Food safety and agricultural planning greatly depends on the accurate prediction of crop yield, in regions with different agroclimatic conditions. This paper proposes a machine learning-based framework that integrates a database containing historical agricultural records and satellite-derived vegetation indices to predict crop yield. Several vegetation indices are derived from Landsat- 8 satellite imagery using the Google Earth Engine. A regression model is tuned and trained for crop yield prediction using the vegetation indices over 21 years, between 2002 and 2022 for wheat crop in western Uttar Pradesh region in India. Several regression models such as Gradient Boosting, K-Nearest Neighbors, Random Forest, Support Vector Regression, and XGBoost are tested to predict the crop yield. The experiments are performed to forecast wheat yield at the district level in western Uttar Pradesh. The results demonstrated that the regression models predicted crop yield with an accuracy up to 89.77 %. The results also shown that the ensemble-based model XGBoost outperformed other regression models with $\mathrm{R}^{2}=0.8146$.

Plants are susceptible to pathogen infections during their growing period leading to reduced crop quality and yield. Traditional disease detection methods such as expert diagnosis and pathogen analysis rely on experienced professionals and could be time-consuming and prone to errors. Deep convolutional neural networks (CNNs) have exhibited their potential to detect plant diseases on the basis of visual patterns of leaves. Most of the existing CNN based methods do not take advantage of additional information. Most of the disease significantly affects the texture of the plant leaves. Therefore, texture features can provide complementary information to get better results. In this paper, local binary pat tern (LBP) technique is used to extract texture information that is stacked with original image. A CNN model is proposed that takes embedded texture and spectral information to detect crop diseases using leaf images. The experiments are carried out on Apple, Corn, and Potato crops from Plant Village dataset. The proposed method achieved the overall accuracy up to 98.73% (κ = 98.04). It is found that LBP makes significant difference in disease classification accuracy and helps the proposed method exhibit better performance than some existing well known CNN models.

Diseases and pests in plants/crops are major causes of significant agricultural losses with economic, social and ecological impacts. Therefore, there is a need for early identification of plant diseases and pests through automated systems. Recently, machine learning-based methods have become popular in solving agricultural problems such as plant diseases faced by technically-noob farmers. This work proposes a novel method based on stacking ensemble machine learning to detect plant diseases in Uradbean precisely. Two classifiers: support vector machine (SVM), random forest (RF) are trained on a dataset consists of Uradbean infected and healthy leaf images. These classifiers are stacked with logistic regression (LR) classifier. In the diverse ensemble, LR classifier is used as a meta-learner which enhanced the precision of the disease classification. The fuzzy C-Means clustering with particle swarm optimization is used for image segmentation. Haralick, Hu Moments and color histogram methods are used in feature extraction. During the tests, the proposed model is also compared with pre-trained networks: DenseNet-201, ResNet-50, and VGG19. It achieved an impressive classification accuracy of 96.82 % which is higher than the individual classifiers and pre-trained networks. To validate model performance, it is evaluated on a benchmark public dataset consists of Apple leaf images and achieved 98.30% accuracy. It is observed that ensemble method reflects an advantage over individual models in increasing the classification rates and reducing the computational overhead in comparison to pre-trained networks which struggle due to the issues such as irrelevant features, generation of pertinent characteristics, and noise

The human population and domestic animals rely heavily on agriculture for their food and livelihood. Agriculture is an important contributor to the national economy of many countries. Plant diseases lead to a significant reduction in agricultural yield, posing a threat to global food security. It is crucial to detect plant diseases in a timely manner to prevent economic losses. Expert diagnosis and pathogen analysis are widely used for the detection of diseases in plants. However, both expert diagnosis and pathogen analysis rely on the real-time investigation experience of experts, which is prone to errors. In this work, an image analysis-based method is proposed for detecting and classifying plant diseases using an involution neural network and self-attention-based model. This method uses digital images of plant leaves and identifies diseases on the basis of image features. Different diseases affect leaf characteristics in different ways; therefore, their visual patterns are highly useful in disease recognition. For rigorous evaluation of the method, leaf images of different crops, including apple, grape, peach, cherry, corn, pepper, potato, and strawberry, are taken from a publicly available PlantVillage dataset to train the developed model. The experiments are not performed separately for different crops; instead, the model is trained to work for multiple crops. The experimental results demonstrate that the proposed method performed well, with an average classification accuracy of approximately 98.73% (κ = 98.04) for 8 different crops with 23 classes. The results are also compared with those of several existing methods, and it is found that the proposed method outperforms the other methods considered in this work.

Plant diseases are a severe cause of crop losses in the agriculture globally. Detection of diseases in plants is difficult and challenging due to the lack of expert knowledge. Deep learning-based models provide promising ways to identify plant diseases using leaf images. However, need of larger training sets, computational complexity, and overfitting, etc. are the major issues with these techniques that still need to be addressed. In this work, a convolutional neural network (CNN) is developed that consists of smaller number of layers leading to lower computational burden. Some augmentation techniques such as shift, shear, scaling, zoom, and flipping are applied to generate additional samples increasing the training set without actually capturing more images. The CNN model is trained for apple crop using a publicly available dataset PlantVillage to identify Scab, Black rot, and Cedar rust diseases in apple leaves. The rigorous experimental results revealed that the proposed model is well fit to identify apple leaf diseases and achieves 98% classification accuracy. It is also evident from the results that it needs lesser amount of storage and takes smaller execution time than several existing deep CNN models. Although, there exist several CNN models for crop disease detection with comparable accuracy, but the proposed model needs lower storage and computational resources. Therefore, it is highly suitable for deploying in handheld devices.

Convolutional neural networks (CNNs) are an effective technique for hyperspectral image classification. Deep learning models require a large number of labeled and diverse samples to properly train a CNN model. But a training set is often not large enough. Transfer learning can help to overcome the need for training sets. In this paper, six pre-trained CNN models: EfficientNetB0, EfficientNetB7, ResNet50, VGG19, DenseNet121 and DenseNet201 are fine-tuned for hyperspectral image classification. The experiments are carried out on two benchmark images Houston and Kennedy Space Center (KSC). The results show that hyperspectral images can be classified with good accuracy by fine-tuned pre-trained CNN models. As compared to training a model from scratch, fine-tuning takes a small number of epochs. Thus, alleviating the requirement for high-end computing resources. Among the tested models, VGG19 achieves the best accuracy of 95.77

Deep learning networks are considered as an important technique for face recognition and image recognition. Convolutional Neural Networks (CNN) is regarded as a problem solver in face recognition challenges. To solve the challenges of occlusion and noise in the image, more clarification is needed to acquire high accuracy. Hence, a deep learning model is developed in this paper. The proposed model covers four main steps: (a) Data acquisition, (b) Pre-processing, (c) pattern extraction, and (d) classification. The benchmark datasets with occluded faces is gathered from public source. Further, the pre-processing of the images is performed by contrast enhancement and Gabor filtering. With these pre-processed images, pattern extraction is done by the optimal local mesh ternary pattern. By inputting the pattern extracted image, a deep learning model “CNN with Gated Recurrent Unit (GRU)” network performs the recognition process. The experimental results are obtained and the proposed model gives better classification accuracy.

Crop yield predictions are important for crop monitoring and agronomic management. The traditional methods for yield predictions are complicated and resource consuming. With the availability of affordable handheld imaging and computing devices, the image processing-based yield prediction methods are gaining popularity. In this work, RGB images of rice panicles are captured using DSLR camera with simple background and processed to determine the panicle area in terms of number of pixels. A machine learning-based model is developed to make predictions for rice yield. The model is trained to make predictions on unseen data. Various machine learning-based regression algorithms including decision tree, random forest, support vector machine, and convolution neural network are tested. The experiments are performed on a publically available dataset from China as well as on a self-acquired dataset in India. The results have shown that image processing and machine learning-based methods can make yield predictions satisfactorily as evident from the coefficient of determination ( R^2 ) that ranges 0.80–0.97 for different cultivars. The prediction error is determined in terms of root mean square error (RMSE) and mean absolute error (MAE). RMSE for different methods lies between 0.14 and 0.40, whereas MAE varies from 0.11 to 0.30. Among the tested algorithms, linear regression achieved the best precision with R ^2 = 0.97, RMSE = 0.14, and MAE = 0.11.

Sentiment analysis technique plays an important role in natural language processing to analyze complex human statements. In the last few years, this technique has become a powerful tool for several social media communication mediums such as WhatsApp, Twitter, Facebook, Instagram, YouTube, LinkedIn, Blog, etc. This paper proposes a machine learning (ML) based method to analyze social media data for sentiment analysis on text data. The presented method is divided into three distinct stages. In the first stage, pre-processing is performed to filter and refine the text data. In the second stage, the feature extraction is performed using the Term Frequency and Inverse Document Frequency (TF-IDF) technique. Moreover, during the third stage, the extracted features are supplied to make predictions for the classifier. The experiments are carried out on a publicly available Twitter dataset for US Airlines. Several ML techniques are utilized for analysis and classification. The results are reported for different evaluation metrics like accuracy, precision, recall, and F1 score. Finally, the support vector machine yielded the most relevant results.

Tomato is one of the most important crops in India. It has a high commercial value and is the second most widely produced crop. Diseases are harmful to crop health and have an impact on plant growth, either directly or indirectly. Plant growth must be monitored to ensure the minimum losses in production. There are numerous types of tomato diseases that deteriorate the quality of the tomatoes. As a result, the early crop treatment is crucial before it affects the entire crop. This paper presents a pre-trained convolutional neural network (CNN) based method for identifying and classifying the leaf diseases in tomato crops using transfer learning. The experiments are carried out on the Plant Village dataset, which includes ten tomato classes: Tomato Bacterial Spot, Early Blight, Late Blight, Leaf Mold, Septoria Leaf Spot, Spider Mites, Target Spot, Mosaic Virus, Yellow Leaf Curl Virus, and Healthy. Various pre-trained CNN models are fine-tuned with transfer learning approach. The tested pre-trained CNN models include DenseNet169, InceptionResNetV2, InceptionV3, VGG-16, VGG-19, DenseNet201, MobileNet, Mo-bileNetV2, and Xception. According to the results, MobileNet outperformed all other models with overall classification accuracy of 96%.

Fusion of complementary information from multisensor data is of great importance for identifying the land covers. However, integration of multisource information is a challenging task. A framework is developed to integrate hyperspectral and LiDAR data for land cover classification. In the proposed method, sparse stacked autoencoders are used to represent the spectral and spatial information in a compact form. The spatial information is extracted both from hyperspectral and LiDAR data using morphological operators. The encoded spectral and spatial features are combined with elevation information to form a joint feature vector. The joint features are fed to a convolutional neural network (CNN) classifier to classify the land covers. The CNN classifier is a hybrid three- and two-dimensional (3D)-(2D) model having three 3D convolutional layers and one 2D convolutional layer. The experiments are carried out on two datasets Houston and Samford to evaluate the performance of the proposed method. The results have demonstrated the effectiveness of the method with global kappa = 0.9285 and global naive accuracy (OA) of 93.44% for Houston data. For Samford data, it achieves kappa = 0.9811 and OA = 98.93 % . (C) 2022 Society of Photo-Optical Instrumentation Engineers (SPIE)

Plant diseases are the major factor behind production loss in agriculture. The traditional manual methods for disease detection in plants involve expert knowledge that may be biased. The modern computing techniques and image processing can assist non-experts in plant disease management. Recently, deep learning techniques have observed remarkable success in image-based health assessment of plants. In this paper, the state-of-the-art pre-trained convolutional neural network (CNN) models are fine-tuned to detect and diagnose the diseases in apple crop using digital images. The experiments are performed on a publicly available dataset PlantVillage. The dataset consists of three classes of apple diseases including Scab, Black Rot, and Cedar Rust, and one class of Healthy leaves. The experimental results on ten well-known CNN models DenseNet201, DenseNet169, InceptionV3, InceptionResNetV2, MobileNet, MobileNetV2, ResNet50, VGG16, VGG19, and Xception showed that deep learning techniques can accurately discriminate the apple diseases. DenseNet201 outperformed the other models with an accuracy of 98.75%. The high accuracy shows that CNN-based methods could be a useful alternative to the conventional methods.

Abstract: In the electronic industry, e-scraps or e-wastes refer to electronic goods that are discarded or unneeded. About 50 million ton of e-wastes are produced every year. Depending on their reactions, there might be potential danger. E-wastes, such as computer batteries and other electrochemical waste, may cause unwanted results, so it is important to consider them along with physical wastes. India generates about 1.5 lakh tons of e-waste annually, and almost all of it ends up in the informal sector as there is no organized alternative. It is well documented that humanity's capabilities were enhanced by the industrial revolution. However, the revolutionary changes experience by societies across the globe due to the application of electronics are deeper and more widespread than the impact of the industrial revolution. Human society has been profoundly changed by the electronics age and has become more connected than ever before. Electronic items have contributed to smoother communication, economic growth, and job opportunities. However, in addition to the positives, technology has brought to light a number of concerns, such as the growing problem of ewaste, which society must confront head on. In the existing situation, it is always possible that human health and the environment would be in trouble. If coordinated legislation and activities for efficient e-waste management and disposal were not enacted. This paper aims to provide a quick overview of the relatively new notion of e-waste, its production in India, and the associated environmental and health implications. It emphasizes the booming informal and nascent official e-waste recycling economies, as well as the urgent need for more explicit legislation and a forward-looking strategy. The paper also examines global e-waste trading and international experience in this area. There is also a list of references at the conclusion for further reading. Each year, hundreds of thousands of consumer electronics, computers, monitors, phones, printers, televisions and other portable devices become outdated and were mainly dumped to the landfills or poorly recycled. Recent technological development and growing demands for new and better functioning electronics accelerate the amount of electronic waste (e-waste) worldwide, making it to be one of the fastest growing streams in many countries. The estimated lifespan of electronics is about three to five years because of the increasing rates of consumption, new developments and urbanization.

In recent years, remote sensing and other applications have used hyperspectral image processing in a variety of ways. For more precise and in-depth information extraction, hyperspectral images offer a wealth of spectral information to recognize and discriminate spectrally identical materials. Numerous cutting-edge methods based on spectral and spatial data are available for hyperspectral image classification. Convolutional neural network (CNN), a subclass of artificial neural networks has gained popularity in a number of fields, including hyperspectral image classification. CNN is built to automatically and adaptively learn spatial hierarchies of data by backpropagation using a variety of building blocks, including convolution layers, pooling layers, and fully connected layers. In this paper, different CNN architectures such as IDCNN, 2D-CNN, 3D-CNN and 3D2D-CNN are evaluated to classify hyperspectral images. Experiments are performed on Indiana Pines and Pavia University images. Experimental results show that 3D2D-CNN gives highest classification accuracy.

Electronic waste or e-waste is a rapidly growing serious threat to the environment. The whole process of managing the e-waste which includes collection, transportation, storage, and recycling or treatment is yet to be well controlled. E-waste disposal has become an emerging issue for public health and the global environment. The convoluted chemicals produced during the e-waste recovery and hazardous by- products raise panic situations for the industry workers and labourers. Generally, the e-waste industry workers are untrained and belong to the informal sector. These people are generally not aware of the necessary precautionary actions to be taken before handling or recovering the e-waste. The inappropriate components, which can’t be reused, are either dumped or burnt outside openly. The toxic gases or hazardous chemicals pollute the environment or can be released directly into water sources. Thus, proper recycling of e-waste in a controlled way is very necessary and ecologically desirable. By promoting the reuse of non-degradable products their extraction rate can be minimized. A formalization of rules for e- waste management and their amendments can potentially offer benefits to this industry and the workers by reducing uncontrolled extraction and providing them employment security. This paper highlights the burden of e-waste, the impact of e-waste on health, the current status of e-waste management concerning the Moradabad region, initiatives for e-waste management including legislation, and current research aspects of e-waste management.

Agriculture has been the most primary source of the livelihood of man for thousands of years. Even today, it provides subsistence to about 50% of the world population. Plant diseases are the serious cause of big losses to crop production every year worldwide. It is necessary to keep the plants healthy at various stages of their growth/development to deal with the financial losses from plant diseases. Symptoms of infections are visible mainly at plant leaves; thus leaves are commonly used to detect and identify the diseases. Detecting the disease through visual observation is itself a challenging task and requires a lot of human expertise. Image processing techniques along with computational intelligence or soft computing techniques can be used to provide a better assistance for disease detection to the farmers. A disease in plants can be detected based on its symptoms extracted in the form of features. Feature extraction techniques thus play a vital role in such systems. The paper emphasizes on the review of hand-crafted and deep learning based feature extraction with their merits and demerits. It provides a comprehensive discussion on a variety of image features such as color, texture, and shape for various disorders in different cultures.

Tomato is one of the major crops in India. The production of tomatoes is rigorously affected by several types of diseases. Therefore, initial detection of disease is vital for the quality and quantity of tomatoes. It is significant to monitor crop growth. There are many diseases that mostly affect the plant leaves. This paper adopts a convolutional neural network (CNN) model to detect and identify diseases using the images of tomato leaves. The proposed CNN model comprises four convolutions and four max pooling layers, which are followed by fully connected layers. The performance of the proposed method is assessed by performing experiments on a well-known PlantVillage dataset. There are nine diseases and one healthy class for tomato crop in the dataset. The overall accuracy of the proposed method is obtained as 96.26%. It is compared with some fine-tuned pre-trained CNN models InceptionResNetV2 and InceptionV3. The results illustrate that the proposed method outperforms all the methods based on fine-tuned models.

Convolutional neural networks (CNNs) have shown tremendous success for hyperspectral image classification in recent years. CNNs are capable of capturing multi-scale spectral-spatial characteristics of hyperspectral image pixels leading to good classification results. Despite the good accuracy, most of the classifiers misclassify some pixels and generate noisy classification maps. A deep CNN and Markov random field (MRF)-based two-stage classification framework is developed for hyperspectral images. The input image is first classified with the help of a deep CNN classifier. The results provided by CNN are further refined by applying stochastic relaxation labeling using MRF on the first-stage classification map to produce a refined classification map with better accuracy. This two-stage classification approach is particularly helpful if smaller misclassified regions are generated during the first-stage classification. Experiments are performed on one satellite-borne and three airborne hyperspectral images: Dioni, Indian Pines, Pavia University, and Salinas. The results show that the proposed method yields good classification accuracy and smoothed classification maps. The refinement by MRF relaxation improved the overall classification accuracy of the first-stage classifier by more than 2% for all the images. The overall classification accuracy in terms of kappa coefficient is obtained as 0.9844, 0.9678, 0.9843, and 0.9841 for Dioni, Indian Pines, Pavia University, and Salinas images, respectively, which is comparable or better than several existing methods. (C) 2021 Society of Photo-Optical Instrumentation Engineers (SPIE)

The role of the agriculture sector in global economic development is important. The development of agriculture and growth in production is essential for achieving global food security. Diseases in plants/crops are the responsible agents for the loss of agricultural production globally. Most of the diseases in plants initially strike the leaves of the plant, later its symptoms are evident on all parts of the plant. The diseases significantly affect the quality and quantity of total crop production. Typically, plant diseases are identified through visual observation or laboratory investigations by phytopathologists, but this is very challenging for farmers or non-specialists. Image processing and machine learning together can play an important role in helping farmers to identify the diseases in crops. The major steps in such methods generally include image acquisition, image pre-processing, image segmentation, feature extraction, and disease classification. This paper presents an analysis of some of the major classification techniques used in such methods. The experiments are carried out for two important crops Apple (Malus domestica) and Blackgram (Vigna mungo) to analyze baseline classifiers such as decision tree, naive Bayes, logistic regression, k-nearest neighbor, linear discriminant analysis, support vector machine, and random forest using plant leaf images. The leaf images of apple are taken from a benchmark PlantVillage dataset, while images of blackgram (urdbean) leaves are obtained from a self-prepared dataset. In both datasets, the leaf images contain a simple eliminated background.

Hyperspectral image sensors capture surface reflectance over a range of wavelengths. The fine spectral information is recorded in terms of hundreds of bands. Hyperspectral image classification has observed a great interest among researchers in remote sensing community. High dimensionality provides rich spectral information for the classification process. But due to dense sampling, some of the bands may contain redundant information. Sometimes, spectral information alone may not be sufficient to obtain desired accuracy of results. Therefore, often spatial and spectral information is integrated for better accuracy. However, unlike spectral information, the spatial information is not directly available with the image. Additional efforts are needed to extract spatial information. Feature extraction is an important step in a classification framework. It has following major objectives: redundancy reduction, dimensionality reduction (usually but not always), enhancing discriminative information, and modelling of spatial features. The spectral feature extraction process transforms the original data to a new space of a different dimension, enhancing the class separability without significant loss of information. Various mathematical techniques are applied for modelling spatial features based on pixel spatial neighbourhood relations. In this paper, a review of the major feature extraction techniques is presented. Experimental results are presented for two benchmark hyperspectral images to evaluate different feature extraction techniques for various parameters.