Shamla Mantri

Bio: Shamla Mantri is an academic researcher from Massachusetts Institute of Technology. The author has contributed to research in topics: Self-organizing map & Population. The author has an hindex of 5, co-authored 20 publications receiving 68 citations. Previous affiliations of Shamla Mantri include College of Engineering, Pune.

Plant Diseases Detection and Classification using Machine Learning Models

Abstract: In the agricultural sector, identification of plant diseases is extremely crucial as they hamper robustness and health of the plant which play a vital role in agricultural productivity. These problems are common in plants, if proper prevention methods are not taken it might seriously affect the cultivation. The current method of detecting disease is done by an expert's opinion and physical analysis, which is time-consuming and costly in the real world. Hence, computer-based detection has become a necessity. This paper comprises of an overview of image segmentation using K-means clustering and HSV dependent classification for recognizing infected part of the leaf and feature extraction using GLCM. The efficiency of the proposed methodology is able to detect and classify the plant diseases successfully with an accuracy of 98% when processed by Random Forest classifier.

Non invasive EEG signal processing framework for real time depression analysis

Abstract: There is a long list of words that describe depression; sadness, unhappiness, sorrow, dejection, low spirit, despondency, woe, gloom, pessimism, desolation, despair, hopelessness, moodiness, and a host of others. This study throws light upon the contribution EEG signal for depression analysis. In this paper, classification of depressed patients from normal subjects are identified by using EEG signal. Experimental results are carried out with the help of 13 depressed patients and 12 normal subjects. This paper tries to classify person's mental state either normal or depressed with the help of EEG signal using signal processing technique FFT and machine learning technique SVM. These noninvasive signal techniques are useful for detection of depression disorders through EEG signals. The proposed work is compared with the other methods. The diagnosis is done and appropriate remedies are taken according to scale of the depression in the patient. This work shows that linear analysis of EEG can be an efficient method for identifying depressed patients from normal subjects. It is recommended that this analysis may be a supporting aid for psychiatrists to identify severity level of depressed patients.

Clinical Depression Analysis Using Speech Features

Abstract: Depression is a most common severe mental disturbance health disorder causing high societal costs. In clinical practice rating for depression depends almost on self questionnaires and clinical patient history report opinion. In recent years, the awareness has generated for automatic detection of depression from the speech signal. Some queries are raised that which features are more responsible for depression from speech and which classifiers gives good results. By identifying proper features from speech signal system even one can save the life of a patient. In this paper, a survey of speech signal features which relates for depression analysis is presented. Specially focused on adolescence speech. After surveying it is hypothesized that many speech features are there which are responsible for depression like linear features Prosodic, cepstral, spectral and glottal features and non-linear feature Teager energy operator (TEO). Some classification methods for depression analysis from previous studies are summarized.

Pattern recognition using neural networks

Abstract: Face Recognition has been identified as one of the attracting research areas and it has drawn the attention of many researchers due to its varying applications such as security systems, medical systems, entertainment, etc. Face recognition is the preferred mode of identification by humans: it is natural, robust and non-intrusive. A wide variety of systems requires reliable personal recognition schemes to either confirm or determine the identity of an individual requesting their services. The purpose of such schemes is to ensure that the rendered services are accessed only by a legitimate user and no one else. Examples of such applications include secure access to buildings, computer systems, laptops, cellular phones, and ATMs. In the absence of robust personal recognition schemes, these systems are vulnerable to the wiles of an impostor. In this paper we have developed and illustrated a recognition system for human faces using a novel Kohonen self-organizing map ( SOM ) or Self-Organizing Feature Map ( SOFM ) based retrieval system. SOM has good feature extracting property due to its topological ordering. The Facial Analytics results for the 400 images of AT&T database reflects that the face recognition rate using one of the neural network algorithm SOM is 85.5% for 40 persons.

Cardiovascular Disease Prediction Using Machine Learning Models

Abstract: Cardiovascular diseases are one of the most vital causes offatality. Cardiovascular disease prediction is a critical challenge in the area of clinical data analysis. Machine learning and Neural Networks are more promising in assisting decide and predict from the massive data produced by healthcare. We have noted different features had used in recent developments of the machine learning model. In this paper, we proposed machine learning techniques to predict cardiovascular disease using features. BMI is one of the highlighting features we used for prediction. BMI is important in predicting cardiovascular disease. The main focus of the article isthe effect ofBMI onthe prediction of cardiovascular disease. The model has proposed with different features as well as regression and classification techniques. We conclude that BMI is a significant factor while predicting cardiovascular disease.

The Self-Organizing Map

Abstract: An overview of the self-organizing map algorithm, on which the papers in this issue are based, is presented in this article.

Object Detection Recognition and Robot Grasping Based on Machine Learning: A Survey

Abstract: With the rapid development of machine learning, its powerful function in the machine vision field is increasingly reflected. The combination of machine vision and robotics to achieve the same precise and fast grasping as that of humans requires high-precision target detection and recognition, location and reasonable grasp strategy generation, which is the ultimate goal of global researchers and one of the prerequisites for the large-scale application of robots. Traditional machine learning has a long history and good achievements in the field of image processing and robot control. The CNN (convolutional neural network) algorithm realizes training of large-scale image datasets, solves the disadvantages of traditional machine learning in large datasets, and greatly improves accuracy, thereby positioning CNNs as a global research hotspot. However, the increasing difficulty of labeled data acquisition limits their development. Therefore, unsupervised learning, self-supervised learning and reinforcement learning, which are less dependent on labeled data, have also undergone rapid development and achieved good performance in the fields of image processing and robot capture. According to the inherent defects of vision, this paper summarizes the research achievements of tactile feedback in the fields of target recognition and robot grasping and finds that the combination of vision and tactile feedback can improve the success rate and robustness of robot grasping. This paper provides a systematic summary and analysis of the research status of machine vision and tactile feedback in the field of robot grasping and establishes a reasonable reference for future research.