate and reliable real-time system for vehicle counting to mitigate traffic congestion in a designated area. The proposed system can identify and track objects inside the region of interest and count detected vehicles. To enhance the accuracy of the system, we used the You Only Look Once version 5 (YOLOv5) model for vehicle identification owing to its high performance and short computing time. Vehicle tracking and the number of vehicles acquired used the DeepSort algorithm with the Kalman filter and Mahalanobis distance as the main components of the algorithm and the proposed simulated loop technique, respectively. Empirical results were obtained using video images taken from a closed-circuit television (CCTV) camera on Tashkent roads and show that the counting system can produce 98.1% accuracy in 0.2408 s.

Meticulous learning of human emotions through speech is an indispensable function of modern speech emotion recognition (SER) models. Consequently, deriving and interpreting various crucial speech features from raw speech data are complicated responsibilities in terms of modeling to improve performance. Therefore, in this study, we developed a novel SER model via attention-oriented parallel convolutional neural network (CNN) encoders that parallelly acquire important features that are used for emotion classification. Particularly, MFCC, paralinguistic, and speech spectrogram features were derived and encoded by designing different CNN architectures individually for the features, and the encoded features were fed to attention mechanisms for further representation, and then classified. Empirical veracity executed on EMO-DB and IEMOCAP open datasets, and the results showed that the proposed model is more efficient than the baseline models. Especially, weighted accuracy (WA) and unweighted accuracy (UA) of the proposed model were equal to 71.8% and 70.9% in EMO-DB dataset scenario, respectively. Moreover, WA and UA rates were 72.4% and 71.1% with the IEMOCAP dataset.

Facial expression recognition (FER) plays a critical role in affective computing, enabling machines to interpret human emotions through facial cues. While recent deep learning models have achieved progress, many still fail under real-world conditions such as occlusion, lighting variation, and subtle expressions. In this work, we propose FERONet, a novel hyper-attentive multimodal transformer architecture tailored for robust and real-time FER. FERONet integrates a triple-attention mechanism (spatial, channel, and cross-patch), a hierarchical transformer with token merging for computational efficiency, and a temporal cross-attention decoder to model emotional dynamics in video sequences. The model fuses RGB, optical flow, and depth/landmark inputs, enhancing resilience to environmental variation. Experimental evaluations across five standard FER datasets—FER-2013, RAF-DB, CK+, BU-3DFE, and AFEW—show that FERONet achieves superior recognition accuracy (up to 97.3%) and real-time inference speeds (<16 ms per frame), outperforming prior state-of-the-art models. The results confirm the model’s suitability for deployment in applications such as intelligent tutoring, driver monitoring, and clinical emotion assessment.

E-commerce systems experience poor quality of performance when the number of records in the customer database increases due to the gradual growth of customers and products. Applying implicit hidden features into the recommender system (RS) plays an important role in enhancing its performance due to the original dataset’s sparseness. In particular, we can comprehend the relationship between products and customers by analyzing the hierarchically expressed hidden implicit features of them. Furthermore, the effectiveness of rating prediction and system customization increases when the customer-added tag information is combined with hierarchically structured hidden implicit features. For these reasons, we concentrate on early grouping of comparable customers using the clustering technique as a first step, and then, we further enhance the efficacy of recommendations by obtaining implicit hidden features and combining them via customer’s tag information, which regularizes the deep-factorization procedure. The idea behind the proposed method was to cluster customers early via a customer rating matrix and deeply factorize a basic WNMF (weighted nonnegative matrix factorization) model to generate customers preference’s hierarchically structured hidden implicit features and product characteristics in each cluster, which reveals a deep relationship between them and regularizes the prediction procedure via an auxiliary parameter (tag information). The testimonies and empirical findings supported the viability of the proposed approach. Especially, MAE of the rating prediction was 0.8011 with 60% training dataset size, while the error rate was equal to 0.7965 with 80% training dataset size. Moreover, MAE rates were 0.8781 and 0.9046 in new 50 and 100 customer cold-start scenarios, respectively. The proposed model outperformed other baseline models that independently employed the major properties of customers, products, or tags in the prediction process.