Search

The media content market has been growing, as various types of content are being mass-produced owing to the recent proliferation of the Internet and digital media. In addition, platforms that provide personalized services for content consumption are emerging and competing with each other to recommend personalized content. Existing platforms use a method in which a user directly inputs video metadata. Consequently, significant amounts of time and cost are consumed in processing large amounts of data. In this study, keyframes and audio spectra based on the YCbCr color model of a movie trailer were extracted for the automatic generation of metadata. The extracted audio spectra and image keyframes were used as learning data for genre recognition in deep learning. Deep learning was implemented to determine genres among the video metadata, and suggestions for utilization were proposed. A system that can automatically generate metadata established through the results of this study will be helpful for studying recommendation systems for media super-personalization. [ABSTRACT FROM AUTHOR]

Recommender systems (RS) are designed to eliminate the information overload problem in today's e-commerce platforms and other data-centric online services. They help users explore and exploit the system's information environment utilizing implicit and explicit data from internal e-commerce systems and user interactions. Today's product catalogues include pictures to provide visual detail at a glance. This approach can effectively convert potential buyers into customers. Since most e-commerce stores use product images to promote, arouse users' visual desires and encourage them to buy products, this paper develops an image-based RS using deep learning techniques. To perform the research, we use five convolutional neural network (CNN) models to extract the features of the products' images. Then, the system uses the features to calculate the similarity between images. The selected CNN models are VGG16, VGG19, ResNet50, Inception V3 and Xception. We also analysed four versions of the MovieLens dataset to demonstrate the accuracy improvement of the recommendations, including 100k, 1M, 10M and 20M. Results of the experiment showed a significant increase in accuracy compared with traditional approaches. Also, we express many related open issues including use of multiple images per item, different similarity metrics, other CNN models, and the hybridization of image-based and different RS techniques for future studies. This method also provides more accurate product recommendations on e-commerce platforms than traditional methods.

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]

Sparse matrix computation is crucial in various modern applications, including large-scale graph analytics, deep learning, and recommender systems. The performance of sparse kernels varies greatly depending on the structure of the input matrix, making it difficult to gain a comprehensive understanding of sparse computation and its relationship to inputs, algorithms, and target machine architecture. Despite extensive research on certain sparse kernels, such as Sparse Matrix-Vector Multiplication (SpMV), the overall family of sparse algorithms has yet to be investigated as a whole. This paper introduces SpChar, a workload characterization methodology for general sparse computation. SpChar employs tree-based models to identify the most relevant hardware and input characteristics, starting from hardware and input-related metrics gathered from Performance Monitoring Counters (PMCs) and matrices. Our analysis enables the creation of a characterization loop that facilitates the optimization of sparse computation by mapping the impact of architectural features to inputs and algorithmic choices. We apply SpChar to more than 600 matrices from the SuiteSparse Matrix collection and three state-of-the-art Arm Central Processing Units (CPUs) to determine the critical hardware and software characteristics that affect sparse computation. In our analysis, we determine that the biggest limiting factors for high-performance sparse computation are (1) the latency of the memory system, (2) the pipeline flush overhead resulting from branch misprediction, and (3) the poor reuse of cached elements. Additionally, we propose software and hardware optimizations that designers can implement to create a platform suitable for sparse computation. We then investigate these optimizations using the gem5 simulator to achieve a significant speedup of up to 2.63× compared to a CPU where the optimizations are not applied. [ABSTRACT FROM AUTHOR]

This paper introduces QSFL (Quantization and Secure Federated Learning), a novel framework designed to enhance the privacy and security of federated learning (FL). While FL enables collaborative training without exposing raw data, it remains vulnerable to white-box inversion and inference attacks. QSFL tackles these vulnerabilities by combining integer quantization with secure multi-party computation (SMC) protocols. Integer quantization transforms floating-point model parameters into integers, thereby reducing storage demands and enhancing computational efficiency. When integrated with SMC and leveraging Elliptic Curve Cryptography (ECC), QSFL ensures robust security, even in environments where up to n-2\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$n-2$$\end{document} of n participants may collude. The effectiveness of QSFL is demonstrated through extensive testing on datasets such as MNIST, CSIC2010, and COVID-19 chest X-rays, showing superior training speed and accuracy compared to existing SMC and differential privacy techniques. This represents a significant advancement in secure and efficient FL. The proposed framework offers a versatile solution to safeguard privacy during the training of deep learning models, making it applicable across various domains including medical, financial, recommendation systems, and decision support in operations research. [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]

This article titled "RETRACTION: Personalized Recommendation System Design for Library Resources through Deep Belief Networks" has been retracted by Wiley due to evidence of systematic manipulation of the publication process. The investigation conducted by the publisher revealed discrepancies in scope, description of the research, availability of data, inappropriate citations, and inclusion of incoherent or irrelevant content. As a result, the reliability of the article's content is compromised, and readers are advised to consider it unreliable. The corresponding author has been given the opportunity to respond to this retraction. [Extracted from the article]

With the increasing abundance of information resources and the development of deep learning techniques, recommender systems (RSs) based on deep learning have gradually become a research focus. Although RSs have evolved in recent years, a systematic review of existing RS approaches is still warranted. The main focus of this paper is on recommendation models that incorporate deep learning techniques. The objective is to guide novice researchers interested in this field through the investigation and application of the proposed recommendation models. Specifically, we first categorize existing RS approaches into four types: content-based recommendations, sequence recommendations, cross-domain recommendations, and social recommendation methods. We then introduce the definitions and address the challenges associated with these RS methodologies. Subsequently, we propose a comprehensive categorization framework and novel taxonomies for these methodologies, providing a thorough account of their research advancements. Finally, we discuss future developments regarding this topic.

In recent years, hybrid recommendation techniques based on feature fusion have gained extensive attention in the field of list ranking. Most of them fuse linear and nonlinear models to simultaneously learn the linear and nonlinear features of entities and jointly fit user-item interactions. These methods are based on implicit feedback, which can reduce the difficulty of data collection and the time of data preprocessing, but will lead to the lack of entity interaction depth information due to the lack of user satisfaction. This is equivalent to artificially reducing the entity interaction features, limiting the overall performance of the model. To address this problem, we propose a two-stage recommendation model named A-DNR, short for Attention-based Deep Neural Ranking. In the first stage, user short-term preferences are modeled through an attention mechanism network. Then the user short-term preferences and user long-term preferences are fused into dynamic user preferences. In the second stage, the high-order and low-order feature interactions are modeled by a matrix factorization (MF) model and a multi-layer perceptron (MLP) model, respectively. Then, the features are fused through a fully connected layer, and the vectors are mapped to scores. Finally, a ranking list is output through the scores. Experiments on three real-world datasets (Movielens100K, Movielens1M and Yahoo Movies) show that our proposed model achieves significant improvements compared to existing methods. [ABSTRACT FROM AUTHOR]

Summary: Nowadays, the online recommender systems based collaborative filtering methods are widely employed to model long term user preferences (LTUP). The deep learning methods, like recurrent neural networks (RNN) have the potential to model short‐term user preferences (STUP). There is no dynamic integration of these two models in the existing recommender systems. Therefore, in this article, a multi‐preference integrated algorithm (MPIA) for deep learning based recommender framework (DLRF) is proposed to perform the dynamic integration of these two models. Moreover, the MPIA addresses improper data and to improve the performance for creating recommendations. This algorithm is depending on an enhanced long short term memory (LSTM) with additional controllers to consider relative information. Here, experiments are carried out by Amazon benchmark datasets, then obtained outcomes are compared with other existing recommender systems. From the comparison, the experimental outcomes show that the proposed MPIA outperforms existing systems under performance metrics, like area under curve, F1‐score. Consequently, the MPIA can be integrated with real time recommender systems. [ABSTRACT FROM AUTHOR]

With the modern advancements in Deep Learning architectures, and abundant research consistently being put forward in areas such as computer vision, natural language processing and forecasting. Models are becoming complicated and datasets are growing exponentially in size demanding high performing and faster computing machines from researchers and engineers. TensorFlow provides a wide range of distributed deep learning high-level APIs to address this issue, that can scale deep learning training from one machine to more than one. In this paper, we have investigated the performance of computing clusters utilizing those APIs. We created clusters of different sizes and discuss performance issues of distributed deep learning under high latency and poor communication conditions. To address the challenge of finding the optimal cluster for fast distributed deep learning, we have proposed a recommendation system, that can provide an optimal cluster size for fastest training time, given batch size and networking latency. Our results show that using a 2 machine cluster is both faster and cheaper than a four machine cluster for certain algorithms when network delay is high. [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]

This paper introduces versatile filters to construct efficient convolutional neural networks that are widely used in various visual recognition tasks. Considering the demands of efficient deep learning techniques running on cost-effective hardware, a number of methods have been developed to learn compact neural networks. Most of these works aim to slim down filters in different ways, e.g., investigating small, sparse or quantized filters. In contrast, we treat filters from an additive perspective. A series of secondary filters can be derived from a primary filter with the help of binary masks. These secondary filters all inherit in the primary filter without occupying more storage, but once been unfolded in computation they could significantly enhance the capability of the filter by integrating information extracted from different receptive fields. Besides spatial versatile filters, we additionally investigate versatile filters from the channel perspective. Binary masks can be further customized for different primary filters under orthogonal constraints. We conduct theoretical analysis on network complexity and an efficient convolution scheme is introduced. Experimental results on benchmark datasets and neural networks demonstrate that our versatile filters are able to achieve comparable accuracy as that of original filters, but require less memory and computation cost. [ABSTRACT FROM AUTHOR]

Click-through rate (CTR) prediction, whose goal is to predict the probability of the user to click on an item, has become increasingly significant in the recommender systems. Recently, some deep learning models with the ability to automatically extract the user interest from his/her behaviors have achieved great success. In these work, the attention mechanism is used to select the user interested items in historical behaviors, improving the performance of the CTR predictor. Normally, these attentive modules can be jointly trained with the base predictor by using gradient descents. In this paper, we regard user interest modeling as a feature selection problem, which we call user interest selection. For such a problem, we propose a novel approach under the framework of the wrapper method, which is named Meta-Wrapper. More specifically, we use a differentiable module as our wrapping operator and then recast its learning problem as a continuous bilevel optimization. Moreover, we use a meta-learning algorithm to solve the optimization and theoretically prove its convergence. Meanwhile, we also provide theoretical analysis to show that our proposed method 1) efficiencies the wrapper-based feature selection, and 2) achieves better resistance to overfitting. Finally, extensive experiments on three public datasets manifest the superiority of our method in boosting the performance of CTR prediction. [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]

Collaborative filtering (CF) is a classical model for recommender systems. Though neural network-based CF models have been shown to perform well in some cases, they still suffer from the sparsity and cold-start issues. To address these issues, we propose a novel neural network-based CF model, termed the cross-domain explicit–implicit-mixed CF neural network (CEICFNet). The proposed model utilizes deep neural networks to learn latent factors not only from the explicit ratings and the implicit interactions but also in a cross-domain manner. In particular, domain-shared multilayer perception (MLP) networks are designed to learn the user rating latent factors and the user interaction latent factors from the explicit ratings and the implicit interactions, respectively, which act as bridges for transferring knowledge across domains. On the other hand, domain-specific MLP networks are designed to learn the item rating latent factors and the item interaction latent factors from the explicit ratings and the implicit interactions, respectively. Then, in each domain, based on the user rating latent factors and the item rating latent factors, the rating predictive representation for each user–item pair can be learned by an MLP. Similarly, the interaction predictive representation for each user–item pair can be learned. For integrating the explicit ratings and the implicit interactions, in each domain, a fully connected layer is used to automatically assign different weights to the rating predictive representations and the interaction predictive representations, based on which the final interaction probability can be generated. Extensive experiments are conducted on five datasets and the results have confirmed the effectiveness of our model. [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]

Recently, deep neural network models for graph-structured data have been demonstrated to be influential in recommendation systems. Graph Neural Network (GNN), which can generate high-quality embeddings by capturing graph-structured information, is convenient for the recommendation. However, most existing GNN models mainly focus on the homogeneous graph. They cannot characterize heterogeneous and complex data in the recommendation system. Meanwhile, it is challenging to develop effective methods to mine the heterogeneity and latent correlations in the graph. In this paper, we adopt Heterogeneous Attributed Network (HAN), which involves different node types as well as rich node attributes, to model data in the recommendation system. Furthermore, we propose a novel graph neural network-based model to deal with HAN for Recommendation, called HANRec. In particular, we design a component connecting potential neighbors to explore the influence among neighbors and provide two different strategies with the attention mechanism to aggregate neighbors' information. The experimental results on two real-world datasets prove that HANRec outperforms other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The explosive growth of e-commerce and online service has led to the development of recommender system. Aiming to provide a list of items to meet a user's personalized need by analyzing his/her interaction1 history, recommender system has been widely studied in academic and industrial communities. Different from conventional recommender systems, sequential recommender systems attempt to capture the pattern of users' sequential behaviors and the evolution of users' preferences.Most of the existing sequential recommendation models only focus on user interaction sequence, but neglect item interaction sequence. An item interaction sequence also contains rich contextual information for capturing the item's dynamic characteristic, since an item's dynamic characteristic can be reflected by the users who interact with it in a period. Furthermore, existing dual sequential models use the same method to handle the user interaction sequence and item interaction sequence, and do not consider their different characteristics. Hence, we propose a novel Double Attention Convolution Neural Network (DACNN), which incorporates user interaction sequence and item interaction sequence into an integrated neural network framework. DACNN leverages the strength of attentionmechanism to capture the temporary suitability and adopts CNN to extract local sequential features. Experimental evaluations on the real datasets show that DACNN outperforms the baseline approaches. [ABSTRACT FROM AUTHOR]

In recent years, especially with the (COVID-19) pandemic, shopping has been a challenging task. Increased online shopping has increased information available via the World Wide Web. Finding new products or identifying the most suitable products according to customers' personalization trends is the main benefit of E-commerce recommendation systems, which use different techniques such as rating, ranking, or reviewing. These recommendations can be formed using different techniques and approaches, particularly using the technology of intelligent agents, and specific interfaces or personal agents can be used to model this type of system. These agents usually use the techniques and algorithms of Artificial Intelligence internally. A recommendation system is a prediction system that has been created to help the user to select the proper product for them, and to reduce the effort spent in the search process using advanced technology such as deep learning techniques. We investigate all studies using a standard review process for collecting and retrieving data from previous studies and illustrate their relevant accuracy and interpretability along with pros and cons helpful to business firms to adopt the most legitimate approach. The study's findings revealed that recommendation problems are solved better by using deep learning algorithms such as CNN, RNN, and sentiment analysis, especially for popular problems such as cold start and sparsity. [ABSTRACT FROM AUTHOR]

The selection of elective courses based on an individual's domain interest is a challenging and critical activity for students at the start of their curriculum. Effective and proper recommendation may result in building a strong expertise in the domain of interest, which in turn improves the outcomes of the students getting better placements, and enrolling into higher studies of their interest, etc. In this paper, an effective course recommendation system is proposed to help the students in facilitating proper course selection based on an individual's domain interest. To achieve this, the core courses in the curriculum are mapped with the predefined domain suggested by the domain experts. These core course contents mapped with the domain are trained semantically using deep learning models to classify the elective courses into domains, and the same are recommended based on the student's domain expertise. The recommendation is validated by analyzing the number of elective course credits completed and the grades scored by a student who utilized the elective course recommendation system, with the grades scored by the student who was subjected to the assessment without elective course recommendations. It was also observed that after the recommendation, the students have registered for a greater number of credits for elective courses on their domain of expertise, which in-turn enables them to have a better learning experience and improved course completion probability. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Music content has recently been identified as useful information to promote the performance of music recommendations. Existing studies usually feed low-level audio features, such as the Mel-frequency cepstral coefficients, into deep learning models for music recommendations. However, such features cannot well characterize music audios, which often contain multiple sound sources. In this paper, we propose to model and fuse chord, melody, and rhythm features to meaningfully characterize the music so as to improve the music recommendation. Specially, we use two user-based attention mechanisms to differentiate the importance of different parts of audio features and chord features. In addition, a Long Short-Term Memory layer is used to capture the sequence characteristics. Those features are fused by a multilayer perceptron and then used to make recommendations. We conducted experiments with a subset of the last.fm-1b dataset. The experimental results show that our proposal outperforms the best baseline by 3. 5 2 % on HR@10. [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]

Food recipe sharing sites are becoming increasingly popular among people who want to learn how to cook or plan their menu. Through online food recipes, individuals can select ingredients that suit their lifestyle and health condition. Information from online food recipes is useful in developing food-related systems such as recommendations and health care systems. However, the information from online recipes is often unstructured. One way of extracting such information into a well-structured format is the technique called named-entity recognition (NER), which is the process of identifying keywords and phrases in the text and classifying them into a set of predetermined categories, such as location, persons, time, and others. We present a food ingredient named-entity recognition model called RNE (recurrent network-based ensemble methods) to extract the entities from the online recipe. RNE is an ensemble-learning framework using recurrent network models such as RNN, GRU, and LSTM. These models are trained independently on the same dataset and combined to produce better predictions in extracting food entities such as ingredient names, products, units, quantities, and states for each ingredient in a recipe. The experimental findings demonstrate that the proposed model achieves predictions with an F1 score of 96.09% and outperforms all individual models by 0.2% to 0.5% in percentage points. This result indicates that RNE can extract information from food recipes better than a single model. In addition, this information extracted by RNE can be used to support various information systems related to food. [ABSTRACT FROM AUTHOR]

CTR (Click-Through Rate) prediction has attracted more and more attention from academia and industry for its significant contribution to revenue. In the last decade, learning feature interactions have become a mainstream research direction, and dozens of feature interaction-based models have been proposed for the CTR prediction task. The most common approach for existing models is to enumerate all possible feature interactions or to learn higher-order feature interactions by designing complex models. However, a simple enumeration will introduce meaningless and harmful interactions, and a complex model structure will bring a higher complexity. In this work, we propose a lightweight, yet effective model called the Gated Adaptive feature Interaction Network (GAIN). We devise a novel cross module to drop meaningless feature interactions and preserve informative ones. Our cross module consists of multiple gated units, each of which can independently learn an arbitrary-order feature interaction. We combine the cross module with a deep module into GAIN and conduct comparative experiments with state-of-the-art models on two public datasets to verify its validity. Our experimental results show that GAIN can achieve a comparable or even better performance compared to its competitors. Furthermore, in order to verify the effectiveness of the feature interactions learned by GAIN, we transfer learned interactions to other models, such as Logistic Regression (LR) and Factorization Machines (FM), and find out that their performance can be significantly improved. [ABSTRACT FROM AUTHOR]

Due to increase of data in online web resources Recommendation System plays a vital role. In many platforms such as music, movie, books, videos, ecommerce for recommending the useful data. Video recommendation system provides users a very highly satisfying recommendations which in turn increase the user stickiness to the site. A personalized recommendation system with collaborative filtering technique is implemented to increase the user satisfaction. This method is used to recommend movies to users depending on their historical data on the streaming site and also by exploring the content watched by the users with similar preferences. A personalized recommendation system using collaborative filtering with multi-layer perceptron is implemented to increase the accuracy of the system. [ABSTRACT FROM AUTHOR]

When a user connects to the Internet to fulfill his needs, he often encounters a huge amount of related information. Recommender systems are the techniques for massively filtering information and offering the items that users find them satisfying and interesting. The advances in machine learning methods, especially deep learning, have led to great achievements in recommender systems, although these systems still suffer from challenges such as cold‐start and sparsity problems. To solve these problems, context information such as user communication network is usually used. In this article, we have proposed a novel recommendation method based on matrix factorization and graph analysis methods, namely Louvain for community detection and HITS for finding the most important node within the trust network. In addition, we leverage deep autoencoders to initialize users and items latent factors, and the Node2vec deep embedding method gathers users' latent factors from the user trust graph. The proposed method is implemented on Ciao and Epinions standard datasets. The experimental results and comparisons demonstrate that the proposed approach is superior to the existing state‐of‐the‐art recommendation methods. Our approach outperforms other comparative methods and achieves great improvements, that is, 15.56% RMSE improvement for Epinions and 18.41% RMSE improvement for Ciao. [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]

Business-based decision support systems have been proposed for a few decades in the e-commerce and textile industries. However, these Decision Support Systems (DSS) have not been so productive in terms of business decision delivery. In our proposed model, we introduce a content-based image retrieval model based on a DSS and recommendations system for the textile industry, either offline or online. We used the Fashion MNIST dataset developed by Zalando to train our deep learning model. Our proposed hybrid model can demonstrate how a DSS can be integrated with a system that can separate customers based on their personal characteristics in order to tailor recommendations of products using behavioral analytics, which is trained based on MBTI personality data and Deap EEG data containing numerous pre-trained EEG brain waves. With this hybrid, a DSS can also show product usage analytics. Our proposed model has achieved the maximum accuracy compared to other proposed state-of-the-art models due to its qualitative analysis. In the first section of our analysis, we used a deep learning algorithm to train our CBIR model based on different classifiers such as VGG-net, Inception-Net, and U-net which have achieved an accuracy of 98.2% with a 2% of minimized error rate. The result was validated using different performance metrics such as F-score, F-weight, Precision, and Recall. The second part of our model has been tested on different machine learning algorithms with an accuracy rate of 89.9%. Thus, the entire model has been trained, validated, and tested separately to gain maximum efficiency. Our proposal for a DSS system, which integrates several subsystems with distinct functional sets and several model subsystems, is what makes this study special. Customer preference is one of the major problems facing merchants in the textile industry. Additionally, it can be extremely difficult for retailers to predict customer interests and preferences to create products that fulfill those needs. The three innovations presented in this work are a conceptual model for personality characterization, utilizing an amalgamation of an ECG classification model, a suggestion for a textile image retrieval model using Denoising Auto-Encoder, and a language model based on the MBTI for customer rating. Additionally, we have proposed a section showing how blockchain integration in data pre-processing can enhance its security and AI-based software quality assurance in a multi-model system. [ABSTRACT FROM AUTHOR]

Recommender systems are information filtering tools that seek to match customers with products or services of interest. Most of the prevalent collaborative filtering recommender systems, such as matrix factorization and AutoRec, suffer from the "cold‐start" problem, where they fail to provide meaningful recommendations for new users or new items due to informative‐missing from the training data. To address this problem, we propose a weighted AutoEncoding model to leverage information from other users or items that share similar characteristics. The proposed method provides an effective strategy for borrowing strength from user or item‐specific clustering structure as well as pairwise similarity in the training data, while achieving high computational efficiency and dimension reduction, and preserving nonlinear relationships between user preferences and item features. Simulation studies and applications to three real datasets show advantages in prediction accuracy of the proposed model compared to current state‐of‐the‐art approaches. [ABSTRACT FROM AUTHOR]

With advances in machine learning, the application of financial services has become increasingly intelligent. The artificial intelligence financial advisory and other customized services have been launched in the market. However, when facing new financial products, recommendation models may not possess sufficient training data, which is called the cold-start problem. To address this problem, we present the few-shot learning model, which aims to learn a new category through a limited number of samples by transferring the past experiences and knowledge to the learning of new categories. We trained our model by using considerable past transaction data and applied a customized bias to adjust the predicted result for each investor. We then tested our model on new stock items by applying few-shot learning and testing. The results of this study indicate that training the proposed network with a customized bias can improve its prediction accuracy, especially for new items. Moreover, the proposed model can transform past experience into knowledge. When new data with only a few available samples are input into the proposed model, it can learn and make predictions and thus achieve few-shot learning. [ABSTRACT FROM AUTHOR]

Cold Start problems in recommender systems pose various challenges in the adoption and use of recommender systems, especially for new item uptake and new user engagement. This restricts organizations to realize the business value of recommender systems as they have to incur marketing and operations costs to engage new users and promote new items. Owing to this, several studies have been done by recommender systems researchers to address the cold start problems. However, there has been very limited recent research done on collating these approaches and algorithms. To address this gap, the paper conducts a systematic literature review of various strategies and approaches proposed by researchers in the last decade, from January 2010 to December 2021, and synthesizes the same into two categories: data-driven strategies and approach-driven strategies. Furthermore, the approach-driven strategies are categorized into five main clusters based on deep learning, matrix factorization, hybrid approaches, or other novel approaches in collaborative filtering and content-based algorithms. The scope of this study is limited to a systematic literature review and it does not include an experimental study to benchmark and recommend the best approaches and their context of use in cold start scenarios. [ABSTRACT FROM AUTHOR]

Recommendation attack attempts to bias the recommendation results of collaborative recommender systems by injecting malicious ratings into the rating database. A lot of methods have been proposed for detecting such attacks. Among these works, the deep learning-based detection methods get rid of the dependence on hand-designed features of recommendation attack besides having excellent detection performance. However, most of them optimize the key hyperparameters by manual analysis which relies too much on domain experts and their experience. To address this issue, in this paper we propose an approach based on the Harris Hawks Optimization (HHO) algorithm to improve the deep learning-based detection methods. Being different from the original detection methods which optimize the key hyperparameters manually, the improved deep learning-based detection methods can optimize the key hyperparameters automatically. We first convert the key hyperparameters of discrete type to continuous type according to the uniform distribution theory to expand the application scope of HHO algorithm. Then, we use the detection stability as an early stop condition to reduce the optimization iterations to improve the HHO algorithm. After that, we use the improved HHO algorithm to automatically optimize the key hyperparameters for the deep learning-based detection methods. Finally, we use the optimized key hyperparameters to train the deep learning-based detection methods to generate classifiers for detecting the recommendation attack. The experiments conducted on two benchmark datasets illustrate that the improved deep learning-based detection methods have effective performance. [ABSTRACT FROM AUTHOR]

In this work, we exploit a classifier based on convolutional neural network to predict users' interests regarding products and services, according to their publications in social media. We aim at designing a customizable recommendation system to target social networks' users as potential buyers. We evaluate the performance of training algorithms that use adaptive learning. The evaluation is performed in terms of the achieved accuracy rate to predict user's interest. The selection result is backed up by the multi-criteria decision making. Two metrics are used to identify the real user interest profile of users based on publicly available photos. [ABSTRACT FROM AUTHOR]

Copyright of Ordnance Industry Automation is the property of Editorial Board for Ordnance Industry Automation and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The immune system can be compromised when humans inhale excessive cooling. Physical activity helps a person's immune system, and influenza seasonally affects immunity and respiratory tract illness when there is no physical activity during the day. Whenever people chill excessively, they become more susceptible to pathogens because they require more energy to maintain a healthy body temperature. There is no doubt that exercise improves the immune system and an individual's fitness. According to an individual's health history, lifestyle, and preferences, the physical activity framework also includes exercises to improve the immune system. This study developed a framework for predicting physical activity based on information about health status, preferences, calorie intake, race, and gender. Using information about comorbidities, regions, and exercise/eating habits, the proposed recommendation system recommends exercises based on the user's preferences. [ABSTRACT FROM AUTHOR]

The large amount of possible online services throws a significant load on the users' service selection decision-making procedure. A number of intelligent suggestion systems have been created in order to lower the excessive decision-making expense. Taking this into consideration, a? RLSD (Recommendation-based Location Services using Deep Learning) model is proposed in this paper. Alongside robustness, this research considers the geographic interface between the client and the service. The suggested model blends a Multi-Layer-Perceptron (MLP) with a similarity Adaptive Corrector (AC), which is meant to detect high-dimensional and non-linear connections, as well as the location correlations amongst client and services. This not only improves recommendation results but also considerably reduces difficulties due to data sparseness. As a result, the proposed RLSD has strong flexibility and is extensible when it comes to leveraging context data like location. [ABSTRACT FROM AUTHOR]

With the advancement of the internet, individuals are becoming more reliant on online applications to meet most of their needs. In the meantime, they have very little spare time to devote to the selection and decision-making process. As a result, the need for recommender systems to help tackle this problem is expanding. Recommender systems successfully provide consumers with individualized recommendations on a variety of goods, simplifying their duties. The goal of this research is to create a recommender system for farmers based on tree data structures. Recommender system has become interesting research by simplifying and saving time in the decision-making process of users. We conducted although a lot of research in various fields, there are insufficient in the agriculture sector. This issue is more necessary for farmers in Quangnam-Danang or all Vietnam countries by severe climate features. Storm from that, this research designs a system based on tree data structures. The proposed model combines the you only look once (YOLO) algorithm in a convolutional neural network (CNN) model with a similarity tree in computing similarity. By experiments on 400 samples and evaluating precision, accuracy, and the value of the predictive test as determined by its positive predictive value (PPV), the research proves that the proposed model is feasible and gain better results compared with other state-of-the-art models. [ABSTRACT FROM AUTHOR]

The similarity recommendation of twitter data is evaluated by using sentiment analysis method. In this paper, the deep learning processes such as classification, clustering and prediction are used to measure the data. Convolutional neural network is applied for analyzing multimedia contents which is received from various sources. Recurrent neural network is used for handling the natural language data. The content based recommendation system is proposed for selecting similarity index in twitter data using deep sentiment learning method. In this paper, sentiment analysis technique is used for finding similar images, contents, texts, etc. The content is selected based on repetitive comments and trending information. Hash tag is also considered for data collection and prediction. The number tweets are accountable and each character is taken for evaluation. Deep belief network is generated using 512 x 512 x 3 layers system and 1056 trained data, 512 test data that are taken for convolution process. The deep belief network is generated using TensorFlow. TensorFlow is used to simulate the deep learning environments. Semantic analysis is applied for handling Twitter Data. The deep learning processes are classified into clustering, regression and prediction that are evaluated by step by setup approach. The experiments are carried out using similarity index calculation and measuring of accuracy. The results of similarity recommendation are compared with existing method and the results are recorded. Our proposed system gives better results comparing with existing experiments. [ABSTRACT FROM AUTHOR]

Background: Twitter is a popular social networking site where short messages or "tweets" of users have been used extensively for research purposes. However, not much research has been done in mining the medical professions, such as detecting the occupations of users from their biographical contents. Mining such professions can be used to build efficient recommender systems for cost-effective targeted advertisements. Moreover, it is highly important to develop effective methods to identify the occupation of users since conventional classification methods rely on features developed by human intelligence. Although, the result may be favorable for the classification problem. However, it is still extremely challenging for traditional classifiers to predict the medical occupations accurately since it involves predicting multiple occupations. Hence this study emphasizes predicting the medical occupational class of users through their public biographical ("Bio") content. We have conducted our analysis by annotating the bio content of Twitter users. In this paper, we propose a method of combining word embedding with state-of-art neural network models that include: Long Short Term Memory (LSTM), Bidirectional LSTM, Gated Recurrent Unit, Bidirectional Encoder Representations from Transformers, and A lite BERT. Moreover, we have also observed that by composing the word embedding with the neural network models there is no need to construct any particular attribute or feature. By using word embedding, the bio contents are formatted as dense vectors which are fed as input into the neural network models as a sequence of vectors. Result: Performance metrics that include accuracy, precision, recall, and F1-score have shown a significant difference between our method of combining word embedding with neural network models than with the traditional methods. The scores have proved that our proposed approach has outperformed the traditional machine learning techniques for detecting medical occupations among users. ALBERT has performed the best among the deep learning networks with an F1 score of 0.90. Conclusion: In this study, we have presented a novel method of detecting the occupations of Twitter users engaged in the medical domain by merging word embedding with state-of-art neural networks. The outcomes of our approach have demonstrated that our method can further advance the process of analyzing corpora of social media without going through the trouble of developing computationally expensive features. [ABSTRACT FROM AUTHOR]

Background and Objective. Skin lesion classification by using deep learning technologies is still a considerable challenge due to high similarity among classes and large intraclass differences, serious class imbalance in data, and poor classification accuracy with low robustness. Approach. To address these issues, a two-stage framework for dermoscopy lesion classification using adversarial training and a fuzzy rank-based ensemble of multilayer feature fusion convolutional neural network (CNN) models is proposed. In the first stage, dermoscopy dataset augmentation based on generative adversarial networks is proposed to obtain realistic dermoscopy lesion images, enabling significant improvement for balancing the number of lesions in each class. In the second stage, a fuzzy rank-based ensemble of multilayer feature fusion CNN models is proposed to classify skin lesions. In addition, an efficient channel integrating spatial attention module, in which a novel dilated pyramid pooling structure is designed to extract multiscale features from an enlarged receptive field and filter meaningful information of the initial features. Combining the cross-entropy loss function with the focal loss function, a novel united loss function is designed to reduce the intraclass sample distance and to focus on difficult and error-prone samples to improve the recognition accuracy of the proposed model. Main results. In this paper, the common dataset (HAM10000) is selected to conduct simulation experiments to evaluate and verify the effectiveness of the proposed method. The subjective and objective experimental results demonstrate that the proposed method is superior over the state-of-the-art methods for skin lesion classification due to its higher accuracy, specificity and robustness. Significance. The proposed method effectively improves the classification performance of the model for skin diseases, which will help doctors make accurate and efficient diagnoses, reduce the incidence rate and improve the survival rates of patients. [ABSTRACT FROM AUTHOR]

Due to the huge system in the field of constitution, the content of cases is complicated, and the number of documents related to constitutional cases is huge. It is incredibly tough to find the information that suits your demands in such a large volume of constitutional documents. The artificial neural network-based deep learning method has made significant progress. Deep learning has been used in the disciplines of computer image and video processing, as well as natural language processing, and has outperformed typical machine learning methods. To that purpose, the content-based recommendation algorithm in this work is improved using deep learning approaches. This paper primarily covers the following topics: (1) the current research status of deep learning technology in recommender systems is reviewed, and the theoretical knowledge of deep neural networks is introduced. (2) A text classification model OCCNN based on character-level convolutional neural network is proposed to solve the problem of document classification of massive cases. A semantic similarity calculation model TF-W2V based on word frequency and word vector is also proposed to solve the problem of semantic similarity calculation of cases. (3) The two methods are tested, and the experimental results show that the accuracy is much higher than that of the conventional method. The model can recommend cases that meet the needs of users according to the requirements put forward by users in the process of handling cases. [ABSTRACT FROM AUTHOR]