Search

In an era overwhelmed by academic big data, students grapple with identifying academic papers that resonate with their learning objectives and research interests, due to the sheer volume and complexity of available information. This study addresses the challenge by proposing a novel academic paper recommendation system designed to enhance personalized learning through the nuanced understanding of academic social networks. Utilizing the theory of social homogeneity, the research first constructs a sophisticated academic social network, capturing high-order social relationships, such as co-authorship and advisor–advisee connections, through hypergraph modeling and advanced network representation learning techniques. The methodology encompasses the development and integration of a hypergraph convolutional neural network and a contrastive learning framework to accurately model and recommend academic papers, focusing on aligning with students' unique preferences and reducing reliance on sparse interaction data. The findings, validated across multiple real-world datasets, demonstrate a significant improvement in recommendation accuracy, particularly in addressing the cold-start problem and effectively mapping advisor–advisee relationships. The study concludes that leveraging complex academic social networks can substantially enhance the personalization and precision of academic paper recommendations, offering a promising avenue for addressing the challenges of academic information overload and fostering more effective personalized learning environments. [ABSTRACT FROM AUTHOR]

E-commerce platforms incorporate reputation systems that allow buyers to rate sellers after transactions. However, existing reputation systems face challenges such as privacy leakage, linkability, and multiple rating attacks. The feedback data can inadvertently expose user information privacy because they reveal the buyers' identities and preferences, which deters a significant number of users from providing their ratings. Moreover, malicious actors can exploit data analysis and machine learning techniques to mine user privacy from the rating data, posing serious threats to user security and trust. This study introduces ARS-Chain, a pioneering and secure blockchain-driven anonymous reputation-sharing framework tailored for e-commerce platforms. The core of ARS-Chain is a dynamic ring addition mechanism with linkable ring signatures (LRS), where the number of LRS rings is dynamically added in alignment with the evolving purchase list, and LRS link tags are constructed with the LRS rings and item identifiers. Further, a consortium blockchain is introduced to store these anonymous ratings on e-commerce platforms. As a result, ARS-Chain ensures full anonymity while achieving cross-platform reputation sharing, making rating records unlinkable, and effectively countering multiple rating attacks. The experimental results confirm that ARS-Chain significantly enhances user information privacy protection while maintaining system performance, having an important impact on the construction of trust mechanisms for e-commerce platforms. [ABSTRACT FROM AUTHOR]

As user–item interaction information is typically limited, collaborative filtering (CF)-based recommender systems often suffer from the data sparsity issue. To address this issue, recent recommender systems have turned to graph neural networks (GNNs) due to their superior performance in capturing high-order relationships. Furthermore, some of these GNN-based recommendation models also attempt to incorporate other information. They either extract self-supervised signals to mitigate the data sparsity problem or employ social information to assist with learning better representations under a social recommendation setting. However, only a few methods can take full advantage of these different aspects of information. Based on some testing, we believe most of these methods are complex and redundantly designed, which may lead to sub-optimal results. In this paper, we propose SSGCL, which is a recommendation system model that utilizes both social information and self-supervised information. We design a GNN-based propagation strategy that integrates social information with interest information in a simple yet effective way to learn user–item representations for recommendations. In addition, a specially designed contrastive learning module is employed to take advantage of the self-supervised signals for a better user–item representation distribution. The contrastive learning module is jointly optimized with the recommendation module to benefit the final recommendation result. Experiments on several benchmark data sets demonstrate the significant improvement in performance achieved by our model when compared with baseline models. [ABSTRACT FROM AUTHOR]

In the competitive landscape of online learning, developing robust and effective learning resource recommendation systems is paramount, yet the field faces challenges due to high-dimensional, sparse matrices and intricate user–resource interactions. Our study focuses on geometric matrix completion (GMC) and introduces a novel approach, graph-based truncated norm regularization (GBTNR) for problem solving. GBTNR innovatively incorporates truncated Dirichlet norms for both user and item graphs, enhancing the model's ability to handle complex data structures. This method synergistically combines the benefits of truncated norm regularization with the insightful analysis of user–user and resource–resource graph relationships, leading to a significant improvement in recommendation performance. Our model's unique application of truncated Dirichlet norms distinctively positions it to address the inherent complexities in user and item data structures more effectively than existing methods. By bridging the gap between theoretical robustness and practical applicability, the GBTNR approach offers a substantial leap forward in the field of learning resource recommendations. This advancement is particularly critical in the realm of online education, where understanding and adapting to diverse and intricate user–resource interactions is key to developing truly personalized learning experiences. Moreover, our work includes a thorough theoretical analysis, complete with proofs, to establish the convergence property of the GMC-GBTNR model, thus reinforcing its reliability and effectiveness in practical applications. Empirical validation through extensive experiments on diverse real-world datasets affirms the model's superior performance over existing methods, marking a groundbreaking advancement in personalized education and deepening our understanding of the dynamics in learner–resource interactions. [ABSTRACT FROM AUTHOR]

The recommendation algorithm based on collaborative filtering is vulnerable to data poisoning attacks, wherein attackers can manipulate system output by injecting a large volume of fake rating data. To address this issue, it is essential to investigate methods for detecting systematically injected poisoning data within the rating matrix. Since attackers often inject a significant quantity of poisoning data in a short period to achieve their desired impact, these data may exhibit spatial proximity. In other words, poisoning data may be concentrated in adjacent rows of the rating matrix. This paper capitalizes on the proximity characteristics of poisoning data in the rating matrix and introduces a sampling-based method for detecting data poisoning attacks. First, we designed a rating matrix sampling method specifically for detecting poisoning data. By sampling differences obtained from the original rating matrix, it is possible to infer the presence of poisoning attacks and effectively discard poisoning data. Second, we developed a method for pinpointing malicious data based on the distance of rating vectors. Through distance calculations, we can accurately identify the positions of malicious data. After that, we validated the method on three real-world datasets. The results demonstrate the effectiveness of our method in identifying malicious data within the rating matrix. [ABSTRACT FROM AUTHOR]

At present, sequence-based models have various applications in recommendation systems; these models recommend the interested items of the user according to the user's behavioral sequence. However, sequence-based models have a limitation of length. When the length of the user's behavioral sequence exceeds the limitation of the model, the model cannot take advantage of the complete behavioral sequence of the user and cannot know the user's holistic interests. The accuracy of the model then goes down. Meanwhile, sequence-based models only pay attention to the sequential signals of the data but do not pay attention to the spatial signals of the data, which will also affect the model's accuracy. This paper proposes a graph sequence-based model called GSRec that combines Graph Convolutional Network (GCN) and Transformer to solve these problems. In the GCN part we designed a reverse-order graph, and in the Transformer part we introduced the user embedding. The reverse-order graph and the user embedding can make the combination of GCN and Transformer more efficient. Experiments on six datasets show that GSRec outperforms the current state-of-the-art (SOTA) models. [ABSTRACT FROM AUTHOR]

Deep learning technology has greatly propelled the development of intelligent and information-driven research on ship infrared automatic target recognition (SIATR). In future scenarios, there will be various recognition models with different mechanisms to choose from. However, in complex and dynamic environments, ship infrared (IR) data exhibit rich feature space distribution, resulting in performance variations among SIATR models, thus preventing the existence of a universally superior model for all recognition scenarios. In light of this, this study proposes a model-matching method for SIATR tasks based on bipartite graph theory. This method establishes evaluation criteria based on recognition accuracy and feature learning credibility, uncovering the underlying connections between IR attributes of ships and candidate models. The objective is to selectively recommend the optimal candidate model for a given sample, enhancing the overall recognition performance and applicability of the model. We separately conducted tests for the optimization of accuracy and credibility on high-fidelity simulation data, achieving Accuracy and EDMS (our credibility metric) of 95.86% and 0.7781. Our method improves by 1.06% and 0.0274 for each metric compared to the best candidate models (six in total). Subsequently, we created a recommendation system that balances two tasks, resulting in improvements of 0.43% (accuracy) and 0.0071 (EDMS). Additionally, considering the relationship between model resources and performance, we achieved a 28.35% reduction in memory usage while realizing enhancements of 0.33% (accuracy) and 0.0045 (EDMS). [ABSTRACT FROM AUTHOR]

A prescriptive simulation model of a process operator's decision making assisted with an artificial intelligence (AI) algorithm in a technical system control loop is proposed. Situations fraught with a catastrophic threat that may cause unacceptable damage were analyzed. The operators' decision making was interpreted in terms of a subjectively admissible probability of disaster and subjectively necessary reliability of its assessment, which reflect the individual psychological aspect of operator's trust in AI. Four extreme decision-making strategies corresponding to different ratios between the above variables were distinguished. An experiment simulating a process facility, an AI algorithm and operator's decision making strategy was held. It showed that depending on the properties of a controlled process (its dynamics and the hazard onset's speed) and the AI algorithm characteristics (Type I and II error rate), each of such strategies or some intermediate strategy may prove to be more beneficial than others. The same approach is applicable to the identification and analysis of sustainability of strategies applied in real-life operating conditions, as well as to the development of a computer simulator to train operators to control hazardous technological processes using AI-generated advice. [ABSTRACT FROM AUTHOR]

With the rapid growth of social media, textual content is increasingly growing. Unstructured texts are a rich source of latent spatial information. Extracting such information is useful in query processing, geographical information retrieval (GIR), and recommender systems. In this paper, we propose a novel approach to infer spatial information from salient features of non-spatial nature in text corpora. We propose two methods, namely DCS and RCS, to represent place-based concepts. In addition, two measures, namely the Shannon entropy and the Moran's I, are proposed to calculate the degree of geo-indicativeness of terms in texts. The methodology is compared with a Latent Dirichlet Allocation (LDA) approach to estimate the accuracy improvement. We evaluated the methods on a dataset of rental property advertisements in Iran and a dataset of Persian Wikipedia articles. The results show that our proposed approach enhances the relative accuracy of predictions by about 10% in case of the renting advertisements and by 13% in case of the Wikipedia articles. The average distance error is about 13.3 km for the advertisements and 10.3 km for the Wikipedia articles, making the method suitable to infer the general region of the city in which a property is located. The proposed methodology is promising for inferring spatial knowledge from textual content that lacks spatial terms. [ABSTRACT FROM AUTHOR]

Large language models have recently gained popularity in various applications due to their ability to generate natural text for complex tasks. Recommendation systems, one of the frequently studied research topics, can be further improved using the capabilities of large language models to track and understand user behaviors and preferences. In this research, we aim to build reliable and transparent recommendation system by generating human-readable explanations to help users obtain better insights into the recommended items and gain more trust. We propose a learning scheme to jointly train the rating prediction task and explanation generation task. The rating prediction task learns the predictive representation from the input of user and item vectors. Subsequently, inspired by the recent success of prompt engineering, these predictive representations are served as predictive prompts, which are soft embeddings, to elicit and steer any knowledge behind language models for the explanation generation task. Empirical studies show that the proposed approach achieves competitive results compared with other existing baselines on the public English TripAdvisor dataset of explainable recommendations. [ABSTRACT FROM AUTHOR]

In the face of problems such as information overload and the information cocoon resulting from big data, it is a key point of current research to solve the problem of semantic fuzziness of online reviews and improve the accuracy of personalized recommendation algorithms by using online reviews. Based on the advantage of the probabilistic language term set to deal with fuzzy information and the historical data of online hotel reviews, this paper proposes a collaborative filtering recommendation algorithm for hotels. Firstly, the text data of hotel online reviews are crawled by a crawler and processed by jieba and TF-IDF tools. Secondly, the hotel evaluation attribute set is constructed, and the sentiment analysis of the review statements is carried out with the help of the HowNet sentiment dictionary and manual annotation method. The probabilistic language term set is used to classify the data and derive statistics, and the maximum deviation method is used to determine the weight of each attribute. Then, the cosine similarity formula is fused with the modified cosine similarity formula to calculate the similarity and construct the decision matrix. Finally, combined with the historical data of the user's hotel selection, the hotel recommendation results are generated. This paper collected review data from 10 hotels in Macau from the official "Ctrip" website. The proposed recommendation algorithm model was then applied to process and analyze the data, resulting in the generation of a ranked list of hotel recommendations. To validate the accuracy and effectiveness of this research, the recommendation results were compared with those produced by other algorithms. [ABSTRACT FROM AUTHOR]

This paper considers the main approaches to building algorithms for the decision support systems of information protection strategies against cyberattacks in the networks of automated process control systems (the so-called recommender systems). The advantages and disadvantages of each of the considered algorithms are revealed, and their applicability to the processing of the information security events of the UNSW-NB 15 dataset is analyzed. The dataset used contains raw network packets collected using the IXIA PerfectStorm software in the CyberRange laboratory of the Australian Cyber Security Centre (Canberra) in order to create a hybrid of the simulation of the real actions and the synthetic behavior of the network traffic generated during attacks. The possibility of applying four semantic proximity algorithms to partition process the data into clusters based on attack type in a distribution control system (DCS) is analyzed. The percentage of homogeneous records belonging to a particular type of attack is used as the metric that determines the optimal method of cluster partitioning. This metric was chosen under the assumption that cyberattacks located "closer" to each other in the multidimensional space have similar defense strategies. A hypothesis is formulated about the possibility of transferring knowledge about attacks from the vector feature space into a semantic form using semantic proximity methods. The percentage of homogeneous entries was maximal when the cosine proximity measure was used, which confirmed the hypothesis about the possibility of applying the corresponding algorithm in the recommender system. [ABSTRACT FROM AUTHOR]

Trip recommendation for groups of tourists (TRGT) is a challenging task in tourism since many tourists travel in groups, inducing social interaction and bringing various social benefits. However, TRGT must address various real-life constraints such as limited time for touring, cost, etc. TRGT aims to design personalized tours that meet the preferences of all group members by addressing a variety of tourists' requirements that may sometimes result in conflicts and stress for the group members. TRGT should satisfy that both the preferences of group members need to be achieved as much as possible and the preferences of group members need to be achieved as evenly as possible. In this paper, we present a methodology for tackling the TRGT problem by reducing it to the Cooperative Location Set Cover Problem (CLSCP), formulated as an integer linear program. The CLSCP aims to select a group of facilities that can satisfy, in aggregate, all demand points. To tackle the CLSCP, we present a new method based on detecting frequent patterns. We also demonstrate the efficiency of the proposed methodology by presenting extensive experimental tests. [ABSTRACT FROM AUTHOR]

Personalized recommender systems are used not only in e-commerce companies but also in various web applications. These systems conventionally use collaborative filtering (CF) and content-based filtering approaches. CF operates using memory-based or model-based methods; both methods use a user-item matrix that considers user preferences as items. This matrix denotes information on user preferences, which refers to the user ratings for items. The model-based method exploits the fact that the input matrix is factorized. CF approaches can effectively provide personalized recommendation results to users; however, cold-start problems arise because both these methods depend on the users' ratings for items to predict users' preferences. We proposed an approach to alleviate the cold-start problem along with a methodology for utilizing blockchain that can enhance the reliability of the processes of the recommendations. We attempted to predict an average rating for a new item to alleviate item-side cold-start problems. First, we applied the concept of word2vec, treating each user's item-selection history as a sentence. Then, we derived genre2Vec based on the skip-gram technique and predicted an average rating for a new item by utilizing the vectors and category ratings. We experimentally demonstrated that our approach could generate more accurate results than conventional CF approaches could. We also designed the processes of the recommendation based on the concept of blockchain addressing the smart contract. Based on our approach, we proposed a system that can secure reliability as well as alleviate the cold-start problems in recommender systems. [ABSTRACT FROM AUTHOR]

Reinforcement learning is an important machine learning method and has become a hot popular research direction topic at present in recent years. The combination of reinforcement learning and a recommendation system, is a very important application scenario and application, and has always received close attention from researchers in all sectors of society. In this paper, we first propose a feature engineering method based on label distribution learning, which analyzes historical behavior is analyzed and constructs, whereby feature vectors are constructed for users and products via label distribution learning. Then, a recommendation algorithm based on value distribution reinforcement learning is proposed. We first designed the stochastic process of the recommendation process, described the user's state in the interaction process (by including the information on their explicit state and implicit state), and dynamically generated product recommendations through user feedback. Next, by studying hybrid recommendation strategies, we combined the user's dynamic and static information to fully utilize their information and achieve high-quality recommendation algorithms. Finally, the algorithm was designed and validated, and various relevant baseline models were compared to demonstrate the effectiveness of the algorithm in this study. With this study, we actually tested the remarkable advantages of relevant design models based on nonlinear expectations compared to other homogeneous individual models. The use of recommendation systems with nonlinear expectations has considerably increased the accuracy, data utilization, robustness, model convergence speed, and stability of the systems. In this study, we incorporated the idea of nonlinear expectations into the design and implementation process of recommendation systems. The main practical value of the improved recommendation model is that its performance is more accurate than that of other recommendation models at the same level of computing power level. Moreover, due to the higher amount of information that the enhanced model contains, it provides theoretical support and the basis for an algorithm that can be used to achieve high-quality recommendation services, and it has many application prospects. [ABSTRACT FROM AUTHOR]

Cloud computing is now a fundamental type of computing due to technological innovation and it is believed to be a benefit for mid-scale enterprises. The use of cloud computing is increasing daily, which improves service quality but also gives rise to security concerns. Finding trustworthy service can be very challenging, take a great deal of time, or produce subpar services. Due to these difficulties, the client needs a service that is dependable, suitable, time-saving, and trustworthy. As a result, from the end user's perspective, adopting a cloud service's trustworthiness becomes crucial. Trust is a measure of how well users' expectations about a service's capabilities are realized. In this research, a recommendation system for cloud service customers based on random iterative fuzzy computation (RIFTC) is proposed. RIFTC focuses on the assessment of trust using Quality of Service (QoS) characteristics. RIFTC calculates trust using the machine learning approach Support Vector Regression (SVR). RIFTC can helpfully recommend a cloud service to the end user and anticipate the trust values of cloud services.. Precision (97%), latency (51%), throughput (25.99 mbps), mean absolute error (54%), and re-call (97%) rates are used to assess how well this recommendation system performs. RIFTC's average F-measure rate is calculated by adjusting the number of users from 200 to 300, and it is 93.46% more accurate on average with less time spent than the current methodologies. [ABSTRACT FROM AUTHOR]

Gas is the transaction-fee metering system of the Ethereum network. Users of the network are required to select a gas price for submission with their transaction, creating a risk of overpaying or delayed/unprocessed transactions involved in this selection. In this work, we investigate data in the aftermath of the London Hard Fork and shed insight into the transaction dynamics of the network after this major fork. As such, this paper provides an update on work previous to 2019 on the link between EthUSD/BitUSD and gas price. For forecasting, we compare a novel combination of machine learning methods such as Direct-Recursive Hybrid LSTM, CNN-LSTM, and Attention-LSTM. These are combined with wavelet threshold denoising and matrix profile data processing toward the forecasting of block minimum gas price, on a 5-min timescale, over multiple lookaheads. As the first application of the matrix profile being applied to gas price data and forecasting that we are aware of, this study demonstrates that matrix profile data can enhance attention-based models; however, given the hardware constraints, hybrid models outperformed attention and CNN-LSTM models. The wavelet coherence of inputs demonstrates correlation in multiple variables on a 1-day timescale, which is a deviation of base free from gas price. A Direct-Recursive Hybrid LSTM strategy is found to outperform other models, with an average RMSE of 26.08 and R2 of 0.54 over a 50-min lookahead window compared to an RMSE of 26.78 and R2 of 0.452 in the best-performing attention model. Hybrid models are shown to have favorable performance up to a 20-min lookahead with performance being comparable to attention models when forecasting 25–50-min ahead. Forecasts over a range of lookaheads allow users to make an informed decision on gas price selection and the optimal window to submit their transaction in without fear of their transaction being rejected. This, in turn, gives more detailed insight into gas price dynamics than existing recommenders, oracles and forecasting approaches, which provide simple heuristics or limited lookahead horizons. [ABSTRACT FROM AUTHOR]

Deep learning, which is a subfield of machine learning, has opened a new era for the development of neural networks. The auto-encoder is a key component of deep structure, which can be used to realize transfer learning and plays an important role in both unsupervised learning and non-linear feature extraction. By highlighting the contributions and challenges of recent research papers, this work aims to review state-of-the-art auto-encoder algorithms. Firstly, we introduce the basic auto-encoder as well as its basic concept and structure. Secondly, we present a comprehensive summarization of different variants of the auto-encoder. Thirdly, we analyze and study auto-encoders from three different perspectives. We also discuss the relationships between auto-encoders, shallow models and other deep learning models. The auto-encoder and its variants have successfully been applied in a wide range of fields, such as pattern recognition, computer vision, data generation, recommender systems, etc. Then, we focus on the available toolkits for auto-encoders. Finally, this paper summarizes the future trends and challenges in designing and training auto-encoders. We hope that this survey will provide a good reference when using and designing AE models. [ABSTRACT FROM AUTHOR]

The study aims to present an architecture for a recommendation system based on user items that are transformed into narrow categories. In particular, to identify the movies a user will likely watch based on their favorite items. The recommendation system focuses on the shortest connections between item correlations. The degree of attention paid to user-group relationships provides another valuable piece of information obtained by joining the sub-groups. Various relationships have been used to reduce the data sparsity problem. We reformulate the existing data into several groups of items and users. As part of the calculations and containment of activities, we consider Pearson similarity, cosine similarity, Euclidean distance, the Gaussian distribution rule, matrix factorization, EM algorithm, and k-nearest neighbors (KNN). It is also demonstrated that the proposed methods could moderate possible recommendations from diverse perspectives. [ABSTRACT FROM AUTHOR]

Recommender systems have become a vital tool to identify items for users based on personalized preferences. The personalized ranking or item recommendation generates a ranked list of items for the users. Clustering methods offer better scalability than collaborative filtering (CF) methods since they make predictions within small clusters. The major challenges of recommender systems are accuracy and scalability. Traditionally, recommendation systems are based on a centralized framework that restrains quick scalability for enormous data volumes. The emergence of cloud technology resolves this issue as it handles vast data and supports massive processing. This paper proposes a time cluster personalized ranking recommender system (TCPRRS) in a multi-cloud environment. TCPRRS is a five-stage system that generates recommendations based on temporal information of user consumption and clustering with personalized ranking. Particle swarm optimization (PSO) is utilized for optimizing the solution. The efficiency of TCPRRS is estimated using similarity metrics. [ABSTRACT FROM AUTHOR]

The explosive increase in educational data and information systems has led to new teaching practices, challenges, and learning processes. To effectively manage and analyze this information, it is crucial to adopt innovative methodologies and techniques. Recommender systems (RSs) offer a solution for advising students and guiding their learning journeys by utilizing statistical methods such as machine learning (ML) and graph analysis to analyze program and student data. This paper introduces an RS for advisors and students that analyzes student records to develop personalized study plans over multiple semesters. The proposed system integrates ideas from graph theory, performance modeling, ML, explainable recommendations, and an intuitive user interface. The system implicitly implements many academic rules through network analysis. Accordingly, a systematic and comprehensive review of different students' plans was possible using metrics developed in the mathematical graph theory. The proposed system systematically assesses and measures the relevance of a particular student's study plan. Experiments on datasets collected at the University of Dubai show that the model presented in this study outperforms similar ML-based solutions in terms of different metrics. Typically, up to 86% accuracy and recall have been achieved. Additionally, the lowest mean square regression (MSR) rate of 0.14 has been attained compared to other state-of-the-art regressors. [ABSTRACT FROM AUTHOR]

Recommendation systems, the best way to deal with information overload, are widely utilized to provide users with personalized content and services with high efficiency. Many recommendation algorithms have been researched and deployed extensively in various e-commerce applications, including the movie streaming services over the last decade. However, sparse data cold-start problems are often encountered in many movie recommendation systems. In this paper, we reported a personalized multimodal movie recommendation system based on multimodal data analysis and deep learning. The real-world MovieLens datasets were selected to test the effectiveness of our new recommendation algorithm. With the input information, the hidden features of the movies and the users were mined using deep learning to build a deep-learning network algorithm model for training to further predict movie scores. With a learning rate of 0.001, the root mean squared error (RMSE) scores achieved 0.9908 and 0.9096 for test sets of MovieLens 100 K and 1 M datasets, respectively. The scoring prediction results show improved accuracy after incorporating the potential features and connections in multimodal data with deep-learning technology. Compared with the traditional collaborative filtering algorithms, such as user-based collaborative filtering (User-CF), item-based content-based filtering (Item-CF), and singular-value decomposition (SVD) approaches, the multimodal movie recommendation system using deep learning could provide better personalized recommendation results. Meanwhile, the sparse data problem was alleviated to a certain degree. We suggest that the recommendation system can be improved through the combination of the deep-learning technology and the multimodal data analysis. [ABSTRACT FROM AUTHOR]

Air quality plays a vital role in people's health, and air quality forecasting can assist in decision making for government planning and sustainable development. In contrast, it is challenging to multi-step forecast accurately due to its complex and nonlinear caused by both temporal and spatial dimensions. Deep models, with their ability to model strong nonlinearities, have become the primary methods for air quality forecasting. However, because of the lack of mechanism-based analysis, uninterpretability forecasting makes decisions risky, especially when the government makes decisions. This paper proposes an interpretable variational Bayesian deep learning model with information self-screening for PM2.5 forecasting. Firstly, based on factors related to PM2.5 concentration, e.g., temperature, humidity, wind speed, spatial distribution, etc., an interpretable multivariate data screening structure for PM2.5 forecasting was established to catch as much helpful information as possible. Secondly, the self-screening layer was implanted in the deep learning network to optimize the selection of input variables. Further, following implantation of the screening layer, a variational Bayesian gated recurrent unit (GRU) network was constructed to overcome the complex distribution of PM2.5 and achieve accurate multi-step forecasting. The high accuracy of the proposed method is verified by PM2.5 data in Beijing, China, which provides an effective way, with multiple factors for PM2.5 forecasting determined using deep learning technology. [ABSTRACT FROM AUTHOR]

A recommender system not only "gains users' confidence" but also helps them in other ways, such as reducing their time spent and effort. To gain users' confidence, one of the main goals of recommender systems in an e-commerce industry is to estimate the users' interest by tracking the users' transactional behavior to provide a fast and highly related set of top recommendations out of thousands of products. The standard ranking-based models, i.e., the denoising auto-encoder (DAE) and collaborative denoising auto-encoder (CDAE), exploit positive-only feedback without utilizing the ratings' ranks for the full set of observed ratings. To confirm the rank of observed ratings (either low or high), a confidence value for each rating is required. Hence, an improved, confidence-integrated DAE is proposed to enhance the performance of the standard DAE for solving recommender systems problems. The correctness of the proposed method is authenticated using two standard MovieLens datasets such as ML-1M and ML-100K. The proposed study acts as a vital contribution for the design of an efficient, robust, and accurate algorithm by learning prominent latent features used for fast and accurate recommendations. The proposed model outperforms the state-of-the-art methods by achieving improved P@10, R@10, NDCG@10, and MAP scores. [ABSTRACT FROM AUTHOR]

The existing knowledge graph embedding (KGE) method has achieved good performance in recommendation systems. However, the relevancy degree among entities reduces gradually along the spread in the knowledge graph. Focusing on the explicit and implicit relationships among entities, this paper proposes an attention knowledge network combining explicit and implicit information (AKNEI) to effectively capture and exactly describe the correlation between entities in the knowledge graph. First, we design an information-sharing layer (ISL) to realize information sharing between projects and entities through implicit interaction. We innovatively propose a cross-feature fusion module to extract high-order feature information in the model. At the same time, this paper uses the attention mechanism to solve the problem of the decline of information relevance in the process of knowledge graph propagation. Finally, the features of KGE and cross feature fusion module are integrated into the end-to-end learning framework, the item information in the recommendation task and the knowledge graph entity information are interacted implicitly and explicitly, and the characteristics between them are automatically learned. We performed extensive experiments on multiple public datasets that include movies, music, and books. According to the experimental results, our model has a great improvement in performance compared with the latest baseline. [ABSTRACT FROM AUTHOR]

With the development of the Web, users spend more time accessing information that they seek. As a result, recommendation systems have emerged to provide users with preferred contents by filtering abundant information, along with providing means of exposing search results to users more effectively. These recommendation systems operate based on the user reactions to items or on the various user or item features. It is known that recommendation results based on sparse datasets are less reliable because recommender systems operate according to user responses. Thus, we propose a method to improve the dataset sparsity and increase the accuracy of the prediction results by using item features with user responses. A method based on the content-based filtering concept is proposed to extract category rates from the user–item matrix according to the user preferences and to organize these into vectors. Thereafter, we present a method to filter the user–item matrix using the extracted vectors and to regenerate the input matrix for collaborative filtering (CF). We compare the prediction results of our approach and conventional CF using the mean absolute error and root mean square error. Moreover, we calculate the sparsity of the regenerated matrix and the existing input matrix, and demonstrate that the regenerated matrix is more dense than the existing one. By computing the Jaccard similarity between the item sets in the regenerated and existing matrices, we verify the matrix distinctions. The results of the proposed methods confirm that if the regenerated matrix is used as the CF input, a denser matrix with higher predictive accuracy can be constructed than when using conventional methods. The validity of the proposed method was verified by analyzing the effect of the input matrix composed of high average ratings on the CF prediction performance. The low sparsity and high prediction accuracy of the proposed method are verified by comparisons with the results by conventional methods. Improvements of approximately 16% based on K-nearest neighbor and 15% based on singular value decomposition, and a three times improvement in the sparsity based on regenerated and original matrices are obtained. We propose a matrix reconstruction method that can improve the performance of recommendations. [ABSTRACT FROM AUTHOR]

Semantic relationships between words provide relevant information about the whole idea in the texts. Existing embedding representation models characterize each word as a vector of numbers with a fixed length. These models have been used in tasks involving text classification, such as recommendation and question–answer systems. However, the embedded information provided by semantic relationships has been neglected. Therefore, this paper proposes an approach that involves semantic relationships in embedding models for text classification, which is evaluated. Three embedding models based on semantic relations extracted from Wikipedia are presented and compared with existing word-based models. Our approach considers the following relationships: synonymy, hyponymy, and hyperonymy. They were considered since previous experiments have shown that they provide semantic knowledge. The relationships are extracted from Wikipedia using lexical-syntactic patterns identified in the literature. The extracted relationships are embedded as a vector: synonymy, hyponymy–hyperonymy, and a combination of all relationships. A Convolutional Neural Network using semantic relationship embeddings was trained for text classification. An evaluation was carried out for the proposed relationship embedding configurations and existing word-based models to compare them based on two corpora. The results were obtained with the metrics of precision, accuracy, recall, and F 1 -measure. The best results for the 20-Newsgroup corpus were obtained with the hyponymy–hyperonymy embeddings, achieving an accuracy of 0.79. For the Reuters corpus, F 1 -measure and recall of 0.87 were obtained using synonymy–hyponymy–hyperonymy. [ABSTRACT FROM AUTHOR]

Social recommendation can effectively alleviate the problems of data sparseness and the cold start of recommendation systems, attracting widespread attention from researchers and industry. Current social recommendation models use social relations to alleviate the problem of data sparsity and improve recommendation performance. Although self-supervised learning based on user–item interaction can enhance the performance of such models, multi-auxiliary information is neglected in the learning process. Therefore, we propose a model based on self-supervision and multi-auxiliary information using multi-auxiliary information, such as user social relationships and item association relationships, to make recommendations. Specifically, the user social relationship and item association relationship are combined to form a multi-auxiliary information graph. The user–item interaction relationship is also integrated into the same heterogeneous graph so that multiple pieces of information can be spread in the same graph. In addition, we utilize the graph convolution method to learn user and item embeddings, whereby the user embeddings reflect both user–item interaction and user social relationships, and the item embeddings reflect user–item interaction and item association relationships. We also design multi-view self-supervising auxiliary tasks based on the constructed multi-auxiliary views. Signals generated by self-supervised auxiliary tasks can alleviate the problem of data sparsity, further improving user/item embedding quality and recommendation performance. Extensive experiments on two public datasets verify the superiority of the proposed model. [ABSTRACT FROM AUTHOR]

Pulmonary diseases are life-threatening diseases commonly observed worldwide, and timely diagnosis of these diseases is essential. Meanwhile, increased use of Convolution Neural Networks has promoted the advancement of computer-assisted clinical recommendation systems for diagnosing diseases using chest radiographs. The texture and shape of the tissues in the diagnostic images are essential aspects of prognosis. Therefore, in the latest studies, the vast set of images with a larger resolution is paired with deep learning techniques to enhance the performance of the disease diagnosis in chest radiographs. Moreover, pulmonary diseases have irregular and different sizes; therefore, several studies sought to add new components to existing deep learning techniques for acquiring multi-scale imaging features from diagnostic chest X-rays. However, most of the attempts do not consider the computation overhead and lose the spatial details in an effort to capture the larger receptive field for obtaining the discriminative features from high-resolution chest X-rays. In this paper, we propose an explainable and lightweight Multi-Scale Chest X-ray Network (MS-CheXNet) to predict abnormal diseases from the diagnostic chest X-rays. The MS-CheXNet consists of four following main subnetworks: (1) Multi-Scale Dilation Layer (MSDL), which includes multiple and stacked dilation convolution channels that consider the larger receptive field and captures the variable sizes of pulmonary diseases by obtaining more discriminative spatial features from the input chest X-rays; (2) Depthwise Separable Convolution Neural Network (DS-CNN) is used to learn imaging features by adjusting lesser parameters compared to the conventional CNN, making the overall network lightweight and computationally inexpensive, making it suitable for mobile vision tasks; (3) a fully connected Deep Neural Network module is used for predicting abnormalities from the chest X-rays; and (4) Gradient-weighted Class Activation Mapping (Grad-CAM) technique is employed to check the decision models' transparency and understand their ability to arrive at a decision by visualizing the discriminative image regions and localizing the chest diseases. The proposed work is compared with existing disease prediction models on chest X-rays and state-of-the-art deep learning strategies to assess the effectiveness of the proposed model. The proposed model is tested with a publicly available Open-I Dataset and data collected from a private hospital. After the comprehensive assessment, it is observed that the performance of the designed approach showcased a 7% to 18% increase in accuracy compared to the existing method. [ABSTRACT FROM AUTHOR]

The current graph-neural-network-based recommendation algorithm fully considers the interaction between users and items. It achieves better recommendation results, but due to a large amount of data, the interaction between users and items still suffers from the problem of data sparsity. To address this problem, we propose a method to alleviate the data sparsity problem by retaining user–item interactions while fully exploiting the association relationships between items and using side-information enhancement. We constructed a "twin-tower" model by combining a user–item training model and an item–item training model inspired by the knowledge distillation technique; the two sides of the structure learn from each other during the model training process. Comparative experiments were carried out on three publicly available datasets, using the recall and the normalized discounted cumulative gain as evaluation metrics; the results outperform existing related base algorithms. We also carried out extensive parameter sensitivity and ablation experiments to analyze the influence of various factors on the model. The problem of user–item interaction data sparsity is effectively addressed. [ABSTRACT FROM AUTHOR]

Graph convolutional networks are widely used in recommendation tasks owing to their ability to learn user and item embeddings using collaborative signals from high-order neighborhoods. Most of the graph convolutional recommendation tasks in existing studies have specialized in modeling a single type of user–item interaction preference. Meanwhile, graph-convolution-network-based recommendation models are prone to over-smoothing problems when stacking increased numbers of layers. Therefore, in this study we propose a multi-behavior recommendation method based on graph transformer collaborative filtering. This method utilizes an unsupervised subgraph generation model that divides users with similar preferences and their interaction items into subgraphs. Furthermore, it fuses multi-headed attention layers with temporal coding strategies based on the user–item interaction graphs in the subgraphs such that the learned embeddings can reflect multiple user–item relationships and the potential for dynamic interactions. Finally, multi-behavior recommendation is performed by uniting multi-layer embedding representations. The experimental results on two real-world datasets show that the proposed method performs better than previously developed systems. [ABSTRACT FROM AUTHOR]

Recommendation systems are now widely used on the Internet. In recommendation systems, user preferences are predicted by the interaction of users with products, such as clicks or purchases. Usually, the heterogeneous information network is used to capture heterogeneous semantic information in data, which can be used to solve the sparsity problem and the cold-start problem. In a more complex heterogeneous information network, the types of nodes and edges are very large, so there are lots of types of metagraphs in a complex heterogeneous information network. At the same time, machine learning tasks on heterogeneous information networks have a large number of parameters and neural network architectures that need to be set artificially. The main goal is to find the optimal hyperparameter settings and neural network architectures for the performance of a task in the set of hyperparameter space. To address this problem, we propose a metapath search method for heterogeneous information networks based on a network architecture search, which can search for metapaths that are more suitable for different heterogeneous information networks and recommendation tasks. We conducted experiments on Amazon and Yelp datasets and compared the architecture settings obtained from an automatic search with manually set structures to verify the effectiveness of the algorithm. [ABSTRACT FROM AUTHOR]

The existing grid infrastructure has already begun transforming into the next-generation cyber-physical smart grid (SG) system. This transformation has improved the grid's reliability and efficiency but has exposed severe vulnerabilities due to growing cyberattacks and threats. For example, malicious actors may be able to tamper with system readings, parameters, and energy prices and penetrate to get direct access to the data. Several works exist to handle the aforementioned issues, but they have not been fully explored. Consequently, this paper proposes an AI-ADP scheme for the SG system, which is an artificial intelligence (AI)-based attack-detection and prevention (ADP) mechanism by using a cryptography-driven recommender system to ensure data security and integrity. The proposed AI-ADP scheme is divided into two phases: (i) attack detection and (ii) attack prevention. We employed the extreme gradient-boosting (XGBoost) mechanism for attack detection and classification. It is a new ensemble learning methodology that offers many advantages over similar methods, including built-in features, etc. Then, SHA-512 is used to secure the communication that employs faster performance, allowing the transmission of more data with the same security level. The performance of the proposed AI-ADP scheme is evaluated based on various parameters, such as attack-detection accuracy, cycles used per byte, and total cycles used. The proposed AI-ADP scheme outperformed the existing approaches and obtained 99.12% accuracy, which is relatively high compared to the pre-existing methods. [ABSTRACT FROM AUTHOR]

Predictive graph learning approaches have been bringing significant advantages in many real-life applications, such as social networks, recommender systems, and other social-related downstream tasks. For those applications, learning models should be able to produce a great prediction result to maximize the usability of their application. However, the paradigm of current graph learning methods generally neglects the differences in link strength, leading to discriminative predictive results, resulting in different performance between tasks. Based on that problem, a fairness-aware predictive learning model is needed to balance the link strength differences and not only consider how to formulate it. To address this problem, we first formally define two biases (i.e., Preference and Favoritism) that widely exist in previous representation learning models. Then, we employ modularity maximization to distinguish strong and weak links from the quantitative perspective. Eventually, we propose a novel predictive learning framework entitled ACE that first implements the link strength differentiated learning process and then integrates it with a dual propagation process. The effectiveness and fairness of our proposed ACE have been verified on four real-world social networks. Compared to nine different state-of-the-art methods, ACE and its variants show better performance. The ACE framework can better reconstruct networks, thus also providing a high possibility of resolving misinformation in graph-structured data. [ABSTRACT FROM AUTHOR]

It is well-known that data sparsity and cold start are two of the open problems in recommendation system research. Numerous studies have been dedicated to dealing with those two problems. Among these, a method of introducing user context information could effectively solve the problem of data sparsity and improve the accuracy of recommendation algorithms. This study proposed a novel approach called IT-PMF (Implicit Trust-Probabilistic Matrix Factorization) based on implicit trust, which consists of local implicit trust relationships and in-group membership. The study started from generating the user commodity rating matrix based on the cumulative purchases for items according to their historical purchase records to find the similarity of purchase behaviors and the number of successful interactions between users, which represent the local implicit trust relationship between users. The user group attribute value was calculated through a fuzzy c-means clustering algorithm to obtain the user's in-group membership. The local implicit trust relationship and the user's in-group membership were adjusted by the adaptive weight to determine the degree of each part's influence. Then, the author integrated the user's score of items and the user's implicit trust relationship into the probabilistic matrix factorization algorithm to form a trusted recommendation model based on implicit trust relationships and in-group membership. The extensive experiments were conducted using a real dataset collected from a community E-commerce platform, and the IT-PMF method had a better performance in both MAE (Mean Absolute Error) and RMSE (Root Mean Square Error) indices compared with well-known existing algorithms, such as PMF (Probabilistic Matrix Factorization) and SVD (Single Value Decomposition). The results of the experiments indicated that the introduction of implicit trust into PMF could improve the quality of recommendations. [ABSTRACT FROM AUTHOR]

The use of computerized formative assessments in K–12 classrooms has yielded valuable data that can be utilized by learning analytics (LA) systems to produce actionable insights for teachers and other school-based professionals. For example, LA systems utilizing computerized formative assessments can be used for monitoring students' progress in reading and identifying struggling readers. Using such LA systems, teachers can also determine whether progress is adequate as the student works towards their instructional goal. However, due to the lack of guidelines on the timing, number, and frequency of computerized formative assessments, teachers often follow a one-size-fits-all approach by testing all students together on pre-determined dates. This approach leads to a rigid test scheduling that ignores the pace at which students improve their reading skills. In some cases, the consequence is testing that yields little to no useful data, while increasing the amount of instructional time that students miss. In this study, we propose an intelligent recommender system (IRS) based on Dijkstra's shortest path algorithm that can produce an optimal assessment schedule for each student based on their reading progress throughout the school year. We demonstrated the feasibility of the IRS using real data from a large sample of students in grade two (n = 668,324) and grade four (n = 727,147) who participated in a series of computerized reading assessments. Also, we conducted a Monte Carlo simulation study to evaluate the performance of the IRS in the presence of unusual growth trajectories in reading (e.g., negative growth, no growth, and plateau). Our results showed that the IRS could reduce the number of test administrations required at both grade levels by eliminating test administrations in which students' reading growth did not change substantially. In addition, the simulation results indicated that the IRS could yield robust results with meaningful recommendations under relatively extreme growth trajectories. Implications for the use of recommender systems in K–12 education and recommendations for future research are discussed. [ABSTRACT FROM AUTHOR]

Accurate and stable wind speed prediction is crucial for the safe operation of large-scale wind power grid connections. Existing methods are typically limited to a certain fixed area when learning the information of the wind speed sequence, which cannot make full use of the spatiotemporal correlation of the wind speed sequence. To address this problem, in this paper we propose a new wind speed prediction method based on collaborative filtering against a virtual edge expansion graph structure in which virtual edges enrich the semantics that the graph can express. It is an effective extension of the dataset, connecting wind turbines of different wind farms through virtual edges to ensure that the spatial correlation of wind speed sequences can be effectively learned and utilized. The new collaborative filtering on the graph is reflected in the processing of the wind speed sequence. The wind speed is preprocessed from the perspective of pattern mining to effectively integrate various information, and the k-d tree is used to match the wind speed sequence to achieve the purpose of collaborative filtering. Finally, a model with long short-term memory (LSTM) as the main body is constructed for wind speed prediction. By taking the wind speed of the actual wind farm as the research object, we compare the new approach with four typical wind speed prediction methods. The mean square error is reduced by 16.40%, 11.78%, 9.57%, and 18.36%, respectively, which demonstrates the superiority of the proposed new method. [ABSTRACT FROM AUTHOR]

The goal of the recommender system is to learn the user's preferences from the entity (user–item) historical interaction data, so as to predict the user's ratings on new items or recommend new item sequences to users. There are two major challenges: (1) Datasets are usually sparse. The item side is often accompanied by some auxiliary information, such as attributes or context; it can help to slightly improve its representation. However, the user side is usually presented in the form of ID due to personal privacy. (2) Due to the influences of confounding factors, such as the popularity of items, users' ratings on items often have bias that cannot be recognized by the traditional recommendation methods. In order to solve these two problems, in this paper, (1) we explore the use of a graph model to fuse the interactions between users and common rating items, that is, incorporating the "neighbor" information into the target user to enrich user representations; (2) the d o () operator is used to deduce the causality after removing the influences of confounding factors, rather than the correlation of the data surface fitted by traditional machine learning. We propose the EGCI model, i.e., enhanced graph learning for recommendation via causal inference. The model embeds user relationships and item attributes into the latent semantic space to obtain high-quality user and item representations. In addition, the mixed bias implied in the rating process is calibrated by considering the popularity of items. Experimental results on three real-world datasets show that EGCI is significantly better than the baselines. [ABSTRACT FROM AUTHOR]

Movies are one of the integral components of our everyday entertainment. In today's world, people prefer to watch movies on their personal devices. Many movies are available on all popular Over the Top (OTT) platforms. Multiple new movies are released onto these platforms every day. The recommendation system is beneficial for guiding the user to a choice from among the overloaded contents. Most of the research on these recommendation systems has been conducted based on existing movies. We need a recommendation system for forthcoming movies in order to help viewers make a personalized decision regarding which upcoming new movies to watch. In this article, we have proposed a framework combining sentiment analysis and a hybrid recommendation system for recommending movies that are not yet released, but the trailer has been released. In the first module, we extracted comments about the movie trailer from the official YouTube channel for Netflix, computed the overall sentiment, and predicted the rating of the upcoming movies. Next, in the second module, our proposed hybrid recommendation system produced a list of preferred upcoming movies for individual users. In the third module, we finally were able to offer recommendations regarding potentially popular forthcoming movies to the user, according to their personal preferences. This method fuses the predicted rating and preferred list of upcoming movies from modules one and two. This study used publicly available data from The Movie Database (TMDb). We also created a dataset of new movies by randomly selecting a list of one hundred movies released between 2020 and 2021 on Netflix. Our experimental results established that the predicted rating of unreleased movies had the lowest error. Additionally, we showed that the proposed hybrid recommendation system recommends movies according to the user's preferences and potentially promising forthcoming movies. [ABSTRACT FROM AUTHOR]

In the era of information explosion, it is difficult for people to obtain their desired information effectively. In tourism, a travel recommender system based on big travel data has been developing rapidly over the last decade. However, most work focuses on click logs, visit history, or ratings, and dynamic prediction is absent. As a result, there are significant gaps in both dataset and recommender models. To address these gaps, in the first step of this study, we constructed two human-annotated datasets for the travel conversational recommender system. We provided two linked data sets, namely, interaction sequence and dialogue data sets. The usage of the former data set was done to fully explore the static preference characteristics of users based on it, while the latter identified the dynamics changes in user preference from it. Then, we proposed and evaluated BERT-based baseline models for the travel conversational recommender system and compared them with several representative non-conversational and conversational recommender system models. Extensive experiments demonstrated the effectiveness and robustness of our approach regarding conversational recommendation tasks. Our work can extend the scope of the travel conversational recommender system and our annotated data can also facilitate related research. [ABSTRACT FROM AUTHOR]

E-learning is a popular area in terms of learning from social media websites in various terms and contents for every group of people in this world with different knowledge backgrounds and jobs. E-learning sites help users such as students, business workers, instructors, and those searching for different educational institutions. Excluding the benefits of this system, there are various challenges that the users face in online platforms. One of the important challenges is the true information and right content based on these resources, search results and quality. This research proposes virtual and intelligent agent-based recommendation, which requires users' profile information and preferences to recommend the proper content and search results based on their search history. We applied Natural Language Processing (NLP) techniques and semantic analysis approaches for the recommendation of course selection to e-learners and tutors. Moreover, machine learning performance analysis applied to improve the user rating results in the e-learning environment. The system automatically learns and analyzes the learner characteristics and processes the learning style through the clustering strategy. Compared with the recent state-of-the-art in this field, the proposed system and the simulation results show the minimizing number of metric errors compared to other works. The achievements of the presented approach are providing a comfortable platform to the user for course selection and recommendations. Similarly, we avoid recommending the same contents and courses. We analyze the user preferences and improving the recommendation system performance to provide highly related content based on the user profile situation. The prediction accuracy of the proposed system is 98% compared to hybrid filtering, self organization systems and ensemble modeling. [ABSTRACT FROM AUTHOR]

Nowadays, recommender systems are vital in lessening the information overload by filtering out unnecessary information, thus increasing comfort and quality of life. Matrix factorization (MF) is a well-known recommender system algorithm that offers good results but requires a certain level of system knowledge and some effort on part of the user before use. In this article, we proposed an improvement using grammatical evolution (GE) to automatically initialize and optimize the algorithm and some of its settings. This enables the algorithm to produce optimal results without requiring any prior or in-depth knowledge, thus making it possible for an average user to use the system without going through a lengthy initialization phase. We tested the approach on several well-known datasets. We found our results to be comparable to those of others while requiring a lot less set-up. Finally, we also found out that our approach can detect the occurrence of over-saturation in large datasets. [ABSTRACT FROM AUTHOR]

Among the inherent problems in recommendation systems are data sparseness and cold starts; the solutions to which lie in the introduction of knowledge graphs to improve the performance of the recommendation systems. The results in previous research, however, suffer from problems such as data compression, information damage, and insufficient learning. Therefore, a DeepFM Graph Convolutional Network (DFM-GCN) model was proposed to alleviate the above issues. The prediction of the click-through rate (CTR) is critical in recommendation systems where the task is to estimate the probability that a user will click on a recommended item. In many recommendation systems, the goal is to maximize the number of clicks so the items returned to a user can be ranked by an estimated CTR. The DFM-GCN model consists of three parts: the left part DeepFM is used to capture the interactive information between the users and items; the deep neural network is used in the middle to model the left and right parts; and the right one obtains a better item representation vector by the GCN. In an effort to verify the validity and precision of the model built in this research, and based on the public datasets ml1m-kg20m and ml1m-kg1m, a performance comparison experiment was designed. It used multiple comparison models and the MKR and FM_MKR algorithms as well as the DFM-GCN algorithm constructed in this paper. Having achieved a state-of-the-art performance, the experimental results of the AUC and f1 values verified by the CTR as well as the accuracy, recall, and f1 values of the top-k showed that the proposed approach was excellent and more effective when compared with different recommendation algorithms. [ABSTRACT FROM AUTHOR]

Agile global software engineering challenges architectural knowledge (AK) management since face-to-face interactions are preferred over comprehensive documentation, which causes AK loss over time. The AK condensation concept was proposed to reduce AK losing, using the AK shared through unstructured electronic media. A crucial part of this concept is a classification mechanism to ease AK recovery in the future. We developed a Slack complement as a classification mechanism based on social tagging, which recommends tags according to a chat/message topic, using natural language processing (NLP) techniques. We evaluated two tagging modes: NLP-assisted versus alphabetical auto-completion, in terms of correctness and time to select a tag. Fifty-two participants used the complement emulating an agile and global scenario and gave us their complement's perceptions about usefulness, ease of use, and work integration. Messages tagged through NLP recommendations showed fewer semantic errors, and participants spent less time selecting a tag. They perceived the component as very usable, useful, and easy to be integrated into the daily work. These results indicated that a tag recommendation system is necessary to classify the shared AK accurately and quickly. We will improve the NLP techniques to evaluate AK condensation in a long-term test as future work. [ABSTRACT FROM AUTHOR]

Existing studies have made a great endeavor in predicting users' potential interests in items by modeling user preferences and item characteristics. As an important indicator of users' satisfaction and loyalty, repeat purchase behavior is a promising perspective to extract insightful information for community e-commerce. However, the repeated purchase behaviors of users have not yet been thoroughly studied. To fill in this research gap from the perspective of repeated purchase behavior and improve the process of generation of candidate recommended items this research proposed a novel approach called ReRec (Repeat purchase Recommender) for real-life applications. Specifically, the proposed ReRec approach comprises two components: the first is to model the repeat purchase behaviors of different types of users and the second is to recommend items to users based on their repeat purchase behaviors of different types. The extensive experiments are conducted on a real dataset collected from a community e-commerce platform, and the performance of our model has improved at least about 13.6% compared with the state-of-the-art techniques in recommending online items (measured by F-measure). Specifically, for active users, with w = 1 and N U A ∈ 5 , 25 , the results of ReRec show a significant improvement (at least 50%) in recommendation. With α and σ as 0.75 and 0.2284, respectively, the proposed ReRec for unactive users is also superior to (at least 13.6%) the evaluation indicators of traditional Item CF when N U B ∈ 6 ,   25 . To the best of our knowledge, this paper is the first to study recommendations in community e-commerce. [ABSTRACT FROM AUTHOR]

Online auctions are now widely used, with all the convenience and efficiency brought by internet technology. Despite the advantages over traditional auction methods, some challenges still remain in online auctions. According to the World Business Environment Survey (WBES) conducted by the World Bank, about 60% of companies have admitted to bribery and manipulation of the auction results. In addition, buyers are prone to the winner's curse in an online auction environment. Since the increase in information availability can reduce uncertainty, easy access to relevant auction information is essential for buyers to avoid the winner's curse. In this study, we propose an Online Auction Price Suggestion System (OAPSS) to protect the data from being interfered with by third-party programs based on Intel's Software Guard Extensions (SGX) technology and the characteristics of the blockchain. Our proposed system provides a smart contract by using α-Sutte indicator in the final transaction price prediction as a bidding price recommendation, which helps buyers to reduce the information uncertainty on the value of the product. The amount spent on the smart contract in this study, excluding deployed contracts, plus the rest of the fees is less than US$1. Experimental results of the simulation show that there is a significant difference (p < 0.05) between the recommended price group and the actual price group in the highest bid. Therefore, we may conclude that our proposed bidder's price recommendation function in the smart contract may mitigate the loss of buyers caused by the winner's curse. [ABSTRACT FROM AUTHOR]

Link prediction tasks have an extremely high research value in both academic and commercial fields. As a special case, link prediction in bipartite graphs has been receiving more and more attention thanks to the great success of the recommender system in the application field, such as product recommendation in E-commerce and movie recommendation in video sites. However, the difference between bipartite and unipartite graphs makes some methods designed for the latter inapplicable to the former, so it is quite important to study link prediction methods specifically for bipartite graphs. In this paper, with the aim of better measuring the similarity between two nodes in a bipartite graph and improving link prediction performance based on that, we propose a motif-based similarity index specifically for application on bipartite graphs. Our index can be regarded as a high-order evaluation of a graph's local structure, which concerns mainly two kinds of typical 4-motifs related to bipartite graphs. After constructing our index, we integrate it into a commonly used method to measure the connection potential between every unconnected node pair. Some of the node pairs are originally unconnected, and the others are those we select deliberately to delete their edges for subsequent testing. We make experiments on six public network datasets and the results imply that the mixture of our index with the traditional method can obtain better prediction performance w.r.t. precision, recall and AUC in most cases. This is a strong proof of the effectiveness of our exploration on motifs structure. Also, our work points out an interesting direction for key graph structure exploration in the field of link prediction. [ABSTRACT FROM AUTHOR]

The processing of a sparse matrix is a hot topic in the recommendation system. This paper applies the method of hesitant fuzzy set to study the sparse matrix processing problem. Based on the uncertain factors in the recommendation process, this paper applies hesitant fuzzy set theory to characterize the historical ratings embedded in the recommendation system and studies the data processing problem of the sparse matrix under the condition of a hesitant fuzzy set. The key is to transform the similarity problem of products in the sparse matrix into the similarity problem of two hesitant fuzzy sets by data conversion, data processing, and data complement. This paper further considers the influence of the difference of user ratings on the recommendation results and obtains a user's recommendation list. On the one hand, the proposed method effectively solves the matrix in the recommendation system; on the other hand, it provides a feasible method for calculating similarity in the recommendation system. [ABSTRACT FROM AUTHOR]

Knowledge-enhanced recommendation (KER) aims to integrate the knowledge graph (KG) into collaborative filtering (CF) for alleviating the sparsity and cold start problems. The state-of-the-art graph neural network (GNN)–based methods mainly focus on exploiting the connectivity between entities in the knowledge graph, while neglecting the interaction relation between items reflected in the user-item interactions. Moreover, the widely adopted BPR loss for model optimization fails to provide sufficient supervisions for learning discriminative representation of users and items. To address these issues, we propose the collaborative knowledge-enhanced recommendation (CKER) method. Specifically, CKER proposes a collaborative graph convolution network (CGCN) to learn the user and item representations from the connection between items in the constructed interaction graph and the connectivity between entities in the knowledge graph. Moreover, we introduce the self-supervised learning to maximize the mutual information between the interaction- and knowledge-aware user preferences by deriving additional supervision signals. We conduct comprehensive experiments on two benchmark datasets, namely Amazon-Book and Last-FM, and the experimental results show that CKER can outperform the state-of-the-art baselines in terms of recall and NDCG on knowledge-enhanced recommendation. [ABSTRACT FROM AUTHOR]

Stroke is among the top 10 leading causes of death and disability around the world. Patients who suffer from this disease usually perform physical exercises at home to improve their condition. These exercises are recommended by therapists based on the patient's progress level, and may be remotely supervised by them if technology is an option for both. At this point, two major challenges must be faced. The first one is the lack of specialized medical staff to remotely handle the growing number of stroke patients. The second one is the difficulty of dynamically adapt the patient's therapy plan in real time whilst they rehabilitate at home, since their evolution varies as the rehabilitation process progresses. In this context, we present a fuzzy system that is able to automatically adapt the rehabilitation plan of stroke patients. The use of fuzzy logic greatly facilitates the monitoring and guidance of stroke patients. Moreover, the system is capable of automatically generating modifications of existent exercises whilst considering their particularities at any given time. A preliminary experiment was conducted to show the advantages of the proposal, and the results suggest that the application of fuzzy logic may help make correct decisions based on the patient's progress level. [ABSTRACT FROM AUTHOR]