Статті в журналах з теми "Training data recommendation"
Щоб переглянути інші типи публікацій з цієї теми, перейдіть за посиланням: Training data recommendation.
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-50 статей у журналах для дослідження на тему "Training data recommendation".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Переглядайте статті в журналах для різних дисциплін та оформлюйте правильно вашу бібліографію.
1
Komurlekar, Runali. "Movie Recommendation Model from Data through Online Streaming." International Journal for Research in Applied Science and Engineering Technology 9, no. 8 (August 31, 2021): 1549–51. http://dx.doi.org/10.22214/ijraset.2021.37495.
Анотація:
Abstract: With the Pandemic era and easy availability of internet, potential of digital movie and tv series industry is in huge demand. Hence it has led to developing an automatic movie recommendation engine and has become a popular issue. Some of these problems can be solved or at least be minimized if we take the right decisions on what kind of movies to ignore, what movies to consider. This paper examines the recommendations that are obtained with considering the sample movies that have never got an above-average rating, where average rating is defined here as the mid-value between 0 and maximum rating used, for example, 2.5 in 1 to 5 rating scale. The technique used is “collaborative filtering”. Comparison of different pre-training model, it is tried to maximize the effectiveness of semantic understanding and make the recommendation be able to reflect meticulous perception on the relationship between user utilisation and user preference. Keywords: movie recommendation system, user similarity, user similarity, consumption pattern
2
Adnan, Muhammad, Yassaman Ebrahimzadeh Maboud, Divya Mahajan, and Prashant J. Nair. "Accelerating recommendation system training by leveraging popular choices." Proceedings of the VLDB Endowment 15, no. 1 (September 2021): 127–40. http://dx.doi.org/10.14778/3485450.3485462.
Анотація:
Recommender models are commonly used to suggest relevant items to a user for e-commerce and online advertisement-based applications. These models use massive embedding tables to store numerical representation of items' and users' categorical variables (memory intensive) and employ neural networks (compute intensive) to generate final recommendations. Training these large-scale recommendation models is evolving to require increasing data and compute resources. The highly parallel neural networks portion of these models can benefit from GPU acceleration however, large embedding tables often cannot fit in the limited-capacity GPU device memory. Hence, this paper deep dives into the semantics of training data and obtains insights about the feature access, transfer, and usage patterns of these models. We observe that, due to the popularity of certain inputs, the accesses to the embeddings are highly skewed with a few embedding entries being accessed up to 10000X more. This paper leverages this asymmetrical access pattern to offer a framework, called FAE, and proposes a hot-embedding aware data layout for training recommender models. This layout utilizes the scarce GPU memory for storing the highly accessed embeddings, thus reduces the data transfers from CPU to GPU. At the same time, FAE engages the GPU to accelerate the executions of these hot embedding entries. Experiments on production-scale recommendation models with real datasets show that FAE reduces the overall training time by 2.3X and 1.52X in comparison to XDL CPU-only and XDL CPU-GPU execution while maintaining baseline accuracy.
3
Wang, Qingren, Min Zhang, Tao Tao, and Victor S. Sheng. "Labelling Training Samples Using Crowdsourcing Annotation for Recommendation." Complexity 2020 (May 5, 2020): 1–10. http://dx.doi.org/10.1155/2020/1670483.
Анотація:
The supervised learning-based recommendation models, whose infrastructures are sufficient training samples with high quality, have been widely applied in many domains. In the era of big data with the explosive growth of data volume, training samples should be labelled timely and accurately to guarantee the excellent recommendation performance of supervised learning-based models. Machine annotation cannot complete the tasks of labelling training samples with high quality because of limited machine intelligence. Although expert annotation can achieve a high accuracy, it requires a long time as well as more resources. As a new way of human intelligence to participate in machine computing, crowdsourcing annotation makes up for shortages of machine annotation and expert annotation. Therefore, in this paper, we utilize crowdsourcing annotation to label training samples. First, a suitable crowdsourcing mechanism is designed to create crowdsourcing annotation-based tasks for training sample labelling, and then two entropy-based ground truth inference algorithms (i.e., HILED and HILI) are proposed to achieve quality improvement of noise labels provided by the crowd. In addition, the descending and random order manners in crowdsourcing annotation-based tasks are also explored. The experimental results demonstrate that crowdsourcing annotation significantly improves the performance of machine annotation. Among the ground truth inference algorithms, both HILED and HILI improve the performance of baselines; meanwhile, HILED performs better than HILI.
4
劉怡, 劉怡. "Research of Art Point of Interest Recommendation Algorithm Based on Modified VGG-16 Network." 電腦學刊 33, no. 1 (February 2022): 071–85. http://dx.doi.org/10.53106/199115992022023301008.
Анотація:
<p>Traditional point of interest (POI) recommendation algorithms ignore the semantic context of comment information. Integrating convolutional neural networks into recommendation systems has become one of the hotspots in art POI recommendation research area. To solve the above problems, this paper proposes a new art POI recommendation model based on improved VGG-16. Based on the original VGG-16, the improved VGG-16 method optimizes the fully connection layer and uses transfer learning to share the weight parameters of each layer in VGG-16 pre-training model for subsequent training. The new model fuses the review information and user check-in information to improve the performance of POI recommendation. Experiments on real check-in data sets show that the proposed model has better recommendation performance than other advanced points of interest recommendation methods.</p> <p> </p>
5
Daniel, Thomas, Fabien Casenave, Nissrine Akkari, and David Ryckelynck. "Data Augmentation and Feature Selection for Automatic Model Recommendation in Computational Physics." Mathematical and Computational Applications 26, no. 1 (February 16, 2021): 17. http://dx.doi.org/10.3390/mca26010017.
Анотація:
Classification algorithms have recently found applications in computational physics for the selection of numerical methods or models adapted to the environment and the state of the physical system. For such classification tasks, labeled training data come from numerical simulations and generally correspond to physical fields discretized on a mesh. Three challenging difficulties arise: the lack of training data, their high dimensionality, and the non-applicability of common data augmentation techniques to physics data. This article introduces two algorithms to address these issues: one for dimensionality reduction via feature selection, and one for data augmentation. These algorithms are combined with a wide variety of classifiers for their evaluation. When combined with a stacking ensemble made of six multilayer perceptrons and a ridge logistic regression, they enable reaching an accuracy of 90% on our classification problem for nonlinear structural mechanics.
6
Salenko, A. A., and E. V. Morar. "DESIGN AND DEVELOPMENT OF A MOVIE RECOMMENDATION SERVICE." Applied Mathematics and Fundamental Informatics 8, no. 2 (2021): 046–53. http://dx.doi.org/10.25206/2311-4908-2021-8-1-46-53.
Анотація:
The article discusses two components of the service: the server part of the application for user interaction and the recommendation algorithm embedded in this service. In the process of work, training data was collected and processed, a neural network was designed and trained, recommendations were generated based on various filtering algorithms. The result of the work is a service for the selection of films
7
Xu, Gaochao, Yan Ding, Yuqiang Jiang, Ming Hu, and Jia Zhao. "A Novel Distributed Recommendation Framework Using Big Data in Social Context." International Journal of Pattern Recognition and Artificial Intelligence 31, no. 08 (May 9, 2017): 1759015. http://dx.doi.org/10.1142/s0218001417590157.
Анотація:
Recently big data have become a research hotspot and been successfully exploited in a few applications such as data mining and business modeling. Although big data contain a plenty of treasures for all the fields of computer science, it is very difficult for the current computing paradigms and computer hardware to efficiently process and utilize big data to attain what are looked forward to. In this work, we explore the possibility of employing big data in recommendation systems. We have proposed a simple recommendation system framework BDRSF (Big Data Recommendation System Framework), which is based on big data with social context theories and has abilities in obtaining the Recommender based on the idea of supervised learning through big data training. Its main idea can be divided into three parts: (1) reduce the scale of the current recommendation problems according to the essence of recommending; (2) design a rational Recommender and propose a novel supervised learning algorithm to get it; (3) utilize the Recommender to deal with the later recommendation problems. Experimental results show that BDRSF outperforms conventional recommendation systems, which clearly indicates the effectiveness and efficiency of big data with social context in personalized recommendation.
8
Zhang, Heng-Ru, Fan Min, and Xu He. "Aggregated Recommendation through Random Forests." Scientific World Journal 2014 (2014): 1–11. http://dx.doi.org/10.1155/2014/649596.
Анотація:
Aggregated recommendation refers to the process of suggesting one kind of items to a group of users. Compared to user-oriented or item-oriented approaches, it is more general and, therefore, more appropriate for cold-start recommendation. In this paper, we propose a random forest approach to create aggregated recommender systems. The approach is used to predict the rating of a group of users to a kind of items. In the preprocessing stage, we merge user, item, and rating information to construct an aggregated decision table, where rating information serves as the decision attribute. We also model the data conversion process corresponding to the new user, new item, and both new problems. In the training stage, a forest is built for the aggregated training set, where each leaf is assigned a distribution of discrete rating. In the testing stage, we present four predicting approaches to compute evaluation values based on the distribution of each tree. Experiments results on the well-known MovieLens dataset show that the aggregated approach maintains an acceptable level of accuracy.
9
Nanry, Charles. "Performance Linked Training." Public Personnel Management 17, no. 4 (December 1988): 457–63. http://dx.doi.org/10.1177/009102608801700409.
Анотація:
Linking training to employee performance and development is an important consideration in justifying particular programs for particular employees. The new Performance Assessment Review (PAR) system attempts to do just that for New Jersey state employees. PAR forces supervisors and managers “to go on record” in the recommendation of specified training to remedy the needs of individual employees. Through the aggregation of PAR generated data the new system also provides a powerful tool for the assessment of broad training needs across agencies and job classes.
10
Zamani, Hamed. "Neural models for information retrieval without labeled data." ACM SIGIR Forum 53, no. 2 (December 2019): 104–5. http://dx.doi.org/10.1145/3458553.3458569.
Анотація:
Recent developments of machine learning models, and in particular deep neural networks, have yielded significant improvements on several computer vision, natural language processing, and speech recognition tasks. Progress with information retrieval (IR) tasks has been slower, however, due to the lack of large-scale training data as well as neural network models specifically designed for effective information retrieval [9]. In this dissertation, we address these two issues by introducing task-specific neural network architectures for a set of IR tasks and proposing novel unsupervised or weakly supervised solutions for training the models. The proposed learning solutions do not require labeled training data. Instead, in our weak supervision approach, neural models are trained on a large set of noisy and biased training data obtained from external resources, existing models, or heuristics. We first introduce relevance-based embedding models [3] that learn distributed representations for words and queries. We show that the learned representations can be effectively employed for a set of IR tasks, including query expansion, pseudo-relevance feedback, and query classification [1, 2]. We further propose a standalone learning to rank model based on deep neural networks [5, 8]. Our model learns a sparse representation for queries and documents. This enables us to perform efficient retrieval by constructing an inverted index in the learned semantic space. Our model outperforms state-of-the-art retrieval models, while performing as efficiently as term matching retrieval models. We additionally propose a neural network framework for predicting the performance of a retrieval model for a given query [7]. Inspired by existing query performance prediction models, our framework integrates several information sources, such as retrieval score distribution and term distribution in the top retrieved documents. This leads to state-of-the-art results for the performance prediction task on various standard collections. We finally bridge the gap between retrieval and recommendation models, as the two key components in most information systems. Search and recommendation often share the same goal: helping people get the information they need at the right time. Therefore, joint modeling and optimization of search engines and recommender systems could potentially benefit both systems [4]. In more detail, we introduce a retrieval model that is trained using user-item interaction (e.g., recommendation data), with no need to query-document relevance information for training [6]. Our solutions and findings in this dissertation smooth the path towards learning efficient and effective models for various information retrieval and related tasks, especially when large-scale training data is not available.
11
Wang, Jinze, Yongli Ren, Jie Li, and Ke Deng. "The Footprint of Factorization Models and Their Applications in Collaborative Filtering." ACM Transactions on Information Systems 40, no. 4 (October 31, 2022): 1–32. http://dx.doi.org/10.1145/3490475.
Анотація:
Factorization models have been successfully applied to the recommendation problems and have significant impact to both academia and industries in the field of Collaborative Filtering ( CF ). However, the intermediate data generated in factorization models’ decision making process (or training process , footprint ) have been overlooked even though they may provide rich information to further improve recommendations. In this article, we introduce the concept of Convergence Pattern, which records how ratings are learned step-by-step in factorization models in the field of CF. We show that the concept of Convergence Patternexists in both the model perspective (e.g., classical Matrix Factorization ( MF ) and deep-learning factorization) and the training (learning) perspective (e.g., stochastic gradient descent ( SGD ), alternating least squares ( ALS ), and Markov Chain Monte Carlo ( MCMC )). By utilizing the Convergence Pattern, we propose a prediction model to estimate the prediction reliability of missing ratings and then improve the quality of recommendations. Two applications have been investigated: (1) how to evaluate the reliability of predicted missing ratings and thus recommend those ratings with high reliability. (2) How to explore the estimated reliability to adjust the predicted ratings to further improve the predication accuracy. Extensive experiments have been conducted on several benchmark datasets on three recommendation tasks: decision-aware recommendation, rating predicted, and Top- N recommendation. The experiment results have verified the effectiveness of the proposed methods in various aspects.
12
Ren, Tianzhi. "Construction of Mobile Screening Movie Recommendation Model Based on Artificial Immune Algorithm." Scientific Programming 2022 (February 17, 2022): 1–10. http://dx.doi.org/10.1155/2022/5700427.
Анотація:
The mobile screening of digital movies can fully take into account the viewing experience of scattered areas. As a public cultural service system, it is playing a pivotal role. The consistency of the film screened with the tastes of the audience in the service area of the screening team has largely affected the quality of rural public culture services. Traditional recommendation algorithms directly use raw data to make predictions, leading to deviations in predictions. This article draws on the principles of immune recognition, clone selection, immune mutation, and self-adaptation of the artificial immune system to improve the recommendation effect of single-type data, the recommendation effect of sparse data, and the recommendation effect of project cold start problems and discusses the recommendation based on artificial immunity. For the single type of data, there are only positive samples, which leads to the problem that the training results are all positive. This paper proposes a single-class recommendation algorithm based on artificial immunity. The algorithm uses the positive and negative sample addition method proposed in this paper to add positive and negative samples related to user selection, so as to effectively solve the problem of difficult definition of data negative samples. Then, the artificial immune network is used to cluster the users of various activities, reduce the size of the candidate neighbor set, calculate the user’s nearest neighbor set, and give recommendations.
13
Thibault, Louis-Philippe, Claude Julie Bourque, Thuy Mai Luu, Celine Huot, Genevieve Cardinal, Benoit Carriere, Amelie Dupont-Thibodeau, and Ahmed Moussa. "Residents as Research Subjects: Balancing Resident Education and Contribution to Advancing Educational Innovations." Journal of Graduate Medical Education 14, no. 2 (April 1, 2022): 191–200. http://dx.doi.org/10.4300/jgme-d-21-00530.1.
Анотація:
ABSTRACT Background Research in education advances knowledge and improves learning, but the literature does not define how to protect residents' rights as subjects in studies or how to limit the impact of their participation on their clinical training. Objective We aimed to develop a consensual framework on how to include residents as participants in education research, with the dual goal of protecting their rights and promoting their contributions to research. Methods A nominal group technique approach was used to structure 3 iterative meetings held with the pre-existing residency training program committee and 7 invited experts between September 2018 and April 2019. Thematic text analysis was conducted to prepare a final report, including recommendations. Results Five themes, each with recommendations, were identified: (1) Freedom of participation: participation, non-participation, or withdrawal from a study should not interfere with teacher-learner relationship (recommendation: improve recruitment and consent forms); (2) Avoidance of over-solicitation (recommendation: limit the number of ongoing studies); (3) Management of time dedicated to participation in research (recommendations: schedule and proportion of time for study participation); (4) Emotional safety (recommendation: requirement for debriefing and confidential counseling); and (5) Educational safety: data collected during a study should not influence clinical assessment of the resident (recommendation: principal investigator should not be involved in the evaluation process of learners in clinical rotation). Conclusions Our nominal group technique approach resulted in raising 5 specific issues about freedom of participation of residents in research in medical education, over-solicitation, time dedicated to research, emotional safety, and educational safety.
14
Chang, Jie. "Research on Enterprise Management Training Based on Cluster Computing." Tobacco Regulatory Science 7, no. 5 (September 30, 2021): 4438–48. http://dx.doi.org/10.18001/trs.7.5.2.10.
Анотація:
Objectives: Based on the cluster calculation, in this paper, the implementation of the training of enterprise personnel recruitment management was studied, starting with the employment recommendation form as the starting point. Methods: First of all, making rational use of previous employment data of college graduates and concludes with a Sensitive-Personal Rank algorithm to calculate the sensitivity of graduates interested in the historical recruitment data of each enterprise. Results: Furthermore, sensitivity to the current graduates and the graduates of the existing correlation between the calculation methods was optimized; finally, it was similar to the previous graduates to the recent graduates to recommend, so as bringing effective employment reference and guidance. Conclusion: The experimental results showed that, RBSI had a relatively high recommendation accuracy and satisfaction.
15
Bock, Joel R., and Akhilesh Maewal. "Adversarial Learning for Product Recommendation." AI 1, no. 3 (September 1, 2020): 376–88. http://dx.doi.org/10.3390/ai1030025.
Анотація:
Product recommendation can be considered as a problem in data fusion—estimation of the joint distribution between individuals, their behaviors, and goods or services of interest. This work proposes a conditional, coupled generative adversarial network (RecommenderGAN) that learns to produce samples from a joint distribution between (view, buy) behaviors found in extremely sparse implicit feedback training data. User interaction is represented by two matrices having binary-valued elements. In each matrix, nonzero values indicate whether a user viewed or bought a specific item in a given product category, respectively. By encoding actions in this manner, the model is able to represent entire, large scale product catalogs. Conversion rate statistics computed on trained GAN output samples ranged from 1.323% to 1.763%. These statistics are found to be significant in comparison to null hypothesis testing results. The results are shown comparable to published conversion rates aggregated across many industries and product types. Our results are preliminary, however they suggest that the recommendations produced by the model may provide utility for consumers and digital retailers.
16
Zhou, Mengyu, Wang Tao, Ji Pengxin, Han Shi, and Zhang Dongmei. "Table2Analysis: Modeling and Recommendation of Common Analysis Patterns for Multi-Dimensional Data." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 01 (April 3, 2020): 320–28. http://dx.doi.org/10.1609/aaai.v34i01.5366.
Анотація:
Given a table of multi-dimensional data, what analyses would human create to extract information from it? From scientific exploration to business intelligence (BI), this is a key problem to solve towards automation of knowledge discovery and decision making. In this paper, we propose Table2Analysis to learn commonly conducted analysis patterns from large amount of (table, analysis) pairs, and recommend analyses for any given table even not seen before. Multi-dimensional data as input challenges existing model architectures and training techniques to fulfill the task. Based on deep Q-learning with heuristic search, Table2Analysis does table to sequence generation, with each sequence encoding an analysis. Table2Analysis has 0.78 recall at top-5 and 0.65 recall at top-1 in our evaluation against a large scale spreadsheet corpus on the PivotTable recommendation task.
17
Guan, Congying, Shengfeng Qin, and Yang Long. "Apparel-based deep learning system design for apparel style recommendation." International Journal of Clothing Science and Technology 31, no. 3 (June 3, 2019): 376–89. http://dx.doi.org/10.1108/ijcst-02-2018-0019.
Анотація:
Purpose The big challenge in apparel recommendation system research is not the exploration of machine learning technologies in fashion, but to really understand clothes, fashion and people, and know what to learn. The purpose of this paper is to explore an advanced apparel style learning and recommendation system that can recognise deep design-associated features of clothes and learn the connotative meanings conveyed by these features relating to style and the body so that it can make recommendations as a skilled human expert. Design/methodology/approach This study first proposes a type of new clothes style training data. Second, it designs three intelligent apparel-learning models based on newly proposed training data including ATTRIBUTE, MEANING and the raw image data, and compares the models’ performances in order to identify the best learning model. For deep learning, two models are introduced to train the prediction model, one is a convolutional neural network joint with the baseline classifier support vector machine and the other is with a newly proposed classifier later kernel fusion. Findings The results show that the most accurate model (with average prediction rate of 88.1 per cent) is the third model that is designed with two steps, one is to predict apparel ATTRIBUTEs through the apparel images, and the other is to further predict apparel MEANINGs based on predicted ATTRIBUTEs. The results indicate that adding the proposed ATTRIBUTE data that captures the deep features of clothes design does improve the model performances (e.g. from 73.5 per cent, Model B to 86 per cent, Model C), and the new concept of apparel recommendation based on style meanings is technically applicable. Originality/value The apparel data and the design of three training models are originally introduced in this study. The proposed methodology can evaluate the pros and cons of different clothes feature extraction approaches through either images or design attributes and balance different machine learning technologies between the latest CNN and traditional SVM.
18
Zeng, Weishan. "DSSMFM: Combining user and item feature interactions for recommendation systems." MATEC Web of Conferences 309 (2020): 03010. http://dx.doi.org/10.1051/matecconf/202030903010.
Анотація:
Effort has been done to optimize machine learning algorithms by applying relevant knowledges in data fields in recommendation systems. Ways are explored to discover the relationship of features independently, making the model more effective and robust. A new model, DSSMFM is proposed in this paper which combines user and item features interactions to improve the performance of recommendation systems. In this model, data are divided into user features and item features represented by one-hot vectors. The pre-training for the model is proceeded through FM, and implicit vectors are obtained for both user and item features. The implicit vectors are used as the input of DSSM, and the training of the DSSM part of the model will maximize the cosine distances of the user attributes vectors and the item attributes vectors. According to the experimental results on dataset of ICME 2019 Short Video Understanding and Recommendation Challenge, the model shows improvements on some results of the baselines.
19
Nini, Lesia, Y. Touvan Juni Samodra, and Edi Purnomo Purnomo. "ATHLETE TRACK AND FIELD RECRUITMENT IN SPORT STUDENT TRAINING CENTER." Altius: Jurnal Ilmu Olahraga dan Kesehatan 9, no. 2 (November 30, 2020): 39–51. http://dx.doi.org/10.36706/altius.v9i2.12650.
Анотація:
Athlete recruitment was importance in sport achievement. If have good athlete based on good talend selected, so it will be greatest opportunities height performance achievement. PPLP given facilities and opportunities for student athlete from secondary and senior high school. The purpose of this study is to determine the management of athlete recruitment, athlete training and training programs and supporting infrastructure for athlete training. The research method used in this is qualitative. Sources of data in this study were athletes, coaches, PPLP managers and administrators of PASI KALBAR. The instruments in this study were observation, semi-structured interviews, field notes and documentation. The technique of checking the validity of the data is by triangulation. The recruitment athlete had charged in 2017, that was recruitment depend on coach recommendation. Coaches made recommendation based on athlete achievement. In 2017 that recruitment based on KEMANPORA rules. From 2012 to 2019 not yet showed significance achievement performance. Base on the data research showed, with new selection recruitment did not effect on achievement.
20
Liu, Chenghao, Xin Wang, Tao Lu, Wenwu Zhu, Jianling Sun, and Steven Hoi. "Discrete Social Recommendation." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 208–15. http://dx.doi.org/10.1609/aaai.v33i01.3301208.
Анотація:
Social recommendation, which aims at improving the performance of traditional recommender systems by considering social information, has attracted broad range of interests. As one of the most widely used methods, matrix factorization typically uses continuous vectors to represent user/item latent features. However, the large volume of user/item latent features results in expensive storage and computation cost, particularly on terminal user devices where the computation resource to operate model is very limited. Thus when taking extra social information into account, precisely extracting K most relevant items for a given user from massive candidates tends to consume even more time and memory, which imposes formidable challenges for efficient and accurate recommendations. A promising way is to simply binarize the latent features (obtained in the training phase) and then compute the relevance score through Hamming distance. However, such a two-stage hashing based learning procedure is not capable of preserving the original data geometry in the real-value space and may result in a severe quantization loss. To address these issues, this work proposes a novel discrete social recommendation (DSR) method which learns binary codes in a unified framework for users and items, considering social information. We further put the balanced and uncorrelated constraints on the objective to ensure the learned binary codes can be informative yet compact, and finally develop an efficient optimization algorithm to estimate the model parameters. Extensive experiments on three real-world datasets demonstrate that DSR runs nearly 5 times faster and consumes only with 1/37 of its real-value competitor’s memory usage at the cost of almost no loss in accuracy.
21
Yin*, Yuyu, Haoran Xu, Tingting Liang*, Manman Chen, Honghao Gao, and Antonella Longo. "Leveraging Data Augmentation for Service QoS Prediction in Cyber-physical Systems." ACM Transactions on Internet Technology 21, no. 2 (March 3, 2021): 1–25. http://dx.doi.org/10.1145/3425795.
Анотація:
With the fast-developing domain of cyber-physical systems (CPS), constructing the CPS with high-quality services becomes an imperative task. As one of the effective solutions for information overload in CPS construction, quality of service (QoS)-aware service recommendation has drawn much attention in academia and industry. However, the lack of most QoS values limits the recommendation performance and it is time-consuming for users to get the QoS values by invoking all the services. Therefore, a powerful prediction model is required to predict the unobserved QoS values. Considering the fact that most existing QoS prediction models are unable to effectively address the data-sparsity problem, a novel two-stage framework called AgQ is proposed for QoS prediction. Specifically, a data augmentation strategy is designed in the first stage to enlarge the training set by drawing additional virtual instances. In the second stage, a prediction model is applied that considers both virtual and factual instances during the training procedure. We conduct extensive experiments on the WSDream dataset to demonstrate the effectiveness of the our QoS prediction framework and verify that the data augmentation strategy can indeed alleviate the data-sparsity problem. In terms of mean absolute error, taking the Multilayer Perceptron model as an example, the maximum improvement achieves 5% under 5% sparsity.
22
Khoali, Mohamed, Yassin Laaziz, Abdelhak Tali, and Habeeb Salaudeen. "A Survey of One Class E-Commerce Recommendation System Techniques." Electronics 11, no. 6 (March 10, 2022): 878. http://dx.doi.org/10.3390/electronics11060878.
Анотація:
Although several recommendation algorithms are widely used by both commercial and non-commercial platforms, they face unique challenges such as sparse data sets and the absence of negative or “neutral” feedback. One-class algorithms attempt to overcome the data sparsity problem by using the implicit feedback inherent in user’s clicks and purchases, which are deduced from both positive and negative feedback. Existing literature uses several heuristic strategies to derive the negative samples needed for training, such as using random sampling or utilizing user-item interaction. However, these assumptions do not always reflect reality. In addition, with the explosive increase in the availability of big data for training recommendation systems, these methods might not adequately encapsulate the representations of the latent vectors. In this paper, we address the common issues of one-class recommendation and provide a survey on approaches that have been used to mitigate the existing challenges. To tackle the identified problems, we propose a neural network-based Bayesian Personalized Ranking (BPR) for item recommendation and personalized ranking from implicit feedback. BPR provides an optimization criterion derived from Bayesian analysis of a problem to develop an optimized model for such a problem. We conduct several experiments on two varieties of MovieLens datasets to illustrate the performance of the proposed approach. Our approach shows an impressive result in mitigating the issues of one-class recommendation when compared with the complexity of the state-of-the-art methods.
23
C, Chanjal. "Feature Re-Learning for Video Recommendation." International Journal for Research in Applied Science and Engineering Technology 9, no. VI (June 30, 2021): 3143–49. http://dx.doi.org/10.22214/ijraset.2021.35350.
Анотація:
Predicting the relevance between two given videos with respect to their visual content is a key component for content-based video recommendation and retrieval. The application is in video recommendation, video annotation, Category or near-duplicate video retrieval, video copy detection and so on. In order to estimate video relevance previous works utilize textual content of videos and lead to poor performance. The proposed method is feature re-learning for video relevance prediction. This work focus on the visual contents to predict the relevance between two videos. A given feature is projected into a new space by an affine transformation. Different from previous works this use a standard triplet ranking loss that optimize the projection process by a novel negative-enhanced triplet ranking loss. In order to generate more training data, propose a data augmentation strategy which works directly on video features. The multi-level augmentation strategy works for video features, which benefits the feature relearning. The proposed augmentation strategy can be flexibly used for frame-level or video-level features. The loss function that consider the absolute similarity of positive pairs and supervise the feature re-learning process and a new formula for video relevance computation.
24
Zheng, Xiaolin, and Disheng Dong. "An Adversarial Deep Hybrid Model for Text-Aware Recommendation with Convolutional Neural Networks." Applied Sciences 10, no. 1 (December 24, 2019): 156. http://dx.doi.org/10.3390/app10010156.
Анотація:
The standard matrix factorization methods for recommender systems suffer from data sparsity and cold-start problems. Thus, in real-world scenarios where items are commonly associated with textual data such as reviews, it becomes necessary to build a hybrid recommendation model that can fully utilize the text features. However, existing methods in this area either cannot extract good features from the texts due to their order–insensitive document modeling approaches or fail to learn the hybrid model in an effective way due to their complexity of inferring the latent vectors. To this end, we propose a deep hybrid recommendation model which seamlessly integrates matrix factorization with a Convolutional Neural Network (CNN), a powerful text feature extraction tool with the capability of detecting the information of word orders. Unlike previous works which use content features as prior knowledge to regularize the latent vectors, we combine CNN into MF in an additive manner to allow training CNN with direct learning signals. Furthermore, we propose an adversarial training framework to learn the hybrid recommendation model, where a generator model is built to learn the distribution over the pairwise ranking pairs while training a discriminator to distinguish generated (fake) and real item pairs. We conduct extensive experiments on three real-world datasets to demonstrate the effectiveness of our proposed model against state-of-the-art methods in various recommendation settings.
25
Dhawan, Sanjeev, Kulvinder Singh, Adrian Rabaea, and Amit Batra. "Session centered Recommendation Utilizing Future Contexts in Social Media." Analele Universitatii "Ovidius" Constanta - Seria Matematica 29, no. 3 (November 1, 2021): 91–104. http://dx.doi.org/10.2478/auom-2021-0036.
Анотація:
Abstract Session centered recommender systems has emerged as an interesting and challenging topic amid researchers during the past few years. In order to make a prediction in the sequential data, prevailing approaches utilize either left to right design autoregressive or data augmentation methods. As these approaches are used to utilize the sequential information pertaining to user conduct, the information about the future context of an objective interaction is totally ignored while making prediction. As a matter of fact, we claim that during the course of training, the future data after the objective interaction are present and this supplies indispensable signal on preferences of users and if utilized can increase the quality of recommendation. It is a subtle task to incorporate future contexts into the process of training, as the rules of machine learning are not followed and can result in loss of data. Therefore, in order to solve this problem, we suggest a novel encoder decoder prototype termed as space filling centered Recommender (SRec), which is used to train the encoder and decoder utilizing space filling approach. Particularly, an incomplete sequence is taken into consideration by the encoder as input (few items are absent) and then decoder is used to predict these items which are absent initially based on the encoded interpretation. The general SRec prototype is instantiated by us employing convolutional neural network (CNN) by giving emphasis on both e ciency and accuracy. The empirical studies and investigation on two real world datasets are conducted by us including short, medium and long sequences, which exhibits that SRec performs better than traditional sequential recommendation approaches.
26
Deng, Fuhu, Panlong Ren, Zhen Qin, Gu Huang, and Zhiguang Qin. "Leveraging Image Visual Features in Content-Based Recommender System." Scientific Programming 2018 (August 12, 2018): 1–8. http://dx.doi.org/10.1155/2018/5497070.
Анотація:
Content-based (CB) and collaborative filtering (CF) recommendation algorithms are widely used in modern e-commerce recommender systems (RSs) to improve user experience of personalized services. Item content features and user-item rating data are primarily used to train the recommendation model. However, sparse data would lead such systems unreliable. To solve the data sparsity problem, we consider that more latent information would be imported to catch users’ potential preferences. Therefore, hybrid features which include all kinds of item features are used to excavate users’ interests. In particular, we find that the image visual features can catch more potential preferences of users. In this paper, we leverage the combination of user-item rating data and item hybrid features to propose a novel CB recommendation model, which is suitable for rating-based recommender scenarios. The experimental results show that the proposed model has better recommendation performance in sparse data scenarios than conventional approaches. Besides, training offline and recommendation online make the model has higher efficiency on large datasets.
27
Chen, Jiawei, Chengquan Jiang, Can Wang, Sheng Zhou, Yan Feng, Chun Chen, Martin Ester, and Xiangnan He. "CoSam: An Efficient Collaborative Adaptive Sampler for Recommendation." ACM Transactions on Information Systems 39, no. 3 (May 22, 2021): 1–24. http://dx.doi.org/10.1145/3450289.
Анотація:
Sampling strategies have been widely applied in many recommendation systems to accelerate model learning from implicit feedback data. A typical strategy is to draw negative instances with uniform distribution, which, however, will severely affect a model’s convergence, stability, and even recommendation accuracy. A promising solution for this problem is to over-sample the “difficult” (a.k.a. informative) instances that contribute more on training. But this will increase the risk of biasing the model and leading to non-optimal results. Moreover, existing samplers are either heuristic, which require domain knowledge and often fail to capture real “difficult” instances, or rely on a sampler model that suffers from low efficiency. To deal with these problems, we propose CoSam, an efficient and effective collaborative sampling method that consists of (1) a collaborative sampler model that explicitly leverages user-item interaction information in sampling probability and exhibits good properties of normalization, adaption, interaction information awareness, and sampling efficiency, and (2) an integrated sampler-recommender framework, leveraging the sampler model in prediction to offset the bias caused by uneven sampling. Correspondingly, we derive a fast reinforced training algorithm of our framework to boost the sampler performance and sampler-recommender collaboration. Extensive experiments on four real-world datasets demonstrate the superiority of the proposed collaborative sampler model and integrated sampler-recommender framework.
28
Chen, Hung-Kai, Fueng-Ho Chen, and Shien-Fong Lin. "An AI-Based Exercise Prescription Recommendation System." Applied Sciences 11, no. 6 (March 16, 2021): 2661. http://dx.doi.org/10.3390/app11062661.
Анотація:
The European Association of Preventive Cardiology Exercise Prescription in Everyday Practice and Rehabilitative Training (EXPERT) tool has been developed for digital training and decision support in cardiovascular disease patients in clinical practice. Exercise prescription recommendation systems for sub-healthy people are essential to enhance this dominant group’s physical ability as well. This study aims to construct a guided exercise prescription system for sub-healthy groups using exercise community data to train an AI model. The system consists of six modules, including three-month suggested exercise mode (3m-SEM), predicted value of rest heart rate (rest HR) difference after following three-month suggested exercise mode (3m-PV), two-month suggested exercise mode (2m-SEM), predicted value of rest HR difference after following two-month suggested exercise mode (2m-PV), one-month suggested exercise mode (1m-SEM) and predicted value of rest HR difference after following one-month suggested exercise mode (1m-PV). A new user inputs gender, height, weight, age, and current rest HR value, and the above six modules will provide the user with a prescription. A four-layer neural network model is applied to construct the above six modules. The AI-enabled model produced 95.80%, 100.00%, and 95.00% testing accuracy in 1m-SEM, 2m-SEM, and 3m-SEM, respectively. It reached 3.15, 2.89, and 2.75 BPM testing mean absolute error in 1m-PV, 2m-PV, and 3m-PV. The developed system provides quantitative exercise prescriptions to guide the sub-healthy group to engage in effective exercise programs.
29
Suharyadi, Joshua, and Adhi Kusnadi. "Design and Development of Job Recommendation System Based On Two Dominants On Psychotest Results Using KNN Algorithm." International Journal of New Media Technology 5, no. 2 (March 19, 2019): 116–20. http://dx.doi.org/10.31937/ijnmt.v5i2.954.
Анотація:
Employees are an important factor in the progress of a company. Employees with good performance will certainly provide positive results for the company. One that can determine employee performance is the right placement in the job. To find out the right placement in a job, one way can be done psychologically. Psikotes can help to know the nature of an employee and suitable work based on their nature. The construction of a job recommendation application system was created to help prospective employees know their true identity and suitable work so that they can apply according to their expertise. This system is built with the programming language PHP, Javascript, HTML for web-based platforms and the KNN algorithm as the method. The KNN algorithm is used to measure the closest distance between training data and test data to produce job recommendations. Training data is taken from expert, and book references. System trials are given to users by filling in psychological tests and questionnaires regarding the satisfaction of system use. After getting feedback from users, the value of system satisfaction reached 85%. This states that the system can provide job recommendations that are in accordance with the psychological test results of the user.
30
Zhou, Fan, Pengyu Wang, Xovee Xu, Wenxin Tai, and Goce Trajcevski. "Contrastive Trajectory Learning for Tour Recommendation." ACM Transactions on Intelligent Systems and Technology 13, no. 1 (February 28, 2022): 1–25. http://dx.doi.org/10.1145/3462331.
Анотація:
The main objective of Personalized Tour Recommendation (PTR) is to generate a sequence of point-of-interest (POIs) for a particular tourist, according to the user-specific constraints such as duration time, start and end points, the number of attractions planned to visit, and so on. Previous PTR solutions are based on either heuristics for solving the orienteering problem to maximize a global reward with a specified budget or approaches attempting to learn user visiting preferences and transition patterns with the stochastic process or recurrent neural networks. However, existing learning methodologies rely on historical trips to train the model and use the next visited POI as the supervised signal, which may not fully capture the coherence of preferences and thus recommend similar trips to different users, primarily due to the data sparsity problem and long-tailed distribution of POI popularity. This work presents a novel tour recommendation model by distilling knowledge and supervision signals from the trips in a self-supervised manner. We propose Contrastive Trajectory Learning for Tour Recommendation (CTLTR), which utilizes the intrinsic POI dependencies and traveling intent to discover extra knowledge and augments the sparse data via pre-training auxiliary self-supervised objectives. CTLTR provides a principled way to characterize the inherent data correlations while tackling the implicit feedback and weak supervision problems by learning robust representations applicable for tour planning. We introduce a hierarchical recurrent encoder-decoder to identify tourists’ intentions and use the contrastive loss to discover subsequence semantics and their sequential patterns through maximizing the mutual information. Additionally, we observe that a data augmentation step as the preliminary of contrastive learning can solve the overfitting issue resulting from data sparsity. We conduct extensive experiments on a range of real-world datasets and demonstrate that our model can significantly improve the recommendation performance over the state-of-the-art baselines in terms of both recommendation accuracy and visiting orders.
31
Liu, Guanglu. "Research on Personalized Minority Tourist Route Recommendation Algorithm Based on Deep Learning." Scientific Programming 2022 (January 7, 2022): 1–9. http://dx.doi.org/10.1155/2022/8063652.
Анотація:
With the improvement of living standards, more and more people are pursuing personalized routes. This paper uses personalized mining of interest points of ethnic minority tourism demand groups, extracts customer data features in social networks, and constructs data features of interesting topic factors, geographic location factors, and user access frequency factors, using LDA topic models and matrix decomposition models to perform feature vectorization processing on user sign-in records and build deep learning recommendation model (DLM). Using this model to compare with the traditional recommendation model and the recommendation model of a single data feature module, the experimental results show the following: (1) The fitting error of DLM recommendation results is significantly reduced, and its recommendation accuracy rate is 50% higher than that of traditional recommendation algorithms. The experimental results show that the DLM constructed in this paper has good learning and training performance, and the recommendation effect is good. (2) In this method, the performance of the DLM is significantly higher than other POI recommendation methods in terms of the accuracy or recall rate of the recommendation algorithm. Among them, the accuracy rates of the top five, top ten, and top twenty recommended POIs are increased by 9.9%, 7.4%, and 7%, respectively, and the recall rate is increased by 4.2%, 7.5%, and 14.4%, respectively.
32
Liu, Huazhen, Wei Wang, Yihan Zhang, Renqian Gu, and Yaqi Hao. "Neural Matrix Factorization Recommendation for User Preference Prediction Based on Explicit and Implicit Feedback." Computational Intelligence and Neuroscience 2022 (January 10, 2022): 1–12. http://dx.doi.org/10.1155/2022/9593957.
Анотація:
Explicit feedback and implicit feedback are two important types of heterogeneous data for constructing a recommendation system. The combination of the two can effectively improve the performance of the recommendation system. However, most of the current deep learning recommendation models fail to fully exploit the complementary advantages of two types of data combined and usually only use binary implicit feedback data. Thus, this paper proposes a neural matrix factorization recommendation algorithm (EINMF) based on explicit-implicit feedback. First, neural network is used to learn nonlinear feature of explicit-implicit feedback of user-item interaction. Second, combined with the traditional matrix factorization, explicit feedback is used to accurately reflect the explicit preference and the potential preferences of users to build a recommendation model; a new loss function is designed based on explicit-implicit feedback to obtain the best parameters through the neural network training to predict the preference of users for items; finally, according to prediction results, personalized recommendation list is pushed to the user. The feasibility, validity, and robustness are fully demonstrated in comparison with multiple baseline models on two real datasets.
33
Wan, Xinyue, Bofeng Zhang, Guobing Zou, and Furong Chang. "Sparse Data Recommendation by Fusing Continuous Imputation Denoising Autoencoder and Neural Matrix Factorization." Applied Sciences 9, no. 1 (December 24, 2018): 54. http://dx.doi.org/10.3390/app9010054.
Анотація:
In recent years, although deep neural networks have yielded immense success in solving various recognition and classification problems, the exploration of deep neural networks in recommender systems has received relatively less attention. Meanwhile, the inherent sparsity of data is still a challenging problem for deep neural networks. In this paper, firstly, we propose a new CIDAE (Continuous Imputation Denoising Autoencoder) model based on the Denoising Autoencoder to alleviate the problem of data sparsity. CIDAE performs regular continuous imputation on the missing parts of the original data and trains the imputed data as the desired output. Then, we optimize the existing advanced NeuMF (Neural Matrix Factorization) model, which combines matrix factorization and a multi-layer perceptron. By optimizing the training process of NeuMF, we improve the accuracy and robustness of NeuMF. Finally, this paper fuses CIDAE and optimized NeuMF with reference to the idea of ensemble learning. We name the fused model the I-NMF (Imputation-Neural Matrix Factorization) model. I-NMF can not only alleviate the problem of data sparsity, but also fully exploit the ability of deep neural networks to learn potential features. Our experimental results prove that I-NMF performs better than the state-of-the-art methods for the public MovieLens datasets.
34
Siles, Ignacio, Andrés Segura-Castillo, Ricardo Solís, and Mónica Sancho. "Folk theories of algorithmic recommendations on Spotify: Enacting data assemblages in the global South." Big Data & Society 7, no. 1 (January 2020): 205395172092337. http://dx.doi.org/10.1177/2053951720923377.
Анотація:
This paper examines folk theories of algorithmic recommendations on Spotify in order to make visible the cultural specificities of data assemblages in the global South. The study was conducted in Costa Rica and draws on triangulated data from 30 interviews, 4 focus groups with 22 users, and the study of “rich pictures” made by individuals to graphically represent their understanding of algorithmic recommendations. We found two main folk theories: one that personifies Spotify (and conceives of it as a social being that provides recommendations thanks to surveillance) and another one that envisions it as a system full of resources (and a computational machine that offers an individualized musical experience through the appropriate kind of “training”). Whereas the first theory emphasizes local conceptions of social relations to make sense of algorithms, the second one stresses the role of algorithms in providing a global experience of music and technology. We analyze why people espouse either one of these theories (or both) and how these theories provide users with resources to enact different modalities of power and resistance in relation to recommendation algorithms. We argue that folk theories thus offer a productive way to broaden understanding of what agency means in relation to algorithms.
35
Guk, Natalia, Olga Verba, and Vladyslav Yevlakov. "Design of a recommendation system based on the transition graph." Eastern-European Journal of Enterprise Technologies 3, no. 4 (111) (June 29, 2021): 24–31. http://dx.doi.org/10.15587/1729-4061.2021.233501.
Анотація:
A recommendation system has been built for a web resource’s users that applies statistics about user activities to provide recommendations. The purpose of the system operation is to provide recommendations in the form of an orderly sequence of HTML pages of the resource suggested for the user. The ranking procedure uses statistical information about user transitions between web resource pages. The web resource model is represented in the form of a web graph; the user behavior model is shown as a graph of transitions between resource pages. The web graph is represented by an adjacency matrix; for the transition graph, a weighted matrix of probabilities of transitions between the vertices of the graph has been constructed. It was taken into consideration that user transitions between pages of a web resource may involve entering a URL in the address bar of a browser or by clicking on a link in the current page. The user’s transition between vertices in a finite graph according to probabilities determined by the weight of the graph’s edges is represented by a homogeneous Markov chain and is considered a process of random walk on the graph with the possibility of moving to a random vertex. Random Walk with Restarts was used to rank web resource pages for a particular user. Numerical analysis has been performed for an actual online store website. The initial data on user sessions are divided into training and test samples. According to the training sample, a weighted matrix of the probability of user transitions between web resource pages was constructed. To assess the quality of the built recommendation system, the accuracy, completeness, and Half-life Utility metrics were used. On the elements of the test sample, the accuracy value of 65‒68 % was obtained, the optimal number of elements in the recommendation list was determined. The influence of model parameters on the quality of recommendation systems was investigated.
36
Chen, Xiaoliang, Jianzhong Zheng, Yajun Du, and Mingwei Tang. "Intelligent Course Plan Recommendation for Higher Education: A Framework of Decision Tree." Discrete Dynamics in Nature and Society 2020 (January 23, 2020): 1–11. http://dx.doi.org/10.1155/2020/7140797.
Анотація:
The framework of outcomes-based education(OBE) has become a central issue for global university education, which is benefited to drive the education development by a series of assessments for historical teaching data, especially student course score, and employment information. The issue of how to timely update the talent training plans for computer major in a university has received considerable critical attention. It is becoming extremely difficult to ignore the requirement of fast shortened update cycle in IT area. One of the main obstacles is that the teaching inertia and the fixed awareness of a major training plan may delay the feedback of teaching problems. There is still a contradiction between the plan rationality and the real-time needs of contemporary IT enterprises. Hence, this paper puts forward a novel data-based framework to evaluate the relevance between the major courses, employment rate, and enterprise needs through the decision tree expression, thus providing reliable data support for systematic curriculum reform. On top of that, A recommendation algorithm is proposed to automatically generate the computer course group that satisfies the staff requirements of IT enterprises. Finally, teaching and employment data of Xihua University in China is applied as an example to undertake course optimization and recommendation. The consequences have an obvious positive effect on student employment and enterprise feedback.
37
Gede Dwidasmara, Ida Bagus, I. Gusti Ngurah Agung Widiaksa Putra, I. Made Widiartha, I. Wayan Santiyasa, Ida Bagus Made Mahendra, and Anak Agung Istri Ngurah Eka Karyawati. "SISTEM REKOMENDASI TEMPAT WISATA MENGGUNAKAN ALGORITMA CHEAPEST INSERTION HEURISTIC DAN NAÏVE BAYES." JELIKU (Jurnal Elektronik Ilmu Komputer Udayana) 10, no. 2 (January 4, 2022): 227. http://dx.doi.org/10.24843/jlk.2021.v10.i02.p05.
Анотація:
Bali is one of the best tourism areas in Indonesia, as evidenced in 2016 Bali received a number of awards on the TripAdvisor Travelers Choice Award in global and Asian scope. However, the Corona virus outbreak from 2019, caused the tourism sector in Bali to decline, thus a solution is needed to restore the tourism sector in Bali, where one solution is to increase cultural tourism to the maximum, as the main attraction of tourist destinations in Bali. Bali. So the author proposes a tourism recommendation system, which aims to recommend tourist attractions that are suitable for tourists, which in this recommendation system is also recommended cultural tourism destinations that are directly recommended by the community, and there is also a mapping of tourist attractions as part of a tourist recommendation system, mapping of tourist attractions public and cultural attractions. In this tourism recommendation system, using the Naïve Bayes Algorithm to recommend general tourist destinations based on the personal motivation of tourists, which is based on the attributes of age, gender, natural interest, artificial interest, cultural interest of tourists, using 200 training data consisting of 14 classes of tourist attractions. . In addition, this tourist recommendation system is equipped with recommendations for routing tourist attractions using the Cheapest Insertion Heuristic Algorithm, to arrange a list of tourist attractions.
Keywords: Recommendation System, Naïve Bayes Algorithm, Cheapest Insertion Heuristic Algorithm, Personal Motivation, Place Mapping.
38
Jin, Yingjie, and Chunyan Han. "A music recommendation algorithm based on clustering and latent factor model." MATEC Web of Conferences 309 (2020): 03009. http://dx.doi.org/10.1051/matecconf/202030903009.
Анотація:
The collaborative filtering recommendation algorithm is a technique for predicting items that a user may be interested in based on user history preferences. In the recommendation process of music data, it is often difficult to score music and the display score data for music is less, resulting in data sparseness. Meanwhile, implicit feedback data is more widely distributed than display score data, and relatively easy to collect, but implicit feedback data training efficiency is relatively low, usually lacking negative feedback. In order to effectively solve the above problems, we propose a music recommendation algorithm combining clustering and latent factor models. First, the user-music play record data is processed to generate a user-music matrix. The data is then analyzed using a latent factor probability model on the resulting matrix to obtain a user preference matrix U and a musical feature matrix V. On this basis, we use two K- means algorithms to perform user clustering and music clustering on two matrices. Finally, for the user preference matrix and the commodity feature matrix that complete the clustering, a user-based collaborative filtering algorithm is used for prediction. The experimental results show that the algorithm can reduce the running cost of large-scale data and improve the recommendation effect.
39
Sun, Zhidong, and Xueqing Li. "Construction of Live Broadcast Training Platform Based on “Cloud Computing” and “Big Data” and “Wireless Communication Technology”." Wireless Communications and Mobile Computing 2021 (September 14, 2021): 1–9. http://dx.doi.org/10.1155/2021/8971195.
Анотація:
With the rapid development of information technology, a scientific theory is brought by the rapid progress of science and technology. The advancement of science and technology of the impact on every field, changing the mode of transmission of information, the advent of big data for promotion and dissemination of resources played their part, let more and more people benefit. In the context of cloud computing, big data ushered in another upsurge of development and growth. Given this, the live broadcast training platform, which focuses on enterprise staff training and network education, arises at the right moment. People favor its convenience, real-time performance, and high efficiency. However, the low-value density of big data and cloud computing’s security problem has difficulties constructing a live broadcast training platform. In this paper, the live broadcast training platform’s structure is improved by constructing three modules: the live training module based on cloud computing, the user recommendation module based on big data, and the security policy guarantee module. In addition, to ensure that the trainees can receive training anytime and anywhere, this paper uses wireless communication technology to ensure the quality and speed of all users’ live video sources.
40
Chen, Shulong, and Yuxing Peng. "A Semi-Supervised Model for Top-N Recommendation." Symmetry 10, no. 10 (October 12, 2018): 492. http://dx.doi.org/10.3390/sym10100492.
Анотація:
Top-N recommendation is an important recommendation technique that delivers a ranked top-N item list to each user. Data sparsity is a great challenge for top-N recommendation. In order to tackle this problem, in this paper, we propose a semi-supervised model called Semi-BPR (Semi-Supervised Bayesian Personalized Ranking). Our approach is based on the assumption that, for a given model, users always prefer items ranked higher in the generated recommendation list. Therefore, we select a certain number of items ranked higher in the recommendation list to construct an intermediate set and optimize the metric Area Under the Curve (AUC). In addition, we treat the intermediate set as a teaching set and design a semi-supervised self-training model. We conduct a series of experiments on three popular datasets to compare the proposed approach with several state-of-the-art baselines. The experimental results demonstrate that our approach significantly outperforms the other methods for all evaluation metrics, especially for sparse datasets.
41
Poon, Paul Kwok Ming, Weiju Zhou, Dicken Cheong Chun Chan, Kin On Kwok, and Samuel Yeung Shan Wong. "Recommending COVID-19 Vaccines to Patients: Practice and Concerns of Frontline Family Doctors." Vaccines 9, no. 11 (November 13, 2021): 1319. http://dx.doi.org/10.3390/vaccines9111319.
Анотація:
Background: Recommendation from doctors is a well-recognized motivator toward vaccine uptake. Family doctors are in the prime position to advise the public on COVID-19 vaccination. We studied the practice and concerns of frontline family doctors concerning COVID-19 vaccination recommendations to patients. Methods: We conducted a cross-sectional online survey of all family doctors in the Hong Kong College of Family Physicians between June and July 2021. Their practice of making COVID-19 recommendation to patients was assessed. Based on the Health Belief Model, factors associated with doctors’ recommendation practices were explored and examined. Multivariate logistic regression models were used to investigate the factors, including COVID-19 vaccine attributes, associated with doctors’ practices in making recommendations. Their own vaccination status and psychological antecedents to vaccine hesitancy were measured. Results: A total of 312 family doctors responded (a 17.6% response rate). The proportion of doctors who had received COVID-19 vaccines was 90.1%. The proportion of doctors who would recommend all patients without contraindications for the vaccination was 64.4%. The proportion of doctors who would proactively discuss COVID-19 vaccines with patients was 52.9%. Multivariate logistic regression analysis showed that doctors’ own COVID-19 vaccination status was the strongest predictor of family doctors making a recommendation to patients (aOR 12.23 95% CI 3.45–43.33). Longer duration of practice, willingness to initiate the relevant discussion with patients and less worry about vaccine side effects on chronic illness patients were the other factors associated with making a COVID-19 vaccination recommendation. Conclusions: Family doctors should be encouraged to get vaccinated themselves and initiate discussions with patients about COVID-19 vaccines. Vaccine safety data on patients with chronic illness, training and guidelines for junior doctors may facilitate the COVID-19 vaccination recommendation practices of family doctors.
42
Zheng, Kai, Xianjun Yang, Yilei Wang, Yingjie Wu, and Xianghan Zheng. "Collaborative filtering recommendation algorithm based on variational inference." International Journal of Crowd Science 4, no. 1 (January 31, 2020): 31–44. http://dx.doi.org/10.1108/ijcs-10-2019-0030.
Анотація:
Purpose The purpose of this paper is to alleviate the problem of poor robustness and over-fitting caused by large-scale data in collaborative filtering recommendation algorithms. Design/methodology/approach Interpreting user behavior from the probabilistic perspective of hidden variables is helpful to improve robustness and over-fitting problems. Constructing a recommendation network by variational inference can effectively solve the complex distribution calculation in the probabilistic recommendation model. Based on the aforementioned analysis, this paper uses variational auto-encoder to construct a generating network, which can restore user-rating data to solve the problem of poor robustness and over-fitting caused by large-scale data. Meanwhile, for the existing KL-vanishing problem in the variational inference deep learning model, this paper optimizes the model by the KL annealing and Free Bits methods. Findings The effect of the basic model is considerably improved after using the KL annealing or Free Bits method to solve KL vanishing. The proposed models evidently perform worse than competitors on small data sets, such as MovieLens 1 M. By contrast, they have better effects on large data sets such as MovieLens 10 M and MovieLens 20 M. Originality/value This paper presents the usage of the variational inference model for collaborative filtering recommendation and introduces the KL annealing and Free Bits methods to improve the basic model effect. Because the variational inference training denotes the probability distribution of the hidden vector, the problem of poor robustness and overfitting is alleviated. When the amount of data is relatively large in the actual application scenario, the probability distribution of the fitted actual data can better represent the user and the item. Therefore, using variational inference for collaborative filtering recommendation is of practical value.
43
Guerin, Bernard, Daniel Palmer, and Rachel Brace. "Pre- and Post-session Assessments: Problems and Recommendations." Behaviour Change 18, no. 1 (April 1, 2001): 1–7. http://dx.doi.org/10.1375/bech.18.1.1.
Анотація:
AbstractWe discuss two common ways that assessment tests or probes have been given in relation to training during applied behavioural interventions when continuous assessment is not possible. With pre-session assessment, target behaviours are tested immediately before training sessions; with post-session assessment, target behaviours are tested immediately after training sessions. Although they are not optimal methods for testing performance, such assessments are not rare, and archival data on the incidence of these two methods for JABA publications in the period 1993 to 1996 show that about 25% of research articles use one or both of these methods. The distinction between pre- and post-session assessment is important because the two methods influence the interpretation of data, and the decision to move to the next phase of an intervention. This influence is illustrated with a comparison between two studies of correspondence training. We then discuss the different positive and negative aspects of each assessment type, and two new methodologies are developed that retain the positive aspects of each assessment type. The final recommendation when such designs are necessary is a new method in which a criterion of three correct post-session assessments is reached first, followed by three correct pre-session assessments, before moving into the next phase of intervention.
44
Sawant, Miss Pratiksha Yuvraj, and Mr Mangesh D. Salunke. "Personalized Mobile App Recommendation by Learning User’s Interest from Social Media." International Journal for Research in Applied Science and Engineering Technology 10, no. 4 (April 30, 2022): 448–50. http://dx.doi.org/10.22214/ijraset.2022.41246.
Анотація:
Abstract: In social media, user interests and knowledge are vital but often overlooked resources. There are a few ways to get a sense of what people are known for, such as Twitter lists and LinkedIn Skill Tags, but most people are untagged, so their interests and expertise are effectively hidden from applications like personalised recommendation and community detection and expert mining. We obtain personalised app recommendations by learning the interest's association between applications and tweets by introducing an unique generative model called IMCF+ to convert user interest from rich tweet information to sparse app usage. We analyse the performance of this technique predicts the top ten apps with an 82.5 percent success rate using only 10% training data. Furthermore, in the high sparsity situation and user cold-start scenario, this purpose technique outperforms the other six state-of-the-art algorithms by 4.7 percent and 10%, demonstrating the effectiveness of our technology. All of these findings show that our method can reliably extract user interests from tweets in order to aid in the solution of the personalised app recommendation problem. Keywords: Social Media, User Profile, deep learning, Privacy, matrix factorization,App recommendation.
45
Thalor, Meenakshi Anurag, and Shrishailapa Patil. "Incremental Learning on Non-stationary Data Stream using Ensemble Approach." International Journal of Electrical and Computer Engineering (IJECE) 6, no. 4 (August 1, 2016): 1811. http://dx.doi.org/10.11591/ijece.v6i4.10255.
Анотація:
<span lang="EN-US">Incremental Learning on non stationary distribution has been shown to be a very challenging problem in machine learning and data mining, because the joint probability distribution between the data and classes changes over time. Many real time problems suffer concept drift as they changes with time. For example, an advertisement recommendation system, in which customer’s behavior may change depending on the season of the year, on the inflation and on new products made available. An extra challenge arises when the classes to be learned are not represented equally in the training data i.e. classes are imbalanced, as most machine learning algorithms work well only when the training data is balanced. The objective of this paper is to develop an ensemble based classification algorithm for non-stationary data stream (ENSDS) with focus on two-class problems. In addition, we are presenting here an exhaustive comparison of purposed algorithms with state-of-the-art classification approaches using different evaluation measures like recall, f-measure and g-mean</span>
46
Thalor, Meenakshi Anurag, and Shrishailapa Patil. "Incremental Learning on Non-stationary Data Stream using Ensemble Approach." International Journal of Electrical and Computer Engineering (IJECE) 6, no. 4 (August 1, 2016): 1811. http://dx.doi.org/10.11591/ijece.v6i4.pp1811-1817.
Анотація:
<span lang="EN-US">Incremental Learning on non stationary distribution has been shown to be a very challenging problem in machine learning and data mining, because the joint probability distribution between the data and classes changes over time. Many real time problems suffer concept drift as they changes with time. For example, an advertisement recommendation system, in which customer’s behavior may change depending on the season of the year, on the inflation and on new products made available. An extra challenge arises when the classes to be learned are not represented equally in the training data i.e. classes are imbalanced, as most machine learning algorithms work well only when the training data is balanced. The objective of this paper is to develop an ensemble based classification algorithm for non-stationary data stream (ENSDS) with focus on two-class problems. In addition, we are presenting here an exhaustive comparison of purposed algorithms with state-of-the-art classification approaches using different evaluation measures like recall, f-measure and g-mean</span>
47
Feng, Qi, Zixuan Feng, and Xingren Su. "Design and Simulation of Human Resource Allocation Model Based on Double-Cycle Neural Network." Computational Intelligence and Neuroscience 2021 (October 25, 2021): 1–10. http://dx.doi.org/10.1155/2021/7149631.
Анотація:
The rationalization of human resource management is helpful for enterprises to efficiently train talents in the field, improve the management mode, and increase the overall resource utilization rate of enterprises. The current computational models applied in the field of human resources are usually based on statistical computation, which can no longer meet the processing needs of massive data and do not take into account the hidden characteristics of data, which can easily lead to the problem of information scarcity. The paper combines recurrent convolutional neural network and traditional human resource allocation algorithm and designs a double recurrent neural network job matching recommendation algorithm applicable to the human resource field, which can improve the traditional algorithm data training quality problem. In the experimental part of the algorithm, the arithmetic F1 value in the paper is 0.823, which is 20.1% and 7.4% higher than the other two algorithms, respectively, indicating that the algorithm can improve the hidden layer features of the data and then improve the training quality of the data and improve the job matching and recommendation accuracy.
48
Chen, Chong, Min Zhang, Yongfeng Zhang, Weizhi Ma, Yiqun Liu, and Shaoping Ma. "Efficient Heterogeneous Collaborative Filtering without Negative Sampling for Recommendation." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 01 (April 3, 2020): 19–26. http://dx.doi.org/10.1609/aaai.v34i01.5329.
Анотація:
Recent studies on recommendation have largely focused on exploring state-of-the-art neural networks to improve the expressiveness of models, while typically apply the Negative Sampling (NS) strategy for efficient learning. Despite effectiveness, two important issues have not been well-considered in existing methods: 1) NS suffers from dramatic fluctuation, making sampling-based methods difficult to achieve the optimal ranking performance in practical applications; 2) although heterogeneous feedback (e.g., view, click, and purchase) is widespread in many online systems, most existing methods leverage only one primary type of user feedback such as purchase. In this work, we propose a novel non-sampling transfer learning solution, named Efficient Heterogeneous Collaborative Filtering (EHCF) for Top-N recommendation. It can not only model fine-grained user-item relations, but also efficiently learn model parameters from the whole heterogeneous data (including all unlabeled data) with a rather low time complexity. Extensive experiments on three real-world datasets show that EHCF significantly outperforms state-of-the-art recommendation methods in both traditional (single-behavior) and heterogeneous scenarios. Moreover, EHCF shows significant improvements in training efficiency, making it more applicable to real-world large-scale systems. Our implementation has been released 1 to facilitate further developments on efficient whole-data based neural methods.
49
Wang, Lifu. "Collaborative Filtering Recommendation of Music MOOC Resources Based on Spark Architecture." Computational Intelligence and Neuroscience 2022 (March 7, 2022): 1–8. http://dx.doi.org/10.1155/2022/2117081.
Анотація:
With the rapid development of MOOC platforms, MOOC resources have grown substantially, causing the problem of information overload. It is difficult for users to select the courses they need from a large number of MOOC resources. It is necessary to help users select the right music courses and at the same time make the outstanding music courses stand out. Recommendation systems are considered a more efficient way to solve the information overload problem. To improve the accuracy of the recommendation results of music MOOC resources, a mixed collaborative filtering recommendation algorithm based on Spark architecture is proposed. First, the user data and item data are modeled and scored by the collaborative filtering algorithm, then the tree structure of the XGBoost model and the features of regular learning are combined to predict the scores, and then the two algorithms are mixed to solve the optimal objective function to obtain the set of candidate recommendation data. Then, the frog-jumping algorithm is used to train the weighting factors, and the optimal combination of weighting factors is used as the training result of the samples to realize the data analysis of the mixed collaborative filtering recommendation algorithm. The experimental results in the music MOOC resource show that the average absolute error and root mean square error of the proposed method are 0.406 and 1.117, respectively, when the sparsity is 30%, which are lower than those of other existing collaborative filtering recommendation methods, with higher accuracy and execution efficiency.
50
Abdurrahmansyah, Nur Ridho, and Muhammad Idham Ananta Timur. "Kelas Cendekia Versi Mobile yang Terintegrasi dengan Sistem Rekomendasi." IJEIS (Indonesian Journal of Electronics and Instrumentation Systems) 8, no. 2 (October 31, 2018): 167. http://dx.doi.org/10.22146/ijeis.34493.
Анотація:
Urgency usefulness of online learning system based on social constructivism which is the mobile virtual classroom learning philosophy is of concern, because the system is built on the pattern of reciprocity between users in order to produce the most quality materials see the absence of a system that provides online learning for it. Content of lecture materials that have been divided into certain categories are processed into virtual versions and delivered lightly. The recommendation system is designed to respond users who have rated it by providing good quality course material. Software is created with Unity Engine and incorporated the recommended system protocol with data stored in a scholarly research database. The recommendation system implemented is the items based collaborative filtering with the specification of training data used are 401 rating data, 51 records and 17 users. With sparsity data training amounted to 53.74%, tested the prediction accuracy resulted RMSE 0.91523 and the accuracy of 81.69%. The mobile version of virtual class that has been planted with recommendation system is tried and tested on several brands of android smartphone. Results obtained on the questionnaire resulted in a rating of 4,762 on performance and 4,572 against the intellectual class software interface. Whereas the level of user enthusiasm for the virtual class reaches 4,0588 on a scale of 1 to 5.