R. K. Samanta

Bio: R. K. Samanta is an academic researcher from University of North Bengal. The author has contributed to research in topics: Physics & Feature selection. The author has an hindex of 5, co-authored 12 publications receiving 144 citations.

Tea Insect Pests Classification Based on Artificial Neural Networks

Abstract: Tea is one of the major health drinks of our society. It is a perennial crop in India and other countries. One of the production barriers of tea is insect pests. This paper presents an automatic diagnosis system for detecting tea insect pests based on artificial neural networks. We apply correlation-based feature selection (CFS) and incremental back propagation network (IBPLN). This is applied on a new database created by the authors based on the records of tea gardens of North Bengal Districts of India. We compare classification results with reduction of dimension and without reduction of dimension. The correct classification rate of the proposed system is 100% in both the cases.

TEAPEST: An Expert System for Insect Pest Management in Tea

Abstract: Tea is one of the major crops of India and is grown over a large area. The loss of crop due to insects is one of the productivity barriers. Insect pest management is a challenging problem to tea cultivators. Proper identification of the insect pests, selection of chemical pesticides and their discriminate use, need human expertise, experience, and judgment. But, sufficient number of competent human experts are not available to cover the large area. To mitigate the lack of human expertise and assist the existing experts for improved decision–making, an expert system for insect pest management would be useful. This article presents a rule–based, object–oriented expert system for insect pest management in tea code named ‘TEAPEST.’ The system identifies major insect pests of tea and suggests appropriate control measures. ‘TEAPEST’ shows good performance as evident from its performance evaluation.

Hepatitis Disease Diagnosis Using Multiple Imputation and Neural Network with Rough Set Feature Reduction

Abstract: Intelligent automated decision support systems are found to be useful for early detection of hepatitis for augmenting survivability. We present here an intelligent system for hepatitis disease diagnosis using UCI data set for experiment. We use multiple imputation technique for managing missing values in the UCI data set. One of the potential tools in this context is neural network for classification. For better diagnostic classification accuracy, various feature selection techniques are deployed as prerequisite. These features are considered to be more informative to the doctors for taking final decision. This work attempts rough set-based feature selection (RS) technique. For classification, we use incremental back propagation learning network (IBPLN), and Levenberg-Marquardt (LM) classification tested on UCI data base. We compare classification results in terms of classification accuracy, specificity, sensitivity and receiver-operating characteristics curve area(AUC).

A comprehensive review on automation in agriculture using artificial intelligence

Abstract: Agriculture automation is the main concern and emerging subject for every country. The world population is increasing at a very fast rate and with increase in population the need for food increases briskly. Traditional methods used by farmers aren't sufficient enough to serve the increasing demand and so they have to hamper the soil by using harmful pesticides in an intensified manner. This affects the agricultural practice a lot and in the end the land remains barren with no fertility. This paper talks about different automation practices like IOT, Wireless Communications, Machine learning and Artificial Intelligence, Deep learning. There are some areas which are causing the problems to agriculture field like crop diseases, lack of storage management, pesticide control, weed management, lack of irrigation and water management and all this problems can be solved by above mentioned different techniques. Today, there is an urgent need to decipher the issues like use of harmful pesticides, controlled irrigation, control on pollution and effects of environment in agricultural practice. Automation of farming practices has proved to increase the gain from the soil and also has strengthened the soil fertility. This paper surveys the work of many researchers to get a brief overview about the current implementation of automation in agriculture. The paper also discusses a proposed system which can be implemented in botanical farm for flower and leaf identification and watering using IOT.

IP102: A Large-Scale Benchmark Dataset for Insect Pest Recognition

Abstract: Insect pests are one of the main factors affecting agricultural product yield. Accurate recognition of insect pests facilitates timely preventive measures to avoid economic losses. However, the existing datasets for the visual classification task mainly focus on common objects, e.g., flowers and dogs. This limits the application of powerful deep learning technology on specific domains like the agricultural field. In this paper, we collect a large-scale dataset named IP102 for insect pest recognition. Specifically, it contains more than 75, 000 images belonging to 102 categories, which exhibit a natural long-tailed distribution. In addition, we annotate about 19, 000 images with bounding boxes for object detection. The IP102 has a hierarchical taxonomy and the insect pests which mainly affect one specific agricultural product are grouped into the same upperlevel category. Furthermore, we perform several baseline experiments on the IP102 dataset, including handcrafted and deep feature based classification methods. Experimental results show that this dataset has the challenges of interand intra- class variance and data imbalance. We believe our IP102 will facilitate future research on practical insect pest control, fine-grained visual classification, and imbalanced learning fields. We make the dataset and pre-trained models publicly available at https://github.com/xpwu95/IP102.