general update

content/papers/1.md

@@ -10,8 +10,9 @@ tags: ["hyperspectral","classification","platform","weed identification"]
 author: ["Mohamed Raju Ahmed", "<span style='color: blue; font-weight: bold;'>Billy G. Ram </span>", "Cengiz Koparan", "Kirk Howatt", "Yu Zhang", "Xin Sun"]
 
 
-description: " The objective of this study was to classify soybean plants and 5 weed species where a hyperspectral imaging camera with a spectral range from 400-1000 nm was used to acquire the images. " 
-summary: "This study classified soybean and 5 weed species using NIR range of 400-1000 nm and PLS-DA model. A platform for green house data collection was fabricated and data pre-processing was applied." 
+description: "Uses HSI and a robotic platform to distinguish soybeans from weeds. Develops a PLSR model for accurate classification. Identifies key wavelengths related to plant chemicals. Demonstrates potential for automated weed management in soybean fields." 
+
+summary: "Hyperspectral imaging (HSI) effectively differentiates soybeans from five weed species. A robotic platform captured HSI data, which was analyzed using partial least squares regression (PLSR). The best model achieved 86.2% accuracy in classification, identifying key wavelengths linked to plant chemicals. This research shows promise for automated weed control in soybean fields." 
 cover:
     image: "p1.png"
     alt: "Multiclass weed classification data acquisition"

content/papers/2.md

@@ -12,8 +12,8 @@ author: ["Cristiano Costa", "Yu Zhang", "Kirk Howatt", "<span style='color: blue
 
 
 
-description: "The objective of this study was to classify Palmer amaranth and soybean in greenhouse environment using chemometrics method." 
-summary: "Hyperspectral image processing was used to classify Palmer amaranth and soybean species with chemometrics methods (PCA, PLS-DA, and SIMCA) to extract features and establish classification models." 
+description: "Uses hyperspectral imaging to distinguish Palmer amaranth and soybeans. Develops classification models using chemometrics. Achieves promising results for potential application in weed management." 
+summary: "Hyperspectral imaging can effectively differentiate Palmer amaranth from soybeans. Chemometrics methods (PLS-DA, SIMCA) were used to analyze spectral data. Preliminary results show promise for using this technology to improve weed control in agriculture." 
 cover:
     # image: "1.jpg"
     alt: "Greenhouse weed classification"

content/papers/4.md

@@ -1,33 +1,34 @@
 ---
 title: " Predicting Gypsum Tofu Quality from Soybean Seeds Using Hyperspectral Imaging and Machine Learning." 
-date: 2023-09-10
+date: 2024-06-10
 # url: /1/
 # aliases: 
 #     - /static/1/1.pdf
 #     - /static/1/1.jpg
 
 tags: ["classification", "deep learning", "convolutional neural networks", "artificial intelligence"]
-author: ["Malik, A.", "<span style='color: blue; font-weight: bold;'>Ram, B.G.</span>", "Arumugam, D.", "Jin, Z.", "Sun, X.", "<span style='color: green; font-weight: bold;'><i> under submission.</i></span>"]
+author: ["Malik, A.", "<span style='color: blue; font-weight: bold;'>Ram, B.G.</span>", "Arumugam, D.", "Jin, Z.", "Sun, X."]
 
 
-description: "The review analyzed 60 technical research papers on weed detection published in the past decade. The authors investigated research gaps in the use of deep learning techniques for weed detection and discussed novel deep learning approaches for weed identification. This review provides valuable insights into the current state of research on weed management in precision agriculture and highlights the potential of deep learning techniques for improving weed detection." 
+description: "Uses HSI to predict tofu quality from soybean seeds. Identifies key wavelengths linked to protein, carbs, and oil. XGBoost model accurately classifies seeds into quality categories, revolutionizing tofu production efficiency."
 
-summary: "In this study, we present a novel approach for categorizing soybean seeds using a Hyperspectral Imaging system and machine learning. Our method focuses on the seeds’ ability to yield high-quality gypsum tofu. We’ve designed a Convolutional Neural Network (CNN) model that effectively sorts soybeans into four groups, with prediction accuracies between 96% and 99%. The model, built on ten chosen spectral bands, is both reliable and efficient. Additionally, we’ve deduced the chemical makeup linked to these bands, offering vital data for tofu quality prediction." 
+
+summary: "Hyperspectral imaging (HSI) and machine learning accurately predict gypsum tofu quality from soybean seeds. A new Yield and Texture Trade-off Theory was proposed. XGBoost outperformed other models, achieving 96-99% accuracy in classifying soybean seeds based on tofu quality."
 cover:
     # image: "1.jpg"
     alt: "Predicting Gypsum Tofu Quality from Soybean Seeds Using Hyperspectral Imaging and Machine Learning"
     relative: false
 editPost:
-    URL: "https://www.sciencedirect.com/journal/food-control"
-    Text: "Food Control (under submission)"
+    URL: "https://doi.org/10.1016/j.foodcont.2024.110357"
+    Text: "Food Control"
 
 
 ---
 
 ##### Download
 
-<!-- + [Paper will be available after submission](p3.pdf) -->
-+ _Paper will be available after submission._
++ [Paper](p4.pdf)
+
 
 
 
@@ -52,17 +53,24 @@ research enabled rapid, non-destructive prediction of tofu quality from soybean
 using HSI and CNN. With further refinements, this approach could revolutionize
 soybean seed quality assessment.
 
-<!-- ---
+---
+
+##### Figure 1: Classification of soybean seeds based on gypsum tofu quality using (A) Hierarchical clustering analysis (HCA) and (B) Principal Component Analysis (PCA) and the loading score of each component. The color of Class I, II, III, and IV are indicated with red, yellow, green, and blue, respectively.
 
-##### Figure 1: Commercial robots that use computer vision techniques to perform in-field weeding tasks. 
+![](p4_scatterplot.jpg)
 
-![](p3.png) -->
+---
+
+##### Figure 2: Hyperspectral imaging (HSI) profile of soybean seeds at the spectral range spanned from 900 to 1700 nm. (A) The HSI wavelength profile of all the soybeans; (B) The HSI wavelength profile of classified soybeans; (C) Images of soybeans at ten featured wavelengths. The 10 featured wavelengths represented by the image planes were acquired by XGBoost with the feature importance listed.
+
+![](p4_lineplot.jpg)
 
 ---
 
+
 ##### Citation
 
-_Citation will be updated after submission._
+Malik, A., Ram, B., Arumugam, D., Jin, Z., Sun, X., & Xu, M. (2024). Predicting gypsum tofu quality from soybean seeds using hyperspectral imaging and machine learning. Food Control, 160, 110357.
 
 ---
 

content/papers/5.md

@@ -11,9 +11,9 @@ tags: ["classification", "machine learning", "weed identification", "hyperspectr
 author: [ "<span style='color: blue; font-weight: bold;'>Ram, B.G.</span>","Zhang, Y.", "Costa, C.", "Ahmed, M. R.", "Peters, T.", "Jhala, A.", "Howatt, K.", "Sun, X." ]
 
 
-description: "This research focused on the development and comparison of nine supervised machine-learning models for data analysis. A hyperspectral data collection platform was created specifically for field data collection, enhancing the accuracy and efficiency of the process. The study also examined the effectiveness of Matthews Correlation Coefficient (MCC) and F1 scores in handling imbalanced datasets. After rigorous training and comparison, a Quadratic Discriminant Classifier was chosen due to its impressive F1 score of 0.95 and MCC of 0.85, demonstrating its superior performance in classifying and predicting data." 
+description: "Uses hyperspectral imaging to identify Palmer amaranth in soybean fields. Develops machine learning model for classification. Achieves high accuracy and paves way for autonomous weed control." 
 
-summary: "This research focused on the development and comparison of nine supervised machine-learning models for data analysis. A hyperspectral data collection platform was created specifically for field data collection, enhancing the accuracy and efficiency of the process. The study also examined the effectiveness of Matthews Correlation Coefficient (MCC) and F1 scores in handling imbalanced datasets. After rigorous training and comparison, a Quadratic Discriminant Classifier was chosen due to its impressive F1 score of 0.95 and MCC of 0.85, demonstrating its superior performance in classifying and predicting data." 
+summary: "Hyperspectral imaging combined with machine learning accurately differentiates Palmer amaranth from soybeans in field conditions. Quadratic discriminant analysis was the best model, achieving high accuracy, precision, recall, F1 score, and MCC. This research paves the way for real-time weed detection and autonomous weed management systems." 
 cover:
     # image: "1.jpg"
     alt: "Palmer amaranth Identification using Hyperspectral Imaging and Machine Learning Technologies in Soybean Field."