Using Computational Models to Detect Autistic Tendencies for Children from their Story Book Narratives

Multimedia Tools and Applications, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 7, 2025

Language: Английский

---

Application of switching-input LSTM network for vessel trajectory prediction

Applied Intelligence, Journal Year: 2025, Volume and Issue: 55(4)

Published: Jan. 9, 2025

Language: Английский

---

Vision transformer based convolutional neural network for breast cancer histopathological images classification

Multimedia Tools and Applications, Journal Year: 2024, Volume and Issue: 83(39), P. 86833 - 86868

Published: July 3, 2024

Language: Английский

---

Machine reading comprehension based named entity recognition for medical text

Multimedia Tools and Applications, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 7, 2025

Language: Английский

---

Adaptive spiking neuron with population coding for a residual spiking neural network

Applied Intelligence, Journal Year: 2025, Volume and Issue: 55(4)

Published: Jan. 9, 2025

Language: Английский

---

Content-aware sentiment understanding: cross-modal analysis with encoder-decoder architectures

Journal of Computational Social Science, Journal Year: 2025, Volume and Issue: 8(2)

Published: Feb. 21, 2025

Language: Английский

---

Enhancing E-commerce recommendations with sentiment analysis using MLA-EDTCNet and collaborative filtering

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Feb. 25, 2025

The rapid growth of e-commerce has made product recommendation systems essential for enhancing customer experience and driving business success. This research proposes an advanced framework that integrates sentiment analysis (SA) collaborative filtering (CF) to improve accuracy user satisfaction. methodology involves feature-level with a multi-step pipeline: data preprocessing, feature extraction using log-term frequency-based modified inverse class frequency (LFMI) algorithm, classification Multi-Layer Attention-based Encoder-Decoder Temporal Convolution Neural Network (MLA-EDTCNet). To address imbalance issues, Modified Conditional Generative Adversarial (MCGAN) generates balanced oversamples. Furthermore, the Ocotillo Optimization Algorithm (OcOA) fine-tunes model parameters ensure optimal performance by balancing exploration exploitation during training. integrated system predicts polarity—positive, negative, or neutral—and combines these insights CF provide personalized recommendations. Extensive experiments conducted on Amazon dataset demonstrate proposed approach outperforms state-of-the-art models in accuracy, precision, recall, F1-score, AUC. By leveraging SA CF, delivers recommendations tailored preferences while engagement highlights potential hybrid deep learning techniques critical challenges systems, including extraction, offering robust solution modern platforms.

Language: Английский

---

DFF-HGNN: Dual-Feature Fusion Heterogeneous Graph Neural Network

Applied Intelligence, Journal Year: 2025, Volume and Issue: 55(7)

Published: April 16, 2025

Language: Английский

---

A novel hybrid CNN-KNN ensemble voting classifier for Parkinson’s disease prediction from hand sketching images

Multimedia Tools and Applications, Journal Year: 2024, Volume and Issue: unknown

Published: May 14, 2024

Language: Английский

---

Melanoma skin cancer detection based on deep learning methods and binary Harris Hawk optimization

Multimedia Tools and Applications, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 2, 2024

Abstract The issue of skin cancer has garnered significant attention from the scientific community worldwide, with melanoma being most lethal and uncommon form disease. Melanoma occurs due to uncontrolled growth melanocyte cells, which are responsible for imparting color skin. If left untreated, can spread throughout body cause death. Early detection lower its mortality rate. In this study, we propose a robust Convolutional Neural Network (CNN)-based method classifying images as healthy or non-healthy. To train test model, utilized public datasets International Skin Imaging Collaboration (ISIC). Additionally, compared our other classification techniques, including Support Vector Machine (SVM), Decision Tree, K-Nearest Neighbors (K-NN), using Harris Hawks Optimization algorithm. results showed superior performance approaches.

Language: Английский

---