Pub Date : 2024-06-14DOI: 10.1109/TAFE.2024.3409396
Daniele M. Crafa;Christian Riboldi;Marco Carminati
Sets of metal electrodes applied along pipelines can serve both for detecting leaks of water, as well as to bring power and transmit data among remote monitoring units. We present a modular electronic system developed to demonstrate this versatile hybrid wired and wireless sensing network concept applied to monitoring water distribution for agricultural applications. The system provides km-scale granularity, submeter spatial resolution and a selectable temporal resolution from seconds to hours. The central unit communicates with the gateway via a LoRa radio and contains the readout of water sensors (pressure, temperature, and flow rate by means of ultrasounds), while the remote unit detects water leakage by a novel sensing concept based on multiplexed differential impedance measurements. The latter is achieved with a 2 MHz analog lock-in circuit sequentially connected to the four electrodes. A small-scale hydraulic loop was built to experimentally validate the system. All parameters are tracked with 1% resolution. The total power consumption was minimized to only 10 mWh/day, easily provided by a compact solar panel for energetic autonomy.
{"title":"Distributed Low-Power Electronic Units for Sensing and Communication in Water Pipeline Monitoring","authors":"Daniele M. Crafa;Christian Riboldi;Marco Carminati","doi":"10.1109/TAFE.2024.3409396","DOIUrl":"https://doi.org/10.1109/TAFE.2024.3409396","url":null,"abstract":"Sets of metal electrodes applied along pipelines can serve both for detecting leaks of water, as well as to bring power and transmit data among remote monitoring units. We present a modular electronic system developed to demonstrate this versatile hybrid wired and wireless sensing network concept applied to monitoring water distribution for agricultural applications. The system provides km-scale granularity, submeter spatial resolution and a selectable temporal resolution from seconds to hours. The central unit communicates with the gateway via a LoRa radio and contains the readout of water sensors (pressure, temperature, and flow rate by means of ultrasounds), while the remote unit detects water leakage by a novel sensing concept based on multiplexed differential impedance measurements. The latter is achieved with a 2 MHz analog lock-in circuit sequentially connected to the four electrodes. A small-scale hydraulic loop was built to experimentally validate the system. All parameters are tracked with 1% resolution. The total power consumption was minimized to only 10 mWh/day, easily provided by a compact solar panel for energetic autonomy.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"2 2","pages":"209-217"},"PeriodicalIF":0.0,"publicationDate":"2024-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142430883","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Fungi can be used as the environmental bioindicators of a given area. Detection and localization of mushrooms in their natural habitats represent an important task that can help scientists and conservationists to classify them and carefully study their interaction with the microclimate. Mushrooms are difficult to identify due to the significant variability of their macroscopic features. To address this, the current work aims to provide the accurate and efficient way of identifying various mushroom species in their natural environments. In this article, a comprehensive dataset of annotated mushroom images was created to test the detection performance of five deep instance segmentation architectures (i.e., mask region-based convolutional neural network (Mask R-CNN), Mask Scoring R-CNN, Cascade Mask R-CNN, Hybrid Task Cascade, and DetectoRS). In addition, the study also compares various convolutional neural network (CNN)-based and visual transformer-based backbone feature extraction components for Mask R-CNN using a set of evaluation metrics. The results showed that the proposed instance segmentation models, which employed transfer learning and fine-tuning, adequately identified mushroom instances despite the complex backgrounds. The Mask R-CNN model architecture with ResNeXt as a backbone was superior to visual transformers. Overall, DetectoRS was the best model to detect mushrooms in various complex natural habitats and reached satisfactory results for instance segmentation (mean average precision = 0.69; recall = 0.79; and F 1-score = 0.74), producing well-defined individual mushroom masks. The findings of this study will support the development of a digital tool for the automated detection and segmentation of various mushroom instances in a wide range of natural environments.
{"title":"Deep Learning-Based Instance Segmentation of Mushrooms in Their Natural Habitats","authors":"Christos Charisis;Konstantinos Karantzalos;Dimitrios Argyropoulos","doi":"10.1109/TAFE.2024.3405179","DOIUrl":"https://doi.org/10.1109/TAFE.2024.3405179","url":null,"abstract":"Fungi can be used as the environmental bioindicators of a given area. Detection and localization of mushrooms in their natural habitats represent an important task that can help scientists and conservationists to classify them and carefully study their interaction with the microclimate. Mushrooms are difficult to identify due to the significant variability of their macroscopic features. To address this, the current work aims to provide the accurate and efficient way of identifying various mushroom species in their natural environments. In this article, a comprehensive dataset of annotated mushroom images was created to test the detection performance of five deep instance segmentation architectures (i.e., mask region-based convolutional neural network (Mask R-CNN), Mask Scoring R-CNN, Cascade Mask R-CNN, Hybrid Task Cascade, and DetectoRS). In addition, the study also compares various convolutional neural network (CNN)-based and visual transformer-based backbone feature extraction components for Mask R-CNN using a set of evaluation metrics. The results showed that the proposed instance segmentation models, which employed transfer learning and fine-tuning, adequately identified mushroom instances despite the complex backgrounds. The Mask R-CNN model architecture with ResNeXt as a backbone was superior to visual transformers. Overall, DetectoRS was the best model to detect mushrooms in various complex natural habitats and reached satisfactory results for instance segmentation (mean average precision = 0.69; recall = 0.79; and \u0000<italic>F</i>\u00001-score = 0.74), producing well-defined individual mushroom masks. The findings of this study will support the development of a digital tool for the automated detection and segmentation of various mushroom instances in a wide range of natural environments.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"2 2","pages":"403-412"},"PeriodicalIF":0.0,"publicationDate":"2024-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142408883","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-24DOI: 10.1109/TAFE.2024.3385185
Giacomo Muntoni;Nicola Curreli;Davide Toro;Andrea Melis;Matteo Bruno Lodi;Antonio Loddo;Giuseppe Mazzarella;Alessandro Fanti
Food quality is crucial in today's processing industry. The organoleptic properties of most food materials are known to depend on their water content. The monitoring of food quality and moisture content calls for engineering solutions. To this aim, given their nondestructive nature and cost-effective features, microwave sensors are a valuable tool. However, for some peculiar food processing industries, suitable engineered microwave devices must be designed. Therein, we will focus on the case of the Carasau bread industry. Carasau bread is a typical food product from Sardinia (IT). In this work, we will present the design, realization, and characterization of a coaxial fixture, working between 0.5 and 3 GHz, for the determination of the complex dielectric permittivity of Carasau bread dough. Through a nonlinear regression model based on a particle swarm optimization routine, the scattering parameters are used to retrieve the electromagnetic properties of bread doughs. By making a comparison with the complex dielectric permittivity measured with an open-ended coaxial probe, an average error of 3% for the real part and 6% for the imaginary part has been found. The proposed device is driven by a Raspberry Pi that controls the acquisition of a pocket-vector network analyzer (VNA), thus representing a cost-effective electronic system for industrial applications.
{"title":"A Coaxial Line Fixture Based on a Hybrid PSO-NLR Model for in Situ Dielectric Permittivity Determination of Carasau Bread Dough","authors":"Giacomo Muntoni;Nicola Curreli;Davide Toro;Andrea Melis;Matteo Bruno Lodi;Antonio Loddo;Giuseppe Mazzarella;Alessandro Fanti","doi":"10.1109/TAFE.2024.3385185","DOIUrl":"https://doi.org/10.1109/TAFE.2024.3385185","url":null,"abstract":"Food quality is crucial in today's processing industry. The organoleptic properties of most food materials are known to depend on their water content. The monitoring of food quality and moisture content calls for engineering solutions. To this aim, given their nondestructive nature and cost-effective features, microwave sensors are a valuable tool. However, for some peculiar food processing industries, suitable engineered microwave devices must be designed. Therein, we will focus on the case of the Carasau bread industry. Carasau bread is a typical food product from Sardinia (IT). In this work, we will present the design, realization, and characterization of a coaxial fixture, working between 0.5 and 3 GHz, for the determination of the complex dielectric permittivity of Carasau bread dough. Through a nonlinear regression model based on a particle swarm optimization routine, the scattering parameters are used to retrieve the electromagnetic properties of bread doughs. By making a comparison with the complex dielectric permittivity measured with an open-ended coaxial probe, an average error of 3% for the real part and 6% for the imaginary part has been found. The proposed device is driven by a Raspberry Pi that controls the acquisition of a pocket-vector network analyzer (VNA), thus representing a cost-effective electronic system for industrial applications.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"2 2","pages":"381-391"},"PeriodicalIF":0.0,"publicationDate":"2024-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10507792","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142408758","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-18DOI: 10.1109/TAFE.2024.3379245
Siqi Zhou;Ling Wang;Jie Liu;Jinshan Tang
Accurate and timely prediction of crop growth is of great significance to ensure crop yields, and researchers have developed several crop models for the prediction of crop growth. However, there are large differences between the simulation results obtained by the crop models and the actual results; thus, in this article, we proposed to combine the simulation results with the collected crop data for data assimilation so that the accuracy of prediction will be improved. In this article, an EnKF-LSTM data assimilation method for various crops is proposed by combining an ensemble Kalman filter and long short-term memory (LSTM) neural network, which effectively avoids the overfitting problem of the existing data assimilation methods and eliminates the uncertainty of the measured data. The verification of the proposed EnKF-LSTM method and the comparison of the proposed method with other data assimilation methods were performed using datasets collected by sensor equipment deployed on a farm.
{"title":"An EnKF-LSTM Assimilation Algorithm for Crop Growth Model","authors":"Siqi Zhou;Ling Wang;Jie Liu;Jinshan Tang","doi":"10.1109/TAFE.2024.3379245","DOIUrl":"https://doi.org/10.1109/TAFE.2024.3379245","url":null,"abstract":"Accurate and timely prediction of crop growth is of great significance to ensure crop yields, and researchers have developed several crop models for the prediction of crop growth. However, there are large differences between the simulation results obtained by the crop models and the actual results; thus, in this article, we proposed to combine the simulation results with the collected crop data for data assimilation so that the accuracy of prediction will be improved. In this article, an EnKF-LSTM data assimilation method for various crops is proposed by combining an ensemble Kalman filter and long short-term memory (LSTM) neural network, which effectively avoids the overfitting problem of the existing data assimilation methods and eliminates the uncertainty of the measured data. The verification of the proposed EnKF-LSTM method and the comparison of the proposed method with other data assimilation methods were performed using datasets collected by sensor equipment deployed on a farm.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"2 2","pages":"372-380"},"PeriodicalIF":0.0,"publicationDate":"2024-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142408755","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-11DOI: 10.1109/TAFE.2024.3379190
Rekha Raja;Akshay K. Burusa;Gert Kootstra;Eldert J. Van Henten
This research article presents an advanced robotic system designed for efficient pick-and-place of deformable poultry pieces from cluttered bins. The system incorporates a novel architecture with seamless integration of various modules, enabling the robot to handle deformable poultry with precision. It introduces a comprehensive evaluation approach to assess the system's performance, considering perception, state modeling, planning and control, gripping and manipulation. The experiments were conducted on two different samples of chicken pieces with varying weights and shapes, under complex and simple scenarios. Performance indicators, failure categories, and cycle time were used for evaluation. The evaluation revealed an overall success rate of 49.4% for picking and placing chicken pieces, with failure rates of 21.8% for perception, 30.7% for gripping, and 11% for manipulation modules. These results highlight areas of improvement, particularly in object detection, grasp pose estimation in clutter, and gripper designs for deformable products, to create a robust pick-and-place solution. The proposed robotic system and evaluation method hold immense potential for revolutionizing the meat processing industry and other food processing sectors, making automation more efficient and adaptable to meet the increasing demand in the food industry.
{"title":"Advanced Robotic System for Efficient Pick-and-Place of Deformable Poultry in Cluttered Bin: A Comprehensive Evaluation Approach","authors":"Rekha Raja;Akshay K. Burusa;Gert Kootstra;Eldert J. Van Henten","doi":"10.1109/TAFE.2024.3379190","DOIUrl":"https://doi.org/10.1109/TAFE.2024.3379190","url":null,"abstract":"This research article presents an advanced robotic system designed for efficient pick-and-place of deformable poultry pieces from cluttered bins. The system incorporates a novel architecture with seamless integration of various modules, enabling the robot to handle deformable poultry with precision. It introduces a comprehensive evaluation approach to assess the system's performance, considering perception, state modeling, planning and control, gripping and manipulation. The experiments were conducted on two different samples of chicken pieces with varying weights and shapes, under complex and simple scenarios. Performance indicators, failure categories, and cycle time were used for evaluation. The evaluation revealed an overall success rate of 49.4% for picking and placing chicken pieces, with failure rates of 21.8% for perception, 30.7% for gripping, and 11% for manipulation modules. These results highlight areas of improvement, particularly in object detection, grasp pose estimation in clutter, and gripper designs for deformable products, to create a robust pick-and-place solution. The proposed robotic system and evaluation method hold immense potential for revolutionizing the meat processing industry and other food processing sectors, making automation more efficient and adaptable to meet the increasing demand in the food industry.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"2 2","pages":"355-371"},"PeriodicalIF":0.0,"publicationDate":"2024-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142430875","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-10DOI: 10.1109/TAFE.2024.3380736
{"title":"IEEE Circuits and Systems Society Information","authors":"","doi":"10.1109/TAFE.2024.3380736","DOIUrl":"https://doi.org/10.1109/TAFE.2024.3380736","url":null,"abstract":"","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"2 1","pages":"C3-C3"},"PeriodicalIF":0.0,"publicationDate":"2024-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10496226","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140544306","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-10DOI: 10.1109/TAFE.2024.3380732
{"title":"IEEE Circuits and Systems Society Information","authors":"","doi":"10.1109/TAFE.2024.3380732","DOIUrl":"https://doi.org/10.1109/TAFE.2024.3380732","url":null,"abstract":"","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"2 1","pages":"C2-C2"},"PeriodicalIF":0.0,"publicationDate":"2024-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10496260","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140544305","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-08DOI: 10.1109/TAFE.2024.3379378
Vasimalla Yesudasu;Rupam Srivastava;Sarika Pal;M S Mani Rajan;Yogendra Kumar Prajapati
The detection of pseudomonas bacteria is crucial for multiple reasons, given its substantial impact on the environment, plants, agrifoods, and human health. This article presents the improvement in the performance of a sophisticated surface plasmon resonance technique-based sensor for detecting pseudomonas bacteria. The proposed sensor structure utilizes three bacterial attachments, namely, toluene, nicotine, and poly (trifluoroethyl methacrylate), as affinity layers. The Kretschmann sensor design includes silver, silicon, titanate material, black phosphorus (BP), an affinity layer, and a sensing medium. Titanate is a ferroelectric substance that presents numerous benefits when employed in sensors and electronic devices. The proposed structure has a maximum provided sensitivity of 430 $^circ /text{RIU}$ , a quality factor of 88.84 $text{RI}{{mathrm{U}}^{ - 1}}$ , and a detection accuracy value of 2.3. The results indicate a substantial enhancement in comparison to the reported sensor in the literature.
{"title":"Surface-Plasmon and Titanate Material-Assisted Sensor Structure for Pseudomonas Bacteria Detection With Increased Sensitivity","authors":"Vasimalla Yesudasu;Rupam Srivastava;Sarika Pal;M S Mani Rajan;Yogendra Kumar Prajapati","doi":"10.1109/TAFE.2024.3379378","DOIUrl":"https://doi.org/10.1109/TAFE.2024.3379378","url":null,"abstract":"The detection of pseudomonas bacteria is crucial for multiple reasons, given its substantial impact on the environment, plants, agrifoods, and human health. This article presents the improvement in the performance of a sophisticated surface plasmon resonance technique-based sensor for detecting pseudomonas bacteria. The proposed sensor structure utilizes three bacterial attachments, namely, toluene, nicotine, and poly (trifluoroethyl methacrylate), as affinity layers. The Kretschmann sensor design includes silver, silicon, titanate material, black phosphorus (BP), an affinity layer, and a sensing medium. Titanate is a ferroelectric substance that presents numerous benefits when employed in sensors and electronic devices. The proposed structure has a maximum provided sensitivity of 430\u0000<inline-formula><tex-math>$^circ /text{RIU}$</tex-math></inline-formula>\u0000, a quality factor of 88.84 \u0000<inline-formula><tex-math>$text{RI}{{mathrm{U}}^{ - 1}}$</tex-math></inline-formula>\u0000, and a detection accuracy value of 2.3. The results indicate a substantial enhancement in comparison to the reported sensor in the literature.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"2 2","pages":"347-354"},"PeriodicalIF":0.0,"publicationDate":"2024-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142430750","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-31DOI: 10.1109/TAFE.2024.3401252
Elena Filipescu;Giovanni Paolo Colucci;Daniele Trinchero
An innovative implementation of an electronic leaf wetness sensor (LWS) is proposed. It utilizes capacitive sensing, combined with an innovative data acquisition method, which implements a capacitance-to-digital converter. The study explores the design procedure of a capacitive LWS, proposing an analytical approach and emphasizing low manufacturing costs. Since the LWS is intended for Internet-of-Things applications, this article estimates its energy consumption, introducing a boost regulator to optimize power usage, contributing to extend the battery life. The study presents simulation results and experimental validations, including an ad-hoc calibration procedure under controlled conditions. The sensors were tested in real agricultural environments over a complete vegetative season, demonstrating their capability to operate continuously without problems.
{"title":"Design and Implementation of a Capacitive Leaf Wetness Sensor Based on Capacitance-to-Digital Conversion","authors":"Elena Filipescu;Giovanni Paolo Colucci;Daniele Trinchero","doi":"10.1109/TAFE.2024.3401252","DOIUrl":"https://doi.org/10.1109/TAFE.2024.3401252","url":null,"abstract":"An innovative implementation of an electronic leaf wetness sensor (LWS) is proposed. It utilizes capacitive sensing, combined with an innovative data acquisition method, which implements a capacitance-to-digital converter. The study explores the design procedure of a capacitive LWS, proposing an analytical approach and emphasizing low manufacturing costs. Since the LWS is intended for Internet-of-Things applications, this article estimates its energy consumption, introducing a boost regulator to optimize power usage, contributing to extend the battery life. The study presents simulation results and experimental validations, including an ad-hoc calibration procedure under controlled conditions. The sensors were tested in real agricultural environments over a complete vegetative season, demonstrating their capability to operate continuously without problems.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"2 2","pages":"244-251"},"PeriodicalIF":0.0,"publicationDate":"2024-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142430802","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-21DOI: 10.1109/TAFE.2024.3374753
Samson Damilola Fabiyi;Paul Murray;Jaime Zabalza;Christos Tachtatzis;Hai Vu;Trung-Kien Dao
Hyperspectral imaging (HSI) has been reported to produce promising results in the classification of rice seeds. However, HSI data often require the use of dimensionality reduction techniques for the removal of redundant data. Folded linear discriminant analysis (F-LDA) is an extension of linear discriminant analysis (LDA, a commonly used technique for dimensionality reduction), and was recently proposed to address the limitations of LDA, particularly its poor performance when dealing with a small number of training samples which is a usual scenario in HSI applications. This article presents an improved version of F-LDA, exploring the feasibility of hybridizing a genetic algorithm (GA) and F-LDA for effective dimensionality reduction in HSI-based rice seeds classification. The proposed approach, inspired by the previous combination of GA with principle component analysis, is evaluated on rice seed datasets containing 256 spectral bands. Experimental results show that, in addition to attaining promising classification accuracies of up to 96.21%, this novel combination of GA and F-LDA (GA + F-LDA) can further reduce the computational complexity and memory requirement in the standalone F-LDA. It is worth noting that these benefits are not without a slight reduction in classification accuracy when evaluated against those reported for the standard F-LDA (up to 96.99%).
{"title":"A New Hybridized Dimensionality Reduction Approach Using Genetic Algorithm and Folded Linear Discriminant Analysis Applied to Hyperspectral Imaging for Effective Rice Seed Classification","authors":"Samson Damilola Fabiyi;Paul Murray;Jaime Zabalza;Christos Tachtatzis;Hai Vu;Trung-Kien Dao","doi":"10.1109/TAFE.2024.3374753","DOIUrl":"https://doi.org/10.1109/TAFE.2024.3374753","url":null,"abstract":"Hyperspectral imaging (HSI) has been reported to produce promising results in the classification of rice seeds. However, HSI data often require the use of dimensionality reduction techniques for the removal of redundant data. Folded linear discriminant analysis (F-LDA) is an extension of linear discriminant analysis (LDA, a commonly used technique for dimensionality reduction), and was recently proposed to address the limitations of LDA, particularly its poor performance when dealing with a small number of training samples which is a usual scenario in HSI applications. This article presents an improved version of F-LDA, exploring the feasibility of hybridizing a genetic algorithm (GA) and F-LDA for effective dimensionality reduction in HSI-based rice seeds classification. The proposed approach, inspired by the previous combination of GA with principle component analysis, is evaluated on rice seed datasets containing 256 spectral bands. Experimental results show that, in addition to attaining promising classification accuracies of up to 96.21%, this novel combination of GA and F-LDA (GA + F-LDA) can further reduce the computational complexity and memory requirement in the standalone F-LDA. It is worth noting that these benefits are not without a slight reduction in classification accuracy when evaluated against those reported for the standard F-LDA (up to 96.99%).","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"2 1","pages":"151-164"},"PeriodicalIF":0.0,"publicationDate":"2024-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140544090","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：