Article
Computer Science, Information Systems
Navaneeth Bhaskar, Vinayak Bairagi, Ekkarat Boonchieng, Mousami V. Munot
Summary: In this paper, an automated medical system for detecting type 2 diabetes from exhaled breath is proposed. The concentration of acetone in the exhaled breath is analyzed using a new sensing module consisting of an array of sensors. A new deep hybrid Correlational Neural Network (CORNN) is designed and implemented to analyze the sensor signals and generate predictions. The proposed detection approach and deep learning algorithm offer improved accuracy compared to other non-invasive techniques.
Article
Neurosciences
Yuwen Ruan, Xiang Chen, Xu Zhang, Xun Chen
Summary: This study explores the feasibility of using principal component analysis (PCA) algorithm to separate gesture pattern-related signals from noise and proposes a PCA-based PPG signal processing scheme to improve gesture recognition accuracy. Experimental results show that PCA decomposition effectively separates relevant signals from noise, and the proposed scheme is particularly effective for finger-related gestures.
FRONTIERS IN NEUROSCIENCE
(2022)
Article
Computer Science, Information Systems
Shashi Bhushan, Mohammed Alshehri, Neha Agarwal, Ismail Keshta, Jitendra Rajpurohit, Ahed Abugabah
Summary: Recognizing facial expressions is a major challenge, especially in the field of industrial Internet of Things. This paper proposes a new framework, FRS-DCT-SVM, that utilizes discrete cosine transform and genetic algorithm optimization for face detection and feature extraction. The framework achieves better results in terms of clustering time and accuracy compared to other methods.
Article
Multidisciplinary Sciences
Jingwei Hao, Senlin Luo, Limin Pan
Summary: Due to concealed initial symptoms, many diabetic patients are not diagnosed in time, delaying treatment. Most machine learning methods lack interpretability, which leads to the use of rule extraction to explain the black box. However, existing rule extraction methods tend to identify healthy people rather than diabetic patients. To address this problem, a method for extracting reduced rules based on biased random forest and fuzzy support vector machine is proposed, which significantly improves interpretability and diagnosis accuracy.
SCIENTIFIC REPORTS
(2022)
Article
Agriculture, Multidisciplinary
Zhen Zhang, Jun Zhou, Zhenghong Yan, Kai Wang, Jiamin Mao, Zizhen Jiang
Summary: Hardness recognition of fruits and vegetables based on tactile array information was proposed in this study, with PCA-KNN and PCA-SVM algorithms achieving accuracy rates of 90.03% and 94.27% respectively. This method allowed the robot to stably grasp products without damage, as verified by an online grabbing recognition experiment with a 90% accuracy rate.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2021)
Review
Chemistry, Analytical
Kaushiki Dixit, Somayeh Fardindoost, Adithya Ravishankara, Nishat Tasnim, Mina Hoorfar
Summary: Researching the application of exhaled breath analysis in diabetes monitoring is crucial yet challenging. A comprehensive evaluation of current technologies and sensing methods can help understand the shortcomings of blood glucose monitoring and further drive the development of non-invasive diabetes monitoring devices. It is important to focus on studying breath biomarker clusters and incorporating novel sensing materials and transduction mechanisms to realize breath analysis as an effective healthcare approach.
Article
Materials Science, Multidisciplinary
Ying Chen, Haochen Peng, Yuzhu Liu
Summary: Identification based on LIBS and machine learning is important for reducing the risk of using low-quality or inappropriate charcoal. This study used different types of charcoal samples for detection and achieved classification accuracy of 96.0% and 97.3% using optimized methods. The results indicate that LIBS combined with machine learning provides a new and effective method for charcoal detection and classification.
JOURNAL OF LASER APPLICATIONS
(2021)
Review
Medical Laboratory Technology
Ting Chen, Tiannan Liu, Ting Li, Hang Zhao, Qianming Chen
Summary: The review introduces the conventional and emerging methods for breath analysis in diagnosing and monitoring various diseases. It discusses the correlation between breath components and specific diseases, as well as unique ideas and devices for the diagnosis of common diseases through exhaled breath analysis. The potential application of exhaled breath analysis for diagnosing and screening different diseases is briefly introduced, offering a new avenue for non-invasive disease detection.
CLINICA CHIMICA ACTA
(2021)
Article
Engineering, Multidisciplinary
Janusz Smulko, Tomasz Chludzinski, Tomasz Majchrzak, Andrzej Kwiatkowski, Sebastian Borys, Aylen Lisset Jaimes-Mogollon, Cristhian Manuel Duran-Acevedo, Omar Geovanny Perez-Ortiz, Radu Ionescu
Summary: This paper presents a procedure and set-up for an electronic nose system to detect patients suffering from dengue, a mosquito-borne tropical disease, by analyzing exhaled breath. Low-power resistive gas sensors were used to detect volatile organic compounds in the breath. The experimental studies showed that the system had a detection accuracy of over 90% for dengue patients.
Article
Chemistry, Physical
Maryam K. Ghassemi, Sahar Barzegari, Parastoo Hajian, Hanieh Zham, Hamid Reza Mirzaei, Farshad H. Shirazi
Summary: In this study, FTIR-ATR spectroscopy was used to compare gastric samples, and data modeling was performed using PCA, SVM, and KNN algorithms. Specific peaks related to malignancy were identified in malignant tissue, which can be used to distinguish between normal and malignant samples.
JOURNAL OF MOLECULAR STRUCTURE
(2021)
Article
Computer Science, Information Systems
Gharbi Alshammari, Majdah Alshammari, Tariq S. Almurayziq, Abdullah Alshammari, Mohammad Alsaffar
Summary: Due to the increased frequency of phishing attacks, researchers are focusing on network security. The large volumes of data created daily include irrelevant features that affect machine learning accuracy. Therefore, a robust method is needed to detect phishing threats and improve accuracy. Three classifiers, decision tree, KNN, and SVM, were applied to improve detection accuracy. Feature selection using the Chaotic Dragonfly Algorithm provided more accurate results than baseline classifiers and indicated the appropriate classifier to detect phishing websites. Three publicly available datasets were used for evaluation.
Article
Engineering, Electrical & Electronic
F. Fachini, B. I. L. Fuly
Summary: The paper compares the voltage and system loading mapping capabilities of various regression algorithms, finding that ANFIS and KNN perform better in critical voltage and load prediction.
ELECTRIC POWER SYSTEMS RESEARCH
(2021)
Article
Meteorology & Atmospheric Sciences
Maayan Kahlon, Azi Lipshtat, Colin Price, Anthony Weiss
Summary: The Comprehensive Nuclear-Test-Ban Treaty Organization utilizes four complementary technologies in the international monitoring system to detect potential treaty violations, mainly focusing on atmospheric nuclear explosions. Research shows that many infrasonically detected events are not accompanied by electromagnetic pulses, indicating they are not nuclear explosions. By using machine learning techniques, it is possible to classify electromagnetic pulses accompanying infrasonic events, reducing the need for manual analysis of infrasound signals.
JOURNAL OF GEOPHYSICAL RESEARCH-ATMOSPHERES
(2022)
Article
Chemistry, Analytical
Lichao Liu, Teng Fei, Xin Guan, Hongran Zhao, Tong Zhang
Summary: The high concentration of ammonia in exhaled breath can be a biomarker for end-stage renal disease, but detecting it using gas sensors is challenging due to the complex components and high humidity of the gases. A new NH3 sensing design using a humidity-activated mechanism at room temperature was developed, with promising results for highly selective detection of NH3 under high humidity conditions. The environmentally friendly biomass hydrogel sensor showed a strong response to 50 ppm NH3 at 80% relative humidity, suggesting its potential for analyzing exhaled breath.
SENSORS AND ACTUATORS B-CHEMICAL
(2021)
Review
Chemistry, Analytical
Bin Hu
Summary: The analysis of exhaled breath using mass spectrometry has shown great potential in disease diagnosis and monitoring. This review article highlights the use of mass spectrometry as a clinical tool for diagnosing human diseases, discussing different breath sampling methods, mass spectrometry techniques, and breath biomarkers. The article also addresses future perspectives and challenges in further developing mass spectrometry-based breath diagnostics.
TRAC-TRENDS IN ANALYTICAL CHEMISTRY
(2023)
Review
Materials Science, Multidisciplinary
Bartlomiej Szafraniak, Lukasz Fusnik, Jie Xu, Feng Gao, Andrzej Brudnik, Artur Rydosz
Summary: This work provides a broad overview and discussion of strontium titanate, barium titanate, and barium strontium titanate-based gas sensors, which are characterized by their perovskite structure and long-term stability. The number of papers testing these materials as gas-sensitive materials has increased tenfold in the last 20 years, reflecting the growing interest in their potential commercial applications. The study also presents the NO2-sensing characteristics of BST-based gas sensors deposited by the authors using magnetron sputtering technology.
Article
Chemistry, Analytical
Anna Paleczek, Bartlomiej Szafraniak, Lukasz Fusnik, Andrzej Brudnik, Dominik Grochala, Stanislawa Kluska, Maria Jurzecka-Szymacha, Erwin Maciak, Piotr Kaluzynski, Artur Rydosz
Summary: Controlling environmental pollution is a pressing issue worldwide, and developing high-performance gas sensors is crucial for pollution control. Through research on the heterostructures of CuO/SnOx and SnOx/CuO, selective detection of NO2 has been achieved.
Article
Materials Science, Multidisciplinary
Yiting Guo, Sichen Wu, Shuhang Liu, Jie Xu, Emilia Pawlikowska, Mikolaj Szafran, Artur Rydosz, Feng Gao
Summary: The regional distribution of fillers in ceramic/polymer composites can significantly impact the electric field distribution and dielectric properties. This study fabricated BST/PVDF monolayer and two sandwich structural composites, PBP and BPB, and found that the BPB structure exhibited the best dielectric performances with higher energy density and dielectric tunability. Finite element simulation further confirmed that the sandwich structure can reduce electrical breakdown and improve energy storage characteristics in the composites.
Article
Physics, Condensed Matter
Qian Chen, Xiaoying Feng, Duo Teng, Jie Xu, Shuyao Cao, Artur Rydosz, Jie Kong, Feng Gao
Summary: The study investigates the influence of different Nb5+ vacancies on the dielectric properties and spontaneous polarization intensity of KSN using first-principles calculations, revealing that vacancies at different Nb sites lead to variations in dielectric constants and polarization responses. Experimental results confirm the effects of Nb5+ vacancies on the polarization behavior of the material.
PHYSICA STATUS SOLIDI B-BASIC SOLID STATE PHYSICS
(2022)
Article
Chemistry, Analytical
Jakub Bronicki, Dominik Grochala, Artur Rydosz
Summary: This paper describes a device developed for controlling the deposition parameters in the glancing angle deposition (GLAD) process of metal-oxide thin films. The device allows scientists to control all parameters during the deposition. With the use of commercially available vacuum components and a formula developed by the team, higher precision readings were achieved.
Article
Materials Science, Composites
Shuhang Liu, Yiting Guo, Jianwei Li, Sichen Wu, Jie Xu, Emilia Pawlikowska, Jie Kong, Artur Maciej Rydosz, Mikolaj Szafran, Feng Gao
Summary: Ceramic/polymer dielectric functional composites, specifically the (Ba0.6Sr0.4)TiO3/PEEK (BST/PEEK) composites, were prepared with high frequency stability of the dielectric constant and low dielectric loss via cold-pressing sintering. The optimal properties of the BST/PEEK composites were achieved at a BST concentration of 40 vol% and sintered at 360°C for 1 hour, showing a permittivity of 23, a loss of 0.0065, F(x) <5%, and a dielectric tunability of 11.9%. The study provides insight for developing new composites with low loss and high frequency stability.
COMPOSITES SCIENCE AND TECHNOLOGY
(2022)
Review
Chemistry, Analytical
Lukasz Fusnik, Bartlomiej Szafraniak, Anna Paleczek, Dominik Grochala, Artur Rydosz
Summary: This paper reviews the current state of the art in gas-sensing measurement and provides overall conclusions on the impact of different set-ups on the obtained results.
Article
Chemistry, Physical
Yiting Guo, Shuhang Liu, Sichen Wu, Jie Xu, Emilia Pawlikwska, Weronika Bulejak, Mikolaj Szafran, Artur Rydosz, Feng Gao
Summary: This study designed Ba0.6Sr0.4TiO3/PVDF composite materials with different dual-gradient structures to achieve serialized relative permittivity and improved breakdown strength. The multilayer dual-gradient structure design was found to enhance the dielectric constant and the enhancement of breakdown strength was further confirmed. The developed dielectric theoretical model of multilayer structure provides a new strategy to effectively improve the dielectric tunability of ceramic/polymer composite materials.
JOURNAL OF ALLOYS AND COMPOUNDS
(2022)
Article
Materials Science, Multidisciplinary
Zhihao Lou, Xin Xu, Ping Zhang, Lingyun Gong, Qian Chen, Jie Xu, Artur Rydosz, Feng Gao
Summary: Entropy engineering has been applied to synthesize a series of high-entropy dielectric ceramics, and the influence of mixing entropy on phase stability and dielectric properties has been investigated. The introduction of tetravalent cations can induce distortion of oxygen octahedron and antiparallel cation displacement, leading to excellent dielectric performance and stability. This research provides valuable insights for entropy engineering to control dielectric properties and phase stability.
JOURNAL OF MATERIALS RESEARCH AND TECHNOLOGY-JMR&T
(2022)
Article
Engineering, Multidisciplinary
Ilona Piekarz, Jakub Sorocki, Sabina Gorska, Heike Bartsch, Artur Rydosz, Robert Smolarz, Krzysztof Wincza, Slawomir Gruszczynski
Summary: A novel label-free detection method for Escherichia coli based on microwave sensing is proposed. The detection is achieved by a transmission-type differential resonator array biosensor covered with polyclonal anti-Escherichia coli antibodies, which provides a robust response with high sensitivity due to resonant operation. The use of specific bacteria-binding antibodies ensures high selectivity. The proposed biosensor operates in a frequency range of 4 - 6 GHz with five distinct resonances, increasing the probability of bacteria detection presence.
Article
Chemistry, Analytical
A. Paleczek, D. Grochala, K. Staszek, S. Gruszczynski, Erwin Maciak, Zbigniew Opilski, Piotr Kaluzynski, Marek Wojcikowski, Tuan-Vu Cao, A. Rydosz
Summary: A microwave system dedicated to detecting nitrogen dioxide in harsh highway environments is proposed. It utilizes an optimized transmission line sensor coated with a tungsten trioxide thin film that changes its electrical properties in the presence of NO2 gas. The system operates within the 1.5 GHz - 4.5 GHz range, allowing for the detection of NO2 concentrations ranging from 0 to 20 ppm.
SENSORS AND ACTUATORS B-CHEMICAL
(2023)
Proceedings Paper
Engineering, Electrical & Electronic
Dominik Grochala, Anna Paleczek, Kamil Staszek, Slawomir Gruszczynski, Artur Rydosz
Summary: This paper presents the development of a MoO3-based gas sensor operating in the microwave frequency range, with enhanced detection achieved through the use of the eight-port reflectometer measurement method.