User attention, doubt and anxiety about reliability in intelligent decisions is continuously increasing with increase in the data overload on the Internet of Things (IoT) frameworks. Recommender system (RS) faces noisy inputs and provides vague recommendations with target disparity, explanation ambiguity, and performance biasness as a consequence. The inactive or less interactive users suffer more from these issues due to the lack of sufficient information about their browsing history on the system’s end. In this work, therefore, we introduce smart Internet of Everything model for knowledge graph-based reliable recommendation (KGR) to overcome irrelevant feeds-in from the IoT networks and ensure pertinence-based data quality at the knowledge base to address the highlighted research challenges in the current IoT-based RSs. Particularly, we verify relevance of the incoming contents with the concerned application scenarios, translate the received data to the embedding space, and apply data quality inspection check on the underlying data. We independently encapsulate user-to-item interactions, and provide independent streams of low-level representations of users and items to the prediction module. It uses deep nonnegative matrix factorization technique to process user-item representations and acquire the required preferences. In experiments on four real world datasets, KGR outperforms the-state-of-the-art methods by successfully meeting the aforementioned challenges.

Studies have substantiated the efficacy of deep learning-based models in various source code modeling tasks. These models are usually trained on large datasets that are divided into smaller units, known as tokens, utilizing either an open or closed vocabulary system. The selection of a tokenization method can have a profound impact on the number of tokens generated, which in turn can significantly influence the performance of the model. This study investigates the effect of different tokenization methods on source code modeling and proposes an optimized tokenizer to enhance the tokenization performance. The proposed tokenizer employs a hybrid approach that initializes with a global vocabulary based on the most frequent unigrams and incrementally builds an open-vocabulary system. The proposed tokenizer is evaluated against popular tokenization methods such as Closed, Unigram, WordPiece, and BPE tokenizers, as well as tokenizers provided by large pre-trained models such as PolyCoder and CodeGen. The results indicate that the choice of tokenization method can significantly impact the number of sub-tokens generated, which can ultimately influence the modeling performance of a model. Furthermore, our empirical evaluation demonstrates that the proposed tokenizer outperforms other baselines, achieving improved tokenization performance both in terms of a reduced number of sub-tokens and time cost. In conclusion, this study highlights the significance of the choice of tokenization method in source code modeling and the potential for improvement through optimized tokenization techniques.

Filtration to optimal exactness is mandatory since the options inundate the online world. Knowledge graph embedding is extraordinarily contributing to the recommendations, but the existing knowledge graph (KG)-based recommendation methods only exploit the correlations among the preferences and stand-alone entities, without bonding the cocurricular features and tendencies of the context. Additionally, the integration of the location-based current data of coronavirus disease 2019 (COVID-19) into the KG is necessary for the recommendation of region-aware precautionary alerts to the concerned people—an essential application of the current and future Internet of Medical Things. Therefore, in this article, we propose a novel deep collaborative alert recommendation (DCA) approach to cope with the situation. Particularly, DCA collects current online data about COVID-19, purifies, and transforms them to the KG. Furthermore, it independently encapsulates the cocurricular features and tendencies of the context in the embedding space and encodes them to the independent hidden factors via a graph neural network. The bi-end hidden factors are computed via matrix factorization to infer the potential connections. Moreover, a relevance estimator and a cross transistor are configured to enhance the generalization capability of the model. Experiments on two real-world datasets are performed to evaluate the effectiveness of DCA. Results and analysis show that the proposed approach has outperformed the baseline methods with fine improvements in providing the required recommendations.