Because of the recent advances in drones or Unmanned Aerial Vehicle (UAV) platforms, sensors and software, UAVs have gained popularity among precision agriculture researchers and stakeholders for estimating traits such as crop yield and diseases. Early detection of crop disease is essential to prevent possible losses on crop yield and ultimately increasing the benefits. However, accurate estimation of crop disease requires modern data analysis techniques such as machine learning and deep learning. This work aims to review the actual progress in crop disease detection, with an emphasis on machine learning and deep learning techniques using UAV-based remote sensing. First, we present the importance of different sensors and image-processing techniques for improving crop disease estimation with UAV imagery. Second, we propose a taxonomy to accumulate and categorize the existing works on crop disease detection with UAV imagery. Third, we analyze and summarize the performance of various machine learning and deep learning methods for crop disease detection. Finally, we underscore the challenges, opportunities and research directions of UAV-based remote sensing for crop disease detection.

The long short-term memory (LSTM) and gated recurrent unit (GRU) models are popular deep-learning architectures for stock market forecasting. Various studies have speculated that incorporating financial news sentiment in forecasting could produce a better performance than using stock features alone. This study carried a normalized comparison on the performances of LSTM and GRU for stock market forecasting under the same conditions and objectively assessed the significance of incorporating the financial news sentiments in stock market forecasting. This comparative study is conducted on the cooperative deep-learning architecture proposed by us. Our experiments show that: (1) both LSTM and GRU are circumstantial in stock forecasting if only the stock market features are used; (2) the performance of LSTM and GRU for stock price forecasting can be significantly improved by incorporating the financial news sentiments with the stock features as the input; (3) both the LSTM-News and GRU-News models are able to produce better forecasting in stock price equally; (4) the cooperative deep-learning architecture proposed in this study could be modified as an expert system incorporating both the LSTM-News and GRU-News models to recommend the best possible forecasting whichever model can produce dynamically.

Recent deep learning methods for fruits classification resulted in promising performance. However, these methods are with heavy-weight architectures in nature, and hence require a higher storage and expensive training operations due to feeding a large number of training parameters. There is a necessity to explore lightweight deep learning models without compromising the classification accuracy. In this paper, we propose a lightweight deep learning model using the pre-trained MobileNetV2 model and attention module. First, the convolution features are extracted to capture the high-level object-based information. Second, an attention module is used to capture the interesting semantic information. The convolution and attention modules are then combined together to fuse both the high-level object-based information and the interesting semantic information, which is followed by the fully connected layers and the softmax layer. Evaluation of our proposed method, which leverages transfer learning approach, on three public fruit-related benchmark datasets shows that our proposed method outperforms the four latest deep learning methods with a smaller number of trainable parameters and a superior classification accuracy. Our model has a great potential to be adopted by industries closely related to the fruit growing and retailing or processing chain for automatic fruit identification and classifications in the future.

COVID‐19 has claimed several human lives to this date. People are dying not only because of physical infection of the virus but also because of mental illness, which is linked to people’s sentiments and psychologies. People’s written texts/posts scattered on the web could help understand their psychology and the state they are in during this pandemic. In this paper, we analyze people’s sentiment based on the classification of tweets collected from the social media platform, Twitter, in Nepal. For this, we, first, propose to use three different feature extraction methods—fastText‐based (ft), domain‐specific (ds), and domain‐agnostic (da)—for the representation of tweets. Among these three methods, two methods (“ds” and “da”) are the novel methods used in this study. Second, we propose three different convolution neural networks (CNNs) to implement the proposed features. Last, we ensemble such three CNNs models using ensemble CNN, which works in an end‐to‐end manner, to achieve the end results. For the evaluation of the proposed feature extraction methods and CNN models, we prepare a Nepali Twitter sentiment dataset, called NepCOV19Tweets, with 3 classes (positive, neutral, and negative). The experimental results on such dataset show that our proposed feature extraction methods possess the discriminating characteristics for the sentiment classification. Moreover, the proposed CNN models impart robust and stable performance on the proposed features. Also, our dataset can be used as a benchmark to study the COVID‐19‐related sentiment analysis in the Nepali language.