Search | Engineering

Subscribe Submit

Home Journals Focus Achievement Fronts About Us 中文版

Resource Type

Journal Article 6

Year

2022 1

2018 2

2016 1

2015 1

2009 1

Keywords

Adaptive boosting 1

Association rules 1

Bag-of-words 1

Class frequency 1

Cross-domain 1

Deep learning 1

Dependency-LDA 1

Disparity estimation 1

Kansei words 1

Key words: Binocular endoscope 1

Labeled latent Dirichlet allocation (L-LDA) 1

Multi-label classification 1

Probabilistic latent semantic analysis 1

Scene category recognition 1

Sentiment classification 1

Supervised topic model 1

Three-dimensional measurement 1

anoxic sludge 1

database 1

design elements 1

open ︾

Search scope:

排序： Display mode:

Beyond bag of latent topics: spatial pyramid matching for scene category recognition

Fu-xiang LU,Jun HUANG

Frontiers of Information Technology & Electronic Engineering 2015, Volume 16, Issue 10, Pages 817-828 doi: 10.1631/FITEE.1500070

Abstract: the latent topics are obtained by using probabilistic latent semantic analysis (pLSA) based on the bag-of-wordsBy combining various interest point detectors and local region descriptors used in the bag-of-words model

Keywords： Scene category recognition Probabilistic latent semantic analysis Bag-of-words Adaptive boosting

HTML PDF Collect

Structure and formation of anoxic granular sludge —A string-bag hypothesis

Binbin WANG,Dangcong PENG,Xinyan ZHANG,Xiaochang WANG

Frontiers of Environmental Science & Engineering 2016, Volume 10, Issue 2, Pages 311-318 doi: 10.1007/s11783-014-0748-8

Abstract: A string-bag hypothesis was proposed to elucidate the structure and formation of the anoxic granular

Keywords： granulation sequencing batch reactor anoxic sludge scanning electron microscope filamentous bacteria

HTML PDF Collect

Review of research and development of computer-aided Kansei Engineering

Li LIN, Chengqi XUE

Frontiers of Mechanical Engineering 2009, Volume 4, Issue 2, Pages 125-128 doi: 10.1007/s11465-009-0023-z

Abstract: Kansei Engineering is an important research approach and has become the hotspot of research in design fields. The concept of Kansei Engineering is introduced based on the investigation of related literatures. The working process and the key technology of computer-aided Kansei Engineering systems are discussed. Finally, the development trend of Kansei Engineering is outlined according to the development of computer and networking technology.

Keywords： Kansei words design elements system database

HTML PDF Collect

Words alignment based on association rules for cross-domain sentiment classification None

Xi-bin JIA, Ya JIN, Ning LI, Xing SU, Barry CARDIFF, Bir BHANU

Frontiers of Information Technology & Electronic Engineering 2018, Volume 19, Issue 2, Pages 260-272 doi: 10.1631/FITEE.1601679

Abstract: One of the major reasons is that people often use different words to express the same sentiment in differentIn this paper, we propose a novel approach called words alignment based on association rules (WAAR) forsentiment classification, which can establish an indirect mapping relationship between domain-specific wordsin different domains by learning the strong association rules between domain-shared words and domain-specificwords in the same domain.

Keywords： Sentiment classification Cross-domain Association rules

HTML PDF Collect

A three-dimensional measurement method for binocular endoscopes based on deep learning Research Article

Hao YU, Changjiang ZHOU, Wei ZHANG, Liqiang WANG, Qing YANG, Bo YUAN,yuanbo@zju.edu.cn

Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 4, Pages 653-660 doi: 10.1631/FITEE.2000679

Abstract: In the practice of clinical endoscopy, the precise estimation of the lesion size is quite significant for diagnosis. In this paper, we propose a three-dimensional (3D) measurement method for binocular endoscopes based on , which can overcome the poor robustness of the traditional binocular matching algorithm in texture-less areas. A simulated binocular image dataset is created from the target 3D data obtained by a 3D scanner and the binocular camera is simulated by 3D rendering software to train a model for 3D measurement. The experimental results demonstrate that, compared with the traditional binocular matching algorithm, the proposed method improves the accuracy and disparity map generation speed by 48.9% and 90.5%, respectively. This can provide more accurate and reliable lesion size and improve the efficiency of endoscopic diagnosis.

Keywords： Key words: Binocular endoscope Three-dimensional measurement Deep learning Disparity estimation

HTML PDF Collect

Supervised topic models with weighted words: multi-label document classification None

Yue-peng ZOU, Ji-hong OUYANG, Xi-ming LI

Frontiers of Information Technology & Electronic Engineering 2018, Volume 19, Issue 4, Pages 513-523 doi: 10.1631/FITEE.1601668

Abstract: However, these models neglect the class frequency information of words (i.e., the number of classes whereTo address this, we propose a method, namely the class frequency weight (CF-weight), to weight words

Keywords： Supervised topic model Multi-label classification Class frequency Labeled latent Dirichlet allocation (L-LDA) Dependency-LDA