Search

In order to provide the personalized news recommendation for users more efficiently, the personalized recommendation system combined with deep network was investigated. Based on the deep network, a news recommendation system for users was designed. By means of neural network and aggregating users' interest characteristics, users' personalized needs for news recommendation was met. In order to solve the problem of inaccurate construction of users' interest preference characteristics, a personalized news method based on users' search records and interest preference was proposed. By constructing exogenous user interest preferences from user search records, the final recommendation list was generated by using the fusion method of the two preferences. Because the traditional recommendation algorithm ignored time series of the users' browsing behaviors, an improved circulation model of neural network algorithm was proposed. The parallel convolution neural network based on attention was used to aggregate characteristics of users' interest and the recursive neural network based on attention mechanism was used to explore hidden time series characteristics. At the same time, it was tested on real news data sets and the results showed that this method had a good recommendation effect. [ABSTRACT FROM AUTHOR]

In recent times, recommender systems have acquired significant popularity as a solution to the issue of information overload. These systems offer personalised recommendations to users. The superiority of multi-criteria recommender systems over their single-criterion counterparts has been demonstrated, as the former are able to provide more precise recommendations by taking into account multiple dimensions of user preferences when rating items. The prevalent recommendation technique, matrix factorization of collaborative filtering, is hindered by the data sparsity problem of the user-item matrix. On the other hand, it is noteworthy that deep learning techniques have demonstrated significant potential in various research domains, including but not limited to image processing, pattern recognition, computer vision, and natural language processing. In recent times, there has been a surge in the utilisation of deep learning techniques in recommender systems, yielding promising outcomes. This study presents a novel approach to multi-criteria recommender systems through the utilisation of deep learning algorithms to mitigate the data sparsity issue. Specifically, deep autoencoders are utilised to uncover complex, non-linear, and latent relationships between users' multi-criteria preferences followed by matrix factorization technique, ultimately leading to more precise recommendations. The proposed model is evaluated by conducting the experiments on the multi-criteria dataset of Yahoo! Movies. According to the outcomes, the proposed approach outperforms the state of the art recommendation methods by generating more accurate and personalized recommendations. Also, it reduces the data sparsity up to 11% from the multi-criteria dataset. [ABSTRACT FROM AUTHOR]

The overwhelming burden on the healthcare system has resulted in increased mortality rates as individuals struggle to receive appropriate medical attention. Machine learning has demonstrated its efficacy across diverse applications, fueling a growing trend in the realm of innovative automation. This is particularly facilitated by drug recommendation systems, which possess the capability to significantly reduce the dependence on specialized assistance. Faced with limited access to medical expertise, a considerable number of individuals have turned to self-medication, often worsening their health conditions. In response to this critical scenario, this paper introduces an inventive drug recommendation system which helps to lessen the strain healthcare professionals. Here, we present the development of a medication recommendation system based on LSTM, utilizing user-provided symptoms and the model's evaluations of past drug recommendations. The results of the comparison between Random Forest, SVM, and LSTM indicated that the modified LSTM-based recommendation system outperforms the other two models, achieving a 94% accuracy rate. [ABSTRACT FROM AUTHOR]

Adaptive Fusion and Transfer Learning for Enhanced E-commerce Recommendations (AFETLER) is a holistic combination of some state-of-the-art recommendation frameworks. Most of the existing frameworks, be it Matrix Factorisation model, Deep learning-based model, Factorisation Machines and Two tower recommendation models, used in real world recommendation engines lack diversity and serendipity. Also, cold start problem is one that downgrade the recommendation algorithm. Defining the optimisation goal and closed feedback improvement loop is also something that is not given primary weightage. To overcome the above stated challenges and provide a novel approach to overcome those, we propose the AFETLER model. AFETLER incorporates an adaptive fusion technique that dynamically combines recommendations from several sources such as new arrivals forecast, Click-Through Rate (CTR) prediction, and popularity estimation. This fusion technique improves accuracy by giving varying weights to each source based on the user's context, history preferences, and current behaviour, resulting in highly relevant and tailored buying recommendations. To address the cold-start problem and improve recommendations for new items, AFETLER employs a transfer learning mechanism inspired by the Adversarial Two-tower Neural Network (ATNN) framework, utilizing knowledge from existing items' interactions to extract valuable features from new items' profiles. Furthermore, AFETLER leverages hierarchical attention methods to effectively capture user-item interaction patterns, boosting feature extraction and overall recommendation quality through dynamic weighing of interaction relevance. Proposed AFETLER model outperforms some of the existing recommendation models by an average 2%-5% on metrics such a precision, ROC-AUC, and Top-K recommendation accuracy. Further, we also see point reduction in Mean absolute error and mean squared error. [ABSTRACT FROM AUTHOR]

Nowadays, Artificial Intelligence (AI) technology, especially, machine learning has received significant attention from many researchers and professionals in several domains. For instance, this technology has revolutionized industrials sectors, such as e-commerce, health, manufacturing, and entertainment, as well as, the educational sector. In this context, during the pandemic, educational institutions around the globe recognized the benefits of adopting remote learning and teaching based on many e-learning platforms. Hence, deploying virtual classrooms is not that easy, due to many constraints, such as time, technological cost, lack of interactivity of learners, and the unsuitability of the learner's cognitive abilities and learning style. To this end, understanding the learner's style and providing adapted and personalized content are the main concerns of today's e-learning systems. To this end, integrating efficient recommender systems into online learning environment is required in order to consider student's behaviors and preferences when recommending various learning materials. Thus, intelligent recommender systems are able to provide a personalized learning path in which the system adapts to the student's learning requirements and abilities. This review discusses the different applications, methods, and challenges of AI-based recommendation systems used to assist different stockholders in an online learning environment. [ABSTRACT FROM AUTHOR]

Although reinforcement learning (RL) can solve complex tasks after training, it's difficult to extend trained agents to target environments with perturbations. This lack of generalization ability has caused the dilemma of large-scale application of RL. Rich neural networks have brought huge improvements to deep learning, but these aren't adapted to RL and even bring negative effects. Therefore, RL algorithms have few choices of neural network, which greatly limits the representation and generalization ability of RL. To overcome these limitations, we propose a deep semi-dense compression network (DSCN) to improve RL generalization ability. First, we perform a structural extension on a general network model for RL. Then based on the information theory, we propose a semi-dense connection to enhance the neural information flow (NIF) of initial features. Finally, drawing on the ideas of course learning, we propose a channel compression approach to filter the redundant information of the deep network. In addition, we innovatively extend the experimental environment and evaluation metrics of the existing platform, which can fully evaluate the performance of DSCN. The experimental results show that our model achieves stable and significant generalization performance improvement. [ABSTRACT FROM AUTHOR]

As a powerful data modeling tool, Heterogeneous Information Network (HIN) has been successfully used in auxiliary information exploitation to boost recommendation performance. For HIN based recommendation, it is challenging to extract and fuse useful features of user preferences and item attributes under different semantic paths in HINs. Existing methods leverage a pre-defined fusion function to integrate different semantics for recommendation, which cannot characterize the complex nonlinear interactions between users and items. In this paper, we present a general framework named MNRec, short for Meta-path fusion based Neural Recommendation, to extract and fuse user and item embeddings under different meta-paths for recommendation. Under the framework, we propose an instantiation of MNRec with Multi-Layer Perceptron (MLP) structure. It consists of two major steps, i.e., meta-path based heterogeneous network embedding and deep learning based rating prediction. Concretely, appropriate meta-paths are first designed according to domain knowledge. Then the embeddings of users and items are obtained through a meta-path and commuting matrix based heterogeneous network embedding method. Finally, in light of the powerful nonlinear modeling capabilities of deep neural networks, the learned embeddings under different meta-paths are integrated into a two-pathway MLP structure for rating prediction. Experimental results on three real-world datasets demonstrate the superiority and effectiveness of MNRec compared with state-of-the-art baselines in rating prediction. [ABSTRACT FROM AUTHOR]

Employers couldn't find relevant candidates without great effort, and job seekers must spend a long time researching the right jobs. To fix this issue, recommender systems are an effective way to make talent and job research more effective and easier to complete. It is possible to analyze job offers and candidate profiles and make pertinent recommendations using techniques like the Recurrent Neural Network (RNN) approach. To accomplish this, we propose a model based on the classification of job profiles using a variant of RNN called LSTM ("Long short-term memory"). It is a long-term memory model based on a deep learning algorithm. To maintain the semantic meaning, first, the input of the LSTM model is transformed into a set of vectors using the doc2Vec method, which transforms a document into a vector of numbers. [ABSTRACT FROM AUTHOR]

The graph neural network has received significant attention in recent years because of its unique role in mining graph-structure data and its ubiquitous application in various fields, such as social networking and recommendation systems. Although most work focuses on learning low-dimensional node representation in static graphs, the dynamic nature of real-world networks makes temporal graphs more practical and significant. In this paper, we propose a dynamic graph representation learning method based on a temporal graph transformer (TGT), which can efficiently preserve high-order information and temporally evolve structural properties by incorporating an update module, an aggregation module, and a propagation module in a single model. The experimental results on three real-world networks demonstrate that the TGT outperforms state-of-the-art baselines for dynamic link prediction and edge classification tasks in terms of both accuracy and efficiency. [ABSTRACT FROM AUTHOR]

Path-based relational reasoning over knowledge graphs has become increasingly popular due to a variety of downstream applications such as question answering in dialogue systems, fact prediction, and recommendation systems. In recent years, reinforcement learning (RL) based solutions for knowledge graphs have been demonstrated to be more interpretable and explainable than other deep learning models. However, the current solutions still struggle with performance issues due to incomplete state representations and large action spaces for the RL agent. We address these problems by developing HRRL (Heterogeneous Relational reasoning with Reinforcement Learning), a type-enhanced RL agent that utilizes the local heterogeneous neighborhood information for efficient path-based reasoning over knowledge graphs. HRRL improves the state representation using a graph neural network (GNN) for encoding the neighborhood information and utilizes entity type information for pruning the action space. Extensive experiments on real-world datasets show that HRRL outperforms state-of-the-art RL methods and discovers more novel paths during the training procedure, demonstrating the explorative power of our method. • Proposing a method to address the multi-hop reasoning problem. • Improving the choice of the action using the heterogeneous context. • Leveraging the neighborhood context for improving the reasoning precision. • Comprehensive evaluation of our model against state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Recommender systems are powerful tools that successfully apply data mining and machine learning techniques. Traditionally, these systems focused on predicting a single interaction, such as a rating between a user and an item. However, this approach overlooks the complexity of user interactions, which often involve multiple interactions over time, such as browsing, adding items to a cart, and more. Recent research has shifted towards leveraging this richer data to build more detailed user profiles and uncover complex user behavior patterns. Sequential recommendation systems have gained significant attention recently due to their ability to model users' evolving preferences over time. This survey explores how these systems utilize interaction history to make more accurate and personalized recommendations. We provide an overview of the techniques employed in sequential recommendation systems, discuss evaluation methodologies, and highlight future research directions. We categorize existing approaches based on their underlying principles and evaluate their effectiveness in various application domains. Additionally, we outline the challenges and opportunities in sequential recommendation systems. • Comprehensive Taxonomy and Classification. • Evaluation Metrics and Methodologies. • Identification of Challenges and Future Directions. • Novel Insights into Advanced Models. [ABSTRACT FROM AUTHOR]

• This research proposes a novel clustering-driven deep learning model designed to address these limitations and enhance the accuracy and personalization of course recommendations. By integrating clustering techniques with Bidirectional Long Short-Term Memory (BiLSTM) networks and Multi-Layer Perceptrons (MLP), the model effectively groups similar courses and users, mitigating data sparsity and cold start issues. The use of BiLSTM enhances feature extraction from course descriptions, leading to more precise content-based recommendations. The model's combined approach ensures both content-based and collaborative filtering aspects are considered, resulting in highly personalized suggestions. Evaluation results demonstrate that the proposed model significantly improves recommendation 96 % of accuracy and scalability compared to existing methods. The rapid growth of online education platforms has necessitated the development of sophisticated recommendation systems to help learners navigate the vast array of available courses. Traditional recommendation techniques such as collaborative filtering, content-based filtering, and matrix factorization, while useful, face significant challenges including data sparsity, cold start problems, and the need for extensive feature extraction. This research proposes a novel clustering-driven deep learning model designed to address these limitations and enhance the accuracy and personalization of course recommendations. By integrating clustering techniques with Bidirectional Long Short-Term Memory (BiLSTM) networks and Multi-Layer Perceptrons (MLP), the model effectively groups similar courses and users, mitigating data sparsity and cold start issues. The use of BiLSTM enhances feature extraction from course descriptions, leading to more precise content-based recommendations. The model's combined approach ensures both content-based and collaborative filtering aspects are considered, resulting in highly personalized suggestions. Evaluation results demonstrate that the proposed model significantly improves recommendation 96 % of accuracy and scalability compared to existing methods. This study's contributions offer a robust framework for advancing recommendation systems in online education, ultimately enhancing user engagement and satisfaction. [ABSTRACT FROM AUTHOR]

An intelligent recommendation system facilitates users by recommending items based on the user's preferences. Most of the existing recommender systems employ collaborative filtering which consider homogenous data only and does not exploit different knowledge sources. Such approaches encounter many challenges such as Cold Start problem, Sparsity, and Scalability. To overcome these setbacks, a novel deep learning & semantic fusion-based recommendation system named DLSF is proposed in this paper which collaborates multiple knowledge sources by employing three modules to generate top-N recommendations. The first module precludes sparsity by using latent representations and deep learning for understanding user-item interactions. The second module exploits semantic information provided to similar items by the users for dealing with cold start problem. And the third module works for new users and items which don't have any prior information. A comprehensive experimental evaluation is conducted over benchmark datasets. The proposed DLSF showed on average 16.02% and 16.71% more efficient over the baselines recommendation systems taken into account in terms of MAE and RMSE respectively. DLSF has found to have significant efficiency in terms of Precision, Recall and overall accuracy. [ABSTRACT FROM AUTHOR]

The tremendous growth in information over the last decade leads to information overwhelming problems for accessing personalized products. The recommender framework that retrieves user preferences on past interactions is known as collaborative filtering (CF). Although, CF is a prevalent technique amongst the techniques applied in the recommender environment. However, it suffers from many problems like information sparsity, scalability, cold-start, etc. Many investigations have been made to tackle some of these issues with the help of matrix factorization (MF) approaches. However, MF cannot handle the nonlinearity among the data. Deep learning is an advanced learning technique that has shown success in many applications such as image classification, computer vision, natural language processing, etc. Little work has been reported on deep learning techniques in the recommender domain. We propose an efficient deep collaborative recommender system that embeds item metadata to handle the nonlinearity in data and sparsity. The model consists of two stages, wherein the first stage, a neural network, is used to retrieve the data's nonlinear features through embedding vectors. These vectors are concatenated together and fed as input to the second stage of the model. The output of the model yields a partially observed rating. The input and the parameters are simultaneously optimized and updated to minimize errors. The proposed strategy is evaluated against the benchmark techniques on two well-known datasets. The exploratory outcomes signify our approach's exactitude and efficiency. Moreover, the missing values can also be recovered by propagating the embedding vectors from the input to the output layers. [ABSTRACT FROM AUTHOR]

The locality of metadata is a critical parameter of data storage and retrieval performance for an ultra-large distributed storage system. The data of an ultra-large distributed storage system is accessed through its distributed metadata servers (MDSs). The distributed MDSs store and cache partial metadata for scalability and performance. The MDSs are connected through varied latencies multipath network connections of using various metadata distribution techniques. The locality of MDS in the metadata distribution techniques improves the metadata query routing and enhances the performance of the distributed storage system. Motivated by this insight, this work introduces an intelligent locality-aware metadata management technique based on recommendation system that exploits MDS path ratings in a globally distributed ultra-large storage system and proposes a novel locality-aware metadata query routing algorithm. The proposed metadata server locality aware employs collaborative filtering with Stacked AutoEncoder to address the sparsity of the path rating matrix and its overfitting issue. The extensive experiments on real datasets show that the proposed metadata server locality aware technique enhances the locality of metadata operations and improves aggregate operations throughput by 12% to 21% of contemporary distributed metadata management techniques in ultra-large distributed storage systems. [ABSTRACT FROM AUTHOR]

Deep learning has dominated the methodology of image inpainting in recent years. However, many of the existing methods still suffer from the defects of unnatural structure and blurry textures when filling large-area holes. To address this issue, we propose a novel coarse-to-fine residual inpainting framework: we first reconstruct the downsampled low-frequency coarse profile at a low computational cost, we then solely focus on generating high-frequency details, which will be added as residuals to the coarse profile, such that structure and texture details in composited result can be better preserved. Meanwhile, we notice that the existing attention mechanism used to build long-distance dependency is unreasonable: either does not adapt to free-form holes, or lacks filtering for invalid information sources, which could compromise feature map reconstruction. To solve this, we propose an improved Selective Free-Form Attention (SFFA) module, selectively allowing the information flow from the valid sources to hole area with free-form shape. We verify the incremental effectiveness of our contributions. We further show that our model outperforms recent state-of-the-art methods both qualitatively and quantitatively on benchmark datasets. [ABSTRACT FROM AUTHOR]

The assortments of global retailers are composed of hundreds of thousands of products linked by several types of relationships such as style compatibility, "bought together", "watched together", etc. Graphs are a natural representation for assortments, where products are nodes and relations are edges. Style compatibility relations are produced manually and do not cover the whole graph uniformly. We propose to use inductive learning to enhance a graph encoding style compatibility of a fashion assortment, leveraging rich node information comprising textual descriptions and visual data. Then, we show how the proposed graph enhancement substantially improves the performance on transductive tasks with a minor impact on graph sparsity. Although demonstrated in a challenging and novel industrial application case, the approach we propose is general enough to be applied to any node-level or edge-level prediction task in very sparse, large-scale networks. [ABSTRACT FROM AUTHOR]

Visual media, in today's world, has swept across most forms of day to day communication. In the paradigm of generative modelling, restricted Boltzmann machines (RBMs) are used to solve complex tasks such as feature extraction, neuroimaging, collaborative filtering, radar target cognition, etc. In this paper, we implement an unsupervised Boltzmann machine-based time-aware recommendation system (UBMTR) which detects underlying hidden features in user-movie ratings data in connection with the time at which each rating was made (temporal information). The model takes ratings and time as a dual-input and outputs binary values via the contrastive divergence algorithm which samples from a Monte Carlo Markov Chain. Arguably, there exists a correlation between the content requested and the temporal conditions, which is exactly what our model tries to exploit. There is seldom any work in the field of recommender systems built using Boltzmann machines that incorporate temporal information, which necessitates research in this domain. RBMs are adept at pattern completion to tackle missing values, and can deal with imbalanced datasets and unstructured data by encoding raw data into latent variables. Using RBM, the UBMTR outperforms many earlier made attempts made at recommendation systems done through CF and deep learning or their hybridized models. [ABSTRACT FROM AUTHOR]

This paper presents a new contribution to the recommendation system following E-commerce reviews. Here, it implements a dictionary-based sentiment analysis based on four main steps (i) Pre-processing (ii) Semantic word extraction (iii) Feature Extraction (iv) Classification. Initially, the tweets or reviews extracted from the database are subjected to pre-processing, which involves three processes: stop word removal, stemming, and blank space removal. In the semantic word extraction process, the semantic words from the dictionary will be extracted by matching with the extracted keywords. The next process is the feature extraction, which extracts joint holoentropy and cross holoentropy of all keywords, and further proceeds with conditional holoentropy-based feature selection process. Finally, the selected features are subjected to a classification process using Deep Belief Network (DBN), which is a well-performing deep learning algorithm. Moreover, the main contribution of the paper relies on the improvement of DBN architecture, where the number of hidden neurons and activation function is optimally tuned by a hybrid optimization algorithm termed as Grey linked Chick Update-based Chicken Swarm Optimization (GCU-CSO). At last, the comparative analysis of proposed and conventional algorithms in terms of various performance metrics proves the efficacy of the proposed E-commerce recommendation system. [ABSTRACT FROM AUTHOR]

Text classification is a technique that automatically classifies and labels text according to certain rules, and is widely used in sentiment analysis, intelligent recommendation systems and intelligent question and answer systems. Deep learning-based text classification methods can automatically identify and extract features in text that are useful for classification, so that it can analyse the text content directly, saving a lot of labour costs required for manual feature extraction. In this paper, the TF-IDF algorithm and the input structure of bidirectional LSTM was modified. Specifically, we rewrote the TF-IDF formula and processed the texts with a sliding window. The word2vec vector was used as the word embedding layer, and the text features were extracted using a combination of bidirectional LSTM and Text-CNN for classification prediction. Bidirectional LSTM treats texts as sequences to grasp information as a whole, while Text-CNN can extract local important features at the sentence level. As a result, good accuracy was achieved. [ABSTRACT FROM AUTHOR]

Systems that rely on dyadic data, which relate entities of two types together, have become ubiquitously used in fields such as media services, tourism business, e-commerce, and others. However, these systems have had a tendency to be black-box systems, despite their objective of influencing people's decisions. There is a lack of research on providing personalised explanations to the outputs of systems that make use of such data, that is, integrating the idea of Explainable Artificial Intelligence into the field of dyadic data. Moreover, the existing approaches rely heavily on Deep Learning models for their training, reducing their overall sustainability. In this work, we propose a computationally efficient model which provides personalisation by generating explanations based on user-created images. In the context of a particular dyadic data system, the restaurant review platform TripAdvisor, we predict, for any (user, restaurant) pair, the review of the restaurant that is most adequate to present it to the user, based on their personal preferences. This model exploits the usage of efficient Matrix Factorisation techniques combined with feature-rich embeddings of the pre-trained Image Classification models, developing a method capable of providing transparency to dyadic data systems while reducing as much as 80% the carbon emissions of training compared to alternative approaches. [ABSTRACT FROM AUTHOR]

Recommender systems are popular tools used in many applications, such as e-commerce, e-learning, and social networks to help users select their desired items. Collaborative filtering is a widely used recommendation technique that employs previous ratings of users to predict their future interests. Lack of sufficient ratings often reduces the performance of collaborative filtering recommendation methods. Additional side resources, such as trust relationships and tag information can be employed to enhance the recommendation accuracy. However, trust and tag data are often heavily sparse as users mainly provide insufficient information about these side resources. Moreover, such additional resources have generally large dimensions which result in increasing the computational complexity of recommendation models in calculating similarity values. To cope with these problems, a new recommendation model is proposed that utilizes deep neural networks to model the representation of trust relationships and tag information. To this end, a sparse autoencoder is used to extract latent features from user-user trust relationships and user-tag matrices. Then, the extracted latent features are utilized to calculate similarity values between users, which are then used to form the nearest neighbors of the target user and predict unseen items. The proposed method can tackle the data sparsity problem and reduce the computational complexity of recommender systems as the extracted latent features have smaller dimensions in comparison to the original data. Experimental results on two benchmark datasets reveal the effectiveness of the proposed method and show its outperformance over state-of-the-art recommender systems. [ABSTRACT FROM AUTHOR]

Recommendation systems (RS) play an important role in e-commerce applications as they help the consumers in choosing the required items within reduced time. The traditional methods of collaborative filtering, fail to capture the visual data associated with the items. Visually-aware recommendation systems are upcoming in e-commerce applications that use the visual features of the products rather than the user profiles. Deep learning techniques are used for the classification and prediction in visual recommendation systems. However, the criticality of the visual recommendation system lies in identifying the similar images for a given target image. In this paper, a visual recommendation system is proposed based on Deep Visual Ensemble similarity metric (DVESM) using Convolutional Autoencoder (CAE) neural network for classification. The basic idea is to get a set of trained feature vectors for the image catalogue using CAE and find the similarity between the trained feature vectors and the target feature vector using DVESM method. The proposed methodology of using DVESM has been demonstrated with the state-of-the-art methods on Amazon 2014, 2015 and Street2Shop datasets. The results show that the DVESM method is most suitable for visually aware recommendation systems as it learns an ensemble of metrics to provide recommendations. [ABSTRACT FROM AUTHOR]

The exploration of non-covalent interactions between drugs and proteins (NCIs) has significantly improved the performance of drug–target interactions (DTIs) prediction models. However, existing methods for simulating NCIs are limited to single or multiple interactions, ignoring the combinatorial effects (i.e., high-order crossover between drugs and proteins (HOC-D&P)) that can arise when multiple NCIs coexist. To overcome this limitation, a multi-channel parallel high-order prediction model (PHCDTI) is proposed, aiming to simulate the complex interactions between drugs and proteins, thereby modeling HOC-D&P. Firstly, a tri-channel parallel model structure is constructed, allowing each channel to independently learn the interaction patterns between drug molecules and amino acid groups. Secondly, the three channels are designed from low-order to high-order, incorporating linear, inner-product, and pair-interaction feature crossover methods to simulate the complex interactions between drug molecules and amino acid groups. The stacking of residual connections enables the model to effectively model HOC-D&P. Additionally, by utilizing multi-head attention mechanisms for inner product and squeeze-excitation networks (SENET) for pair-interaction, the interpretability of the NCIs modeling process and the specific representation of drug molecules or amino acid groups are achieved. PHCDTI was evaluated on three benchmark datasets in four experimental settings, and the results indicated that it outperformed the most recent baseline model. In all cases, the average accuracy, precision, recall, AUC, and AUPR of PHCDTI are improved over the best baseline model by 3.56%, 6.06%, 3.99%, 2.50%, and 8.11%, respectively. Moreover, strong information filtering capabilities were exhibited by PHCDTI, with the effectiveness of the three-channel design confirmed by ablation studies. Finally, a case study on the human γ -aminobutyric acid receptors (GABARs) demonstrated that PHCDTI can serve as a powerful tool for real-world drug screening and design. [ABSTRACT FROM AUTHOR]

In recommender system, the proportion of interacted items with users is extremely sparse compared to the total number of items. This data sparsity problem particularly affects collaborative filtering methods. Even in modern collaborative filtering recommendation models based on deep learning, effectively acquiring more neighbor information and exploring how to utilize this information efficiently remains a promising research area. This paper not only explores heuristic algorithms for neighbor selection but also extends the application of neighbor selection to the GAN framework and negative sampling. To capture user neighbors that contain more potential feature information, this paper proposes a neighbor strategy that integrates explicit and implicit user information. It aggregates reciprocal neighbors of users based on the fusion of their explicit and implicit information, aiming to capture user preference information through neighborhood information. Furthermore, by designing an MRNGAN model based on a twin-tower generator, this paper successfully embeds user neighborhood information as feature embedding into the generator of GAN. In addition, this paper also proposes a heuristic negative sampling mechanism in the recall phase. It uses explicit and implicit information to fuse the nearest neighbors of items with the farthest neighbors of users. Negative samples that contain user neighborhood information are embedded into the discriminator of MRNGAN. The deep relationships between nearest and farthest neighbors are explored through the adversarial training of GAN, and their impact on recommendation performance is validated. The experimental results on three real-world datasets show that the MRNGAN model significantly improves the accuracy of Top-N recommendation. [ABSTRACT FROM AUTHOR]

With the increasing ubiquity of booking restaurants through online platforms, the need for restaurant recommender systems that satisfy individual preferences has grown. Previous studies have found it challenging to reflect preferences in multiple aspects because customers' restaurant experiences were approached from a single aspect. This study proposes a novel personalized recommender system that uses the aspect-based sentiment analysis (ABSA) technique to derive granular customer preferences and recommend restaurants accordingly. The proposed model's performance was empirically validated using customer review data from the global review platform Yelp. Initially, the ABSA technique was used to elaborately analyze sentiment scores for five major aspects of restaurants. Subsequently, aspect-specific sentiment scores were applied to a deep learning prediction model to learn the latent interactions between customers and restaurants. The proposed restaurant recommendation model demonstrated superior prediction compared to the five previous proposed recommendation model, especially yielding improved performance instead of models reflecting overall sentiment scores. Additionally, the impact of various aspect sentiments for the restaurant recommender system was empirically validated, and the results were presented from multiple perspectives based on the model configuration and parameters. • This study proposes a recommendation model for the restaurant industry, utilizing various aspects found in online reviews. • The BERT-based ABSA technique was used to analyze sentiment scores for five significant aspects of restaurants elaborately. • Superior prediction compared to five benchmarks shows improved performance over models based on overall sentiment scores. [ABSTRACT FROM AUTHOR]

The variety of enormous information on the web encourages the field of recommender systems (RS) to flourish. In recent times, deep learning techniques have significantly impacted information retrieval tasks, including RS. The probabilistic and non-linear views of neural networks emerge to generative models for recommendation tasks. At present, there is an absence of extensive survey on deep generative models for RS. Therefore, this article aims at providing a coherent and comprehensive survey on recent efforts on deep generative models for RS. In particular, we provide an in-depth research effort in devising the taxonomy of deep generative models for RS, along with the summary of state-of-art methods. Lastly, we highlight the potential future prospects based on recent trends and new research avenues in this interesting and developing field. Public code links, papers, and popular datasets covered in this survey are accessible at: https://github.com/creyesp/Awesome-recsys?tab=readme-ov-file#papers. [ABSTRACT FROM AUTHOR]

Easy internet access and technological advancements have resulted in information overload and a plethora of options, making decision-making extremely difficult. Recommender System (RS) is a potential solution for assisting users in making decisions by recommending or predicting product ratings. Three fundamental forms of RS that use implicit or explicit feedback for recommendation are collaborative, content-based, and hybrid filtering. Ratings are the most common form of feedback, but product descriptions, reviews, images, audios, and videos are also important and can help improve the performance of the traditional RS. These additional variables can have a significant impact on RS's performance. Traditional RSs used approaches based on the nearest neighbor or other machine learning models, but thanks to recent advances in artificial intelligence and deep learning, RSs are now being developed using Convolutional Neural Networks (CNN), which can efficiently exploit auxiliary information. In addition to comparing CNN-based RSs on common grounds, this article provides a full examination of CNN-based RSs and how they might use various types of auxiliary information. The study also discusses data characteristics, data statistics, and auxiliary information in a variety of publicly available datasets. Different evaluation measures for RSs are also discussed, and readers are provided with interesting challenges and open research issues. [ABSTRACT FROM AUTHOR]

The tremendous growth the pharmaceutical field witnessed especially concerning drug-development, caused drug-related experiments such as those concerned with estimating their interactions with targets harder to conduct. This issue led researchers to transition from vivo and vitro to selico experimenting methods, which deploy artificial intelligence (AI) techniques such as recommender systems (RS) to solve problems at hand. However, most RSs depend on global features such as indices, which render them incapable of fully understanding the behaviors of individuals. In this paper, we introduce our Convolutional Recurrent Deep Learning model-based RS approach, or 'RSCRDL', which tackles the interaction prediction problem from a natural language processing approach's (NLP) point of view. RSCDRL processes the textual representations of both protein sequences and drugs in order to learn the implicit features of the tokens forming them, rendering it able to process unseen and non-reactive individuals indirectly. We also present a greedier variant of RSCRDL that can exploit additional drugs explicit features for better predictive abilities. Experiments performed on two real-world datasets show significant outperformance achieved by our models over two general-purpose state-of-the-art RSs, while other experiments conducted on orphan protein sequences helped deduce drug candidates that are assumed to be capable of inhibiting their activities. [ABSTRACT FROM AUTHOR]

Vector database management systems have emerged as an important component in modern data management, driven by the growing importance for the need to computationally describe rich data such as texts, images and video in various domains such as recommender systems, similarity search, and chatbots. These data descriptions are captured as numerical vectors that are computationally inexpensive to store and compare. However, the unique characteristics of vectorized data, including high dimensionality and sparsity, demand specialized solutions for efficient storage, retrieval, and processing. This narrative literature review provides an accessible introduction to the fundamental concepts, use-cases, and current challenges associated with vector database management systems, offering an overview for researchers and practitioners seeking to facilitate effective vector data management. [ABSTRACT FROM AUTHOR]

The cross-domain recommendation (CDR) model addresses challenges such as data sparsity, the long tail distribution of user–item interactions, and the cold start of items or users. However, solely transferring domain-shared knowledge based on the co-occurrence patterns, without considering user preferences, leads to negative transfer in CDR. To overcome these limitations, we propose an advanced deep learning CDR model called the Domain Adversarial Deep Interest Network (DADIN) aims to facilitate smooth knowledge transfer from the source domain to the target domain and effectively alleviate negative transfer. Firstly, the joint distribution alignment of user preference in DADIN is realized by introducing a skip-connection-based domain agnostic layer, and then the domain classifier is artificially designed to distinguish between the information coming from the source domain or the target domain. Additionally, DADIN combines prediction loss, global domain confusion loss, and intra-class domain confusion losses through the Min-Max game and gradient reverse layer to achieve collaborative optimization. Two real-world experiments show the area under curve (AUC) of DADIN is 0.78 on the Huawei dataset, and it outperforms its competitors by 0.71% on the Amazon dataset, showcasing its state-of-the-art performance. Moreover, our ablation studies further demonstrate that domain adversarial technique increases the AUC by 2.34% on the Huawei dataset and 16.67% on the Amazon dataset, respectively. • DADIN first employing domain adversarial method in Cross-Domain Recommendation (CDR). • With label information in source domain, DADIN addresses negative transfer in CDR. • The Joint distribution alignment of user preferences is achieved in DADIN. • Hierarchical attention is employed to enhance feature representation in DADIN. • DADIN achieving competitive performance in comparison with popular baseline models. [ABSTRACT FROM AUTHOR]

In this work, we examine the advantages of using multiple types of behaviours in recommendation systems. Intuitively, each user often takes some implicit actions (e.g., click) before making an explicit decision (e.g., purchase). Previous studies show that implicit and explicit feedback has different roles for a useful recommendation. However, these studies either exploit implicit and explicit behaviours separately or ignore the semantics of sequential interactions between users and items. In addition, we go from the hypothesis that a user's preferences at a time are combinations of long-term and short-term interests. In this paper, we propose some Deep Learning architectures. The first one is Implicit to Explicit (ITE) , to exploit users' interests through the sequence of their actions. The second and third ones are two versions of ITE with Bidirectional Encoder Representations from Transformers based (BERT-based) architecture called BERT-ITE and BERT-ITE-Si , which combine users' long- and short-term preferences without and with side information to enhance users' representations. The experimental results show that our models outperform previous state-of-the-art ones and also demonstrate our views on the effectiveness of exploiting the implicit to explicit order as well as combining long- and short-term preferences in three large-scale datasets. The source code of our paper is available at: https://github.com/tranquyenbk173/BERT_ITE. [ABSTRACT FROM AUTHOR]

Location-based Social Networks (LBSNs) enable users to socialize with friends and acquaintances by sharing their check-ins, opinions, photos, and reviews. A huge volume of data generated from LBSNs opens up a new avenue of research that gives birth to a new sub-field of recommendation systems, known as Point-of-Interest (POI) recommendation. A POI recommendation technique essentially exploits users' historical check-ins and other multi-modal information such as POI attributes and friendship network, to recommend the next set of POIs suitable for a user. A plethora of earlier works focus on traditional machine learning techniques that use hand-crafted features from the dataset. With the recent surge of deep learning research, we have witnessed a large variety of POI recommendation works utilizing different deep learning paradigms. These techniques largely vary in problem formulations, proposed techniques, used datasets and features, etc. To the best of our knowledge, this work is the first comprehensive survey of all major deep learning-based POI recommendation works. Our work categorizes and critically analyzes the recent POI recommendation works based on different deep learning paradigms and other relevant features. This review can be considered a cookbook for researchers or practitioners working in the area of POI recommendation. [ABSTRACT FROM AUTHOR]

[Display omitted] • To the best of our knowledge, our work is the first attempt to model search-and-go human behavior as a CTR-like binary classification problem in recommender system. • We propose an effective end-to-end deep learning model with a wide&deep architecture by utilizing LSTM attention and factorization-machine, to learn the sophisticated interactions between mobility data and search data. • We evaluate the framework on real-world dataset collected from Yahoo! Japan portal application, and demonstrate satisfactory performances on multiple search-and-go scenarios at a nation-wide level. • Our propsed model DeepSTIN achieved better performances comparing with the baseline models such as GBDT, DNN, Factorization-supported Neural Network [48], Product-based Neural Network [26], Wide&Deep [2], Deep & Cross Network [31], DeepFM [10], and XDeepFM [19]. • DeepSTIN improves the performance of DeepFM on four datasets by {6.4%, 7.9%, 11.8%, 9.3%} in AUC and {7.8%, 8.5%, 22.0%, 26.8%} in LogLoss. Every day, people are using search engines for different purposes such as research, shopping, or entertainment. Among the behaviors of search engine users, we are particularly interested in search-and-go behavior, which intuitively corresponds to a simple but challenging question, i.e., will users go where they search? Accurately estimating such behavior can be of great importance for Internet companies to recommend point-of-interest (POI), advertisement, and route, as well as for governments and public service operators like metro companies to conduct traffic monitoring, crowd management, and transportation scheduling. Therefore, in this study, we first collect search log data and GPS log data with linked and consistent user ID from Yahoo! Japan portal application installed in millions of smart-phones and tablets. Then we propose a framework including a complete data-processing procedure and an end-to-end deep learning model to predict whether a user will check-in the searched place or not. Specifically, as users' daily activities are considered to have high correlation with their travel, eating, and recreation decision in the future (i.e., go or not), Deep Spatial–Temporal Interaction Network (DeepSTIN) is elaborately designed to automatically learn the sophisticated spatiotemporal interactions between mobility data and search query data. Experimental results based on the standard metrics demonstrate that our proposed framework can achieve satisfactory performances on multiple real-world search scenarios. [ABSTRACT FROM AUTHOR]

Session-based recommendation, which aims to predict subsequent user actions based on anonymous sessions, plays a significant role in many online services. Existing methods construct each session as a digraph and then capture the rich transition relationship of items by using graph neural networks. However, their ability to obtain the user's static intentions is insufficient and they suffer from improper combinations of different user intentions. In this study, we propose a dynamic and static intentions integrated graph neural network (DSGNN) for session-based recommendation, in which the user's intentions captured by a digraph and an undigraph are comprehensively considered to enhance the recommendation performance. The prediction results from the dynamic and static intentions are combined using a lightweight gating network, which reduces the conflict between the two kinds of information. Furthermore, the weighted inner product is designed to alleviate the impact of the value of the item representation vectors. Extensive experiments on three real-world datasets show that the DSGNN outperforms other state-of-the-art methods and demonstrates that the components in our model are effective. [ABSTRACT FROM AUTHOR]

• We propose a fast, compact and parameter-efficient party-ignorant framework based on emotional recurrent unit. • We design generalized neural tensor block which is suitable for different structures, to perform context compositionality. • Experiments on three standard benchmarks indicate that our model outperforms the state of the art with fewer parameters. Sentiment analysis in conversations has gained increasing attention in recent years for the growing amount of applications it can serve, e.g., sentiment analysis, recommender systems, and human-robot interaction. The main difference between conversational sentiment analysis and single sentence sentiment analysis is the existence of context information that may influence the sentiment of an utterance in a dialogue. How to effectively encode contextual information in dialogues, however, remains a challenge. Existing approaches employ complicated deep learning structures to distinguish different parties in a conversation and then model the context information. In this paper, we propose a fast, compact and parameter-efficient party-ignorant framework named bidirectional emotional recurrent unit for conversational sentiment analysis. In our system, a generalized neural tensor block followed by a two-channel classifier is designed to perform context compositionality and sentiment classification, respectively. Extensive experiments on three standard datasets demonstrate that our model outperforms the state of the art in most cases. [ABSTRACT FROM AUTHOR]

• This study proposes novel approach for Quality of Service prediction for Cloud Service Recommendation. • A unique ensemble of Deep Learning models to learn user and service correlation is presented. • This approach combines neighbourhood based method and Neural Network models. • The proposed approach has better performance than other state-of-the-art approaches. Applications of Cloud Services are increasing day by day, and so is the difficulty of choosing the best-suited service for a customer. Quality of Service (QoS) parameters can be used for quality assurance and evaluation; further, a service can be recommended based on these QoS parameters' values. Recommendation systems are getting much attention lately. It has a crucial role in almost all the major commercial platforms and many improvements are being made to make the recommendations more precise and closer to the user's requirements. Conventional Machine Learning algorithms and statistical analysis methods, presently are not that efficient in learning the complex correlation between data elements. Lately, Deep Learning models have proven to be practical and precise in areas like natural language processing, image processing, data mining, & data interpretation. However, there are not many examples of complete Deep Learning applications for cloud service recommendation systems, though some works partially use Deep Learning. We propose the Ensemble of Deep Neural Networks (EDNN) method, which is of the hybrid type, i.e., the fusion of neighborhood-based and neural network model-based methods. The output obtained from both the models are combined using another different neural network model. Our approach for predicting QoS values is simple and different from previous works, and the results show that it outperforms other classical methods marginally. [ABSTRACT FROM AUTHOR]

As an effective deep representation learning technique for graph data, graph convolutional network (GCN) has recently been widely applied to obtain better embedding of vertex. The existing studies have successfully explored user-item interaction via GCN for recommendation task and proved its effectiveness. We argue that a significant limitation of these methods is that social relation, which has been proven to impose positive effects for recommendation in many loss optimization models, has received relatively little scrutiny in GCN. Thus, the resultant embeddings are insufficient to model the potential social propagation effect. In our work, we propose to obtain embeddings by using the neighborhood propagation mechanism on two coupled graphs, i.e. user-item interaction graph and social relation graph, which is capable of capturing the interplay between the user's item taste and user's friend relationship to integrate social effect into the embeddings. In particular, to address the challenge that different factors on neighborhood propagation process make different contributions for the embedding, we develop Attentional Social Recommendation system (ASR), a new social recommendation framework with hierarchical attention(i.e., neighbor-level and graph-level attention). This allows much flexibility for adaptively acquiring relative importance for different factors. Extensive experiment on three real-world datasets not only show the superior performance of our proposed model over the baselines, but also demonstrate the effectiveness of simultaneous neighborhood propagation on two graphs. [ABSTRACT FROM AUTHOR]

Although a huge amount of data has been provided on the web to meet different needs of users, it has been more difficult to quickly make satisfactory choices. Therefore, recommender systems have been introduced for offering relevant data and providing users with personalized recommendations. Traditional collaborative based methods modelled efficiently users and items from their rating patterns. By cons, they suffered from the data sparsity problem. As a solution, text user-generated data (e.g., reviews) were useful to provide rich semantic information of user preferences and item features. Seeing that opinions and ratings were complementary, we proposed to fuse them and learn more accurate representations of users and items for recommendation. Unlike Arabic which has received less attention, the majority of methods offered have been focused on English language. It has been represented a fundamental issue in Natural Language Processing (NLP) and artificial intelligence. In this paper, a neural collaborative embedding- and filtering-based approach was proposed for Arabic textual documents recommendation. Due to the recent advances on neural networks, our idea was to couple deep features learning- and deep interaction modelling- based encoders. Indeed, two branches of recurrent neural networks were combined to extract latent features of users and items. Using the generated representations as inputs, deep user-item interactions were captured by stacking multiple layers. This method has proved its efficiency to simultaneously capture the global context and the word frequency information, learn thereafter the obtained high-level latent features and produce final ratings. Extensive experiments on a standard Arabic dataset showed the superiority of our model than state-of-the art methods. [ABSTRACT FROM AUTHOR]

Recently, deep neural networks are widely applied in recommender systems for their effectiveness in capturing/modeling users' preferences. Especially, the attention mechanism in deep learning enables recommender systems to incorporate various features in an adaptive way. Specifically, as for the next item recommendation task, we have the following three observations: 1) users' sequential behavior records aggregate at time positions ("time-aggregation"), 2) users have personalized taste that is related to the "time-aggregation" phenomenon ("personalized time-aggregation"), and 3) users' short-term interests play an important role in the next item prediction/recommendation. In this paper, we propose a new T ime-aware L ong- and S hort-term A ttention N etwork (TLSAN) to address those observations mentioned above. Specifically, TLSAN consists of two main components. Firstly, TLSAN models "personalized time-aggregation" and learn user-specific temporal taste via trainable personalized time position embeddings with category-aware correlations in long-term behaviors. Secondly, long- and short-term feature-wise attention layers are proposed to effectively capture users' long- and short-term preferences for accurate recommendation. Especially, the attention mechanism enables TLSAN to utilize users' preferences in an adaptive way, and its usage in long- and short-term layers enhances TLSAN's ability of dealing with sparse interaction data. Extensive experiments are conducted on Amazon datasets from different fields (also with different size), and the results show that TLSAN outperforms state-of-the-art baselines in both capturing users' preferences and performing time-sensitive next-item recommendation. [ABSTRACT FROM AUTHOR]

The main objective of the recommender system is to determine user behavior or preference and suggest the items of interest to the user. We notice that topic information is one of the significant factors that enables a user to choose the next items. To mimic this behavior, we design a topic diversity discovering (TDD) model to capture user preferences on topics. Unlike the previous studies applied the topic information to recommender systems, which only considered the item topics. In this paper, we not only focus on the item topic information but also consider the user topic information on the recommender system. We develop a TDD model to learn the topic information from the item, and we then utilize the transfer learning to obtain the user topic information. We then integrate the TDD model with the Bayesian personalized ranking (BPR) model to build a novel TDD-BPR recommender system. We experiment on three well-known three datasets MovieLens-1 M, Pinterest, and TMDB dataset, which achieved 71.8%, 91.2%, and 96.1% in the Hit Ratio@10. Empirical evidence showed that TDD-BPR discover the potential topic information to understand the user's preferences and get better recommendation performance. [ABSTRACT FROM AUTHOR]

Agriculture plays an imperative role in many countries' economies and is a substantive source of survival. The variation in a soil nutrient decreases crop yield. An accurate soil fertility classification and application of fertilizers are essential for enhancing crop productivity. Currently, soil fertility levels are assessed through laboratory testing of soil samples, and fertilizers are applied randomly. This traditional practice increases fertilization costs and causes environmental pollution. Thus, it is necessary to develop robust and inexpensive soil fertility classification and fertilizer application. This study identifies the machine learning (ML) or deep learning-based soil fertility classifications. A comprehensive review is conducted according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The purpose of this study is to examine different approaches that researchers use to predict or classify soil fertility. It also discusses the fertilizer recommendation developed by the researchers. The earlier research showed that ML-based approaches could accurately classify soil fertility. Furthermore, this study discusses the importance of soil nutrients and preventive measures to be taken on the imbalance of soil nutrients. This study explores research gaps and challenges in soil fertility classification and fertilizer recommendation systems. Most studies predicted the fertility levels of soil parameters, whereas a few researchers classified soil fertility. Few researchers recommended fertilizers for soil nutrient depletion. Most studies relied on expensive laboratory measurements or regional soil data collected from satellites. Based on the identified research gaps, this study suggests potential future research possibilities in soil fertility classification and the recommendation of fertilizers. It aims to develop a low-cost soil fertility classifier to prescribe fertilizers. The developed model can help farmers to enhance soil fertility with reduced fertilization costs. • Precise soil fertilization is essential to increase sustainable agricultural yield. • A systematic study on soil fertility estimation is conducted using PRISMA guidelines. • An overview of 42 prior research on soil fertility estimation is provided. • Highlights research gaps and future directions in the estimation of soil fertility. • Discusses various machine learning-based regression and classification approaches. [ABSTRACT FROM AUTHOR]

Existing food recommendation models have typically suggested foods or recipes to single users. However, in reality, users may be members of a group, family, or community, requiring food recommendation systems to support the whole group. Food recommendations to groups are a more challenging task than food recommendations to individuals, as each person's preferences in the group should be addressed before giving the recommendations. Suggesting healthy food is also important in a food recommendation system, given that unhealthy diets can lead to different diseases. To address these challenges, a new healthy group food recommendation system based on deep social community detection and user popularity is developed in this study. To this end, an innovative deep community detection approach based on feature learning and deep neural networks is developed using the calculated time-aware user similarity measure. In addition, a health-aware rate prediction measurement, which considers both group preferences and health factors, is developed. Different experiments are designed on two real-food social networks to specify the efficiency of the suggested model, and the results indicate that it enhanced the single-user and group satisfaction metrics. • Developing a novel healthy food recommendation to user groups. • Utilizing deep community detection and popularity measure in recommendation. • Considering user ratings, food ingredients and nutrition in the recommendation. • Results obtained from two real datasets demonstrated the efficacy of our model. [ABSTRACT FROM AUTHOR]

Due to the requirements of privacy protection and data asset ownership, recommender systems (RSs) based on centralized training process may be infeasible in some practical situations. In these situations, federated recommender systems (FedRec) based on deep learning are regarded as the substitutes with extensive application backgrounds and enormous potential business values. However, which deep learning algorithm and federated learning aggregation strategy perform best in the training of FedRec is still an unsolved question. To answer this question, experiments are conducted for comparing the performances of four popular deep learning algorithms and three federated learning aggregation strategies in FedRec. The experiments are conducted on 8 public datasets to obtain 96 FedRec precisions (4 deep learning algorithms × 3 federated learning aggregation strategies × 8 datasets). Then, the Wilcoxon test is used to verify whether there is a significant difference between the FedRec combinations and to derive the best combination. The result shows that, in terms of recommendation precision, the best FedRec is the combination of neural FM and federated averaging. In terms of execution iterations, the best FedRec is the combination of deep crossing and attentive federated aggregation. The obtained results would be valuable for further promoting the development of RSs under the situations that a centralized training process is infeasible. [ABSTRACT FROM AUTHOR]

The Chronic injuries caused by the venous valve called as Varicose ulcers. The pressure in the veins is increased as the valves of the veins allows blood to flow in backward direction. Detecting and segmenting varicose ulcer wound region is a separate step prior to the classification operation. In this work the novel customized Deep Ulcer Tissue Classification Network is proposed and it is named as "DUTC Net". The goal of the proposed DUTC Net is i) to classify the tissue type by generating tissue map using segmented ulcer wound image ii) to identify the stages of ulcer and iii) Percentage of affected tissues in the wound. The dataset contains various stages of varicose ulcer wound images. The first step is to preprocess the ulcer wound image to remove light artifacts and noise. After preprocessing segmentation is done to isolate the region of the varicose ulcer using active contour algorithm. The segmented area can be fed into proposed DUTC Net to get the respective tissue map of the ulcer wound images. The tissue map images are assigned as input to DUTC Net at the phase II. In this phase II, DUTC Net learns the features from the tissue map of the phase I and classifies the stages and percentage of affected tissues in the varicose ulcer wound image. While experimental analysis, the proposed method DUTC Net results sensitivity 97.9%, specificity 98% and accuracy 97.2% for the average of tissue classification and sensitivity 97.1%, specificity 98% and accuracy 97.5% for the average of stage classification. The proposed work is mainly used to classify the varicose ulcer stages, tissues types and affected area using DUTC Net to investigate the patients status and treatment methods. [ABSTRACT FROM AUTHOR]

In the age of information overload, modern recommendation systems provide an important role in helping people screen massive information. With the development of deep learning, personalized recommendations are further promoted to enhance user engagement and improve user satisfaction. Meanwhile, when the content provider has high-priority content to peddle, it often just exposes it to a conspicuous location without considering different users' preferences, which may even lead to negative impressions. To tackle this problem, in this paper, we propose a target-driven user preference transferring (TDUPTrans) module that will gradually orientate the user's preferences toward the target content. It is a brand new attempt that applies the user preference transfer process on personalized recommendations so that users don't just "see" the target item but also "like" it. To be specific, we propose a greedy-strategy-based intermediate content choosing algorithm, which can recommend different intermediate contents to users with different initial interests, and eventually lead users' interests to the target content. We give a clear interpretation of how our proposed process works through a news-based case study. Moreover, extensive experiments on real-world data sets demonstrate the interpretability of the guiding process, the abilities of our proposed TDUPTrans fusing with pre-existed recommendation algorithms, and the significantly improved target recommendation success rate with this TDUPTrans module plugged in. [ABSTRACT FROM AUTHOR]

With the proliferation and deepening of service-oriented architecture, more and more enterprises and organizations are exposing their computing functions and big data to the Internet in the form of cloud APIs to support service-oriented software development. This has resulted in a plethora of cloud APIs with similar functionality appearing on the Web, drowning users in a sea of cloud API choices. To solve this problem, quality of service (QoS)-aware recommender system is then widely applied to the selection of cloud APIs. Due to the dynamic and open network environment, the QoS-aware cloud API recommender systems are vulnerable to data poisoning attacks, where attackers inject poisoned data to skew the recommender system and make the recommendation direction follow the attacker's will. Given the lack of data poisoning attack methods and robustness analysis for existing QoS-aware cloud API recommender systems, in this work, we first built a general poisoning attack framework for QoS-aware cloud API recommender systems to elucidate and standardize the attack process. Then, we proposed a deep learning-based poison attack approach, which uses generative adversarial network (GAN) to learn the cloud API QoS data distribution of real users in an adversarial way, so as to generate high-quality fake user attack vectors. We conducted extensive experiments on real-world QoS datasets, and the experimental results show that our proposed GAN-based poisoning attack is effective and can better hide itself from being detected. In addition, we analyzed the data poisoning attack mechanism and the robustness of the cloud API recommender system based on four categories of twelve recommendation methods, thereby raising awareness about the security of cloud API recommendation and helping the recommender system defenders to develop more targeted defense strategies. [ABSTRACT FROM AUTHOR]

With the development of e-commerce platforms, user reviews have become a vital source of information to address the sparsity problems for enhancing the predictive performance of the recommendation systems (RSs). However, the traditional methods of the RSs used to model user/item latent features based on static vectors in an independent manner without considering the dynamic nature of the user-item interactions which potentially affect the accuracy of the recommendation process. Thus, this paper proposes a RS model that exploits neural attention techniques to learn user/item representations by jointly considering the fine-grained semantic information for the user-item pairs. The proposed model utilizes both review-based and interaction-specific features for the user/item reviews to learn heterogeneous user/item representations. First, a BiLSTM sequence encoder is used to learn the contextual information of words, and a Co-attention network is then designed to jointly capture the most relevant semantic information of reviews for the user-item pair. To better capture user/item latent factors comprehensively, interaction-specific features based on the rating scores are further integrated with the review-specific latent features via a shared hidden layer. Finally, an attentive factorization machine (FM) is then applied on the shared hidden layer of the integrated user/item features for the final prediction. We carry out a series of experiments using real-world datasets and the results demonstrate that our proposed method is better than the baseline approaches in terms of both rating prediction and ranking performance. [ABSTRACT FROM AUTHOR]

Cross-domain recommendation is becoming increasingly popular recently. Existing cross-domain recommendation often assumes that, a sufficient set of bridged users across domains is given in advance which disregards the scenario with insufficient bridged users. In this paper, we propose a novel Trust-aware Latent Space Mapping approach for Cross-domain Recommendation, called TLSM-CDR. This represents one of the first attempts to address the challenge of insufficient bridged users from the perspective of users' trust relationships to facilitate user sharing cross-domain recommendation. First, our model employs the Probabilistic Matrix Factorization (PMF) to generate user and item matrices. Then, Deep Neural Network (DNN) and graph Laplacian are seamlessly incorporated into our trust-aware non-linear mapping function to capture the latent space relationships between both bridged and non-bridged users. Finally, we predict the optimized users' rating matrix in the target domain. Extensive experiments conducted on two real-world datasets demonstrate that, our TLSM-CDR model significantly outperforms several state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The click-through rate (CTR) prediction is an essential task in the recommendation system. Available raw category features and feature combinations are important for CTR prediction, but their sparsity and high-dimension lead to huge computation. In recent years, methods based on deep learning, factorization machines and attention mechanism are widely used to model feature interactions among features for effective sparse predictive analysis. However, these previous algorithms are affected by irrelevant information. In this paper, we propose a novel model ESAtInt to model high-dimensional and sparse features, while being able to explicitly select meaningful higher-order feature interactions and eliminate the impact of irrelevant information. Specifically, we further conduct automatic feature interaction learning through a concentrated attention mechanism with explicit selection. Our model can explicitly select the most relevant parts to emphasize the attention to global features. Experimental results on the real-world dataset show that our proposed method is superior to state-of-the-art approaches for CTR prediction. [ABSTRACT FROM AUTHOR]