MLMI

As the complexity of processing issues increases, deep neural networks require more computing and storage resources. At the same time, the researchers found that the deep neural network contains a lot of redundancy, causing unnecessary waste, and the ...

A recommendation system predicts a top-N list of items that a target user might like by considering the user's previous rating history. In this paper, we solve the task of recommendation by developing a method that implements an NMF-based DCG ...

Spam detection task is of much more importance than earlier due to the increase in the use of messaging and mailing services. Efficient classification in such a variety of messages is a comparatively onerous task. There are a variety of machine learning ...

This paper presents Content based Image Retrieval with Relevance Feedback to retrieve relevant images based on an image query. Three main steps are proposed, first, obtain 2D feature representation of an image query and image database using the ...

Constructing predictive models with neural networks has always been the focus of research in chaotic time series prediction. Since Hinton proposed the concept of deep learning in 2006, the development of neural networks is getting faster and faster, and ...

In this paper, we present a new approach for increasing motivation, specially for students, by integrating new software and e-learning concepts. We focused on including the students and their needs and preferences within the software to be used. We ...

The Probabilistic Orienteering Problem (POP) is a variant of the orienteering problem where customers are available with a certain probability. In a previous work, we approximated its objective function value by using a Monte Carlo Sampling method. A ...

In order to solve the path planning problem of time-dependent road network(TDRN), an dynamic A* landmarks triangle algorithm(ALT) is proposed based on landmark-oriented technique and short-path tree(SPT). There are three main contributions: (1) ...

Web crawling is a process performed to collect web pages from the web, in order to be indexed and used for displaying the search results according to users' requirements. In addition, web crawlers must continually revisit web pages, to keep the search ...

Car drivers select their routes based on the information obtained about accidents and traffic congestion along the route. In recent years, nowcasting and forecasting of various traffic risk events is being performed by using diverse sensor data. However,...

Intelligent Transportation Systems (ITS) cover a variety of services related to topics such as traffic control and safe driving, among others. In the context of car insurance, a recent application for ITS is known as Usage-Based Insurance (UBI). UBI ...

Mobility and the integration of public transport are concepts that are consolidating more and more on a global scale and Latin America it is not the exception. The need to establish more inclusive and sustainable public transport programs has brought ...

As the major ocean transport tool of large intact cargo, the SSHTV (semi-submersible heavy transport vessel) has become more and more valued with the rapid advance of ocean engineering, polar exploration and global trade. Simultaneously, higher safety, ...

In order to accurately analyze the distribution characteristics of Air Traffic Management Technical Support System(ATMTSS), based on complex network theory, the weighted network model of air traffic management system was established. From the three ...