The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Recommender systems based on deep learning technology pay huge attention recently. In this paper, we propose a collaborative filtering based recommendation algorithm that utilizes the difference of similarities among users derived from different layers in stacked denoising autoencoders. Since different layers in a stacked autoencoder represent the relationships among items with rating at different...
Emergence of big data is directly proportional to the data shared in social media. Audio, video, text or the combination of all the above are the data shared in social media. Social networking is achieved by Social Networking Sites (SNS). In real world business, analysts use software tools to analyze product sales, promotion of brand and also tend to identify influential factors that impact their...
The need of machine learning in the defence planning and strategies is increasing day by day due to the increasing amount of breaches and decimations caused by terrorist forces. A myriad of military bases, temporary campaigns, base camps etc. are being targeted and attacked by several terrorist forces. The common problem in the warfare and tumultuous international borders is the frequent and violent...
The random forest algorithm is a new classification and prediction model algorithm. So far, there is not much research on the problem of unbalanced data for random forest classification, ditto, no direct and effective method. On the basis of feature selection algorithm based on correlation measure, the integration feature selection method was helpful to increase the selection probability of classification...
Each and every company are interested to know about the status of performance in their business. Bankruptcy prediction is an important issue and it plays a vital role in creating decisions in the field of corporate and financial organization. It has its influence on both economic as well as social factors, e.g., investors, creditors, government, managers, employees, etc. So, it is important and useful...
Because of the volatility of memory, nodes in in-memory storage system crashing down would lead to data lost. One solution to this problem is backing data up. However, if we backup data to a node which is about to fail down, the data should be recopied again. That would lead to a large amount of backup data, and in turn reduce the system reliability. We first establish a correlated failure model with...
In recent years, multi-label classification problem has become a controversial issue. In this kind of classification, each sample is associated with a set of class labels. Ensemble approaches are supervised learning algorithms in which an operator takes a number of learning algorithms, namely base-level algorithms and combines their outcomes to make an estimation. The simplest form of ensemble learning...
Stereotactic radiotherapy such as Cyberknife is one of the main methods of treatment for lung cancer, but tumor location change caused by human respiration has brought great difficulties to accurate radiation therapy. The main method to reduce the effect of respiratory motion in the process of radiotherapy is respiratory motion real-time tracking technology. The basis of real-time tracking is establishing...
A data-driven model predictive control (MPC) in modified partial least squares (PLS) framework is proposed in this paper after a brief summary of MPC strategy in PLS framework. A theoretical comparison between data-driven MPC strategy in these two framework is presented, which demonstrates that MPC in modified PLS framework benefits in both computation complexity and robustness. The feature of modeling...
Multi-label classification has attracted many attentions in various fields, such as text categorization and semantic image annotation. Aiming to classify an instance into multiple labels, various multi-label classification methods have been proposed. However, the existing methods typically build models in the identical feature (sub)space for all labels, possibly inconsistent with real-world problems...
Sampling through crawling is an important research topic in social network analysis. However there is very little existing work on sampling through crawling in directed networks. In this paper we present a new method of sampling a directed network, with the objective of maximizing the node coverage. Our proposed method, Predicted Max Degree (PMD) Sampling, works by predicting which k open nodes are...
Multi-label data with high dimensionality arise frequently in data mining and machine learning. It is not only time consuming but also computationally unreliable when we use high-dimensional data directly. Supervised dimensionality reduction approaches are based on the assumption that there are large amounts of labeled data. It is infeasible to label a large number of training samples in practice...
In big cities, taxi service is imbalanced. In some areas, passengers wait too long for a taxi, while in others, many taxis roam without passengers. Knowledge of where a taxi will become available can help us solve the taxi demand imbalance problem. In this paper, we employ a holistic approach to predict taxi demand at high spatial resolution. We showcase our techniques using two real-world data sets,...
In this paper, we propose algorithms for biomolecular docking sites selection problem by various machine learning approaches with selective features reduction. The proposed method can reduce the number of various amino acid features before constructing machine learning prediction models. Given frame boxes with features, the proposed method analyzes the important features by correlation coefficients...
Weighted signed networks (WSNs) are networks in which edges are labeled with positive and negative weights. WSNs can capture like/dislike, trust/distrust, and other social relationships between people. In this paper, we consider the problem of predicting the weights of edges in such networks. We propose two novel measures of node behavior: the goodness of a node intuitively captures how much this...
Bursty behavior normally indicates that the workload generated by data accesses happens in short time, uneven spurts. In order to handle the bursts, the physical resources of IT devices have to be configured to offer capability which goes far beyond the average resource utilization, thus satisfying the performance. However, this kind of fat provisioning incurs wasting resources when the system does...
Essential proteins play a crucial role in the survival and development process of life, as they provide all available nutrients to maintain life. Therefore, many researchers pay attention to the identification of essential proteins. As experiments methods are usually costly and time-consuming, more and more computational algorithms have been developed to discover essential proteins based on biological...
Being able to automatically predict digital picture quality, as perceived by human observers, has become important in many applications where humans are the ultimate consumers of displayed visual information. Standard dynamic range (SDR) images provide 8 bits/color/pixel. High dynamic range (HDR) images which are usually created from multiple exposures of the same scene, can provide 16 or 32 bits/color/pixel,...
This paper presents a novel patient-specific algorithm for prediction of seizures in epileptic patients. Spectral power features, including relative spectral powers and spectral power ratios, and cross correlation coefficients between all pairs of electrodes, are extracted as two independent feature sets. Both feature sets are selected independently in a patient-specific manner by classification and...
The following work is an application proposal based on machine learning algorithms for a possible solution for the public safety problem in a South American city. The aim of this application is to reduce the threat risk of the physical integrity of pedestrians by geolocating, in real-time, safer places to walk. In this context for a city, San Isidro, a business district of Lima, has been established...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.