Figure 1.
Web based Paddy Disease Detection System.
Wound healing (WH) is a fundamental physiological process to keep the integrity of the skin, therefore impaired and chronic WH is a common and severe medical problem and represent one of the biggest challenges of public health. The resolution of the WH inflammatory phase is characterized by a complex series of events that involves many cellular types, especially neutrophils, macrophages and inflammatory mediators, which are crucial for a correct wound closure. MicroRNAs (miRNAs) play essential roles in wound repair. In fact, miR-142 is linked to inflammation modulating neutrophils' chemotaxis and polarization, while the polarization of M1 toward the M2 phenotype is driven by miR-223 and miR-132 is linked to chemokines and cytokines that activate endothelial cells and attract leukocytes and peripheral cells to the damage site. Thus, understanding the dysregulation of miRNAs in WH will be decisive for the development of new and more effective therapies for the management of chronic wounds.
Citation: Federica Serra, Lisa Aielli, Erica Costantini. The role of miRNAs in the inflammatory phase of skin wound healing[J]. AIMS Allergy and Immunology, 2021, 5(4): 264-278. doi: 10.3934/Allergy.2021020
| [1] | Jiaxin Luo, Lin Wu, Dinghui Liu, Zhaojun Xiong, Linli Wang, Xiaoxian Qian, Xiaoqiang Sun . Gene regulatory network analysis identifies key genes and regulatory mechanisms involved in acute myocardial infarction using bulk and single cell RNA-seq data. Mathematical Biosciences and Engineering, 2021, 18(6): 7774-7789. doi: 10.3934/mbe.2021386 |
| [2] | Linqian Guo, Qingrong Meng, Wenqi Lin, Kaiyuan Weng . Identification of immune subtypes of melanoma based on single-cell and bulk RNA sequencing data. Mathematical Biosciences and Engineering, 2023, 20(2): 2920-2936. doi: 10.3934/mbe.2023138 |
| [3] | Kaiyu Shen, Shuaiyi Ke, Binyu Chen, Tiantian Zhang, Hongtai Wang, Jianhui Lv, Wencang Gao . Identification and validation of biomarkers for epithelial-mesenchymal transition-related cells to estimate the prognosis and immune microenvironment in primary gastric cancer by the integrated analysis of single-cell and bulk RNA sequencing data. Mathematical Biosciences and Engineering, 2023, 20(8): 13798-13823. doi: 10.3934/mbe.2023614 |
| [4] | Shaoyu Li, Su Xu, Xue Wang, Nilüfer Ertekin-Taner, Duan Chen . An augmented GSNMF model for complete deconvolution of bulk RNA-seq data. Mathematical Biosciences and Engineering, 2025, 22(4): 988-1018. doi: 10.3934/mbe.2025036 |
| [5] | Yi Shi, Xiaoqian Huang, Zhaolan Du, Jianjun Tan . Analysis of single-cell RNA-sequencing data identifies a hypoxic tumor subpopulation associated with poor prognosis in triple-negative breast cancer. Mathematical Biosciences and Engineering, 2022, 19(6): 5793-5812. doi: 10.3934/mbe.2022271 |
| [6] | Xiao Tu, Qinran Zhang, Wei Zhang, Xiufen Zou . Single-cell data-driven mathematical model reveals possible molecular mechanisms of embryonic stem-cell differentiation. Mathematical Biosciences and Engineering, 2019, 16(5): 5877-5896. doi: 10.3934/mbe.2019294 |
| [7] | Changxiang Huan, Jiaxin Gao . Insight into the potential pathogenesis of human osteoarthritis via single-cell RNA sequencing data on osteoblasts. Mathematical Biosciences and Engineering, 2022, 19(6): 6344-6361. doi: 10.3934/mbe.2022297 |
| [8] | Haiqiang Liu, Feifei Shen, Hewei Zhang, Weikai Zhang . Expression and role of cystatin C in hyperthermia-induced brain injury in rats. Mathematical Biosciences and Engineering, 2023, 20(2): 2716-2731. doi: 10.3934/mbe.2023127 |
| [9] | Heyrim Cho, Ya-Huei Kuo, Russell C. Rockne . Comparison of cell state models derived from single-cell RNA sequencing data: graph versus multi-dimensional space. Mathematical Biosciences and Engineering, 2022, 19(8): 8505-8536. doi: 10.3934/mbe.2022395 |
| [10] | Jingxi Xu, Jiangtao Li . Construction of a three commitment points for S phase entry cell cycle model and immune-related ceRNA network to explore novel therapeutic options for psoriasis. Mathematical Biosciences and Engineering, 2022, 19(12): 13483-13525. doi: 10.3934/mbe.2022630 |
Wound healing (WH) is a fundamental physiological process to keep the integrity of the skin, therefore impaired and chronic WH is a common and severe medical problem and represent one of the biggest challenges of public health. The resolution of the WH inflammatory phase is characterized by a complex series of events that involves many cellular types, especially neutrophils, macrophages and inflammatory mediators, which are crucial for a correct wound closure. MicroRNAs (miRNAs) play essential roles in wound repair. In fact, miR-142 is linked to inflammation modulating neutrophils' chemotaxis and polarization, while the polarization of M1 toward the M2 phenotype is driven by miR-223 and miR-132 is linked to chemokines and cytokines that activate endothelial cells and attract leukocytes and peripheral cells to the damage site. Thus, understanding the dysregulation of miRNAs in WH will be decisive for the development of new and more effective therapies for the management of chronic wounds.
In India, agriculture is the significant contribution of the life of people. The quality of food and huge production at lower expenditure is the consideration for the agricultural field. The most vital source of crop management is the exact detection and giving a timely solution to the problem. Detection of a problem in manually is a very complex task against numerous parameters. The advancement of image processing techniques provides an easier solution to these problems. Rice (Oryzae Sativa) is the main food commodity over 75% of the world. There are several rice plant diseases like Leaf Blast, Bacterial Blight, Brown Spot, sheath Blight, leaf streak, Sheath rot, false Smut, etc., occur in the rice-growing fields. Out of these, the proposed method takes into account of five diseases, namely Bacterial Blight, Rice Blast, Brown Spot, Bacterial Leaf Streak, and false Smut. This proposed method recognizes and classifies the disease type of the paddy plant and notifies the stage of the disease to the farmers.
Paddy plant diseases significantly reduce the quality and yield quantity of the rice. These diseases origins are mainly viruses, fungi, and Bacteria. These diseases can cause in parts like leaf, stem, and root. The most common paddy diseases are Leaf Blast, Brown Spot, Bacterial Leaf Blight, Leaf Streak, False Smut, etc. In this work, focus the following four conditions.
(a) Leaf Blast
Leaf Blast is formed by the Magnaporthe Oryzae fungus. It infects all the parts above the ground of the rice plant. It occurs in low soil moisture areas, frequent rain shower areas, and chill temperature in the daytime. Initial symptoms of this disease appear as white to gray-green lesions or spots, with dark green borders. In the developing stage, the lesions on the leaves are elliptical or spindle-shaped and whitish to gray centers with red to brownish or necrotic border. Lesions can first appear in a diamond shape and expand to grow up, which destroys the entire leaf.
(b) Brown Spot
Brown Spot is caused by Cochliobolus Miyabeanus fungus. Brown spot is one of the most common rice diseases which causes huge damaging in the rice plant. This disease affects the coleoptiles, leaves, leaf sheath, panicle branches, glumes, and spikelet. When the infection started in the seed, the discolored seeds are formed especially with a round to oval, dark-brown lesions with a yellow or gold halo.
(c) Bacterial Leaf Blight
Bacterial Leaf Blight is formed by Xanthomonas Oryzae pv. Oryzae fungus. It causes flopping of seedlings and yellowing and drying of leaves. The diseases develop in the weed areas and stubbles. In both temperate and tropical environments, these diseases are highly designed specifically an irrigated and lowland rained areas.
(d) False Smut
False Smut created by grains silkiness, which tends to decrease the grain weight. It also minimizes the germination of seeds. The false Smut is developed in the areas of Rain, high humidity, and high nitrogen soils. Wind also spread the disease spores from one plant to other plants. It is visible only after panicle exertion. It affects the plant at the flowering stage.
The authors [1] proposed a plant disease detection system using statistical based thresholding segmentation. The authors also developed a Raspberry pi-3+ board. They achieved an overall detection accuracy of 98.5%. The authors [2] have made a survey on major technologies using the Internet of Things. They have also reviewed the various applications giving significance to all people. The authors [3] have described the Wireless Moisture Sensor Network (WMSN) and IoT based system for a greenhouse environment. They investigated and observed that the moisture level was reached at the predefined threshold while the plants were watered. And, it is also observed that the fertilizer and the water optimize the described method. The authors [4] presented an algorithm for image segmentation technique for automatic detection and classification of plant leaf diseases. In which, they surveyed different disease classification techniques used for plant leaf disease detection. Image segmentation is performed using a genetic algorithm.
The authors [5] have presented the studies the image processing technologies deployed in paddy domain. They also proposed the architecture for identifying the early stage of the leaf diseases and finding the weed species. This system reduces the risk of diseases and to increase the yield of paddy. The authors [6] have proposed a new technique to diagnose and classify rice diseases. Four rice diseases have identified and classified using minimum distance classifier and K Nearest Neighbor classifier (KNN). By using this different algorithm, features like shape, the color of a diseased portion of the leaf has extracted. The authors got the overall accuracy rated of 87.02% using K Nearest Neighbor classifier (KNN) and 89.2% by using Minimum Distance Classifier (MDC).
The authors [7] developed a three layer IoT architecture used for precision agriculture applications. It collects the required data and relays it to a cloud-based back-end. There it is processed and analyzed. They also developed a prototype of proposed architecture to show its performance advantages. The authors [8] presented the detection and classification of leaf diseases of grape using Support Vector Machine (SVM) classification technique to detect the type of leaf disease. This system detected the diseases with an accuracy of 88.89%. The authors [9] developed an Android based detecting stem diseases on the plant by using image analysis. Hue-based segmentation is used to segment the image and feature values are extracted from the segmented portion for texture analysis using color co-occurrence method.
The authors [10] discussed the methods used for the detection of plant diseases using their leaves images. And also they discussed some segmentation and feature extraction algorithm used in plant disease detection. The authors [11] presented a study on the image processing techniques used to identify and classify fungal disease symptoms affected by different agriculture/horticulture crops. The authors [12] described the different image segmentation algorithms and compared the diseased portion of the rice plant leaves.
The authors [13] proposed a cloud deployment model "Agri-Assistant" to provide agriculture related information assistance to Indian farmers living in rural areas, facing financial and connectivity constraints. This model leverages the existing Government services and mobile service to provide a solution to the existing scenario with minimum burden on farmer's pocket. The authors [14] presented the survey methods to detect, quantify and classify plant diseases from digital images in the visible spectrum using image processing techniques. The authors [15] described a pest disease detection system of different plant leaves. They proposed an automatic detection and calculation of the infected area of leaves in the early stage.
The authors [16] presented an effective method for disease detection in Malus Domestica using techniques like K-Mean clustering, color, and texture analysis. The authors [17] introduced the review of rapid, cost-effective, and reliable health-monitoring sensor which facilitate advancements in agriculture. They also described the modern technologies used for developing a ground-based sensor system to assist in monitoring health and diseases in plants under field conditions. These technologies include spectroscopic and imaging-based, and volatile profiling-based plant disease detection method.
The authors [18] developed an image recognition system to recognize paddy diseases. Images were acquired under laboratory condition using a digital camera. They selected three major diseases Rice Blast (Magnaporthe grisea), Rice sheath blight (Rhizoctonia solani) and Brown Spot (Cochiobolus miyabeanus) for their work. Agriculture work made comfort by the advancement of web based technologies. A digital system for agriculture is developed to increase the crop quality with the help of the Internet of Things (IoT). And, also by developing a website, to help farmers make decisions in advance about his farm, in case they detect any disease. An image processing algorithm based on the pattern recognition methods has been developed for leaf disease detection and classification, and thereby eliminates conventional protruding and time consuming techniques.
A novel Web Enabled Paddy Disease Detection using Compressed Sensing is proposed to detect and classify Paddy diseases. This proposed system will upload the acquired and segmented image to the cloud using Compressed Sensing. This system is useful to minimize the complexity of manual monitoring in the big farms and easily identify the diseases at a very early stage. The Figure shows the web enabled paddy disease detection system.
Images are captured using a digital camera. The segmentation methods are used to perform segmentation for infected area. Then for further classification, the segmented image is uploaded to the cloud. The storage complexity of the cloud is reduced using the Compressed Sensing technique. At the monitor side, the segmented image is reconstructed from the cloud using Compressed Sensing recovery algorithm. Then the features are extracted using statistical Gray Level Co-occurrence Matrix (GLCM) method.
Further using Support Vector Machine (SVM) classifier is used to classify the diseases and give suggestions to the farmers.
The Proposed System consists of Image capturing, Pre-processing, Segmentation by Compressed Sensing in the transmitter section and feature extraction and classification is at the receiver side.
The images of leaves are captured using a digital camera and then applied to the segmentation process to separate the diseased area. The image quality is enhanced using the pre-processing, which is done before the segmentation.
In the pre-processing stage, first contrast enhancement of the image is performed. Then the RGB to L*a*b* transformation is performed. Then the pre-processed image is segmented using K-Means clustering algorithm. Figure 2 shows the input image, Contrast enhancement, and LAB image. Figure 3 shows the LAB color space result.
In the segmentation part, the proposed system uses the K-Means clustering method to segment the diseased part of the leaves. Then the segmented image performs the process of Compressed Sensing algorithm to reduce the storage complexity of the segmented images which are transmitted to the cloud through a wireless medium. The segmented image is shown in Figure 4.
K-Means clustering technique used for segmentation partitions the images into K number of clusters depends on their features. The classification is performed using Euclidean distance is given below.
| (E.d)2=min(μ1−μk)i=n∑i=1j=n∑j=1|X(i,j)−μ2| | (1) |
| μk=∑i=ni=1P(i)+i∑i=ni=1P(i) | (2) |
The first step in K-Means clustering algorithm is getting input image. Using the output of K means, labeling of each pixel is done. Image is segmented based on color. Then the infected part of the image is selected. Figure 5 shows the K-Means clustering output.
The segmented image extracts the measurements using Compressed Sensing. The Discrete Cosine Transform is used to transform the segmented image to the sparse image. Compressed Sensing is applied only to sparse signals. In this proposed method, Block Based Compressed Sensing (BBCS) approach is employed to minimize the computational complexity of the process of Compressed Sensing. The Eqs 3 and 4 gives the blocks corresponding to the disease infected areas which undergoes a Compressed Sensing and to transmit the measurements to the cloud.
| St1/4WrSt | (3) |
| Y1/4StUSt | (4) |
Where rst the sparse vector of the segmented blocks, t = 0, 1, …, T the blocks, w the basis matrix, yst the measurement vector of the segmented block and U the hybrid measurement matrix.
After getting all the measurements, it is uploaded to the cloud. Figure 6 shows the segmented image uploaded into the cloud.
Using the Orthogonal Matching point Pursuit (OMP) algorithm, the segmented images are reconstructed after all the measurements are retrieved from the cloud. This method is an easy and simple method to estimate the sparse signals using the iteration process. Then the segmented image is reconstructed using inverse Discrete Cosine Transform (DCT).
Figure 7 shows the Compressed Sensing (CS) reconstructed segmented image.
Feature extraction is used to extract statistical texture features. These features are obtained using the Gray Level Co-occurrence Matrix (GLCM). The Gray Level Co-occurrence Matrix (GLCM) extracts the first order features such as mean, standard Deviation, Kurtosis, and Skewness and second order features namely contrast, correlation, entropy, energy, homogeneity, variance, and Root Mean Square (RMS).
The extracted features are applied to the classification algorithm. The Support Vector Machine (SVM) classifier is used for the classification which gives high accuracy with the texture features. SVM uses the linear kernel function to classify the healthy and diseased leaves.
The Support Vector Machine (SVM) is a binary classifier which uses the hyper-plane. It is also called the decision boundary between two of the classes. The Figure shows the concept of Support Vector Machine. Different kernels are used to divide the classes. SVM is a binary classifier which examines the hyper-plane dividing into two categories. The boundary is maximized between the hyperplane and the two classes. The samples that are nearest to the margin will be selected in determining the hyperplane are called as support vectors.
Multiclass classification is also possible either by using one-to-one or one-to-many. The highest output function will be determined as the winning class. Classification is performed by considering a larger number of support vectors of the training samples. The standard form of SVM was intended for two-class problems. However, in real life situations, it is often necessary to separate more than two classes at the same time.
After classification, the results are analyzed by the experts, and the information is sent to the farmers. This disease detection makes the farmers take decisions and increases the yield cultivation. Figure 9 shows the classifier output.
The proposed web enabled paddy disease detection is analyzed using simulation and experimental method. The Paddy images are taken from the internet and Indian Rice Research Institute website. There are 1140 images used for this work, 840 images used for training and 400 images taken for testing, and the same images are classified using K Nearest Neighbor (KNN) and Support Vector Machine (SVM) Classifiers.
The diseases considered for this work are Leaf Blast, Bacterial Blight, Brown Spot, and False Smut. The performance evaluation of the proposed system is done in terms of accuracy, sensitivity, and specificity.
The proposed web enabled paddy disease detection is simulated using MATLAB R2016 in Windows 10 PC. The input samples of Paddy with the disease symptoms of Leaf Blast, Bacterial Blight, Brown Spot, False Smut, and Healthy paddy are considered as the input data. The Table 1 shows the percentage of reduction in data for different leaf diseases proportional to the number of the blocks corresponding to the segmented image.
| Leaf diseases | Affected area (%) | Number of Blocks corresponding to the affected area | Percentage of reduction in data (%) |
| Leaf Blast | 16.23 | 205 | 89.1 |
| Bacterial Blight | 15.6 | 514 | 72.8 |
| Brown Spot | 17.5 | 640 | 67.4 |
| False Smut | 16 | 587 | 74.6 |
| Healthy | 15 | 629 | 63.3 |
DownLoad:
CSV
Figures 2, 3, 4 and 7 show the input images, pre-processed images, segmented images, and reconstructed segmented images from cloud after CS recovery of Paddy plant diseases.
Table 2 describes the number of leaves disease samples classified into four categories of leaves disease using the proposed algorithm.
| Disease category | Leaf mages used for training | Leaf images used for testing |
| Healthy | 250 | 100 |
| Blast | 150 | 75 |
| Bacterial Blight | 130 | 75 |
| Brown Spot | 110 | 70 |
| False Smut | 100 | 80 |
DownLoad:
CSV
From Table 3, it can be seen that only two leaves from Blast, Brown Spot, and False Smut leaves are misclassified. Only one leaf with Bacterial Blight disease is classified as healthy, and two Blast diseases are classified as Bacterial Blight and False Smut. Similarly, two Brown Spot leaves are classified as Blast and Healthy leaf. False Smut leaf is classified as Blast and Brown Spot.
| Accuracy = 98.38% | Predicted class | |||||
| Healthy | Blast | Bacterial Blight | Brown Spot | False Smut | ||
| Actual class | Healthy | 98 | 0 | 0 | 1 | 1 |
| Blast | 0 | 73 | 1 | 0 | 1 | |
| Bacterial Blight | 1 | 0 | 74 | 0 | 0 | |
| Brown Spot | 1 | 1 | 0 | 68 | 0 | |
| False Smut | 0 | 1 | 0 | 1 | 78 | |
DownLoad:
CSV
From the experimental results, it is observed that the proposed method can identify and classify the leaf diseases in their initial stages with a less computational effort. The disease recognition rate is assessed using the K Nearest Neighbor (KNN) and Support Vector Machine (SVM) Classifier. Table 3 shows the disease recognition rate of K Nearest Neighbor (KNN) and Support Vector Machine (SVM) Classifier.
Table 4 gives the recognition rate of various diseases and healthy leaf. The KNN classifier produces the accuracy rate of 95.6% for Bacterial Blast, 96% for Bacterial Blight, 96.77% for False Smut, Brown Spot, and healthy leaf. The Multiclass SVM gives the recognition rate of 97.33% for leaf blast, 98.38% for Brown Spot, 98.66% for False Smut, 97.14% for Bacterial Blight and for healthy leaf the recognition rate is 98%. From the results, it is clear that the Multiclass SVM classifier achieves the highest accuracy than other classifiers used in this work.
| Classifiers | Disease recognition rate | ||||
| Healthy (%) | Blast (%) | Bacterial Blight (%) | Brown Spot (%) | False Smut (%) | |
| KNN | 96.77 | 95.6 | 96 | 96.77 | 96.77 |
| Multi class SVM | 98 | 97.33 | 97.14 | 98.38 | 98.66 |
DownLoad:
CSV
The classification of diseased and healthy leaves is done effectively using multiclass SVM classifier, which is shown in the illustrated in the above graph. The Multiclass SVM classifier achieves the best performance with an accuracy of 98.38%, i.e., out of 400 leaves, 391 leaves were correctly classified, while 9 were not. The KNN has produced the accuracy at 96%. In addition to the overall accuracy, the performance of the proposed system is also assessed by the performance measures of sensitivity, specificity, precision, FP rate and kappa, etc.
The Figure 11 depicts the performance measures of the rice blast image. The classification accuracy of proposed method is compared with other existing method which are shown in Table 5. The classification accuracy of 98.38% is achieved using the proposed method.
| Classifier | Classification accuracy (%) | ||
| Thresholding | K-Means clustering | K-Means clustering with CS | |
| Support Vector Machine | 98.44 | 94.4 | 98.37 |
| K-Nearest Neighborhood | 93.4 | 94.4 | 96.77 |
DownLoad:
CSV
The experimental evaluation performed using Arduino is shown in Figure 12. Which is operated using MATLAB software.
The Paddy Disease detection and classification is implemented using Arduino board. Arduino Board is interfacing with MATLAB using Thingspeak Platform. The segmentation measurements are obtained using CS algorithm. The CS measurements are uploaded to the cloud from Arduino board using the inbuilt Wi-Fi.
Figure 13 shows the Block diagram of IoT system.
The Manager/Superuser performs the task of detecting the diseases present in the leaf image. It is interfaced to a platform called ThingSpeak where a user can check his/her result. Thingspeak is the IoT platform which is used to collect the data privately from the sensor. Thingspeak has both private and public channels to upload the data, and each channel is assigned with an ID. The disease output obtained by hardware is shown in Figure 14.
Paddy disease detection is the most noteworthy for agricultural applications to increase the yield. In this paper the digital camera is used to capture the diseased leaves and analyse using image processing techniques. An efficient web based system using Compressed Sensing is proposed for automatic detection and classification of the Paddy diseases namely Leaf Blast, Brown Spot, Bacterial Blight and False Smut and furthermore gives the auspicious notice to agriculturists utilizing web based tool.
The captured images are segmented using K-Means clustering and then the segmented images are uploaded to the cloud using Compressed Sensing algorithm. Then at the monitoring side the segmented images are reconstructed using the compressing sensing recovery algorithm. This method extracts the features using statistical Gray Level Co-occurrence Matrix (GLCM) algorithm. It is trained and tested using the K Nearest Neighbor (KNN) and Support Vector Machine (SVM) Classifiers. The proposed system is also experimentally tested using Arduino, and the CS measurements are transmitted to the Thingspeak IoT platform in real time. The experiment is implemented using MATLAB and measurements are uploaded to the cloud using Thingspeak channels.
This proposed system pertaining only for paddy plants and it can also be applied to other plants by including more diseases and a large number of samples in the input database. It will increase the accuracy rate of disease identification. The proposed and implemented methods have given better performance in terms of accuracy using Support Vector Machine (SVM) classifier than the K Nearest Neighbor (KNN) classifiers.
| [1] |
Liu J, Shu B, Zhou Z, et al. (2020) Involvement of miRNA203 in the proliferation of epidermal stem cells during the process of DM chronic wound healing through Wnt signal pathways. Stem Cell Res Ther 11: 348. doi: 10.1186/s13287-020-01829-x
|
| [2] |
Li D, Peng H, Qu L, et al. (2021) miR-19a/b and miR-20a promote wound healing by regulating the inflammatory response of keratinocytes. J Invest Dermatol 141: 659-671. doi: 10.1016/j.jid.2020.06.037
|
| [3] |
Xu J, Wu W, Zhang L, et al. (2012) The role of microRNA-146a in the pathogenesis of the diabetic wound-healing impairment: correction with mesenchymal stem cell treatment. Diabetes 61: 2906-2912. doi: 10.2337/db12-0145
|
| [4] |
Wu J, Li X, Li D, et al. (2020) MicroRNA-34 family enhances wound inflammation by targeting LGR4. J Invest Dermatol 140: 465-476. doi: 10.1016/j.jid.2019.07.694
|
| [5] |
O'Brien J, Hayder H, Zayed Y, et al. (2018) Overview of MicroRNA biogenesis, mechanisms of actions, and circulation. Front Endocrinol 9: 402. doi: 10.3389/fendo.2018.00402
|
| [6] |
Lu TX, Rothenberg ME (2018) MicroRNA. J Allergy Clin Immun 141: 1202-1207. doi: 10.1016/j.jaci.2017.08.034
|
| [7] |
Ramalingam P, Palanichamy JK, Singh A, et al. (2014) Biogenesis of intronic miRNAs located in clusters by independent transcription and alternative splicing. RNA 20: 76-87. doi: 10.1261/rna.041814.113
|
| [8] |
Bartel DP (2004) MicroRNAs: genomics, biogenesis, mechanism, and function. Cell 116: 281-297. doi: 10.1016/S0092-8674(04)00045-5
|
| [9] |
Vishnoi A, Rani S (2017) MiRNA Biogenesis and regulation of diseases: An overview. Methods Mol Biol 1509: 1-10. doi: 10.1007/978-1-4939-6524-3_1
|
| [10] |
Johanson TM, Lew AM, Chong MM (2013) MicroRNA-independent roles of the RNase III enzymes Drosha and Dicer. Open Biol 3: 130144. doi: 10.1098/rsob.130144
|
| [11] |
Zhang L, Lu Q, Chang C (2020) Epigenetics in health and disease. Adv Exp Med Biol 1253: 3-55. doi: 10.1007/978-981-15-3449-2_1
|
| [12] |
Saliminejad K, Khorram Khorshid HR, Soleymani Fard S, et al. (2019) An overview of microRNAs: Biology, functions, therapeutics, and analysis methods. J Cell Physiol 234: 5451-5465. doi: 10.1002/jcp.27486
|
| [13] |
Krol J, Loedige I, Filipowicz W (2010) The widespread regulation of microRNA biogenesis, function and decay. Nat Rev Genet 11: 597-610. doi: 10.1038/nrg2843
|
| [14] |
Lao TD, Le TAH (2020) MicroRNAs: Biogenesis, functions and potential biomarkers for early screening, prognosis and therapeutic molecular monitoring of nasopharyngeal carcinoma. Processes 8: 966. doi: 10.3390/pr8080966
|
| [15] |
Xu J, Chen Q, Zen K, et al. (2013) Synaptosomes secrete and uptake functionally active microRNAs via exocytosis and endocytosis pathways. J Neurochem 124: 15-25. doi: 10.1111/jnc.12057
|
| [16] |
Ganju A, Khan S, Hafeez BB, et al. (2017) miRNA nanotherapeutics for cancer. Drug Discov Today 22: 424-432. doi: 10.1016/j.drudis.2016.10.014
|
| [17] |
Rousselle P, Braye F, Dayan G (2019) Re-epithelialization of adult skin wounds: Cellular mechanisms and therapeutic strategies. Adv Drug Deliver Rev 146: 344-365. doi: 10.1016/j.addr.2018.06.019
|
| [18] |
Wang Y, Feng Z, Yang M, et al. (2021) Discovery of a novel short peptide with efficacy in accelerating the healing of skin wounds. Pharmacol Res 163: 105296. doi: 10.1016/j.phrs.2020.105296
|
| [19] |
Dini V, Janowska A, Oranges T, et al. (2020) Surrounding skin management in venous leg ulcers: A systematic review. J Tissue Viability 29: 169-175. doi: 10.1016/j.jtv.2020.02.004
|
| [20] |
Lindley LE, Stojadinovic O, Pastar I, et al. (2016) Biology and biomarkers for wound healing. Plast Reconstr Surg 138: 18S-28S. doi: 10.1097/PRS.0000000000002682
|
| [21] |
Gosain A, DiPietro LA (2004) Aging and wound healing. World J Surg 28: 321-326. doi: 10.1007/s00268-003-7397-6
|
| [22] |
Han G, Ceilley R (2017) Chronic wound healing: A review of current management and treatments. Adv Ther 34: 599-610. doi: 10.1007/s12325-017-0478-y
|
| [23] |
Etulain J (2018) Platelets in wound healing and regenerative medicine. Platelets 29: 556-568. doi: 10.1080/09537104.2018.1430357
|
| [24] |
Rodrigues M, Kosaric N, Bonham CA, et al. (2019) Wound healing: A cellular perspective. Physiol Rev 99: 665-706. doi: 10.1152/physrev.00067.2017
|
| [25] |
Opneja A, Kapoor S, Stavrou EX (2019) Contribution of platelets, the coagulation and fibrinolytic systems to cutaneous wound healing. Thromb Res 179: 56-63. doi: 10.1016/j.thromres.2019.05.001
|
| [26] |
Reinke JM, Sorg H (2012) Wound repair and regeneration. Eur Surg Res 49: 35-43. doi: 10.1159/000339613
|
| [27] |
Wilkinson HN, Hardman MJ (2020) Wound healing: cellular mechanisms and pathological outcomes. Open Biol 10: 200223. doi: 10.1098/rsob.200223
|
| [28] |
Velnar T, Bailey T, Smrkolj V (2009) The wound healing process: An overview of the cellular and molecular mechanisms. J Int Med Res 37: 1528-1542. doi: 10.1177/147323000903700531
|
| [29] |
de Oliveira S, Rosowski EE, Huttenlocher A (2016) Neutrophil migration in infection and wound repair: going forward in reverse. Nat Rev Immunol 16: 378-391. doi: 10.1038/nri.2016.49
|
| [30] |
Gonzalez AC, Costa TF, Andrade ZA, et al. (2016) Wound healing—A literature review. An Bras Dermatol 91: 614-620. doi: 10.1590/abd1806-4841.20164741
|
| [31] |
Thuraisingam T, Xu YZ, Eadie K, et al. (2010) MAPKAPK-2 signaling is critical for cutaneous wound healing. J Invest Dermatol 130: 278-286. doi: 10.1038/jid.2009.209
|
| [32] |
Werner S, Krieg T, Smola H (2007) Keratinocyte-fibroblast interactions in wound healing. J Invest Dermatol 127: 998-1008. doi: 10.1038/sj.jid.5700786
|
| [33] |
Jevtić M, Löwa A, Nováčková A, et al. (2020) Impact of intercellular crosstalk between epidermal keratinocytes and dermal fibroblasts on skin homeostasis. Biochim Biophys Acta Mol Cell Res 1867: 118722. doi: 10.1016/j.bbamcr.2020.118722
|
| [34] |
Broughton G, Janis JE, Attinger CE (2006) The basic science of wound healing. Plast Reconstr Surg 117: 12S-34S. doi: 10.1097/01.prs.0000225430.42531.c2
|
| [35] |
Demidova-Rice TN, Hamblin MR, Herman IM (2012) Acute and impaired wound healing: pathophysiology and current methods for drug delivery, part 1: normal and chronic wounds: biology, causes, and approaches to care. Adv Skin Wound Care 25: 304-314. doi: 10.1097/01.ASW.0000416006.55218.d0
|
| [36] |
Lang H, Zhao F, Zhang T, et al. (2017) MicroRNA-149 contributes to scarless wound healing by attenuating inflammatory response. Mol Med Rep 16: 2156-2162. doi: 10.3892/mmr.2017.6796
|
| [37] |
Raziyeva K, Kim Y, Zharkinbekov Z, et al. (2021) Immunology of acute and chronic wound healing. Biomolecules 11: 700. doi: 10.3390/biom11050700
|
| [38] |
Fordham JB, Naqvi AR, Nares S (2015) Regulation of miR-24, miR-30b, and miR-142-3p during macrophage and dendritic cell differentiation potentiates innate immunity. J Leukocyte Biol 98: 195-207. doi: 10.1189/jlb.1A1014-519RR
|
| [39] |
Tahamtan A, Teymoori-Rad M, Nakstad B, et al. (2018) Anti-inflammatory MicroRNAs and their potential for inflammatory diseases treatment. Front Immunol 9: 1377. doi: 10.3389/fimmu.2018.01377
|
| [40] |
Mori R, Tanaka K, Shimokawa I (2018) Identification and functional analysis of inflammation-related miRNAs in skin wound repair. Dev Growth Differ 60: 306-315. doi: 10.1111/dgd.12542
|
| [41] |
Tanaka K, Kim SE, Yano H, et al. (2017) MiR-142 is required for staphylococcus aureus clearance at skin wound sites via small GTPase-mediated regulation of the neutrophil actin cytoskeleton. J Invest Dermatol 137: 931-940. doi: 10.1016/j.jid.2016.11.018
|
| [42] | de Kerckhove M, Tanaka K, Umehara T, et al. (2018) Targeting miR-223 in neutrophils enhances the clearance of Staphylococcus aureus in infected wounds. EMBO Mol Med 10: e9024. |
| [43] |
Li D, Wang A, Liu X, et al. (2015) MicroRNA-132 enhances transition from inflammation to proliferation during wound healing. J Clin Invest 125: 3008-3026. doi: 10.1172/JCI79052
|
| [44] |
Xu X, Hong P, Wang Z, et al. (2021) MicroRNAs in transforming growth factor-beta signaling pathway associated with fibrosis involving different systems of the human body. Front Mol Biosci 8: 707461. doi: 10.3389/fmolb.2021.707461
|
| [45] |
Li D, Landén NX (2017) MicroRNAs in skin wound healing. Eur J Dermatol 27: 12-14. doi: 10.1684/ejd.2017.3040
|
| [46] |
Mahesh G, Biswas R (2019) MicroRNA-155: A master regulator of inflammation. J Interferon Cytokine Res 39: 321-330. doi: 10.1089/jir.2018.0155
|
| [47] |
Cao M, Shikama Y, Kimura H, et al. (2017) Mechanisms of impaired neutrophil migration by MicroRNAs in myelodysplastic syndromes. J Immunol 198: 1887-1899. doi: 10.4049/jimmunol.1600622
|
| [48] |
Wang CR, Zhu HF, Zhu Y (2019) Knockout of MicroRNA-155 ameliorates the Th17/Th9 immune response and promotes wound healing. Curr Med Sci 39: 954-964. doi: 10.1007/s11596-019-2128-x
|
| [49] |
Yang LL, Liu JQ, Bai XZ, et al. (2014) Acute downregulation of miR-155 at wound sites leads to a reduced fibrosis through attenuating inflammatory response. Biochem Biophys Res Commun 453: 153-159. doi: 10.1016/j.bbrc.2014.09.077
|
| [50] |
Ye J, Kang Y, Sun X, et al. (2017) MicroRNA-155 inhibition promoted wound healing in diabetic rats. Int J Low Extrem Wounds 16: 74-84. doi: 10.1177/1534734617706636
|
| [51] | Eissa MG, Artlett CM (2019) The MicroRNA miR-155 is essential in fibrosis. Noncoding RNA 5: 23. |
| [52] |
Fujiwara N, Kobayashi K (2005) Macrophages in inflammation. Curr Drug Targets Inflammation Allergy 4: 281-286. doi: 10.2174/1568010054022024
|
| [53] |
Dang CP, Leelahavanichkul A (2020) Over-expression of miR-223 induces M2 macrophage through glycolysis alteration and attenuates LPS-induced sepsis mouse model, the cell-based therapy in sepsis. PLoS One 15: e0236038. doi: 10.1371/journal.pone.0236038
|
| [54] |
Meng ZX, Wang GX, Lin JD (2012) A microRNA circuitry links macrophage polarization to metabolic homeostasis. Circulation 125: 2815-2917. doi: 10.1161/CIRCULATIONAHA.112.111518
|
| [55] |
Das A, Ganesh K, Khanna S, et al. (2014) Engulfment of apoptotic cells by macrophages: a role of MicroRNA-21 in the resolution of wound inflammation. J Immunol 192: 1120-1129. doi: 10.4049/jimmunol.1300613
|
| [56] |
Sheedy FJ (2015) Turning 21: induction of miR-21 as a key switch in the inflammatory response. Front Immunol 6: 19. doi: 10.3389/fimmu.2015.00019
|
| [57] |
Banerjee J, Sen CK (2013) MicroRNAs in skin and wound healing. Methods Mol Biol 936: 343-356. doi: 10.1007/978-1-62703-083-0_26
|
| [58] |
Lai WF, Siu PM (2014) MicroRNAs as regulators of cutaneous wound healing. J Biosciences 39: 519-524. doi: 10.1007/s12038-014-9421-4
|
| [59] |
Liechty C, Hu J, Zhang L, et al. (2020) Role of microRNA-21 and its underlying mechanisms in inflammatory responses in diabetic wounds. Int J Mol Sci 21: 3328. doi: 10.3390/ijms21093328
|
| [60] |
Wang JK, Wang Z, Li G (2019) MicroRNA-125 in immunity and cancer. Cancer Lett 454: 134-145. doi: 10.1016/j.canlet.2019.04.015
|
| [61] |
Tili E, Michaille JJ, Cimino A, et al. (2007) Modulation of miR-155 and miR-125b levels following lipopolysaccharide/TNF-alpha stimulation and their possible roles in regulating the response to endotoxin shock. J Immunol 179: 5082-5089. doi: 10.4049/jimmunol.179.8.5082
|
| [62] |
Meng Z, Zhou D, Gao Y, et al. (2018) miRNA delivery for skin wound healing. Adv Drug Deliver Rev 129: 308-318. doi: 10.1016/j.addr.2017.12.011
|
| [63] |
Hoppstädter J, Dembek A, Linnenberger R, et al. (2019) Toll-Like receptor 2 release by macrophages: An anti-inflammatory program induced by glucocorticoids and lipopolysaccharide. Front Immunol 10: 1634. doi: 10.3389/fimmu.2019.01634
|
| [64] |
Lee HM, Kim TS, Jo EK (2016) MiR-146 and miR-125 in the regulation of innate immunity and inflammation. BMB Rep 49: 311-318. doi: 10.5483/BMBRep.2016.49.6.056
|
| [65] |
Oliveira-Nascimento L, Massari P, Wetzler LM (2012) The role of TLR2 in infection and immunity. Front Immunol 3: 79. doi: 10.3389/fimmu.2012.00079
|
| [66] |
Meisgen F, Landén NX, Bouez C, et al. (2014) Activation of toll-like receptors alters the microRNA expression profile of keratinocytes. Exp Dermatol 23: 281-283. doi: 10.1111/exd.12361
|
| [67] |
Zhang X, Liu J, Wu L, et al. (2020) MicroRNAs of the miR-17~92 family maintain adipose tissue macrophage homeostasis by sustaining IL-10 expression. Elife 9: e55676. doi: 10.7554/eLife.55676
|
| [68] |
Li D, Peng H, Qu L, et al. (2021) miR-19a/b and miR-20a promote wound healing by regulating the inflammatory response of keratinocytes. J Invest Dermatol 141: 659-671. doi: 10.1016/j.jid.2020.06.037
|
| [69] |
Zhang C, Qian D, Zhao H, et al. (2018) MiR17 improves insulin sensitivity through inhibiting expression of ASK1 and anti-inflammation of macrophages. Biomed Pharmacother 100: 448-454. doi: 10.1016/j.biopha.2018.02.012
|
| [70] | Li H, Han X, Zuo K, et al. (2018) miR-23b promotes cutaneous wound healing through inhibition of the inflammatory responses by targeting ASK1. Acta Biochim Biophys Sin 50: 1104-1113. |
| [71] |
Zhao F, Lang H, Wang Z, et al. (2019) Human novel MicroRNA Seq-915_x4024 in keratinocytes contributes to skin regeneration by suppressing scar formation. Mol Ther Nucleic Acids 14: 410-423. doi: 10.1016/j.omtn.2018.12.016
|
| [72] |
Ban E, Jeong S, Park M, et al. (2020) Accelerated wound healing in diabetic mice by miRNA-497 and its anti-inflammatory activity. Biomed Pharmacother 121: 109613. doi: 10.1016/j.biopha.2019.109613
|
| [73] |
Bajan S, Hutvagner G (2020) RNA-based therapeutics: From antisense oligonucleotides to miRNAs. Cells 9: 137. doi: 10.3390/cells9010137
|
| [74] |
Li X, Li D, Wang A, et al. (2017) MicroRNA-132 with therapeutic potential in chronic wounds. J Invest Dermatol 137: 2630-2638. doi: 10.1016/j.jid.2017.08.003
|
| [75] |
Devalliere J, Chang WG, Andrejecsk JW, et al. (2014) Sustained delivery of proangiogenic microRNA-132 by nanoparticle transfection improves endothelial cell transplantation. FASEB J 28: 908-922. doi: 10.1096/fj.13-238527
|
| [76] |
Simonson B, Das S (2015) MicroRNA therapeutics: the next magic bullet? Mini Rev Med Chem 15: 467-474. doi: 10.2174/1389557515666150324123208
|
| 1. | Emerson Navarro, Nuno Costa, António Pereira, A Systematic Review of IoT Solutions for Smart Farming, 2020, 20, 1424-8220, 4231, 10.3390/s20154231 | |
| 2. | Mai Ha Thi, Le Hoang Son, Nguyen Tran Quoc Vinh, Nguyen Thi Huong Quynh, 2021, Computing Infrastructure Of IoT Applications In Smart Agriculture: A Systematical Review, 978-1-6654-1784-6, 1, 10.1109/CITISIA53721.2021.9719974 | |
| 3. | Tejas Tawde, Kunal Deshmukh, Lobhas Verekar, Ajay Reddy, Shailendra Aswale, Pratiksha Shetgaonkar, 2021, Identification of Rice Plant Disease Using Image Processing and Machine Learning Techniques, 978-1-6654-2087-7, 102, 10.1109/ICTAI53825.2021.9673214 | |
| 4. | Nimmy Ann Mathew, Megha P. Krishna, Renu Jose, 2023, Chapter 36, 978-981-99-4633-4, 459, 10.1007/978-981-99-4634-1_36 | |
| 5. | Ajmeera Kiran, Arpit Namdev, Radha Raman Chandan, Pravin B. Waghmare, Dharmesh Dhabliya, Ankur Gupta, 2023, A Novel Cloud-Based Framework for Leaf Disease Detection and Classification: Enhancing Plant Health Using Android Applications, 979-8-3503-3072-4, 892, 10.1109/AECE59614.2023.10428363 | |
| 6. | Hammad Shahab, Muhammad Iqbal, Ahmed Sohaib, Farid Ullah Khan, Mohsin Waqas, IoT-based agriculture management techniques for sustainable farming: A comprehensive review, 2024, 220, 01681699, 108851, 10.1016/j.compag.2024.108851 | |
| 7. | Aasha Nandhini S, Hemalatha R, Radha S, Shreya Gaur, Selvarajan R, A smart agriculturing IoT system for banana plants disease detection through inbuilt compressed sensing devices, 2023, 82, 1380-7501, 45519, 10.1007/s11042-023-15442-6 | |
| 8. | Muhammad Arif, Juan Augusto Maya, Narendiran Anandan, Dailys Arronde Pérez, Andrea M. Tonello, Hubert Zangl, Bernhard Rinner, Resource-Efficient Ubiquitous Sensor Networks for Smart Agriculture: A Survey, 2024, 12, 2169-3536, 193332, 10.1109/ACCESS.2024.3516814 |
Figures(3)
Federica Serra, Lisa Aielli, Erica Costantini. The role of miRNAs in the inflammatory phase of skin wound healing[J]. AIMS Allergy and Immunology, 2021, 5(4): 264-278. doi: 10.3934/Allergy.2021020
| Leaf diseases | Affected area (%) | Number of Blocks corresponding to the affected area | Percentage of reduction in data (%) |
| Leaf Blast | 16.23 | 205 | 89.1 |
| Bacterial Blight | 15.6 | 514 | 72.8 |
| Brown Spot | 17.5 | 640 | 67.4 |
| False Smut | 16 | 587 | 74.6 |
| Healthy | 15 | 629 | 63.3 |
DownLoad:
CSV
| Disease category | Leaf mages used for training | Leaf images used for testing |
| Healthy | 250 | 100 |
| Blast | 150 | 75 |
| Bacterial Blight | 130 | 75 |
| Brown Spot | 110 | 70 |
| False Smut | 100 | 80 |
DownLoad:
CSV
| Accuracy = 98.38% | Predicted class | |||||
| Healthy | Blast | Bacterial Blight | Brown Spot | False Smut | ||
| Actual class | Healthy | 98 | 0 | 0 | 1 | 1 |
| Blast | 0 | 73 | 1 | 0 | 1 | |
| Bacterial Blight | 1 | 0 | 74 | 0 | 0 | |
| Brown Spot | 1 | 1 | 0 | 68 | 0 | |
| False Smut | 0 | 1 | 0 | 1 | 78 | |
DownLoad:
CSV
| Classifiers | Disease recognition rate | ||||
| Healthy (%) | Blast (%) | Bacterial Blight (%) | Brown Spot (%) | False Smut (%) | |
| KNN | 96.77 | 95.6 | 96 | 96.77 | 96.77 |
| Multi class SVM | 98 | 97.33 | 97.14 | 98.38 | 98.66 |
DownLoad:
CSV
| Classifier | Classification accuracy (%) | ||
| Thresholding | K-Means clustering | K-Means clustering with CS | |
| Support Vector Machine | 98.44 | 94.4 | 98.37 |
| K-Nearest Neighborhood | 93.4 | 94.4 | 96.77 |
DownLoad:
CSV
| Leaf diseases | Affected area (%) | Number of Blocks corresponding to the affected area | Percentage of reduction in data (%) |
| Leaf Blast | 16.23 | 205 | 89.1 |
| Bacterial Blight | 15.6 | 514 | 72.8 |
| Brown Spot | 17.5 | 640 | 67.4 |
| False Smut | 16 | 587 | 74.6 |
| Healthy | 15 | 629 | 63.3 |
| Disease category | Leaf mages used for training | Leaf images used for testing |
| Healthy | 250 | 100 |
| Blast | 150 | 75 |
| Bacterial Blight | 130 | 75 |
| Brown Spot | 110 | 70 |
| False Smut | 100 | 80 |
| Accuracy = 98.38% | Predicted class | |||||
| Healthy | Blast | Bacterial Blight | Brown Spot | False Smut | ||
| Actual class | Healthy | 98 | 0 | 0 | 1 | 1 |
| Blast | 0 | 73 | 1 | 0 | 1 | |
| Bacterial Blight | 1 | 0 | 74 | 0 | 0 | |
| Brown Spot | 1 | 1 | 0 | 68 | 0 | |
| False Smut | 0 | 1 | 0 | 1 | 78 | |
| Classifiers | Disease recognition rate | ||||
| Healthy (%) | Blast (%) | Bacterial Blight (%) | Brown Spot (%) | False Smut (%) | |
| KNN | 96.77 | 95.6 | 96 | 96.77 | 96.77 |
| Multi class SVM | 98 | 97.33 | 97.14 | 98.38 | 98.66 |
| Classifier | Classification accuracy (%) | ||
| Thresholding | K-Means clustering | K-Means clustering with CS | |
| Support Vector Machine | 98.44 | 94.4 | 98.37 |
| K-Nearest Neighborhood | 93.4 | 94.4 | 96.77 |
