177 research outputs found
An Authoring Tool of VIsion-based Somatosensory Action (ATVISA)
No full textHuman-Computer Interaction (HCI) in tradition is narrow defined the communication of information between human and machines. Because the limited of the HCI's speed and the natural level, it needs to use the medium form such as symbol instructions and buttons to express the intent of human. In recent year, the trend of HCI development will be focused on human, with directly computing, determining, and displaying technologies progress, and constantly innovation. Somatosensory equipment not only breaks through the limit of HCI but also the mode of interaction of traditional equipment. Somatosensory equipment can retrieve images through the infrared projector or visible camera, capture the human motion and action, and increase its interaction for natural and intuition. But unfortunately, most of systems are limited to a unique application for special areas, and only detected specific sequences of actions. Once changing the interaction of applications then users have to rewrite the action sequences recognition program to satisfy the somatosensory demands. System cannot be defined human action sequences flexible according the applications request of users, the production process is complex and the scope of application is narrow.
This thesis presents an Authoring Tool of Vision-based Somatosensory Action (ATVISA) to improve the drawback. Users can define the human action sequences by the graphical interface, customize the visual detection quickly and recognize correspond to the Somatosensory Action. Till the Somatosensory equipment detects the defined action sequences, triggering the correspond event and dealing with the event request. This thesis employs ATVISA applied to the action sequences and three rehabilitation projects, that with the flexibility and diversification. Users also can compile human action sequences with professional expertise to application to area of education, game, rehabilitation, and so on
CUHK electronic theses & dissertations collection
No full textChiang, Ka Chon.Thesis M.Phil. Chinese University of Hong Kong 2015.Includes bibliographical references (leaves 79-82).Abstracts also in Chinese.Title from PDF title page (viewed on 12, December, 2016)
An extended fuzzy-kNN approach to solving class-imbalanced problems
No full textIn this paper, for solving imbalanced classification problem, more attention is placed on data points in the boundary area between two classes. The fuzzy k-nearest neighbors algorithm, which has good performance in conventional classification problems, is adapted here to solve imbalanced classification problems, where G-mean accuracy is used to evaluate our proposal method and compare it with other approaches
A hybrid FAM–CART model and its application to medical data classification
No full textIn this paper, a hybrid model consisting of the fuzzy ARTMAP (FAM) neural network and the classification and regression tree (CART) is formulated. FAM is useful for tackling the stability–plasticity dilemma pertaining to data-based learning systems, while CART is useful for depicting its learned knowledge explicitly in a tree structure. By combining the benefits of both models, FAM–CART is capable of learning data samples stably and, at the same time, explaining its predictions with a set of decision rules. In other words, FAM–CART possesses two important properties of an intelligent system, i.e., learning in a stable manner (by overcoming the stability–plasticity dilemma) and extracting useful explanatory rules (by overcoming the opaqueness issue). To evaluate the usefulness of FAM–CART, six benchmark medical data sets from the UCI repository of machine learning and a real-world medical data classification problem are used for evaluation. For performance comparison, a number of performance metrics which include accuracy, specificity, sensitivity, and the area under the receiver operation characteristic curve are computed. The results are quantified with statistical indicators and compared with those reported in the literature. The outcomes positively indicate that FAM–CART is effective for undertaking data classification tasks. In addition to producing good results, it provides justifications of the predictions in the form of a decision tree so that domain users can easily understand the predictions, therefore making it a useful decision support tool
Novel Improvement Techniques To Fuzzy Artmap And Their Evolutionary Models For Pattern Classification
No full textThis thesis is focused on the development of evolutionary artificial neural network (EANN) models for pattern classification
LOW-TEMPERATURE GROWN SEMICONDUCTING GaAs EPILAYER ON Si BY MOLECULAR BEAM EPITAXY AND ITS APPLICATION TO LASER DIODES
No full textPh.DDOCTOR OF PHILOSOPH
A hybrid FAM-CART model for online data classification
No full textIn this paper, an online soft computing model based on an integration between the fuzzy ARTMAP (FAM) neural network and the classification and regression tree (CART) for undertaking data classification problems is presented. Online FAM network is useful for conducting incremental learning with data samples, whereas the CART model prevails in depicting the knowledge learned explicitly in a tree structure. Capitalizing on their respective advantages, the hybrid FAM‐CART model is capable of learning incrementally while explaining its predictions with knowledge elicited from data samples. To evaluate the usefulness of FAM‐CART, 2 sets of benchmark experiments with a total of 12 problems are used in both offline and online learning modes. The results are examined and compared with those published in the literature. The experimental outcome positively indicates that the online FAM‐CART model is useful for tackling data classification tasks. In addition, a decision tree is produced to allow users in understanding the predictions, which is an important property of the hybrid FAM‐CART model in supporting decision‐making tasks
A self-adaptive class-imbalance TSK neural network with applications to semiconductor defects detection
No full textThis paper develops a hybrid approach integrating an adaptive artificial neural network (ANN) and a fuzzy logic system for tackling class-imbalance problems. In particular, a supervised learning ANN based on Adaptive Resonance Theory (ART) is combined with a Tagaki–Sugeno–Kang-based fuzzy inference mechanism to learn and detect defects of a real large highly imbalanced dataset collected from a semiconductor company. A benchmark study is also conducted to compare the classification performance of the proposed method with other published methods in the literature. The real dataset collected from the semiconductor company intrinsically demonstrates class overlap and data shift in a highly imbalanced data environment. The generalization ability of the proposed method in detecting semiconductor defects is evaluated and compared with other existing methods, and the results are analyzed using statistical methods. The outcomes from the empirical studies positively indicate high potentials of the proposed approach in classifying the highly imbalanced dataset posing overlap class and data shift
Identifying and Removing Outlier Features Using Neighborhood Rough Set
No full textThe neighborhood rough set (NRS) is used to remove redundant features after identifying neighborhood relation among samples of features. In this study, a new NRS is proposed to determine and remove outlier features. An outlier score is calculated by measuring the neighborhood relation and non-neighborhood relation among samples with respect to a feature. Features that have an outlier score below the average outlier score are removed from the data set. In this research work, a support vector machine (SVM) and its extended version to reduce input features are used to evaluate the quality of the selected features from the proposed NRS. The experiment involves twelve real world data sets. The results show that the proposed method can reduce at least half of the features effectively from these data sets. Although the classification accuracy is slightly lower than both SVM-based solutions, the proposed NRS with SVM could significantly remove more number of input attributes and requires much shorter execution time
A parsimonious radial basis function-based neural network for data classification
No full textThe radial basis function neural network trained with a dynamic decay adjustment (known as RBFNDDA) algorithm exhibits a greedy insertion behavior as a result of recruiting many hidden nodes for encoding information during its training process. In this chapter, a new variant RBFNDDA is proposed to rectify such deficiency. Specifically, the hidden nodes of RBFNDDA are re-organized through the supervised Fuzzy ARTMAP (FAM) classifier, and the parameters of these nodes are adapted using the Harmonic Means (HM) algorithm. The performance of the proposed model is evaluated empirically using three benchmark data sets. The results indicate that the proposed model is able to produce a compact network structure and, at the same time, to provide high classification performances
- …
