Search

Machine learning (ML) is a useful technique for improving building operations. However, if data can only be obtained from a target building, the data shortage will limit the use of general ML models. To overcome this issue, simplified targets and limited numbers of feature variables are required. In building engineering, building physics can be used to promote ML implementations. In this paper, a case study targeting the operation of engineered natural ventilation is performed based on energy simulations. The target issue is simplified to select the preferable opening pattern, full or half open, throughout the day. Two models using two or three feature variable types are compared. The ML method can effectively predict the correct operation scheme, even in the first year of use. The correct answer rate in the case of three variable types increases from 83% to 95% in the second year, although no significant improvement is observed in the case with two variable types. The results imply the strategy of creating a simplified model first and improving the model following data acquisition works for ML model implementation in building operations.

Recommender systems search the underlying preferences of users according to their historical ratings and recommend a list of items that may be of interest to them. Rating information plays an important role in revealing the true tastes of users. However, previous research indicates that natural noises may exist in the historical ratings and mislead the recommendation results. To deal with natural noises, different methods have been proposed, such as directly removing noises, correcting noise by re-predicting, or using additional information. However, these methods introduce some new problems, such as data sparsity and introducing new sources of noise. To address the problems, we present a new approach to managing natural noises in recommendation systems. Firstly, we provide the detection criteria for natural noises based on the classifications of users and items. After the noises are detected, we correct them with threshold values weighted by probabilities. Experimental results show that the proposed method can effectively correct natural noise and greatly improve the quality of recommendations.

Collaborative filtering recommendation systems are facing the data sparsity problem associated with interaction data, and social recommendations introduce user social information to alleviate this problem. Existing social recommendation methods cannot express the user interaction interest and social influence deeply, which limits the recommendation performance of the system. To address this problem, in this paper we propose a graph neural network social recommendation algorithm integrating multi-head attention mechanism. First, based on the user-item interaction graph and social network graph, the graph neural network is used to learn the high-order relationship between users and items and deeply extract the latent features of users and items. In the process of learning user embedding vector representation based on the social network graph, the multi-head attention mechanism is introduced to increase the importance of friends with high influence. Then, we make rating predictions for the target users according to the learned user embedding vector representation and item embedding vector. The experimental results on the Epinions dataset show that the proposed method outperforms the existing methods in terms of both Recall and Normalized Discounted Cumulative Gain.

Sentiment Analysis is a technique that is being used abundantly nowadays for customer reviews analysis, popularity analysis of electoral candidates, hate speech detection and similar applications. Sentiment analysis on tweets encounters challenges such as highly skewed classes, high dimensional feature vectors and highly sparse data. In this study, we have analyzed the improvement achieved by successively addressing these problems in order to determine their severity for sentiment analysis of tweets. Firstly, we prepared a comprehensive data set consisting of Urdu Tweets for sentiment analysis-based hate speech detection. To improve the performance of the sentiment classifier, we employed dynamic stop words filtering, Variable Global Feature Selection Scheme (VGFSS) and Synthetic Minority Optimization Technique (SMOTE) to handle the sparsity, dimensionality and class imbalance problems respectively. We used two machine learning algorithms i.e., Support Vector Machines (SVM) and Multinomial Naïve Bayes’ (MNB) for investigating performance in our experiments. Our results show that addressing class skew along with alleviating the high dimensionality problem brings about the maximum improvement in the overall performance of the sentiment analysis-based hate speech detection.

Currently, collaborative filtering technology has been widely used in personalized recommender systems. The problem of data sparsity is a severe challenge faced by traditional collaborative filtering methods based on matrix factorization techniques. A lot of improved collaborative filtering methods have been proposed to alleviate the data sparsity problem; However, due to the sparsity of the user rating matrix, the latent factor learned by these improved methods may be not efficient. In this paper, we propose a novel recommendation algorithm named SSAERec by integrating stacked sparse auto-encoder into matrix factorization for rating prediction, which can learn effective representation from user-item rating matrix. Extensive experiments on three real-world datasets demonstrate the proposed method outperforms other baselines in the rating prediction task.

In the current era of online information overload, recommendation systems are very useful for helping users locate content that may be of interest to them. A personalized recommendation system presents content based on information such as a user’s browsing history and the videos watched. However, information filtering-based recommendation systems are vulnerable to data sparsity and cold-start problems. Additionally, existing recommendation systems suffer from the large overhead incurred in learning regression models used for preference prediction or in selecting groups of similar users. In this study, we propose a preference-tree-based real-time recommendation system that uses various tree models to predict user preferences with a fast runtime. The proposed system predicts preferences based on two balance constants and one similarity threshold to recommend content with a high accuracy while balancing generalized and personalized preferences. The results of comparative experiments and ablation studies confirm that the proposed system can accurately recommend content to users. Specifically, we confirmed that the accuracy and novelty of the recommended content were, respectively, improved by 12.1% and 27.2% compared to existing systems. Furthermore, we verified that the proposed system satisfies real-time requirements and mitigates both cold-start and overfitting problems.

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

Estimating the global burden of antimicrobial resistance (AMR) is laden with challenges, but undertaking this enormous task is crucial for steadfast decisions on resource allocation from a national, regional, and global perspective, as well as for research prioritisation and intervention evaluation. In the global burden of antimicrobial resistance research endeavor there are plenty issues with data gaps and data sparsity, while sepsis and infectious syndrome analytical steps rely on data with incomplete geographical coverage. Data completeness and fidelity are particularly scarce in low-income and middle-income countries (LMICs). Akin to missing essential pieces of a global puzzle, we recognise the importance of ongoing studies to bring estimates like ours closer to the truth, and we call for and enthusiastically welcome any data sources that can improve the estimation process.

Personalized location recommendations aim to recommend places that users want to visit, which can save their decision-making time in daily life. However, the recommending task faces a serious data sparsity problem because users have only visited a small part of total places in a city. This problem directly leads to the difficulty in learning latent representations of users and locations. In order to tackle the data sparsity problem and make better recommendations, users’ app usage records in different locations are introduced to compensated for both users’ interests and locations’ characteristics in this paper. An attributed graph-based representation model is proposed to dig out user–app–location associations with high-order features aggregated. Extensive experiments prove that better representations of users and locations are obtained by our proposed model, thus it greatly improves location recommendation performances compared with the state-of-art methods. For example, our model achieves 13.20%, 10.1%, and 9.44% higher performance than the state-of-art (SOTA) models in Top3Hitrate, Top3Accuracy, and nDCG3, respectively, in the Telecom dataset. In the TalkingData dataset, our model achieves 9.34%, 13.35%, and 8.56% better performance than the SOTA models in Top2Hitrate, Top2Accuracy, and nDCG2, respectively. Furthermore, numerical results demonstrate that our model can effectively alleviate the data sparsity problem in recommendation systems.

With the transition to neural architectures, machine translation achieves very good quality for several resource-rich languages. However, the results are still much worse for languages with complex morphology, especially if they are low-resource languages. This paper reports the results of a systematic analysis of adding morphological information into neural machine translation system training. Translation systems presented and compared in this research exploit morphological information from corpora in different formats. Some formats join semantic and grammatical information and others separate these two types of information. Semantic information is modeled using lemmas and grammatical information using Morpho-Syntactic Description (MSD) tags. Experiments were performed on corpora of different sizes for the English–Slovene language pair. The conclusions were drawn for a domain-specific translation system and for a translation system for the general domain. With MSD tags, we improved the performance by up to 1.40 and 1.68 BLEU points in the two translation directions. We found that systems with training corpora in different formats improve the performance differently depending on the translation direction and corpora size.

We address the problem of recommending relevant items to a user in order to "complete" a partial set of items already known. We consider the two scenarios of citation and subject label recommendation, which resemble different semantics of item co-occurrence: relatedness for co-citations and diversity for subject labels. We assess the influence of the completeness of an already known partial item set on the recommender performance. We also investigate data sparsity through a pruning parameter and the influence of using additional metadata. As recommender models, we focus on different autoencoders, which are particularly suited for reconstructing missing items in a set. We extend autoencoders to exploit a multi-modal input of text and structured data. Our experiments on six real-world datasets show that supplying the partial item set as input is helpful when item co-occurrence resembles relatedness, while metadata are effective when co-occurrence implies diversity. This outcome means that the semantics of item co-occurrence is an important factor. The simple item co-occurrence model is a strong baseline for citation recommendation. However, autoencoders have the advantage to enable exploiting additional metadata besides the partial item set as input and achieve comparable performance. For the subject label recommendation task, the title is the most important attribute. Adding more input modalities sometimes even harms the result. In conclusion, it is crucial to consider the semantics of the item co-occurrence for the choice of an appropriate recommendation model and carefully decide which metadata to exploit., Comment: arXiv admin note: text overlap with arXiv:1907.12366

Recommender systems have been widely used by large companies in the e-commerce segment as aid tools in the search for relevant contents according to the user’s particular preferences. A wide variety of algorithms have been proposed in the literature aiming at improving the process of generating recom- mendations; in particular, a collaborative, diffusion-based hybrid algorithm has been proposed in the lit- erature to solve the problem of sparse data, which affects the quality of recommendations. This algorithm was the basis for several others that effectively solved the sparse data problem. However, this family of algorithms does not differentiate users according to their profiles. In this paper, a new algorithm is pro- posed for learning the user profile and, consequently, generating personalised recommendations through diffusion, combining novelty with the popularity of items. Experiments performed in well-known datasets show that the results of the proposed algorithm outperform those from both diffusion-based hybrid al- gorithm and traditional collaborative filtering algorithm, in the same settings. 146 113149

Collaborative filtering recommender systems traditionally recommend products to users solely based on the given user-item rating matrix. Two main issues, data sparsity and scalability, have long been concerns. In our previous work, an approach was proposed to address the scalability issue by clustering the products using the content of the user-item rating matrix. However, it still suffers from these concerns. In this paper, we improve the approach by employing user comments to address the issues of data sparsity and scalability. Word2Vec is applied to produce item vectors, one item vector for each product, from the comments made by users on their previously bought goods. Through the user-item rating matrix, the user vectors of all the customers are produced. By clustering, products and users are partitioned into item groups and user groups, respectively. Based on these groups, recommendations to a user can be made. Experimental results show that both the inaccuracy caused by a sparse user-item rating matrix and the inefficiency due to an enormous amount of data can be much alleviated.

Medical text categorization is a specific area of text categorization. Classification for medical texts is considered a special case of text classification. Medical text includes medical records and medical literature, both of which are important clinical information resources. However, medical text contains complex medical vocabularies, medical measures, which has problems with high-dimensionality and data sparsity, so text classification in the medical domain is more challenging than those in other general domains. In order to solve these problems, this paper proposes a unified neural network method. In the sentence representation, the convolutional layer extracts features from the sentence and a bidirectional gated recurrent unit (BIGRU) is used to access both the preceding and succeeding sentence features. An attention mechanism is employed to obtain the sentence representation with the important word weights. In the document representation, the method uses the BIGRU to encode the sentences, which is obtained in sentence representation and then decode it through the attention mechanism to get the document representation with important sentence weights. Finally, a category of medical text is obtained through a classifier. Experimental verifications are conducted on four medical text datasets, including two medical record datasets and two medical literature datasets. The results clearly show that our method is effective.

Recommendation systems have a wide application in e-business and have been successful in guiding users in their online purchases. The use of data mining techniques, to aid recommendation systems in their goal to learn the correct user profiles, is an active area of research. In most recent works, recommendations are obtained by applying a supervised learning method, notably the k-nearest neighbour (k-NN) algorithm. However, classification algorithms require a class label, and in many applications, such labels are not available, leading to extensive domain expert labelling. In addition, recommendation systems suffer from a data sparsity problem, i.e. the number of items purchased by a customer is typically a small subset of all ĉvailable products. One solution to overcome the labelling and data sparsity problems is to apply cluster analysis techniques prior to classification. Cluster analysis allows one to learn the natural groupings, i.e. similar customer profiles. In this paper, we s tudy the value of applying cluster analysis techniques to customer ratings prior to applying classification models. Our HCC-Learn framework combines content-based analysis in the cluster analysis stage, with collaborative filtering in the recommending stage. Our experimental results show the value of combining cluster analysis and classification against two real-world data sets., 10th International Conference on Knowledge Discovery and Information Retrieval, September 18-20, 2018, Seville, Spain

In grocery stores, large-scale transaction data with identification, such as point of sales (POS) data, is being accumulated as a result of the introduction of frequent shopper programs. We propose two recommendation systems based on transaction data of a grocery store. In recommending product items in grocery stores, data sparsity is a problem. This is because individual customers only purchase very few of the total number of product items a store sells. We evaluate various recommendation methods including SVD-type recommendation based on real POS data and summarize methods suitable for the proposed recommendation systems.

ACM-ICPSACM International Conference Proceeding Series In this work, we attempt to ameliorate the impact of data sparsity in the context of session-based recommendation. Specifically, we seek to devise a machine learning mechanism capable of extracting subtle and complex underlying temporal dynamics in the observed session data, so as to inform the recommendation algorithm. To this end, we improve upon systems that utilize deep learning techniques with recurrently connected units; we do so by adopting concepts from the field of Bayesian statistics, namely variational inference. Our proposed approach consists in treating the network recurrent units as stochastic latent variables with a prior distribution imposed over them. On this basis, we proceed to infer corresponding posteriors; these can be used for prediction and recommendation generation, in a way that accounts for the uncertainty in the available sparse training data. To allow for our approach to easily scale to large real-world datasets, we perform inference under an approximate amortized variational inference (AVI) setup, whereby the learned posteriors are parameterized via (conventional) neural networks. We perform an extensive experimental evaluation of our approach using challenging benchmark datasets, and illustrate its superiority over existing state-of-the-art techniques.

Lexical-semantic relationships between words are key information for many NLP tasks, which require this knowledge in the form of lexical resources. This thesis addresses the acquisition of lexical-semantic relation instances. State of the art systems rely on word pair representations based on patterns of contexts where two related words co-occur to detect their relation. This approach is hindered by data sparsity: even when mining very large corpora, not every semantically related word pair co-occurs or not frequently enough. In this work, we investigate novel representations to predict if two words hold a lexical-semantic relation. Our intuition was that these representations should contain information about word co-occurrences combined with information about the meaning of words involved in the relation. These two sources of information have to be the basis of a generalization strategy to be able to provide information even for words that do not co-occur., Les relacions lexicosemàntiques entre paraules són una informació clau per a moltes tasques del PLN, què requereixen aquest coneixement en forma de recursos lingüístics. Aquesta tesi tracta l’adquisició d'instàncies lexicosemàntiques. Els sistemes actuals utilitzen representacions basades en patrons dels contextos en què dues paraules coocorren per detectar la relació que s'hi estableix. Aquest enfocament s'enfronta a problemes de falta d’informació: fins i tot en el cas de treballar amb corpus de grans dimensions, hi haurà parells de paraules relacionades que no coocorreran, o no ho faran amb la freqüència necessària. Per tant, el nostre objectiu principal ha estat proposar noves representacions per predir si dues paraules estableixen una relació lexicosemàntica. La intuïció era que aquestes representacions noves havien de contenir informació sobre patrons dels contextos, combinada amb informació sobre el significat de les paraules implicades en la relació. Aquestes dues fonts d'informació havien de ser la base d'una estratègia de generalització que oferís informació fins i tot quan les dues paraules no coocorrien.

With the rapid development of cyber-physical systems (CPS), building cyber-physical systems with high quality of service (QoS) has become an urgent requirement in both academia and industry. During the procedure of building Cyber-physical systems, it has been found that a large number of functionally equivalent services exist, so it becomes an urgent task to recommend suitable services from the large number of services available in CPS. However, since it is time-consuming, and even impractical, for a single user to invoke all of the services in CPS to experience their QoS, a robust QoS prediction method is needed to predict unknown QoS values. A commonly used method in QoS prediction is collaborative filtering, however, it is hard to deal with the data sparsity and cold start problem, and meanwhile most of the existing methods ignore the data credibility issue. Thence, in order to solve both of these challenging problems, in this paper, we design a framework of QoS prediction for CPS services, and propose a personalized QoS prediction approach based on reputation and location-aware collaborative filtering. Our approach first calculates the reputation of users by using the Dirichlet probability distribution, so as to identify untrusted users and process their unreliable data, and then it digs out the geographic neighborhood in three levels to improve the similarity calculation of users and services. Finally, the data from geographical neighbors of users and services are fused to predict the unknown QoS values. The experiments using real datasets show that our proposed approach outperforms other existing methods in terms of accuracy, efficiency, and robustness.

Trabajo presentado a la conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL-HLT), celebrada en San Diego, California (US) del 12 al 17 de junio de 2016., We address the task of annotating images with semantic tuples. Solving this problem requires an algorithm able to deal with hundreds of classes for each argument of the tuple. In such contexts, data sparsity becomes a key challenge. We propose handling this sparsity by incorporating feature representations of both the inputs (images) and outputs (argument classes) into a factorized log-linear model., This work was partly funded by the Spanish MINECO project RobInstruct TIN2014-58178-R and by the ERA-net CHISTERA projects VISEN PCIN- 2013-047 and I-DRESS PCIN-2015-147.

In this dissertation we developed theoretical models to analyse Gaussian and multinomial distributions. The analysis is focused on classification in high dimensional feature spaces and provides a basis for dealing with issues such as data sparsity and feature selection (for Gaussian and multinomial distributions, two frequently used models for high dimensional applications). A Naïve Bayesian philosophy is followed to deal with issues associated with the curse of dimensionality. The core treatment on Gaussian and multinomial models consists of finding analytical expressions for classification error performances. Exact analytical expressions were found for calculating error rates of binary class systems with Gaussian features of arbitrary dimensionality and using any type of quadratic decision boundary (except for degenerate paraboloidal boundaries). Similarly, computationally inexpensive (and approximate) analytical error rate expressions were derived for classifiers with multinomial models. Additional issues with regards to the curse of dimensionality that are specific to multinomial models (feature sparsity) were dealt with and tested on a text-based language identification problem for all eleven official languages of South Africa. Thesis (M.Ing. (Computer Engineering))--North-West University, Potchefstroom Campus, 2009.