Mrityunjaya V. Latte

Bio: Mrityunjaya V. Latte is an academic researcher from JSSATE Noida. The author has contributed to research in topics: Median filter & Filter (signal processing). The author has an hindex of 9, co-authored 38 publications receiving 214 citations. Previous affiliations of Mrityunjaya V. Latte include JSSATE & Jawaharlal Nehru Technological University, Hyderabad.

Crop yield prediction: two-tiered machine learning model approach

Abstract: Nutrient deficiency analysis is essential to ensure good yield. The crop yield is dependent on the nutrient contents and drastically affects the health of the crop. In this paper the nutrient deficiency of a paddy crop is considered. Tensor Flow’s (Google’s Machine Learning Library) is used to build a neural network to classify them into nitrogen, potassium, phosphorous deficiencies or healthy independently. It is necessary to have an optimal balance between nitrogen, potassium and phosphorous content. Tensor Flow’s model identifies the deficiency using a set of images. The result is fed to “machine learning driven layer” to estimate the level of deficiency on a quantitative basis. It specifically makes use of k means-clustering algorithm. It is then evaluated through the rule-matrix to estimate the cropland’s yield. A fair prediction of 76–77% was observed with two tired machine learning models.

Multiple nutrient deficiency detection in paddy leaf images using color and pattern analysis

Abstract: Paddy being the staple food of India is majorly affected by deficiency of primary nutrient elements like nitrogen, phosphorus and potassium. Leaves can be deficient with multiple nutrient elements at a same time. This can alter natural color of paddy leaves. Such leaves are considered as defective. The proposed work is to automate multiple nutrient element deficiency identification of paddy leaves. Pattern analysis RGB color features are extracted to identify defective paddy leaves. Firstly the database of healthy, nitrogen, phosphorus and potassium defected paddy leaves are created. For any test image effective comparison at different levels are employed such as multiple color comparison, multiple pattern comparison and combination of color and patterns comparison, so that defectiveness is accurately identified for combination of deficiency such as nitrogen-phosphorus(NP), nitrogen-potassium(NK) and phosphorous-potassium (KP).

ROI Based Encoding of Medical Images: An Effective Scheme Using Lifting Wavelets and SPIHT for Telemedicine

Abstract: 338 Abstract—Telemedicine characterized by transmission of medical data and images between users is one of the emerging fields in medicine. Huge bandwidth is necessary for transmitting medical images over the internet. Resolution factor and number of images per diagnosis makes even the size of the images that belongs to a single patient to be very large in size. So there is an immense need for efficient compression techniques for use in compressing these medical images. Each of the regions that are considered to be more important than others in medical images is termed as a Region of Interest (ROI) e.g. tumor region of the brain MRI. Thus, the regions of interest can be coded with high spatial resolution than the background while transmitting the images. By this, ROI of high compression rate and high quality can be obtained. This paper reviews the application of ROI coding in the field of telemedicine. Wavelet transform with lifting is used to perform image coding based on Set Partitioning in Hierarchical Trees (SPIHT). ROI coding with high spatial resolution than the background is accomplished using tiling method. High compression ratio is achieved by obtaining the ROI through user interaction and coding with the user given resolution. The experimental result shows that the application of ROI coding achieves high compression rate and quality ROI by using wavelet with lifting and tiling method

Multimodal Biometric Person Authentication using Speech, Signature and Handwriting Features

Abstract: The objective of this work is to develop a multimodal biometric system using speech, signature and handwriting information. Unimodal biometric person authentication systems are initially developed for each of these biometric features. Methods are then explored for integrating them to obtain multimodal system. Apart from implementing state-of-the art systems, the major part of the work is on the new explorations at each level with the objective of improving performance and robustness. The latest research indicates multimodal person authentication system is more effective and more challenging. This work demonstrates that the fusion of multiple biometrics helps to minimize the system error rates. As a result, the identification performance is 100% and verification performances, False Acceptance Rate (FAR) is 0%, and False Rejection Rate (FRR) is 0%.

Machine Learning in Agriculture: A Comprehensive Updated Review.

Abstract: The digital transformation of agriculture has evolved various aspects of management into artificial intelligent systems for the sake of making value from the ever-increasing data originated from numerous sources. A subset of artificial intelligence, namely machine learning, has a considerable potential to handle numerous challenges in the establishment of knowledge-based farming systems. The present study aims at shedding light on machine learning in agriculture by thoroughly reviewing the recent scholarly literature based on keywords’ combinations of “machine learning” along with “crop management”, “water management”, “soil management”, and “livestock management”, and in accordance with PRISMA guidelines. Only journal papers were considered eligible that were published within 2018–2020. The results indicated that this topic pertains to different disciplines that favour convergence research at the international level. Furthermore, crop management was observed to be at the centre of attention. A plethora of machine learning algorithms were used, with those belonging to Artificial Neural Networks being more efficient. In addition, maize and wheat as well as cattle and sheep were the most investigated crops and animals, respectively. Finally, a variety of sensors, attached on satellites and unmanned ground and aerial vehicles, have been utilized as a means of getting reliable input data for the data analyses. It is anticipated that this study will constitute a beneficial guide to all stakeholders towards enhancing awareness of the potential advantages of using machine learning in agriculture and contributing to a more systematic research on this topic.

Real-time blob-wise sugar beets vs weeds classification for monitoring fields using convolutional neural networks

Abstract: . UAVs are becoming an important tool for field monitoring and precision farming. A prerequisite for observing and analyzing fields is the ability to identify crops and weeds from image data. In this paper, we address the problem of detecting the sugar beet plants and weeds in the field based solely on image data. We propose a system that combines vegetation detection and deep learning to obtain a high-quality classification of the vegetation in the field into value crops and weeds. We implemented and thoroughly evaluated our system on image data collected from different sugar beet fields and illustrate that our approach allows for accurately identifying the weeds on the field.