Search

Summary: This paper presents a comprehensive three‐step approach (CNN‐JSO‐LSTM) for predictive modeling using a pandemic such as COVID‐19 as a test case. Initially, a Convolutional Neural Network (CNN) is employed to extract crucial features pertinent to the pandemic. Subsequently, the Jellyfish Search Optimizer (JSO) algorithm is applied for feature selection, identifying the most relevant factors. These chosen features are then inputted into a Long Short‐Term Memory (LSTM) network, responsible for classifying samples into "healthy" and "diseased" categories. Our method enhances LSTM performance using the Jellyfish Search optimizer, resulting in exceptional prediction accuracy. Our experiments achieved remarkable metrics, with an accuracy of 95.32%, high sensitivity (94.87%), and precision (94.28%), surpassing alternative methods. In conclusion, our study presents a promising and highly accurate approach for pandemic prediction, harnessing deep learning and swarm intelligence techniques. These findings suggest a potential for more effective pandemic management and intervention strategies. [ABSTRACT FROM AUTHOR]

Today, millions of active users spend a percentage of their time on location‐based social networks like Yelp and Gowalla and share their rich information. They can easily learn about their friends' behaviors and where they are visiting and be influenced by their style. As a result, the existence of personalized recommendations and the investigation of meaningful features of users and Point of Interests (POIs), given the challenges of rich contents and data sparsity, is a substantial task to accurately recommend the POIs and interests of users in location‐based social networks (LBSNs). This work proposes a novel pipeline of POI recommendations named DeePOF based on deep learning and the convolutional neural network. This approach only takes into consideration the influence of the most similar pattern of friendship instead of the friendship of all users. The mean‐shift clustering technique is used to detect similarity. The most similar friends' spatial and temporal features are fed into our deep CNN technique. The output of several proposed layers can predict latitude and longitude and the ID of subsequent appropriate places, and then using the friendship interval of a similar pattern, the lowest distance venues are chosen. This combination method is estimated on two popular datasets of LBSNs. Experimental results demonstrate that analyzing similar friendships could make recommendations more accurate and the suggested model for recommending a sequence of top‐k POIs outperforms state‐of‐the‐art approaches. [ABSTRACT FROM AUTHOR]

Matrix factorization (MF) is one of the most important regression analysis methods used in recommendation systems. Max margin matrix factorization (MMMF) is a variant of MF which transforms the regression analysis problem into a single multi‐class classification problem, and then learns a multi‐class max margin classifier to achieve to a better error rate. One drawback of multi‐class MMMF is its bias towards class with small sample size. Therefore, hierarchical MMMF (HMF) which uses some two‐class MMMF problems in a hierarchical manner for multi‐class classification was proposed. Each two‐class MMMF of HMF is learned on the basis of thresholded training data which is too imbalanced for some two‐class MMMFs. Meanwhile, all training data is used in each two‐class MMMF. In the test phase of HMF, an imbalanced tree is used to estimate rating. Each node of this tree is a learned two‐class MMMF. In this paper, we propose a balanced HMF, which constructs a balanced tree with minimum depth. Each node of this tree is a learned two‐class MMMF on the basis of a part of data which is selected such that to be more balanced than that of the traditional HMF. Moreover, each part of data in our proposed balanced HMF does not have overlap with all previous parts of data. Therefore, the overall training data used in each step of balanced HMF is smaller than that of in the traditional HMF. Experimental results on real datasets show that training time, test time and error rate of our proposed balanced HMF is better than those of the traditional HMF. [ABSTRACT FROM AUTHOR]

Nowadays, the recommendation is an important task in the decision-making process about the selection of items especially when item space is large, diverse, and constantly updating. As a challenge in the recent systems, the preference and interest of users change over time, and existing recommender systems do not evolve optimal clustering with sufficient accuracy over time. Moreover, the behavior history of the users is determined by their neighbours. The purpose of the time parameter for this system is to extend the time-based priority. This paper has been carried out a time-aware recommender systems based on memetic evolutionary clustering algorithm called RecMem for recommendations. In this system, clusters that evolve over time using the memetic evolutionary algorithm and extract the best clusters at every timestamp, and improve the memetic algorithm using the chaos criterion. The system provides appropriate suggestions to the user based on optimum clustering. The system uses optimal evolutionary clustering using item attributes for the cold-start item problem and demographic information for the cold start user problem. The results show that the proposed method has an accuracy of approximately 0.95, which is more effective than existing systems. [ABSTRACT FROM AUTHOR]

The number of metal-organic frameworks (MOF) as well as the number of applications of this material are growing rapidly. With the number of characterized compounds exceeding 100,000, manual sorting becomes impossible. At the same time, the increasing computer power and established use of automated machine learning approaches makes data science tools available, that provide an overview of the MOF chemical space and support the selection of suitable MOFs for a desired application. Among the different data science tools, graph theory approaches, where data generated from numerous real-world applications is represented as a graph (network) of interconnected objects, has been widely used in a variety of scientific fields such as social sciences, health informatics, biological sciences, agricultural sciences and economics. We describe the application of a particular graph theory approach known as social network analysis to MOF materials and highlight the importance of community (group) detection and graph node centrality. In this first application of the social network analysis approach to MOF chemical space, we created MOFSocialNet. This social network is based on the geometrical descriptors of MOFs available in the CoRE-MOFs database. MOFSocialNet can discover communities with similar MOFs structures and identify the most representative MOFs within a given community. In addition, analysis of MOFSocialNet using social network analysis methods can predict MOF properties more accurately than conventional ML tools. The latter advantage is demonstrated for the prediction of gas storage properties, the most important property of these porous reticular networks. [ABSTRACT FROM AUTHOR]

Based on twin support vector machines (TWSVM) model, the twin support vector clustering (TWSVC) is a planar clustering model that increases inter-cluster separation. Because the TWSVC is not a standard model for some variables, its solving algorithm consumes lots of time and does not always converge to the optimal solution. To solve the problem, this paper proposes a novel clustering model, denoted as TWSVC+, based on twin support vector machines (TWSVM). The TWSVC+ is convex and standard with respect to each variable. Therefore, it is possible to solve this model rapidly with an algorithm that converges to a global optimal solution relative to each variable. The author presented linear TWSVC+ and non-linear TWSVC+ for clustering linear separable clusters and linear inseparable clusters, respectively. Experimental results on real datasets of UCI repository show that the TWSVC+ was better than TWSVC and support vector clustering (SVC) in accuracy and training time. [ABSTRACT FROM AUTHOR]

Abstract Data mining and machine learning approaches can be used to predict breast cancer recurrence. However, real datasets often include missing values for various reasons. In this paper, a hybrid imputation method is proposed with respect to the dependency between the attributes and the type of incomplete attributes in order to especially improve the prediction of breast cancer recurrence. After splitting the dataset into two discrete and numerical subsets, first missing values of the discrete fields are imputed using Bayesian network. Then, using Tensor factorization, the integrated dataset, which comprises of the filled-subset of the previous stage and numerical missing values subset, is constructed so that both continuous missing values are imputed and the accuracy of imputation is enhanced. We evaluated the proposed method versus six imputation methods i.e. mean, Hot-deck, K-NN, Weighted K-NN, Tensor factorization and Bayesian network on three datasets and used three classifiers, namely decision tree, K-Nearest Neighbor and Support Vector Machine for recurrence prediction. Experimental results show that the proposed method has as average 0.26 prediction improvement. Also, the prediction performance of the proposed approach outperforms all other imputation-classifier pairs in terms of specificity, sensitivity and accuracy. [ABSTRACT FROM AUTHOR]

Social annotation systems (SAS) allow users to annotate different online resources with keywords (tags). These systems help users in finding, organizing, and retrieving online resources to significantly provide collaborative semantic data to be potentially applied by recommender systems. Previous studies on SAS had been worked on tag recommendation. Recently, SAS-based resource recommendation has received more attention by scholars. In the most of such systems, with respect to annotated tags, searched resources are recommended to user, and their recent behavior and click-through is not taken into account. In the current study, to be able to design and implement a more precise recommender system, because of previous users' tagging data and users' current click-through, it was attempted to work on the both resource (such as web pages, research papers, etc.) and tag recommendation problem. Moreover, by applying heat diffusion algorithm during the recommendation process, more diverse options would present to the user. After extracting data, such as users, tags, resources, and relations between them, the recommender system so called 'Swallow' creates a graph-based pattern from system log files. Eventually, following the active user path and observing heat conduction on the created pattern, user further goals are anticipated and recommended to him. Test results on SAS data set demonstrate that the proposed algorithm has improved the accuracy of former recommendation algorithms. [ABSTRACT FROM AUTHOR]

Social networks are generally sets of individuals or organizations that are connected with one or more links. Usually, social networks are presented by undirected graphs, where the set of vertices V and the set of edges E state the individuals and relation between them respectively. One of the most applicable problems in these networks is the centrality values allocation problem to the vertices and edges. Recently, a new evaluation criterion for the edge centrality so called centrality index of k paths has been proposed which is based on intranet issuing the messages along with random paths composed of k edges. From the other side, it has been vivid the importance of computing the edges centrality through these years. In this study, by referring to message propagation along random paths, a new diffusion model was reached by applying heat diffusion algorithm. This model was based such that the vertex on the way of heat diffusion of most of vertices could be considered as an important node and it could obtain centrality edges by scoring the edges on the heat diffusion path. The proposed technique was compared with centrality drawing method by means of random paths of length k and the results of analyzing the algorithm performance on online large social networks' data set show a remarkable efficacy of the proposed method to the mentioned method. Utilizing known large social networks in evaluation proves the efficiency of the proposed method for analyzing the large scale network. [ABSTRACT FROM AUTHOR]