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.
The task of visual relationship recognition (VRR) is recognizing multiple objects and their relationships in an image. A fundamental difficulty of this task is class-number scalability, since the number of possible relationships we need to consider causes combinatorial explosion. Another difficulty of this task is modeling how to avoid outputting semantically redundant relationships. To overcome these...
We treat failure prediction in a supervised learning framework using a convolutional neural network (CNN). Due to the nature of the problem, learning a CNN model on this kind of dataset is generally associated with three primary problems: 1) negative samples (indicating a healthy system) outnumber positives (indicating system failures) by a great margin; 2) implementation design often requires chopping...
Cyanobacteria bloom is a serious public health threat and a global challenge. Literature on the bloom prediction and forecasting has been accumulating and the emphasis appears to have been on the relation between the blooms and environmental factors, whilst the complexity of the bloom mechanism makes it difficult to reach adequate output of the models. Rapid development of next generation sequencing...
Given the heterogeneity of the data that can be extracted from the software development process, defect prediction techniques have focused on associating different sources of data with the introduction of faulty code, usually relying on handcrafted features. While these efforts have generated considerable progress over the years, little attention has been given to the fact that the performance of...
In this study, a deep denoising recurrent temporal restricted Boltzmann machine network is proposed for long-term prediction of time series. The network is a deep dynamic network model which is stacked by multiple denoising recurrent temporal restricted Boltzmann machines with strong modeling ability for complex high noise time series data. To better deal with high noise data, a random noise is added...
This paper introduces an ensemble model that solves the binary classification problem by incorporating the basic Logistic Regression with the two recent advanced paradigms: extreme gradient boosted decision trees (xgboost) and deep learning. To obtain the best result when integrating sub-models, we introduce a solution to split and select sets of features for the sub-model training. In addition to...
Size and complexity of contemporary High Performance Computing (HPC) systems increases permanently. While the reliability of a single component and compute node is high, the huge amount of components comprising these systems results in the fact that defects happen regularly. This drives the need to manage failure situations. Common issues are component failures or node soft lock-ups that typically...
Accurate automatic optimization heuristics are necessary for dealing with thecomplexity and diversity of modern hardware and software. Machine learning is aproven technique for learning such heuristics, but its success is bound by thequality of the features used. These features must be hand crafted by developersthrough a combination of expert domain knowledge and trial and error. This makesthe quality...
The process of identifying and assigning the relationship between two bodies of text is referred to as stance classification. Given a headline and the corresponding body they are compared and their relationship is classified into one of the following two classes — unrelated or related where related is further divided into agree, disagree and discuss. In this article, data is collected from news articles...
Platforms that are based on heterogeneous architectures require an intelligent resource manager. An intelligent resource manager should be able to accurately predict the future workload of the system at hand and take it into consideration. In this paper, we show that there exist patterns in the interarrival times of resource requests, and that these patterns can be used for modeling and prediction...
Mental illness is becoming a serious global health problem worldwide, with a growing number of patients suffering from depression, anxiety and other disorders. New solutions are needed to tackle this issue. The main goal of this research project is to develop prediction models to classify users with poor mental health from social network data and then implement an intervention model to help these...
High dropout rate of MOOC is criticized while a dramatically increasing number of learners are appealed to these online learning platforms. Various works have been done on analysis and prediction of dropout. Machine learning techniques are widely applied to this field. However, a single classifier may not always perform reliable for predictions. In this work, we study dropout prediction for MOOC....
Exploitable software vulnerabilities pose severe threats to its information security and privacy. Although a great amount of efforts have been dedicated to improving software security, research on quantifying software exploitability is still in its infancy. In this work, we propose ExploitMeter, a fuzzing-based framework of quantifying software exploitability that facilitates decision-making for software...
The amount of data being created and processed daily has grown exponentially with the introduction of the internet and social media. While the data are available, there is a struggle to determine how to effectively use and interpret the data. One of the most popular uses for the large quantities of data is to create models to predict the behavior or tendencies. One important application of prediction...
Manufacturing quality prediction performance is influenced by multi-parameter in manufacturing multi-stage processes. To solve this problem, a two-step feature learning approach (TFLR) is proposed in this paper. For the first step learning, the multi-parameter feature (high-dimensional information) is learned by a manifold learning algorithm (ML), which can enhance the representation of the multi-parameter...
Saliency detection aims to highlight the most relevant objects in an image. Methods using conventional models struggle whenever salient objects are pictured on top of a cluttered background while deep neural nets suffer from excess complexity and slow evaluation speeds. In this paper, we propose a simplified convolutional neural network which combines local and global information through a multi-resolution...
Credit scoring is an important process in every financial institution and bank. Its high accuracy in classifying customers helps decrease the credit risk and increase reliability and profit. In this paper, we propose a binary classification approach that can classify customers who apply for loans. A statistical technique called Stepwise Regression (SR) is used as a pre-process to select important...
This paper presents a deep learning based time series model to predict the traffic flow of transportation systems, DeepTFP, which exploits the effectiveness of time series function in analyzing sequence data and deep learning in extracting traffic flow features. Accurate and timely prediction on the future traffic flow is strongly needed by individual travelers, public transport, and transport planning...
Advanced Monitoring Systems are fundamental in advanced manufacturing for control, quality and maintenance purposes. Nowadays, with the increasing availability of data in production and equipment, the need for high-dimensional Anomaly Detection techniques is thriving; anomalies are data patterns that have different data characteristics from normal production instances and that may be associated with...
Nowadays, the ability to convert call records from voice to text makes it possible to apply text mining methods to extract information from calls. In this study, it is aimed not only to evaluate the sentiment (positive/negative) of the calls in general, but also to measure the customer satisfaction and representative's performance by using call record texts. New features have been extracted from texts...
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.