The estimation of the density of a population of behaviourally diverse agents based on limited sensor data is a challenging task. We employed different machine learning algorithms and assessed their suitability for so...
详细信息
ISBN:
(纸本)9783319729268;9783319729251
The estimation of the density of a population of behaviourally diverse agents based on limited sensor data is a challenging task. We employed different machine learning algorithms and assessed their suitability for solving the task of finding the approximate number of honeybees in a circular arena based on data from an autonomous stationary robot's short range proximity sensors that can only detect a small proportion of a group of bees at any given time. We investigate the application of different machine learning algorithms to classify datasets of pre-processed, highly variable sensor data. We present a new method for the estimation of the density of bees in an arena based on a set of rules generated by the algorithms and demonstrate that the algorithm can classify the density with good accuracy. This enabled us to create a robot society that is able to develop communication channels (heat, vibration and airflow stimuli) to an animal society (honeybees) on its own.
Leptospirosis is a potentially life-threatening disease primarily affecting low-income populations, with an estimated annual incidence of 1.03 million infections worldwide. This disease has symptoms often confused wit...
详细信息
Leptospirosis is a potentially life-threatening disease primarily affecting low-income populations, with an estimated annual incidence of 1.03 million infections worldwide. This disease has symptoms often confused with other febrile syndromes, such as dengue fever, influenza and viral hepatitis, often making diagnosis challenging. Improving the accuracy of early diagnosis of patients with leptospirosis will increase the speed of appropriate antibiotic treatment delivery, and both will improve clinical outcomes for this potentially fatal disease. The authors conducted an analysis of clinically and epidemiologically defined leptospirosis cases to predict disease using data mining classification algorithms. They conducted four sets of experiments to evaluate the performance of the algorithms, assessing their predictive accuracy of using different training and test datasets. The JRIP algorithm achieved 84% sensitivity using a dataset of only confirmed leptospirosis cases, and a specificity of 99% using a dataset of only confirmed dengue cases. Therefore, the approach successfully predicted leptospirosis cases, differentiated them from similar febrile illnesses, and may represent a new tool to assist health professionals, particularly in endemic areas for leptospirosis, accelerating targeted treatment and minimising disease exacerbation and mortality.
In this paper we introduce a method called CL.E.D.M. (classification through ELECTRE and datamining), that employs aspects of the methodological framework of the ELECTRE I outranking method, and aims at increasing th...
详细信息
In this paper we introduce a method called CL.E.D.M. (classification through ELECTRE and datamining), that employs aspects of the methodological framework of the ELECTRE I outranking method, and aims at increasing the accuracy of existing data mining classification algorithms. in particular, the method chooses the best decision rules extracted from the training process of the data mining classification algorithms, and then it assigns the classes that correspond to these rules, to the objects that must be classified. Three well known data mining classification algorithms are tested in five different widely used databases to verify the robustness of the proposed method. (C) 2008 Elsevier Ltd. All rights reserved.
暂无评论