This paper consists of two parts. In part one;we give a new reference definition for service, based on some fundamental concepts in economics such as homo economics and utility. Part two is primarily concerned with a ...
详细信息
This paper consists of two parts. In part one;we give a new reference definition for service, based on some fundamental concepts in economics such as homo economics and utility. Part two is primarily concerned with a service description framework, which includes the service provider, service receiver, service content, service medium and service environment, together with some examples.
Subspace-based analysis has increasingly become the preferred method for clustering high-dimensional data. A visually interactive exploration of subspaces and clusters is a cyclic process. Every meaningful discovery w...
详细信息
ISBN:
(纸本)9781509014521
Subspace-based analysis has increasingly become the preferred method for clustering high-dimensional data. A visually interactive exploration of subspaces and clusters is a cyclic process. Every meaningful discovery will motivate users to re-search subspaces that can provide improved clustering results and reveal the relationships among clusters that can hardly coexist in the original subspaces. However, the combination of dimensions from the original subspaces is not always effective in finding the expected subspaces. In this study, we present an approach that enables users to reconstruct new dimensions from the data projections of subspaces to preserve interesting cluster information. The reconstructed dimensions are included into an analytical workflow with the original dimensions to help users construct target-oriented subspaces which clearly display informative cluster structures. We also provide a visualization tool that assists users in the exploration of subspace clusters by utilizing dimension reconstruction. Several case studies on synthetic and real-world data sets have been performed to prove the effectiveness of our approach. Lastly, further evaluation of the approach has been conducted via expert reviews.
In recent years, ROS (Robot Operating System) packages have become increasingly popular as a type of software artifact that can be effectively reused in robotic software development. Indeed, finding suitable ROS packa...
详细信息
In recent years, ROS (Robot Operating System) packages have become increasingly popular as a type of software artifact that can be effectively reused in robotic software development. Indeed, finding suitable ROS packages that closely match the software’s functional requirements from the vast number of available packages is a nontrivial task using current search methods. The traditional search methods for ROS packages often involve inputting keywords related to robotic tasks into general-purpose search engines (e.g., Google) or code hosting platforms (e.g., Github) to obtain approximate results of all potentially suitable ROS packages. However, the accuracy of these search methods remains relatively low because the task-related keywords may not precisely match the functionalities offered by the ROS packages. To improve the search accuracy of ROS packages, this paper presents a novel semantic-based search approach that relies on the semantic-level ROS Package Knowledge Graph (RPKG) to automatically retrieve the most suitable ROS packages. Firstly, to construct the RPKG, we employ multi-dimensional feature extraction techniques to extract semantic concepts, including code file name, category, hardware device, characteristics, and function, from the dataset of ROS package text descriptions. The semantic features extracted from this process result in a substantial number of entities (32,294) and relationships (54,698). Subsequently, we create a robot domain-specific small corpus and further fine-tune a pre-trained language model, BERT-ROS, to generate embeddings that effectively represent the semantics of the extracted features. These embeddings play a crucial role in facilitating semantic-level understanding and comparisons during the ROS package search process within the RPKG. Secondly, we introduce a novel semantic matching-based search algorithm that incorporates the weighted similarities of multiple features from user search queries, which searches out more accurate
Modeling and predicting the performance of students in collaborative learning paradigms is an important task. Most of the research presented in literature regarding collaborative learning focuses on the discussion for...
详细信息
Hard hearing and deaf people are communicating with other people using the sign language. This is the only way of communication of such people to convey Since this is the only means by which these individuals can comm...
Hard hearing and deaf people are communicating with other people using the sign language. This is the only way of communication of such people to convey Since this is the only means by which these individuals can communicate, it is imperative that others be able to understand their language. Sign language recognition by computer begins with the acquisition of sign gestures and ends with recognition and conversion to text or voice. Static and dynamic are the two ways of sign gestures used. This study aims at focusing on the dynamic gesture recognition and the steps for recognizing sign language are discussed. The collected data are preprocessed and feature are extracted for classification. Finally the results are all investigated and developed for single user.
The authors have developed a system to automatically adjust the gray level of magnetic resonance (MR) images using a neural network. The gray level of an MR image is adjusted by setting the display window (gray-level)...
详细信息
The authors have developed a system to automatically adjust the gray level of magnetic resonance (MR) images using a neural network. The gray level of an MR image is adjusted by setting the display window (gray-level) width and level (WWL). The authors define an index, EW, for the evaluation of displayed image clarity, and they prove its effectiveness. They use a neural network to learn the relationship between image histogram features and displayed image clarity. The authors calculated image clarity using the NN, performed two-stage searching, and determined the best possible WWL. They also evaluated the WWL adjusted by the system using the clarity index, EW.< >
Feature modeling is an essential activity for modeling and managing the variability of a software product line. On the other hand, aspect-oriented programming provides effective means for modularizing feature implemen...
详细信息
Feature modeling is an essential activity for modeling and managing the variability of a software product line. On the other hand, aspect-oriented programming provides effective means for modularizing feature implementation. Although current AOP tools (e.g., AJDT) provide a mechanism for switching aspect modules on and off to configure a product, this becomes infeasible in the context of large-scale product lines with thousands of variations. In this paper, we describe how feature modeling can be integrated with aspect-oriented programming to perform automated product derivation efficiently and effectively in the context of large-scale product lines.
In the age estimation competition organized by ChaLearn, apparent ages of images are provided. Uncertainty of each apparent age is induced because each image is labeled by multiple individuals. Such uncertainty makes ...
详细信息
In the age estimation competition organized by ChaLearn, apparent ages of images are provided. Uncertainty of each apparent age is induced because each image is labeled by multiple individuals. Such uncertainty makes this age estimation task different from common chronological age estimation tasks. In this paper, we propose a method using deep CNN (Convolutional Neural Network) with distribution-based loss functions. Using distributions as the training tasks can exploit the uncertainty induced by manual labeling to learn a better model than using ages as the target. To the best of our knowledge, this is one of the first attempts to use the distribution as the target of deep learning. In our method, two kinds of deep CNN models are built with different architectures. After pre-training each deep CNN model with different datasets as one corresponding stream, the competition dataset is then used to fine-tune both deep CNN models. Moreover, we fuse the results of two streams as the final predicted ages. In the final testing dataset provided by competition, the age estimation performance of our method is 0.3057, which is significantly better than the human-level performance (0.34) provided by the competition organizers.
Ensuring safety in smart buildings is crucial due to the increasing prevalence of smoke and fire hazards in modern environments. This paper introduces a novel privacy-preserving FL approach based on a CNN1D for smoke ...
详细信息
暂无评论