This paper introduces a novel sensor calibration scheme, the Hybrid Analytical and Network (HAN) model, which is especially suitable for regression based on neural networks with small training datasets. Through the HAN model, qualitative physical knowledge can be used to facilitate network training so that the demand on training data can be significantly reduced. Furthermore, training results can be transferred to the calibration of other types of sensors. The HAN model has been used to calibrate two haptic sensors, namely, the balance sensor and the skin sensor, which both operate on the principle of Frustrated Total Internal Reflection (FTIR), but for two different applications. The balance sensor is designed for human balance ability assessment, while the skin sensor is designed for evaluation of human skin properties. The calibration results using the HAN model are far more accurate and faster than other neural network training methods, especially for a small experiment dataset. The strong transfer ability of the HAN model is also demonstrated by the transfer attempt from balance sensor calibration to that of the skin sensor. The HAN model provides a new method to integrate model-based and data-driven sensor calibration methods, and shows greater efficacy. Its application is not restricted to sensor calibration but has broader potential value in all neural network regression tasks.

Calibration of Haptic Sensors Using Transfer Learning

In this paper, we propose an object recognition algorithm allowing for learning in the compressed space and reconstructing to the spatial space when images need to be processed in their spatial forms. Instead of using the traditional cameras, a novel compressive sampling camera is simulated to directly capture the natural scene to compressed images based on compressive sampling theory. We evaluate the recognition performance and reconstruction quality on a traffic database providing a solution to the reliable situation awareness problem for the self-driving cars. We also exploit the effectiveness of our method on a publicly available face database. It is experimentally observed that the proposed approach can obtain a high recognition rate and achieve the image reconstruction.

Learning object recognition based on compressive sampling

This paper presents a novel human balance ability assessment device, called balance sensor, which uses the principle of Frustrated Total Internal Reflection (FTIR) to measure pressure distribution under human feet. Experiment is conducted to quantitatively calibrate the relationship between pressure and pixel value and physical model is established for this relationship. A special neural network is designed. The established physical model can be transferred into such neural network as initialization. Moreover, we invented a training paradigm called Recurrent Transfer Learning (RTL), which is especially suitable for regression by neural network. The regression performance outperforms state-of-art neural network initialization methods.

Recurrent Transfer Learning by Neural Network Regression for Human Balance Sensor Calibration

Robots play important roles in improving the productivity and efficiency in modern product assembly lines. However, most objects involved in the assembly tasks are rigid. When the objects are flexible and deformable, it is challenging to manipulate them and use them as feedback to control the motion of robots. This paper proposes an assembly framework to first manipulate deformable cables to desired shapes, then to move the robot to target assembly locations to achieve the assembly tasks. The manipulation approach aims to learn the relationship between cable deformation and robot actions based on a convolutional neural network. A vision-based control method is also developed to move the robot to the assembly locations. Experiments are conducted to validate the performance of the proposed framework.

Cable Assembly Based on Robot Manipulation and Control

Prototype Based Personalized Federated Learning for Planetary Gearbox Fault Diagnosis

This paper presents the development of a novel balance sensor capable of assessing human balance ability. This sensor can effectively detect the tread force distribution information under human feet with high resolution and frame rate while they are trying to balance themselves. The principle and performance of the sensor are discussed in the paper. We have used this sensor to capture tread force distribution variation videos from 6 categories of different human balancing actions. A novel 3D convolutional neural network is developed to classify these 6 actions. The high accuracy of video classifications have been achieved using 3D CNN. In addition, our preliminary experimental results demonstrates that applying deep learning method, this sensor is able to recognize different human motion patterns. Ongoing work is to exploit its potential use in neural disease diagnosis.

Sensing and Data Analysis for Assessing Human Balance Ability

Robot motion control aims to generate control inputs for a robotic system to track a planned trajectory. Feedback provided by sensors plays an essential role in motion control by improving system performance when external disturbances and/or initial errors exist. However, feedback signals, such as images are often of a large size, which imposes a heavy computational burden on the system. In this paper, a new robot motion control scheme is proposed based on compressive feedback to improve feedback rate. The controller is designed in non-vector space using compressive feedback. As an application, visual servoing is formulated under the proposed framework by considering a feedback image as a set, instead of a traditional feature vector. Experiments are conducted to validate the proposed scheme.

Robot Motion Control with Compressive Feedback

Deep learning (DL)-based methods can realize superior performance in fault diagnosis with sufficient samples and consistent distribution. However, lacking labeled samples hampers DL’s application in nuclear circulating water pump (NCWP) fault diagnosis. Moreover, complex and varying working conditions of NCWP would remarkably lower the performance of the DL-based model because domain shift occurs in data distribution. To address these problems, the triplet adaptive attention multiscale Resnet (TAAMR) with ensemble empirical mode decomposition-local maximum mean discrepancy (EEMD-LMMD) generalized feature extraction is introduced for few-shot multi-domain fault diagnosis in NCWP planetary gearbox. Based on the EEMD-LMMD mechanism, domain-invariant features can be extracted more efficiently. TAAMR consists of an adaptive attention module, a multi-scale Resnet, and a triplet structure. With few-shot multi-domain learning, TAAMR utilizes the adaptive attention module to realize the identification of the importance of multiscale features. And the triplet structure is designed to optimize the distribution of features. The effectiveness of the proposed TAAMR is demonstrated on the NCWP test bench datasets, and the results show good adaptability in different working conditions.

Few-shot Multi-domain Fault Diagnosis for Planetary Gearbox in Nuclear Circulating Water Pump

Compressive sensing (CS) provides a method to perform sampling and compression simultaneously when a signal is sparse or compressible. The conventional CS is established on the prior knowledge of sparsity and cannot reconstruct the signals if they fail to be represented explicitly in a sparse form. Semantic CS is a new approach for sensing a signal based on its content knowledge, which can reduce the sensing rate and the sparsity constraint. However, the effects of content knowledge on the reconstruction quality is still not clear. In this paper, we provide an approach for designing a sensing matrix for semantic CS and experimentally study how content knowledge affects the reconstruction performance of the proposed CS.

Using Content Knowledge to Improve Reconstruction Performance by Semantic Compressive Sensing

In this paper, an optics-based new sensor capable of assessing human balance is developed and used to measure Body Alcohol concentration (BAC) before and after alcohol consumption in 23 healthy individuals of different ages, and a correlation is made between the calculated cross-entropy of center of pressure (CoP) and center of gravity (CoG) before and after alcohol consumption in the same individual. The correlations between BAC and the cross-entropy of CoP and CoG are compared and analyzed. The results demonstrate that through drunkenness data analysis, this optics-based new sensor can measure human CoP and the changes in human balance ability with BAC can be obtained through subsequent analysis. The future work is to improve the proposed method to verify the concept of drunk driving more accurately.

Body Alcohol Level Detection Based on Measurements of Human Balancing

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Song Wang

Author Tools

Chat about Author