A new method for recommendation based on embedding spectral clustering in heterogeneous networks (RESCHet)

Expert Systems with Applications, Journal Year: 2023, Volume and Issue: 231, P. 120699 - 120699

Published: June 8, 2023

Language: Английский

---

CFCAI: improving collaborative filtering for solving cold start issues with clustering technique in the recommender systems

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

Published: Jan. 20, 2025

Language: Английский

---

Time-aware multi-behavior graph network model for complex group behavior prediction

Information Processing & Management, Journal Year: 2024, Volume and Issue: 61(3), P. 103666 - 103666

Published: Jan. 20, 2024

Language: Английский

---

An extended trust and distrust network-based dual fuzzy recommendation model and its application based on user-generated content

Expert Systems with Applications, Journal Year: 2024, Volume and Issue: 248, P. 123360 - 123360

Published: Feb. 3, 2024

Language: Английский

---

Broad information diffusion modeling for sharing link click prediction using knowledge graphs

Expert Systems with Applications, Journal Year: 2025, Volume and Issue: unknown, P. 127276 - 127276

Published: March 1, 2025

Language: Английский

---

Trust Models Go to the Web: Learning How to Trust Strangers

ACM Transactions on the Web, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 29, 2025

We study emerging traits of interpersonal and social trust in online networks needs (OSNNs), where interactions start evolve into in-person meetings. present a lightweight web scraping solution to harness data from networks; thanks it we were able monitor nation-wide portal for childcare see the evolution reviews both families carers. analysed by first considering topological information test centrality metrics as proxies trustworthiness. Next, focused on features/profile analysis tested Castelfranchi-Falcone model Psychology (CF-T), fitting services. Even though such are relatively scarce seemingly skewed, feature-engineered CF-T predict reviews, treated trust. By aggregating scores at regional level discovered strong correlation with per capita GDP, which suggests that high levels reflect capital.

Language: Английский

---

TCA4Rec: Contrastive Learning with Popularity-aware Asymmetric Augmentation for Robust Sequential Recommendation

Research Square (Research Square), Journal Year: 2025, Volume and Issue: unknown

Published: April 11, 2025

Sequential recommender systems play a pivotal role in modern recommendation scenarios by capturing users' dynamic interests through their historical interactions. While existing methods often rely on sophisticated deep models to enhance quality, they suffer from performance degradation due sparse supervision signals and popularity bias the training data. In this paper, we propose TCA4Rec, robust sequential framework that addresses these challenges via novel two-stage contrastive learning approach. Our incorporates an additional memory module aggregate sequence embeddings, thereby providing flexible generalized representations of user preferences. To mitigate bias, derive Asymmetric Multi-instance Noise Contrastive Estimation (AMINCE) loss function supplies rich, bias-aware signals, while our strategy significantly reduces over-dominance popular items during optimization. \added{Extensive experiments three real-world datasets demonstrate TCA4Rec achieves significant improvements over state-of-the-art baselines. Specifically, it attains absolute gains 19.26% HR@5 17.97% NDCG@5 Amazon-sports dataset. The also shows promising practical potential for applications e-commerce engines, video streaming platforms requiring long-tail content exposure, computational advertising where mitigating can directly impact advertiser ROI.}

Language: Английский

---

A novel pipeline for tunnel multi-object tracking integrating cross-modality and motion model

Expert Systems with Applications, Journal Year: 2025, Volume and Issue: unknown, P. 127640 - 127640

Published: April 1, 2025

Language: Английский

---

Optimal Integration of Machine Learning for Distinct Classification and Activity State Determination in Multiple Sclerosis and Neuromyelitis Optica

Technologies, Journal Year: 2023, Volume and Issue: 11(5), P. 131 - 131

Published: Sept. 20, 2023

The intricate neuroinflammatory diseases multiple sclerosis (MS) and neuromyelitis optica (NMO) often present similar clinical symptoms, creating challenges in their precise detection via magnetic resonance imaging (MRI). This challenge is further compounded when detecting the active inactive states of MS. To address this diagnostic problem, we introduce an innovative framework that incorporates state-of-the-art machine learning algorithms applied to features culled from MRI scans by pre-trained deep models, VGG-NET InceptionV3. develop test methodology, utilized a robust dataset obtained King Abdullah University Hospital Jordan, encompassing cases diagnosed with both MS NMO. We benchmarked thirteen distinct discovered support vector (SVM) K-nearest neighbor (KNN) performed superiorly our context. Our results demonstrated KNN’s exceptional performance differentiating between NMO, precision, recall, F1-score, accuracy values 0.98, 0.99, respectively, using leveraging extracted VGG16. In contrast, SVM excelled classifying versus MS, achieving 0.97, VGG16 VGG19. advanced methodology outshines previous studies, providing clinicians highly accurate, efficient tool for diagnosing these diseases. immediate implication research potential streamline treatment processes, thereby delivering timely, appropriate care patients suffering complex

Language: Английский

---

Enhancing user and item representation with collaborative signals for KG-based recommendation

Neural Computing and Applications, Journal Year: 2024, Volume and Issue: 36(12), P. 6681 - 6699

Published: Feb. 21, 2024

Language: Английский

---