QingHui Wang, Zhong-Dong Huang, JingRong Li and Jia-Wu Liu
Realistic force sensation can help operators better feel and manipulate parts for virtual assembly (VA). Moreover, for VA of mechanical parts, it is necessary to consider their…
Abstract
Purpose
Realistic force sensation can help operators better feel and manipulate parts for virtual assembly (VA). Moreover, for VA of mechanical parts, it is necessary to consider their tolerance levels so as to apply proper assembly forces. Out of the three common assembly fit types, the type of clearance fit is the focus of virtual manual assembly, as parts with such fit type require precise force feedback to assist users’ assembly operations.
Design/methodology/approach
This study proposes a novel force rendering model for VA of mechanical parts with clearance fits. By decomposing an actual assembly operation into three consecutive states, the corresponding forces are formulated.
Findings
A prototype system is designed and developed to implement the model, and comparative case studies are conducted to investigate the users’ performance with the other three common approaches, namely, a typical WIMP (window-icon-menu-pointer) interface with CAD software, a physics simulation with collision detection and the approach that combines physics simulation and geometric constraints restriction. The results have shown that the proposed model is more realistic by providing continuous and realistic force feedback to the users.
Originality/value
The users’ feeling of immersion and their operational efficiency are greatly enhanced with the force sensation provided.
Details
Keywords
Mousumi Bose, Lilly Ye and Yiming Zhuang
Today's marketing is dominated by decision-making based on artificial intelligence and machine learning. This study focuses on one semi- and unsupervised machine learning…
Abstract
Today's marketing is dominated by decision-making based on artificial intelligence and machine learning. This study focuses on one semi- and unsupervised machine learning technique, generative adversarial networks (GANs). GANs are a type of deep learning architecture capable of generating new data similar to the training data that were used to train it, and thus, it is designed to learn a generative model that can produce new samples. GANs have been used in multiple marketing areas, especially in creating images and video and providing customized consumer contents. Through providing a holistic picture of GANs, including its advantage, disadvantage, ethical considerations, and its current application, the study attempts to provide business some strategical orientations, including formulating strong marketing positioning, creating consumer lifetime values, and delivering desired marketing tactics in product, promotion, pricing, and distribution channel. Through using GANs, marketers will create unique experiences for consumers, build strategic focus, and gain competitive advantages. This study is an original endeavor in discussing GANs in marketing, offering fresh insights in this research topic.
Details
Keywords
Huaxiang Song, Hanjun Xia, Wenhui Wang, Yang Zhou, Wanbo Liu, Qun Liu and Jinling Liu
Vision transformers (ViT) detectors excel in processing natural images. However, when processing remote sensing images (RSIs), ViT methods generally exhibit inferior accuracy…
Abstract
Purpose
Vision transformers (ViT) detectors excel in processing natural images. However, when processing remote sensing images (RSIs), ViT methods generally exhibit inferior accuracy compared to approaches based on convolutional neural networks (CNNs). Recently, researchers have proposed various structural optimization strategies to enhance the performance of ViT detectors, but the progress has been insignificant. We contend that the frequent scarcity of RSI samples is the primary cause of this problem, and model modifications alone cannot solve it.
Design/methodology/approach
To address this, we introduce a faster RCNN-based approach, termed QAGA-Net, which significantly enhances the performance of ViT detectors in RSI recognition. Initially, we propose a novel quantitative augmentation learning (QAL) strategy to address the sparse data distribution in RSIs. This strategy is integrated as the QAL module, a plug-and-play component active exclusively during the model’s training phase. Subsequently, we enhanced the feature pyramid network (FPN) by introducing two efficient modules: a global attention (GA) module to model long-range feature dependencies and enhance multi-scale information fusion, and an efficient pooling (EP) module to optimize the model’s capability to understand both high and low frequency information. Importantly, QAGA-Net has a compact model size and achieves a balance between computational efficiency and accuracy.
Findings
We verified the performance of QAGA-Net by using two different efficient ViT models as the detector’s backbone. Extensive experiments on the NWPU-10 and DIOR20 datasets demonstrate that QAGA-Net achieves superior accuracy compared to 23 other ViT or CNN methods in the literature. Specifically, QAGA-Net shows an increase in mAP by 2.1% or 2.6% on the challenging DIOR20 dataset when compared to the top-ranked CNN or ViT detectors, respectively.
Originality/value
This paper highlights the impact of sparse data distribution on ViT detection performance. To address this, we introduce a fundamentally data-driven approach: the QAL module. Additionally, we introduced two efficient modules to enhance the performance of FPN. More importantly, our strategy has the potential to collaborate with other ViT detectors, as the proposed method does not require any structural modifications to the ViT backbone.