Abstract

Sleep analysis is considered as an important process in sleep disorders identification and highly dependent of sleep scoring. Sleep scoring is a complex, time consuming and exhausting task for experts. In this paper, we propose an automatic sleep scoring model based on unsupervised learning to avoid the pre-labeling task. Taking advantage of the distributed nature of Multi-agent Systems (MAS), we propose a classification model based on various physiological signals coming from heterogeneous sources. The proposed model offers a totally cooperative learning to automatically score sleep into several stages based on unlabeled data. The existing heterogeneous adaptive agents are dealing with a dynamic environment of various physiological signals. The efficiency of our approach was investigated using real data. Promising results were reached according to a comparative study carried out with the often used classification models. The generic proposed model could be used in fields where data are coming from heterogeneous sources and classification rules are not predefined.

Abstract

Cloud computing is an emerging technology that is largely adopted by the current computing industry. With the growing number of Cloud services, Cloud providers’ main focus is how to best offer efficient services (eg, SaaS, BPaaS, mobile services, etc) in order to hook the eventual customers. To meet this goal, services arrangement and placement in the cloud is becoming a serious problem because an optimal placement of these applications and their related data in accordance with the available resources can increase companies’ benefits. Since there is a widespread deployment of business processes in the cloud, the hereinafter conducted research works aim to enhance the business processes’ outsourcing by providing an optimized placement scheme that would attract cloud customers. In the light of these facts, the purpose of this paper is to deal with the BPaaS placement problem while optimizing both the total execution time and cloud resources’ usage. To do so, we first determine the redundant BPaaS fragments using a DNA Fragment Assembly technique. We apply a variant of the Genetic Algorithm to resolve it. Then, we propose a placement algorithm, which produces an optimized placement scheme on the basis of the determined fragments relations. We follow that by an implementation of the whole placement process and a set of experimental results that have shown the feasibility and efficiency of the proposed approach.

Abstract

Automatic sleep scoring has, recently, captured the attention of authors due to its importance in sleep abnormalities detection and treatments. The majority of the proposed works are based on supervised learning and considered mostly a single physiological signal as input. To avoid the exhausting pre-labeling task and to enhance the precision of the sleep staging process, we propose an unsupervised classification model for sleep stages identification based on a flexible architecture to handle different physiological signals. The efficiency of our approach was investigated using real data. Promising results were reached according to a comparative study carried out with the often used classification models.

Abstract

Feature selection and construction are important preprocessing techniques in data mining. They allow not only dimensionality reduction but also classification accuracy and efficiency improvement. While feature selection consists in selecting a subset of relevant feature from the original feature set, feature construction corresponds to the generation of new high-level features, called constructed features, where each one of them is a combination of a subset of original features. Based on these definitions, feature construction could be seen as a bi-level optimization problem where the feature subset should be defined first and then the corresponding (near) optimal combination of the selected features should be found. Motivated by this observation, we propose, in this paper, a bi-level evolutionary approach for feature construction. The basic idea of our algorithm, named bi-level feature construction genetic algorithm (BFC-GA), is to evolve an upper-level population for the task of feature selection, while optimizing the feature combinations at the lower level by evolving a follower population. It is worth noting that for each upper-level individual (feature subset), a whole lower-level population is optimized to find the corresponding (near) optimal feature combination (constructed feature). In this way, BFC-GA would be able to output a set of optimized constructed features that could be very informative to the considered classifier. A detailed experimental study has been conducted on a set of commonly used datasets with varying dimensions. The statistical analysis of the obtained results shows the competitiveness and the outperformance of our bi-level feature construction approach with respect to many state-of-the-art algorithms.

Abstract

Perception is presented as a predominant concern in the functioning of a driving system, where it is necessary to understand how the information, events, and actions of each influence the state of the environment and the objectives of the driver, immediately and in the near future. In this context, we present in this paper a driving model composed of five layers which ensure the autonomy and road safety of a driver agent, in particular, we are interested in this article in the concept of perception which is translated by the first three layers of our driving model, which are: visual perception, comprehension and projection, where the execution of these three layers is based on the driving behavior adopted by the driver agent, which is in our case the car-following driving behavior. Furthermore, we present in this paper two simulation scenarios, the first one is realized based on urban area conditions, and the second one is conducted by using Next Generation SIMulation (NGSIM) dataset of a highway in Los Angeles, California. In this context, the experimental results present the effectiveness of our driving model based on the imitation of human behavior and according to reducing the duration of perception.

Abstract

Feature selection and construction are important
pre-processing techniques in data mining. They allow not only
dimensionality reduction but also classification accuracy and
efficiency improvement. While feature selection consists in selecting a subset of relevant features from the original feature
set, feature construction corresponds to the generation of new
high-level features, called constructed features, where each one
of them is a combination of a subset of original features. However,
different features can have different abilities to distinguish
different classes. Therefore, it may be more difficult to construct
a better discriminating feature when combining features that are
relevant to different classes. Based on these definitions, feature
construction could be seen as a BLOP (Bi-Level Optimization
Problem) where the feature subset should be defined in the upper
level and the feature construction is applied in the lower level
by performing mutliple followers, each of which generates a set
class dependent constructed features. In this paper, we propose a
new bi-level evolutionary approach for feature construction called
BCDFC that constructs multiple features which focuses on distinguishing one class from other classes using Genetic Programming
(GP). A detailed experimental study has been conducted on six
high-dimensional datasets. The statistical analysis of the obtained
results shows the competitiveness and the outperformance of our
bi-level feature construction approach with respect to many stateof-art algorithms.

Abstract

Feature selection aims at selecting relevant features from the original
feature set, but these features do not have the same degree of importance. This can
be achieved by feature weighting, which is a method for quantifying the capability of features to discriminate instances from different classes. Multiple feature
selection methods have shown that different feature subset can reduce the data
dimensionality and maintain or even improve the classification accuracy. However, different features can have different abilities to distinguish instances of one
class from the other classes, which makes the feature selection process a difficult task by finding the optimal feature subset weighting vectors for each class.
Motivated by this observation, feature selection and feature weighting could be
seen as a BLOP (Bi-Level Optimization Problem) where the feature selection is
performed in the upper level, and the feature weighting is applied in the lower
level by performing mutliple followers, each of which generates a set of weighting vectors for each class. Only the optimal feature subset weighting vector is
retrieved for each class. In this paper, we propose a bi-level evolutionary approach for class-dependent feature selection and weighting using Genetic Algorithm (GA), called Bi-level Class-Dependent Weighted Feature Selection (BCDWFS). The basic idea of our BCDWFS is to exploit the bi-level model for performing upper level feature selection and lower level feature weighting with the
aim of finding the optimal weighting vectors of a subset of features for each class.
Our approach has been assessed on ten datasets and compared to three existing
approaches, using three different classifiers for accuracy evaluation. Experimental results show that our proposed algorithm gives competitive and better results
with respect to the state-of-the-art algorithms.

Abstract