Review
Chemistry, Analytical
Alishba T. John, Krishnan Murugappan, David R. Nisbet, Antonio Tricoli
Summary: Electonic noses, relying on an array of chemical gas sensors, are used for identifying various compounds, particularly in the food industry and environmental monitoring. Advances in nanofabrication, sensor design, neural networks, and system integration have improved their efficacy. Commercial and custom Enoses face challenges in wider adoption and use across different applications.
Article
Chemistry, Applied
Yu Li, Chenghao Fei, Chunqin Mao, De Ji, Jingwen Gong, Yuwen Qin, Lingyun Qu, Wei Zhang, Zhenhua Bian, Lianlin Su, Tulin Lu
Summary: This study analyzed the quality assessment and flavor characteristics of 69 vinegar samples and established an evaluation system and flavor analysis method. The flash GC e-nose was better at reflecting the flavor characteristics of vinegar samples than physicochemical parameters, with an accuracy rate of 98.6%.
Article
Chemistry, Multidisciplinary
Garam Bae, Minji Kim, Wooseok Song, Sung Myung, Sun Sook Lee, Ki-Seok An
Summary: This study systematically investigates the impact of selectivity for a target gas on the prediction accuracy of gas concentration using machine learning. The results show a proportional relationship between selectivity factor and prediction accuracy, suggesting that combining sensors with different selectivity factors can enhance the prediction accuracy.
Article
Engineering, Electrical & Electronic
James A. Covington, Santiago Marco, Krishna C. Persaud, Susan S. Schiffman, H. Troy Nagle
Summary: The human olfactory system is difficult to replicate and poses challenges for real-time detection and analysis of odors. Artificial olfaction has stimulated interdisciplinary research and commercial development for various applications. Engineers and scientists have been working on solving odor measurement and control problems over the past century.
IEEE SENSORS JOURNAL
(2021)
Review
Chemistry, Physical
Wenwen Hu, Weiwei Wu, Yingying Jian, Hossam Haick, Guangjian Zhang, Yun Qian, Miaomiao Yuan, Mingshui Yao
Summary: This review article critically considers and summarizes the volatolomics in healthcare, clarifying the relationship between the volatolome and specific diseases and introducing analytical instruments and advanced detection technologies.
Article
Chemistry, Analytical
Felix Melendez, Patricia Arroyo, Jaime Gomez-Suarez, Sergio Palomeque-Mangut, Jose Ignacio Suarez, Jesus Lozano
Summary: In this study, a novel prototype of an electronic nose using digital and analog sensors is presented, capable of detecting and classifying low concentrations of TCA in cork samples, as well as predicting their concentrations.
Article
Optics
Incheol Cho, Kichul Lee, Young Chul Sim, Jae-Seok Jeong, Minkyu Cho, Heechan Jung, Mingu Kang, Yong-Hoon Cho, Seung Chul Ha, Kuk-Jin Yoon, Inkyu Park
Summary: Electronic nose (e-nose) technology using chemoresistive sensors has been widely studied for its applications in smart factory and personal health monitoring. To address cross-reactivity issues, a novel sensing strategy based on a single micro-LED embedded photoactivated gas sensor has been proposed. This method utilizes time-variant illumination and a deep neural network for species and concentrations identification of various target gases, achieving high accuracy with low power consumption.
LIGHT-SCIENCE & APPLICATIONS
(2023)
Article
Engineering, Electrical & Electronic
Wenwen Zhang, Hongtao Xiang, Yuanxi Wang, Xiao Bi, Yanzhe Zhang, Pengju Zhang, Jia Chen, Lei Wang, Yuanjin Zheng
Summary: This paper presents a gas recognition model using the wavelet transform coefficient map-capsule network (WTCM-CapsNet) that improves the accuracy of gas recognition by utilizing dynamic feature information.
IEEE SENSORS JOURNAL
(2022)
Article
Chemistry, Analytical
Anup Vanarse, Adam Osseiran, Alexander Rassau, Peter van der Made
Summary: This paper presents the development and application of artificial olfactory systems, focusing on bioinspired algorithms and spiking neural networks. The authors demonstrate that deploying a SNN-based classifier on neuromorphic hardware can achieve high accuracy and real-time performance with low power consumption.
Article
Chemistry, Analytical
Alessandro Tonacci, Alessandro Scafile, Lucia Billeci, Francesco Sansone
Summary: The technological developments have enabled innovative approaches for disease diagnosis. Researchers have been studying the microbiota composition in biological fluids to develop less invasive and more affordable tools such as electronic nose and electronic tongue which are gaining importance in the field.
Article
Chemistry, Analytical
Zhifang Liang, Lei Zhang, Fengchun Tian, Congzhe Wang, Liu Yang, Tan Guo, Lian Xiong
Summary: Sensor drift caused by aging components and environmental factors seriously affects the performance and lifespan of electronic nose (E-nose). Existing research mainly uses offline compensation techniques, but the dynamic and uncertainty of sensor drift make offline techniques unsuitable for practical applications. A semi-supervised online method based on the WWH problem is proposed to address when, which, and how to update the prediction model for drift compensation. Experiment results demonstrate that sensor drift can be effectively compensated online using this method.
SENSORS AND ACTUATORS B-CHEMICAL
(2021)
Review
Chemistry, Analytical
Tomasz Wasilewski, Jacek Gebicki
Summary: Explosives detection systems rely on artificial olfaction technologies to detect a wide range of explosive materials and their vapours. The trend is towards improving sensors' fundamental metrological parameters to construct sensor arrays for detecting trace quantities of explosives. Progress in nanotechnology and mimicking biological sense of smell have expanded the boundaries of artificial olfaction technologies.
MICROCHEMICAL JOURNAL
(2021)
Article
Computer Science, Artificial Intelligence
Jie Xie, Kai Hu, Guofa Li, Ya Guo
Summary: This study presents a CNN-based method for driving behavior classification using multi-sliding window fusion. By constructing multiple sliding windows of different sizes to extract features and utilizing CNN for classification, the proposed method achieves a macro F1-score of up to 80.25% on the UAH-DriveSet dataset, outperforming other fusion methods.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Engineering, Chemical
Ziyi Guan, Suijun Liu, Ying Liu, Ting Cui, Linchao Yang, Jinhui Cai, Bin Liu, Yuhao Liu, Jinming Li
Summary: This paper proposes an anomaly detection method based on the sliding-window recursive Lasso algorithm, which tracks the changes in flowmeter operating conditions and ensures accurate flow measurement, promoting high-quality cigarette production.
Review
Engineering, Electrical & Electronic
Xingan Yang, Meng Li, Xiaohua Ji, Junqing Chang, Zanhong Deng, Gang Meng
Summary: This article introduces the rapid applications of the smart electronic nose (E-nose) in various fields and emphasizes the role of recognition algorithms in its performance. The traditional algorithms and artificial neural networks (ANNs)-based algorithms are analyzed in detail, along with the evaluation metrics and challenges.
IEEE SENSORS JOURNAL
(2023)
Article
Computer Science, Artificial Intelligence
Ivan Garcia-Aguilar, Rafael Marcos Luque-Baena, Ezequiel Lopez-Rubio
Summary: This research focuses on small object detection in video surveillance images, proposing a method to enhance detection performance without modifying the structure of existing pre-trained models. Experimental results demonstrate the effectiveness of this approach in a variety of traffic images, achieving significant improvement in average scores compared to the initial pre-trained model accuracy.
Article
Computer Science, Artificial Intelligence
Mercedes Garcia-Salguero, Jesus Briales, Javier Gonzalez-Jimenez
Summary: This paper proposes a method for solving the Relative Pose problem with optimality guarantees through optimization of the set of essential matrices to minimize squared epipolar error. By leveraging equivalent definitions and overconstrained characteristics, a fast and reliable solver is presented, suitable for various real-world applications.
JOURNAL OF MATHEMATICAL IMAGING AND VISION
(2022)
Article
Computer Science, Artificial Intelligence
Jose Luis Matez-Bandera, Javier Monroy, Javier Gonzalez-Jimenez
Summary: In this paper, an attention mechanism is proposed for mobile robots to address the problem of place categorization. The approach utilizes active perception to capture environment images with distinctive details, aiming to improve the efficiency of place categorization. By controlling the line-of-sight of the robot's camera and predicting the robot's movements through estimated navigation paths, the proposed method selects the most informative view and makes consistent decisions. Experimental results demonstrate the superiority of the proposed method over traditional camera configurations and pure exploratory approaches in terms of quickness and accuracy.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Chemistry, Analytical
Jose-Luis Matez-Bandera, David Fernandez-Chaves, Jose-Raul Ruiz-Sarmiento, Javier Monroy, Nicolai Petkov, Javier Gonzalez-Jimenez
Summary: This paper proposes LTC-Mapping, a method for building object-oriented semantic maps that remain consistent in the long-term operation of mobile robots. It focuses on preventing object duplication and handling dynamic scenes by using 3D bounding boxes to model objects and analyzing their visibility. The method also incorporates semantic information and includes a mechanism to remove objects that are no longer detected.
Article
Computer Science, Interdisciplinary Applications
Miguel A. Molina-Cabello, Karl Thurnhofer-Hemsi, David Molina-Cabello, Esteban J. Palomo
Summary: Understanding student learning styles is crucial in designing effective teaching methods that can enhance performance with less effort. This study proposes a new software based on the Honey-Alonso Learning Styles Questionnaire, which clusters student learning styles and analyzes the possible relation between grades and learning style profiles. The results obtained from three different computer science engineering courses demonstrate the potential correlation, providing valuable insights into how students approach learning materials.
COMPUTER APPLICATIONS IN ENGINEERING EDUCATION
(2023)
Article
Computer Science, Artificial Intelligence
Ivan Garcia-Aguilar, Jorge Garcia-Gonzalez, Rafael Marcos Luque-Baena, Ezequiel Lopez-Rubio
Summary: The use of technology in road management systems has led to real-time visual information in thousands of locations on road networks. Convolutional neural networks have greatly improved object detection in this field, overcoming deficiencies in pre-trained models for detecting small objects. However, retraining the model with manual labeling from each IP camera on the extensive road network is not feasible. Our proposal introduces an automatic procedure for detecting small-scale objects in traffic sequences.
PATTERN RECOGNITION LETTERS
(2023)
Article
Chemistry, Analytical
Andres Gongora, Javier Monroy, Faezeh Rahbar, Chiara Ercolani, Javier Gonzalez-Jimenez, Alcherio Martinoli
Summary: This paper proposes an efficient exploration algorithm for 2D gas distribution mapping with an autonomous mobile robot, which combines a Gaussian Markov random field estimator and a partially observable Markov decision process. It continuously updates the gas map and chooses the next location based on the information provided, leading to an efficient sampling path and a complete gas map with a relatively low number of measurements. It also accounts for wind currents in the environment, improving the reliability of the gas map.
Article
Robotics
Mercedes Garcia-Salguero, Javier Gonzalez-Jimenez
Summary: This letter presents a fast and certifiable solver for the N-view triangulation problem in field robotic systems, which doesn't require specific optimization software package and can be implemented with any linear algebra library. The solver can solve problem instances with $N=10$ views in 150 microseconds on a standard desktop computer, and obtains and certifies the optimal solution in more than 99% of the problem instances on real data.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Article
Computer Science, Artificial Intelligence
Ivan Garcia-Aguilar, Jorge Garcia-Gonzalez, Daniel Medina, Rafael Marcos Luque-Baena, Enrique Dominguez, Ezequiel Lopez-Rubio
Summary: This work proposes a real-time deep learning-based framework to estimate vehicle speeds from image captures through an onboard camera. The proposed system can detect and track vehicles using deep neural networks and a tracking algorithm, and estimate their speeds based on their positions and sizes in the camera frame. It provides a low-cost solution for speed estimation in vehicles and has potential applications in vehicle safety systems, driver assistance, and autonomous driving technologies.
Proceedings Paper
Computer Science, Artificial Intelligence
Rafael M. Luque-Baena, Irene Romero Granados, Ariadna Jimenez-Partinen, Esteban J. Palomo, Manuel Jimenez-Navarro
Summary: The emergence of deep learning has led to its wide application in various fields, including the clinical field. This study aims to develop an artificial intelligence-based system for analyzing coronary angiography images to detect and predict cardiovascular diseases.
2022 IEEE INTERNATIONAL CONFERENCE ON METROLOGY FOR EXTENDED REALITY, ARTIFICIAL INTELLIGENCE AND NEURAL ENGINEERING (METROXRAINE)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Esteban J. Palomo, Miguel A. Zafra-Santisteban, Rafael M. Luque-Baena
Summary: This paper proposes a Computer-Aided Diagnosis (CAD) system based on Convolutional Neural Networks (CNNs) for pneumonia detection in chest X-ray images. The experimental results demonstrate an accuracy rate of 98.59% for the proposed system.
2022 IEEE INTERNATIONAL CONFERENCE ON METROLOGY FOR EXTENDED REALITY, ARTIFICIAL INTELLIGENCE AND NEURAL ENGINEERING (METROXRAINE)
(2022)
Article
Robotics
Jose-Luis Matez-Bandera, Javier Monroy, Javier Gonzalez-Jimenez
Summary: This letter introduces Sigma-FP, a novel 3D reconstruction method that obtains the floor plan of a multi-room environment using RGB-D images captured by a wheeled mobile robot. The method extracts planar patches of visible walls from each image and characterizes them using a multivariate Gaussian distribution. It takes into account the probabilistic nature of robot localization and combines the planar patches into a 3D global model. Additionally, it detects openings in the wall using depth data to create a more realistic representation.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Miguel A. Molina-Cabello, Karl Thurnhofer-Hemsi, Enrique Dominguez, Ezequiel Lopez-Rubio, Esteban J. Palomo
Summary: Learning styles describe the predominant skills for learning tasks. In the context of university education, knowing students' learning styles provides a great opportunity to improve teaching and evaluation. This study conducted a longitudinal analysis on the correlation between students' grades and the results of the Honey-Alonso Learning Styles Questionnaire (CHAEA), focusing on two different computer science engineering courses in the academic years 2018/2019, 2019/2020, and 2020/2021. The results were analyzed to evaluate the impact of adapting to digital lessons during the last year.
14TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE IN SECURITY FOR INFORMATION SYSTEMS AND 12TH INTERNATIONAL CONFERENCE ON EUROPEAN TRANSNATIONAL EDUCATIONAL (CISIS 2021 AND ICEUTE 2021)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Esteban J. Palomo, Jesus Benito-Picazo, Enrique Dominguez, Ezequiel Lopez-Rubio, Francisco Ortega-Zamorano
Summary: This paper proposes a new color quantization method based on a self-organized artificial neural network called the Growing Hierarchical Bregman Neural Gas (GHBNG). The GHBNG uses Bregman divergences to select the best suitable divergence for color quantization. Experimental results confirm the effectiveness of this approach.
16TH INTERNATIONAL CONFERENCE ON SOFT COMPUTING MODELS IN INDUSTRIAL AND ENVIRONMENTAL APPLICATIONS (SOCO 2021)
(2022)
Article
Automation & Control Systems
Haifei Peng, Jian Long, Cheng Huang, Shibo Wei, Zhencheng Ye
Summary: This paper proposes a novel multi-modal hybrid modeling strategy (GMVAE-STA) that can effectively extract deep multi-modal representations and complex spatial and temporal relationships, and applies it to industrial process prediction.
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS
(2024)
