Heart disease is the biggest cause of death in the globe. The method of predicting cardiac disease is exceedingly complex. It can only be done properly if the doctor has a lot of expertise and is well-versed in the condition. IoT-based illness prediction is a relatively recent technology for accurately classifying diseases based on sensor data. This system proposes an enhanced deep learning-based framework for predicting the heart disease. The general publicly available Hungarian heart disease dataset is utilized for the implementation, which includes heart disease related data collected from patients through IoT sensor devices. The input dataset is preprocessed using Median Studentized Residual approach for resolving error data and missing values. Preprocessed data values are feature selected by Harris Hawk Optimization (HHO) approach. The selected features are then classified into normal and abnormal by Modified Deep Long Short-Term Memory (MDLSTM). The modification in LSTM output is altered using Improved Spotted Hyena Optimization (ISHO) algorithm. The results are implemented in the working platform of Phyton with the metrics such as specificity, sensitivity, F-Score, Kappa value, Accuracy, BER and Execution time. The analyzed results shows that the implemented methodology is superior in the prediction of heart disease with an accuracy of 98.01% and reduced error rate of 91.11 compared with other existing techniques.

In agricultural industry, paddy diseases play a vital role to cause economic losses. Hence, the detection of diseases of paddy plants and give suggestions to the peasants is beneficial to increase the yield quantity of rice. In this paper, a novel web-based paddy disease detection using Compressed Sensing is proposed to detect and classify paddy diseases. First, the diseased leaf is pre-processed using contrast enhancement, and then LAB color space is applied. The segmentation is done using K-Means clustering. The storage complexity is reduced using the Compressed Sensing technique. The segmented leaf images are compressed and then uploaded to the cloud. In the transmitter section, the Compressed Sensing recovery algorithm is used to reconstruct the segmented image. Then Statistical Gray Level Co-occurrence Matrix (GLCM) method is used to extract the features from the segmented image. Support Vector Machine classifier is used to classify the diseases. The performance of the proposed method is compared with other existing techniques. The proposed system is also experimentally tested with Arduino board. The proposed system achieves the disease recognition rate of 98.38%.

In fruit harvesting systems, automatic yield counting of fruits becomes a big issue. Image processing techniques minimizes the manual task of recognizing and counting the fruits. In this paper, an image processing system for automatic segmentation and yield prediction of fruits is proposed on the basis of color and shape features is being performed. Initially the preprocessing is done on input fruit tree images. Then it is converted from RGB to HSV color space to detect the fruit region from its background. Color thresholding is used to mask the desired colors. Gaussian filter is used to remove noise. The contour of the image is taken. Then these images are processed by image processing algorithm. Color and shape based counting of fruit is presented at the output. The edge detection and combination of a circular fitting algorithm is applied for the automatic segmentation and automatic counting of fruits in the image. Different types of fruits (orange/tangerine, pomegranate, apple, lemon, mango, cherry) are used for automatic counting. Open CV Python software is used to perform the required image processing operations.

It is great challenge to meet the needs of quality assessment on rice grains. Testing on quality is gaining importance in food industry for classifying and grading the grains. Since manual testing is time consuming, costly and inaccurate, machine vision based quality analysis of rice grains is preferred. In machine vision based testing, we take both physical (grain shape and size) and chemical characteristics (amylose content, gel consistency) for evaluation and grading of rice grains. Quality assessment is done by finding 1) the region of boundary and 2) the end points of each grain by measuring the length, breadth and diagonal size of grain. In this proposed image processing algorithm, quality and grading of rice grains were analysed using the average values of the features extracted and it was implemented in Mat Lab.

Indian Economy mainly determined by the agriculture. Tomato is one of the highest used food crops in India. Due to which detection of disease on tomato plant becomes essential. The manual detection of plant diseases are very complex and high cost. Hence, image processing based detection of plant diseases gives the solution. Disease detection involves the steps like image capturing , various processing steps and classification. Most of the diseases of tomato plant detected at initial stages as they affect leaves first. By detecting the diseases at initial stage on leaves will surely avoid impending loss. The classifier, the classification is performed to classify the healthy and disease affected tomato leaves. Finally, the performance of K-nearest neighbor (KNN) and multi class Support Vector machine (SVM) are compared. The proposed system assured an excellent performance to farmers and researchers in admissible way.