Article
Chemistry, Analytical
Hugo Meyer, Peter Wei, Xiaofan Jiang
Summary: HOMER is a cloud-based system for video highlight generation that surpasses state-of-the-art solutions by combining video content features and user emotion data. Through two experiments, it demonstrated an improvement of up to 38% in F-1 score compared to the baseline, without requiring external hardware. The system's portability and scalability were showcased through the implementation of two smartphone applications.
Article
Optics
Mingyang Sun, Miao Yu, Haoran Wang, Kaiwen Song, Inyu Guo, Songfeng Xue, Hongwei Zhang, Yanbin Shao, Hongliang Cui, Tianying Chang, Tianyu Zhang
Summary: This study proposes a Noise Adaptive Mask-Masked Autoencoders (NAM-MAE) algorithm based on a novel mask mode of Masked Autoencoders (MAE) for intelligent event recognition in Distributed Optical Acoustic Sensing (DAS). The NAM-MAE algorithm achieves higher training accuracy and convergence speed compared to other models, with a final test accuracy of 96.6134%.
Article
Computer Science, Information Systems
Zheqi Yu, Adnan Zahid, Ahmad Taha, William Taylor, Julien Le Kernec, Hadi Heidari, Muhammad Ali Imran, Qammer H. Abbasi
Summary: This article introduces a framework that utilizes multisensor data fusion technology and neuromorphic computing for precise human activity recognition. The data is collected from IMU sensors, software-defined radios, and radars, and feature extraction and selection are performed. The framework uses a discrete Hopfield neural network for one-shot learning and determines conformity to the standard activity feature pattern. The proposed method achieves high accuracy in human activity recognition and can be enhanced by incorporating additional hardware signal processing.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Engineering, Electrical & Electronic
Cheng Shen, Zhongcai Pei, Weihai Chen, Jianhua Wang, Jianbin Zhang, Zuobing Chen
Summary: This study explores the generalization ability of gesture recognition via surface electromyography (sEMG) and proposes a new feature extraction method to reduce the influence of limb position on sEMG-based pattern recognition. The results show significant improvements in accuracy and generalization compared to traditional methods.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Review
Chemistry, Multidisciplinary
Tao Song, Zhe Yan, Shuai Guo, Yuwen Li, Xianhua Li, Fengfeng Xi
Summary: Surface electromyography (sEMG) is a promising technology for controlling robots through human-machine interfaces by capturing muscle activation signals. This article provides an overview of sEMG-based robot control, including signal processing and classification methods, as well as robot control strategies and methods based on sEMG. The article discusses the steps in sEMG signal processing, commonly used data acquisition and feature extraction methods, and introduces machine-learning-based pattern recognition methods for sEMG signal classification. It also classifies user intent-based robot control strategies into three categories and compares their control methods and applicable scenarios.
APPLIED SCIENCES-BASEL
(2023)
Article
Engineering, Environmental
U. K. Adarsh, E. Bhoje Gowd, Aseefhali Bankapur, V. B. Kartha, Santhosh Chidangil, V. K. Unnikrishnan
Summary: Mounting plastic waste poses a serious threat to the environment and public health. Recycling is a practical solution, but it relies on accurate waste sorting techniques. This study proposes a multi-modal spectroscopic sensor that combines laser-induced breakdown spectroscopy (LIBS) and Raman spectroscopy to assist in plastic identification and sorting for recycling. The system shows promising results in classifying different types of plastics in both laboratory and real-world conditions.
Article
Nuclear Science & Technology
Mohamed S. El-Tokhy
Summary: This paper introduces a digital inspection approach for normalized neutron pulses in the presence of high counting rate, utilizing signal processing, feature extraction, and classifier matching. The fuzzy-KNN classifier outperforms artificial neural network in terms of computational time and accuracy.
PROGRESS IN NUCLEAR ENERGY
(2021)
Article
Computer Science, Artificial Intelligence
Yongbai Liu, Keping Liu, Gang Wang, Jiliang Zhang, Yao Chou, Zhongbo Sun
Summary: In recent years, intelligent robots have been widely used in the industry and intelligent rehabilitation. The human-robot interaction (HRI) control strategy plays a vital role and needs improvement. This study presents a parallel execution intelligent control framework to address the issues related to HRI control in the presence of unknown external disturbances.
CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY
(2023)
Article
Chemistry, Analytical
Zheng-Yong Zhang, Xiao-Jing Shi, Ya-Ju Zhao, Yin-Sheng Zhang, Hai-Yan Wang
Summary: This study investigates and discusses an intelligent identification technology based on Raman spectroscopy for brand identification of soybean milk powder samples. By employing various spectral processing technologies, the recognition accuracy of these samples is significantly improved. Under the optimized conditions, the best recognition effect for soybean milk brand identification can be achieved, and the entire process is fast and convenient.
JOURNAL OF ANALYTICAL CHEMISTRY
(2022)
Article
Engineering, Electrical & Electronic
Abdulrahman Al-Malahi, Abubaker Farhan, HanCong Feng, Omar Almaqtari, Bin Tang
Summary: The accuracy of radar emitter signal sorting deteriorates due to the high flexibility and complexity of modern radar pulse streams and the density of crowded electromagnetic environment. Conventional methods usually fail to achieve acceptable accuracy and lack stable performance. To address this problem, a machine learning architecture called Unified Residual Recurrent Neural Network (URRNN) is proposed. URRNN combines and modifies residual neural network and recurrent neural network to enhance the model performance in both classification and deinterleaving tasks.
IET RADAR SONAR AND NAVIGATION
(2023)
Article
Chemistry, Multidisciplinary
Kumaranchira Ramankutty Krishnadas, Ani Baghdasaryan, Rania Kazan, Ewa Banach, Jeremie Teyssier, Valentin Paul Nicu, Thomas Buergi
Summary: In this study, distinct Raman spectroscopic signatures of the metal core of atomically precise, ligand-protected noble metal nanoclusters are reported using model systems Au-38(PET)(24) and Au38-xAgx(PET)(24). The low-frequency Raman spectra are shown to be a characteristic fingerprint of atomically precise clusters, while the vibrations associated with the outer metal-ligand staple motifs do not shift significantly with increasing Ag content. DFT calculations reveal weak Raman bands at higher frequencies related to the rattling of two central gold atoms of the bi-icosahedral Au-23 core.
Article
Computer Science, Artificial Intelligence
Sengul Dogan, Turker Tuncer
Summary: A new method using statistical decimal pattern and tunable Q-factor wavelet transform has been proposed in this study, which achieved high accuracy rates in surface electromyogram signal classification and outperformed other state-of-the-art methods according to the experimental results.
Article
Engineering, Biomedical
Narek N. Unanyan, Alexey A. Belov
Summary: This paper aims to develop an upper limb prosthetic device controlled by myoelectric signals to assist disabled individuals in their daily activities. It proposes an amplitude-based window recognition method to overcome the complex multi-finger control issue, and can be implemented in real-time using a low-cost Arduino microcontroller.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Engineering, Biomedical
Egle Butkeviciute, Liepa Bikulciene, Tomas Blazauskas
Summary: This study investigates the application of continuous non-invasive bio-signal recordings in daily life activities using smart devices and cloud-based technologies. A new ECG feature extraction algorithm for movement-contaminated signals was proposed and validated through comparisons with other methods. This research is significant for real-time data processing and health monitoring.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2022)
Article
Computer Science, Hardware & Architecture
Alex Qi, Muxin Ma, Yunlong Luo, Guillaume Fernandes, Ge Shi, Jun Fan, Yihong Qi, Jianhua Ma
Summary: This article introduces a contactless sensor based on electromagnet-wave, which has advantages in privacy, convenience, and affordability. While traditional researches usually focus on specific topics, the proposed systematic framework and architecture minimize the noise in hardware and digital signal processing for various human-centric applications.
IEEE WIRELESS COMMUNICATIONS
(2023)
Article
Instruments & Instrumentation
Andressa Cristina de M. Bezerra, Nelize Maria de A. Coelho, Felipe Bertelli, Marcos Tadeu T. Pacheco, Landulfo Silveira
Summary: This study used Raman spectroscopy to evaluate the temperature-induced changes and degradation levels of mineral, semi-synthetic, and synthetic automotive lubricating oils. Results showed that synthetic oil exhibited the least degradation during heating cycles, while mineral oil experienced the most degradation. Principal component analysis and partial least squares regression were able to accurately predict heating times for each oil type with high correlation and low prediction error. The Raman technique proves to be valuable in identifying chemical changes in lubricant oils due to heating, making it a useful tool for preventive maintenance in the automotive industry.
APPLIED SPECTROSCOPY
(2021)
Article
Engineering, Biomedical
Fernanda SantAna de Siqueira e Oliveira, Adriano Moraes da Silva, Marcos Tadeu Tavares Pacheco, Hector Enrique Giana, Landulfo Silveira Jr
Summary: This study evaluated the differences in Raman spectra of clinical bacterial species, correlating them with chemical composition to develop a classification model for rapid strain categorization. The results showed that Raman spectroscopy has potential applications for identifying spectral differences related to the biochemical content of pathogenic microorganisms.
LASERS IN MEDICAL SCIENCE
(2021)
Article
Oncology
Antonio L. B. Pinheiro, Luiz G. P. Soares, Aline C. P. da Silva, Nicole R. S. Santos, Anna Paula L. T. da Silva, Bruno Luiz R. C. Neves, Amanda P. Soares, Landulfo Silveira Jr
PHOTODIAGNOSIS AND PHOTODYNAMIC THERAPY
(2020)
Article
Chemistry, Analytical
Douglas de Jesus Passoni, Marcos Tadeu T. Pacheco, Landulfo Silveira Jr
INSTRUMENTATION SCIENCE & TECHNOLOGY
(2020)
Article
Engineering, Biomedical
Stella Giansante, Hector Enrique Giana, Adriana Barrinha Fernandes, Landulfo Silveira
Summary: The study evaluated the analytical performance of Raman spectroscopy for analyzing lipid profile, non-protein nitrogenous compounds, and glucose in human serum samples. The results demonstrated that Raman spectroscopy can be an important methodology, especially for screening serum triglycerides and cholesterol in the population. The analytical error was within acceptable ranges for most components, showing good potential for future widespread use.
LASERS IN MEDICAL SCIENCE
(2022)
Article
Spectroscopy
Ana Cristina Castro Goulart, Renato Amaro Zangaro, Henrique Cunha Carvalho, Landulfo Silveira Jr
Summary: Raman spectroscopy has been utilized for diagnosing COVID-19 mainly based on the presence of immunoglobulins M and G in serum samples. Principal component analysis revealed significant spectral differences between positive Ig groups and Control, with key features related to proteins like albumin and lipids.
JOURNAL OF RAMAN SPECTROSCOPY
(2021)
Article
Biochemistry & Molecular Biology
Pedro J. L. Crugeira, Paulo F. de Almeida, Igor C. F. Sampaio, Luiz G. P. Soares, David A. Moraga Amador, Ifor D. W. Samuel, Saydulla Persheyev, Landulfo Silveira Jr, Antonio L. B. Pinheiro
Summary: The study demonstrates that LED irradiation (630 nm wavelength) during both the growth and production phases of Xanthomonas campestris can increase both the production and viscosity of Xanthan gum.
JOURNAL OF PHOTOCHEMISTRY AND PHOTOBIOLOGY B-BIOLOGY
(2022)
Article
Engineering, Biomedical
Ana Cristina Castro Goulart, Landulfo Silveira Jr, Henrique Cunha Carvalho, Cristiane Bissoli Dorta, Marcos Tadeu T. Pacheco, Renato Amaro Zangaro
Summary: This study proposed the use of Raman spectroscopy for diagnosing COVID-19 by analyzing blood serum samples. The spectral differences between positive and negative COVID-19 patients were identified through exploratory analysis and discriminant analysis. The results showed specific spectral features associated with COVID-19 infection, indicating the potential of this label-free technique for rapid and cost-effective diagnosis.
LASERS IN MEDICAL SCIENCE
(2022)
Article
Dermatology
Alexandre S. Melitto, Victor E. A. Arias, Jorge Y. Shida, Luiz H. Gebrim, Landulfo Silveira
Summary: Raman spectroscopy was used to discriminate human breast cancer and its subtypes from normal tissue with high accuracy, making it a useful tool for cancer diagnosis.
LASERS IN SURGERY AND MEDICINE
(2022)
Article
Chemistry, Analytical
Luciana Lopes Guimaraes, Leandra Paula Marques de Sousa Rosa Nita, Walber Toma, Marcos Tadeu Tavares Pacheco, Landulfo Silveira
Summary: Stability studies are necessary to ensure the quality of drugs from production to expiration. This research used Raman spectroscopy to identify changes in commercial formulations containing dipyrone during the shelf time and model the expiration date. The study demonstrated that Raman spectroscopy is feasible for characterizing the degradation of dipyrone and estimating the shelf time.
INSTRUMENTATION SCIENCE & TECHNOLOGY
(2023)
Article
Engineering, Biomedical
Ana Mara Ferreira Lima, Camila Ribeiro Daniel, Marcos Tadeu Tavares Pacheco, Pedro Luiz de Brito, Landulfo Silveira
Summary: This study used Raman spectroscopy to analyze the blood serum samples of normal subjects, leukemic subjects, and non-leukemic subjects, and identified spectral differences related to biomolecules. Classification models were developed to accurately classify and discriminate the spectra. The results showed that Raman spectroscopy could be used for the biochemical differentiation of leukemias and other types of cancer in serum samples of children and adolescents.
LASERS IN MEDICAL SCIENCE
(2022)
Article
Engineering, Biomedical
Melissa de Almeida Melo Maciel Mangueira, Egas Caparelli-Daquer, Ozimo Pereira Gama Filho, Diogo Souza Ferreira Rubim de Assis, Janyeid Karla Castro Sousa, Willy Leite Lima, Antonio Luiz Barbosa Pinheiro, Landulfo Silveira, Nilton Maciel Mangueira
Summary: This study evaluated the effects of low-level laser therapy (LLLT) on sciatic nerve regeneration after compression injury. The results showed that 660 nm laser treatment had a better therapeutic effect and effectively promoted neurofunctional recovery.
LASERS IN MEDICAL SCIENCE
(2022)
Article
Engineering, Biomedical
Ricardo Pinto Aguiar, Edgar Teixeira Falcao, Carlos Augusto Pasqualucci, Landulfo Silveira
Summary: This study used Raman spectroscopy to identify biochemical differences between normal brain tissue and tumors, and demonstrated that both the concentrations of biochemical compounds and the information contained in Raman spectra can be used to classify pathological groups.
LASERS IN MEDICAL SCIENCE
(2022)