Earticle

Delineating brain tumor boundaries from multi-modality magnetic resonance images (MRIs) is a crucial step in brain cancer surgical and treatment planning. In this paper, we propose a fully automatic technique for brain tumor segmentation from multi-modality human brain MRIs. We first use the intensities of different modalities in MRIs to represent the features of both normal and abnormal tissues. Then, the multiple classifier system (MCS) is applied to calculate the probabilities of brain tumor and normal brain tissue in the whole image. At last, the spatial-contextual information is proposed by constraining the classified neighbors to improve the classification accuracy. Our method was evaluated on 20 multi-modality patient datasets with competitive segmentation results.

Nowadays, activity recognition becomes a hot topic in context-aware computing. In activity recognition, machine learning techniques have been widely applied to learn the activity models from labeled activity samples. Most of the existing work uses only one learning method for activity learning and is focused on how to effectively utilize the labeled samples by refining the learning method. However, not much attention has been paid to the use of multiple classifiers for boosting the learning performance. In this paper, we use two methods to generate multiple classifiers. In the first method, the basic learning algorithms for each classifier are the same, while the training data is different (ASTD). In the second method, the basic learning algorithms for each classifier are different, while the training data is the same (ADTS). Experimental results indicate that ADTS can effectively improve activity recognition performance, while ASTD cannot achieve any improvement of the performance. We believe that the classifiers in ADTS are more diverse than those in ASTD.

Real-time energy monitoring systems is a demand-response system which is reported to be effective in saving energy up to 12%. Real-time energy monitoring system is commonly composed of smart-plugs which sense how much electrical power is consumed and IHD(In-Home Display device) which displays power consumption patterns. Even though the monitoring system is effective, users should themselves match which smart plus is connected to which appliance. In order to make the matching work to be automatic, the monitoring system need to have appliance identification algorithm, and some works have made under the name of NILM(Non-Intrusive Load Monitoring). This paper proposed an algorithm which utilizes multiple classifiers to improve accuracy of appliance identification. The algorithm proposes to understand each classifiers performance, that is, when a classifier make a result how much the result is reliable, and utilize it in choosing the final result among result candidates from many classifiers. By using the proposed algorithm this paper make 4.5% of improved accuracy with respect to using single best classifier, and 2.9% of improved accuracy with respect to other method using multiple classifiers, so called CDM(Commitee Decision Mechanism) method.

어려운 패턴인식 문제를 다루기 위하여, 다수 인식기를 사용하는 다수 인식기 시스템의 개발에 관한 연구가 활성화 되었으나, 다수 인식기 시스템의 효율적인 구축에 관한 체계적인 시도는 그리 많지 않았다. 다수 인식기 시스템의 효율성은 인식기 집합에 포함되는 인식기의 선택 방법과 선택된 인식기들의 결합 방법에 의해서 결정되는 시스템의 인식 성능으로 판단될 수 있다. 따라서, 이들 요인을 고려하여 효율성이 높은 다수 인식기 시스템을 구축하는 방법을 살펴보고자 한다.