检索结果-内蒙古大学图书馆

Pluggable multitask diffractive neural networks based on cascaded metasurfaces

Opto-Electronic Advances 2024年第2期7卷 23-31页

作者： Cong He Dan Zhao Fei Fan Hongqiang Zhou Xin Li Yao Li Junjie Li Fei Dong Yin-Xiao Miao Yongtian Wang Lingling Huang Beijing Engineering Research Center of Mixed Reality and Advanced Display Key Laboratory of Photoelectronic Imaging Technology and System of Ministry of Education of ChinaSchool of Optics and PhotonicsBeijing Institute of TechnologyBeijing 100081China Institute of Modern Optics Tianjin Key Laboratory of Optoelectronic Sensor and Sensing Network TechnologyNankai UniversityTianjin 300350China Department of Physics and Optoelectronics Faculty of ScienceBeijing University of TechnologyBeijing 100124China Beijing National Laboratory for Condensed Matter Physics Institute of PhysicsChinese Academy of SciencesBeijing 100191China Beijing Aerospace Institute for Metrology and Measurement Technology Beijing 100076China

Optical neural networks have significant advantages in terms of power consumption,parallelism,and high computing speed,which has intrigued extensive attention in both academic and engineering *** has been considered as one of the powerful tools in promoting the fields of imaging processing and object ***,the existing optical system architecture cannot be reconstructed to the realization of multi-functional artificial intelligence systems *** push the development of this issue,we propose the pluggable diffractive neural networks(P-DNN),a general paradigm resorting to the cascaded metasurfaces,which can be applied to recognize various tasks by switching internal *** the proof-of-principle,the recognition functions of six types of handwritten digits and six types of fashions are numerical simulated and experimental demonstrated at near-infrared ***,the proposed paradigm not only improves the flexibility of the optical neural networks but paves the new route for achieving high-speed,low-power and versatile artificial intelligence systems.

关键词： optical neural networks diffractive deep neural networks cascaded metasurfaces

来源：评论

学校读者我要写书评

暂无评论

Electrical Impedance Tomography Image Reconstruction with apriori Knowledge for Gesture Recognition 19

Electrical Impedance Tomography Image Reconstruction with ap...

引用

19th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2022

作者： Alasasfeh, Hayat Hafsa, Mariem Bader, Oumaima Ibbini, Mohammed Hasan, Sameer Kanoun, Olfa Jordan University of Science and Technology Biomedical Engineering Department Irbid Jordan Université de Sousse Ecole Nationale d'Ingénieurs de Sousse LATIS- Laboratory of Advanced Technology and Intelligent Systems Sousse4023 Tunisia Measurement and Sensor Technology Technische Universität Chemnitz Chemnitz Germany

ISBN: (数字)9781665471084

ISBN: (纸本)9781665471084

Electrical impedance tomography (EIT) reconstructs the conductivity images of an object based on the voltages and the currents at the surface of the object. Among the clinical applications of EIT thorax imaging, brain function monitoring and breast cancer screening. However, EIT suffers from a poor signal-to-noise ratio and spatial resolution. To improve the quality of reconstructed images and provide clear information about the structure, the paper proposes to include prior knowledge about the structure from MRI. The proposed techniques could be very promising with more work. To illustrate this technique in this paper, eight electrodes with the adjacent current pattern were employed in this research. For each gesture, forty data points are recorded. The Gauss-Newton and Back-Projection algorithms are used for image reconstruction with prior knowledge of the human forearm from MRI images. The resultant contours of the Forearm, Ulna, and Radius have been used to build the mesh. In the Gauss-Newton algorithm, the results reveal that structural information improves image quality and conductivity distribution, particularly in the region of two bones. In addition, the reconstructed images using the Gauss-Newton algorithm performed better than images reconstructed using the back-projection algorithm. © 2022 IEEE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Feature engineering for Accurate Low-Power Electrical Impedance Tomography in Hand Sign Recognition

Feature Engineering for Accurate Low-Power Electrical Impeda...

引用

IEEE SSD International Multi-Conference on Systems, Signals and Devices

作者： Bilel Ghoul Rim Barioul Salwa Sahnoun Ahmed Fakhfakh Olfa Kanoun Measurement and Sensor Technology Faculty of Electrical Engineering and Information Technology Chemnitz University of Technology Chemnitz Germany Laboratory of Signals Systems Artificial Intelligence and Networks Digital Research Centre of Sfax National School of Electronics and Telecommunications of Sfax Technopole of Sfax Ons City Tunisia

ISBN: (数字)9798331542726

ISBN: (纸本)9798331542733

Achieving high classification accuracy from raw measurements in Electrical Impedance Tomography (EIT) for hand sign recognition is a significant challenge due to the inherent ill-posed nature of the corresponding inverse problem to solve. Energy consumption is an issue, especially for wearable devices, so there is a growing preference to measure EIT with fewer electrodes or fewer current injections. In a previous study, we demonstrated that an 8-electrode hand gesture recognition system could achieve high accuracy with only 5 current injections instead of 8, resulting in significant power savings. In this study, we investigate feature extraction and selection techniques to improve the classification accuracy in the low-power EIT system based on less measurements. We evaluate the performance of 12 statistical features by analyzing the Feature Importance (FI) and identify 8 features with non-zero values: WL, MAV, Kurtosis, VORDER, DASDV, RMS, P2P and VAR. Using K-Nearest Neighbour (KNN), a comparative classification is performed using subsets of the best ranked features ranging from 2 to 8. Compared to the 96% accuracy achieved with raw data, our solution achieves 99.8% accuracy with the 8 extracted features. The results show that feature engineering significantly improves classification accuracy compared to the use of raw data.

关键词： Hands Performance evaluation Electrical impedance tomography Reactive power Accuracy Current measurement Nearest neighbor methods Feature extraction Kurtosis Wearable devices

来源：评论

学校读者我要写书评

暂无评论

Biomimetic Robotic Hand with Highly Sensitive Integrated Nanocomposite Force sensors for Adaptive Grasping

Biomimetic Robotic Hand with Highly Sensitive Integrated Nan...

引用

International Workshop on Robot Sensing (ROSE)

作者： Ahmed Attaoui Achraf Djemal Bilel Ben Atitallah Asma El Jaoui Olfa Kanoun Professorship Measurement and Sensor Technology Chemnitz University of Technology Chemnitz Germany Laboratory of Mechanics of Sousse National Engineering School of Sousse University of Sousse Sousse Tunisia Laboratory of Signals Systems Artificial Intelligence and Networks National School of Electronics and Telecommunications of Sfax Sfax Tunisia

ISBN: (数字)9798350362367

ISBN: (纸本)9798350362374

Robotic hands have immense potential for a wide range of applications, but the key challenge is still to achieve human-like dexterity. This requires overcoming several challenges, such as high system complexity, slow response time, and difficulties in integrating effective sensors. In this study, we present a novel robotic hand with 17 degrees-of-freedom equipped with nanocomposite based pressure and strain sensors. Inspired by the human hand's capabilities, the hand's design strives to mimic its dexterity and shape. The implemented nanocomposite sensors have exceptional electrical, mechanical, and electrochemical capabilities, making them ideal for integration into our robotic hand system design. The pressure sensor has a rapid response time, high pressure sensitivity of 4.4 kΩ /kPa, and remains stable over more than 5,000 cycles, demonstrating a high reliability. The strain sensor also maintains good linearity of 0.98 when subjected to strains from 0% to 24.49%. To address the challenge of balancing secure grasping and delicate touch, a finite state machine (FSM) control method is proposed enabling the hand to dynamically adjust its grasping pressure based on the real-time sensor feedback, allowing for precise manipulation of fragile objects. Experiments demonstrate the effectiveness of the proposed approach, paving the way for the development of intelligent robotic systems with enhanced dexterity and adaptability for real-world applications.

关键词： Automata Tactile sensors Grasping Robot sensing systems Capacitive sensors sensor systems sensors

来源：评论

学校读者我要写书评

暂无评论

A Portable Dynamic Path-Length Optical sensor for Phenol Detection

SSRN

引用

SSRN 2025年

作者： Zhang, Junru Chen, Ying Liu, Junfei Li, Wanwen Zhu, Dandan Niu, Liyong Zhu, Qiguang Hebei Province Key Laboratory of Test/Measurement Technology and Instrument School of Electrical Engineering Yanshan University Hebei Qinhuangdao066004 China Hebei Province Key Laboratory of Special Fiber and Fiber Sensor School of Information Science and Engineering Yanshan University Hebei Qinhuangdao066004 China

A current challenge faced by portable phenol sensors is their susceptibility to environmental factors, which affects their robustness under low-cost constraints. This study develops a low-cost optical sensor for phenol detection. The system utilizes a UV-sensitive photodetector paired with specific wavelength filters for wavelength selection. It further optimizes detection accuracy and robustness through a specially designed dynamic optical path quartz cuvette. Additionally, the use of a dual detection unit and standardized methodology minimizes the interference of external environmental factors on the sensor. Experimental results demonstrate that the detection system exhibits linearity within the range of 0.1 to 5 mg/L, with an average absolute error of 0.1604 in real-world environmental testing. This provides an efficient and economical solution for on-site rapid detection of phenolic wastewater. The sensor has a detection limit of 0.038 mg/L and a total cost of $251.01. © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Remote platform for lung monitoring based on Electrical Impedance Tomography measurements 19

Remote platform for lung monitoring based on Electrical Impe...

引用

19th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2022

作者： Hafsa, Mariem Bchir, Ons Bader, Oumaima Ben Amara, Najoua Essoukri Kanoun, Olfa Université de Sousse Ecole Nationale d' Ingénieurs de Sousse LATIS- Laboratory of Advanced Technology and Intelligent Systems Sousse4023 Tunisia Professorship of Measurement and Sensor Technology Technische Universität Chemnitz Chemnitz Germany University of Sousse National EngineeringSchool of Sousse Computer Engineering Department Sousse Tunisia

ISBN: (数字)9781665471084

ISBN: (纸本)9781665471084

Electrical Impedance Tomography (EIT) is a non-invasive, non-ionizing medical imaging method that has been on the rise in biomedical field. For lung monitoring, electrodes are attached around patient's thorax. Several boundary voltages are measured on the surface of these electrodes, which result from the injection of a small alternating current. Based on these measurements, the inner conductivity distribution of the patient's lung can be determined and used for monitoring and diagnosis. EIT can be used for extended periods of time, which makes it ideal for continuous monitoring, especially for intensive care patients. Several stationary EIT-based lung monitoring platforms have been developed for this reason. In this work, however, we propose a web and cloud-based monitoring solution that allows remote access for the doctors and medical staff. The implemented solution provides real-time, continuous monitoring as well as a visualization of extracted lung features that aid the diagnosis, © 2022 IEEE.

关键词： Electrodes

来源：评论

学校读者我要写书评

暂无评论

Post-processing for Thorax Imaging based on Electrical Impedance Tomography using Deep Learning 19

Post-processing for Thorax Imaging based on Electrical Imped...

引用

19th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2022

作者： Haddad, Hamdi Hafsa, Mariem Bader, Oumaima Ben Amara, Najoua Essoukri Kanoun, Olfa University of Sousse National Engineering School of Sousse Computer Engineering Department Sousse Tunisia Université de Sousse Ecole Nationale d'Ingénieurs de Sousse LATIS- Laboratory of Advanced Technology and Intelligent Systems Sousse4023 Tunisia Professorship of Measurement and Sensor Technology Technische Universität Chemnitz Chemnitz Germany

ISBN: (数字)9781665471084

ISBN: (纸本)9781665471084

Electrical Impedance Tomography (EIT) for lung monitoring is a non-ionizing medical imaging technique that is on the rise in biomedical engineering research in the recent decades. It reflects the inner conductivity distribution of biological tissue based on boundary voltages that appear on the electrodes, after injecting an alternating current of a certain amplitude into the human thorax. EIT, however, has a low spatial resolution and is susceptible to errors caused by electrode movement and poor contact quality, which can lead to the generation of blurry images. Post-processing imaging techniques can, in fact, be a beneficial tool for fine-tuning this issue. The focus of this work is to implement a U-NET multi-class semantic segmentation deep learning model to post-process reconstructed EIT thorax images to enhance its characteristics such as contrast, resolution... The model has achieved an overall accuracy of 72.43%. The resulting reconstructed images have reflected the physical changes during the breathing cycle, have deleted artifacts, and have made the shapes of the lungs and heart clearer. © 2022 IEEE.

关键词： Electrodes

来源：评论

学校读者我要写书评

暂无评论

Exploring the Real-Time Capability of Electrical Impedance Tomography for Hand Sign Recognition in Robotic Hand Control

Exploring the Real-Time Capability of Electrical Impedance T...

引用

International Workshop on Robot Sensing (ROSE)

作者： Bilel Ghoul Bilel Ben Atitallah Rim Barioul Ahmed Fakhfakh Olfa Kanoun Measurement and Sensor Technology Faculty of Electrical Engineering and Information Technology Chemnitz University of Technology Chemnitz Germany Laboratory of Signals Systems Artificial Intelligence and Networks Digital Research Centre of Sfax National School of Electronics and Telecommunications of Sfax Technopole of Sfax Ons City Tunisia

ISBN: (数字)9798350362367

ISBN: (纸本)9798350362374

Electrical impedance tomography (EIT) can monitor the influence of the muscle activity on the conductivity distribution across the forearm and is therefore suitable for Hand Sign Recognition (HSR). However, the method is relatively complex, so realizing real-time classification based on EIT measurements is still considered a major challenge. In addition, the accuracy of EIT for HSR is highly dependent on the injection configuration parameters applied. In this study, we investigate the influence of the injection configuration on the achieved accuracy of the hand robot control and the feasibility of a real-time classification based on EIT measurements. To assess real-time feasibility, experimental data have been collected for a sign set of 36 American Sign Language (ASL) performed by one healthy subject. Moreover, a comparative study of the adjacent, opposite, and cross injection configurations has been conducted on 10 subjects performing the ASL set. An ambiguity study based on the measured signals was performed to assess the discrimination potential between the hand signs. The adjacent EIT configuration exhibited higher sensitivity in discriminating hand signs. For a real-time classification, we propose the use of a Support Vector Machine (SVM) model realizing an overall accuracy of 71.38%. To validate the system's real-time behavior, the classification result is visualized by a robotic hand reproducing 6 different hand signs from the 36 ASL set reaching an accuracy of 80%. The results demonstrate the potential of EIT to facilitate real-time Hand Sign Recognition for robot control applications.

关键词： Support vector machines Electrical impedance tomography Surface impedance Accuracy Robot control Muscles Robot sensing systems

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Data Reduction Methods in Electrical Impedance Tomography For Hand Sign Recognition

Comparative Study of Data Reduction Methods in Electrical Im...

引用

International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)

作者： Bilel Ghoul Bilel Ben Atitallah Salwa Sahnoun Ahmed Fakhfakh Olfa Kanoun Measurement and Sensor Technology Faculty of Electrical Engineering and Information Technology Chemnitz University of Technology Chemnitz Germany Digital Research Centre of Sfax National School of Electronics and Telecommunications of Sfax Technopole of Sfax Laboratory of Signals Systems Artificial Intelligence and Networks Ons City Tunisia

ISBN: (数字)9798350351484

ISBN: (纸本)9798350351491

Several studies have shown that electrical impedance tomography (EIT) on the human forearm can be used to classify hand signs without the need for cameras or gloves. However, the amount of measured data is in relatively high, leading to long execution times and high processing complexity. In this study, we investigate the influence of reducing the number of EIT measurements on the classification accuracy. Four different algorithms were used to halve the number of measurements, namely Principal Component Analysis (PCA), Chi-square tests, Minimum Redundancy Maximum Relevance (MRMR) and Laplacian scores. These algorithms were applied to a dataset of forearm EIT measurements corresponding to the practice of American Sign Language (ASL) in a healthy subject. The results show a slight drop in accuracy when using the quadratic support vector machine (SVM) classifier, with accuracy dropping from 95.3% to 93.4% in the best cases. A method based on a genetic algorithm (GA) was also used. This approach exploits the strengths of genetic algorithms in exploring a large solution space and converging on the near-optimal combination. This approach resulted in an increase in accuracy to 96.7%. The study demonstrated that the number of EIT measurements can be reduced without compromising overall accuracy.

关键词： Support vector machines Electrical impedance tomography Sign language Accuracy Image recognition Laplace equations Assistive technologies

来源：评论

学校读者我要写书评

暂无评论

Parameters Estimation of Cole-Cole Bio-Impedance Model with a Minimum Number of Frequencies

Parameters Estimation of Cole-Cole Bio-Impedance Model with ...

引用

IEEE Instrumentation and measurement technology Conference

作者： Nour Ammar Cherif Ouni Ahmed Yahia Kallel Ahmed Fakhfakh Nabil Derbel Olfa Kanoun Measurement and Sensor Technology Faculty of Electrical Engineering and Information Technology Chemnitz University of Technology Chemnitz Germany Control and Energy Management Laboratory National Engineering School of Sfax University of Sfax Sfax Tunisia Laboratory of Signals Systems Artificial Intelligence and Networks Digital Research Centre of Sfax National School of Electronics and Telecommunications of Sfax Sfax Tunisia

ISBN: (数字)9798350380903

ISBN: (纸本)9798350380910

Wearable bioimpedance devices are becoming increasingly popular due to their portability and non-invasiveness. However, these devices consume a lot of energy during measurement time, limiting the operating time. The number of frequencies must be reduced to reduce the measurement time and energy. In this paper, we propose using three frequencies and investigating their optimal values for accurate measurement. The remaining two frequencies at high frequencies are chosen by eliminating the high frequencies that have a high deviation. Lastly, a third frequency is optimally chosen based on a combination of the frequencies whose non-linear least-squares fitting parameters results lead to the smallest deviations. First, a simulation is used to validate the results, where a Cole-Cole model is used with different noise levels. Two high frequencies in combination with a frequency close to the characteristic frequency yielded the best results, regardless of the presence of noise. Second, the measurement was experimentally validated in STM32 with a physical Cole-Cole model, which confirmed the results, where 7.94 kHz, close to the characteristic frequency, had mean deviations of 2.43% in $R_{l}$ , 3.7% in $R_{E}$ , and 2.55% in C. Using three points reduces the measurement time from 9.7 ms to 0.41 ms.

关键词： Time-frequency analysis Accuracy Biological system modeling Fitting Energy measurement Time measurement Frequency estimation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：