scispace - formally typeset
Search or ask a question
Author

Anu Mehra

Bio: Anu Mehra is an academic researcher from Amity University. The author has contributed to research in topics: CMOS & Adder. The author has an hindex of 6, co-authored 71 publications receiving 189 citations. Previous affiliations of Anu Mehra include Guru Gobind Singh Indraprastha University.

Papers published on a yearly basis

Papers
More filters
Proceedings ArticleDOI
09 Jun 2016
TL;DR: A fully automatic method is introduced to detect brain tumors and is carried out by using Area and Circularity as a criteria and the results are verified by comparing them with the manually segmented Ground Truth.
Abstract: A brain tumor or intracranial neoplasm is formed when abnormal cells get accumulated within the brain. These cells multiply in an uncontrolled manner and damage the brain tissues. Magnetic Resonance Imaging (MRI) scans are commonly used to diagnose brain tumors. However, segmenting and detecting the brain tumor manually is a tedious task for the radiologists. Hence, there is a need for automatic systems which yield accurate results. In this paper, a fully automatic method is introduced to detect brain tumors. The proposed method consists of five stages, viz., Image Acquisition, Preprocessing, Segmentation using Fuzzy C Means technique, Tumor Extraction and Evaluation. Tumor extraction is carried out by using Area and Circularity as a criteria. The results are finally verified by comparing them with the manually segmented Ground Truth. Dice coefficient is also calculated and the average dice coefficient value obtained was 0.729.

59 citations

Proceedings ArticleDOI
01 Feb 2015
TL;DR: Wide range of results for leakage power reduction techniques of CMOS technologies from 180nm to 45nm is covered which will be helpful for further research in this area.
Abstract: This paper compares various leakage reduction techniques including Multi-threshold CMOS, Super-Cutoff CMOS, Zigzag, Stack Effect, Input Vector Control, LECTOR, Sleepy Stack, Sleepy Keeper, VCLEARIT, GALEOR, Dual Sleep, Sleepy-Pass Gate and Transistor Gating. The paper elaborately explores the working, comparison and analysis of all these techniques in different CMOS technologies. Leakage Power is analyzed during the standby mode of operation. It has been observed that for a particular circuit leakage depends on CMOS technology as well as leakage reduction technique. In this paper, wide range of results for leakage power reduction techniques of CMOS technologies from 180nm to 45nm is covered which will be helpful for further research in this area.

22 citations

Proceedings ArticleDOI
27 Apr 2015
TL;DR: A methodology for emotion recognition from speech signals and textual information together to improve the confidence level of emotion classification by using the threshold fusion and shows that the accuracy of the combined system has been improved as compared to the two individual methodologies.
Abstract: This paper presents a methodology for emotion recognition from speech signals and textual information together to improve the confidence level of emotion classification by using the threshold fusion. Some of acoustic features are extracted from the speech signal to analyze the characteristics and behavior of speech. Support Vector Machines (SVMs) are used for recognition of the emotional states. In this approach textual analysis of all emotions and emotional contents are manually defined and labeled. Emotion intensity levels of all emotional content and emotional words are calculated. The absolute emotional state is predicted from the acoustic features and textual contents using threshold based fusion. Results obtained from proposed approach show that the accuracy of the combined system has been improved as compared to the two individual methodologies.

18 citations

Proceedings ArticleDOI
24 Mar 2014
TL;DR: The highlight of result is that a prior knowledge about the gender of speaker increases the performance of proposed system, which has easy learning on large speech databases and its accuracy as compared to other approaches is reasonably good.
Abstract: This paper proposes an emotion recognition system which allows recognizing a person's emotional state from speech signal. The aim of proposed solution is to improve the interaction among humans and computers. The emotion recognition system must be capable of recognizing at least six basic emotions (happiness, anger, surprise, disgust, fear, sadness) and the neutral circumstances. The proposed system has two subsystems Gender Recognition (GR) and Emotion Recognition (ER) and also distinguishes a single emotion versus all the others. An appropriate emotion recognition method is applied after extracting features like pitch, energy and MFCC having emotional information. The performance in terms of accuracy is shown in results. The highlight of result is that a prior knowledge about the gender of speaker increases the performance of proposed system. Proposed approach has been implemented by using Naive Bayes method. This is a simple and efficient classification approach. It has easy learning on large speech databases and its accuracy as compared to other approaches is reasonably good. In future this system can be implemented over mobile devices such as smart phones.

14 citations

Proceedings ArticleDOI
01 Feb 2015
TL;DR: An algorithm that is divided in two parts: computing the repeated frames by processing the image pixels to produce a frame-by-frame motion energy time and computing the tampering attack and its location with the help of the Support Vector Machine helps to predict whether the given video has been tampered or not.
Abstract: The large amount of video content is being transmitted over internet and other channels. With the help of existing multimedia editing tools one can easily change the content of data which lead to lose the authenticity of the information. Thus, it becomes necessary to develop different methods by which the authenticity of the videos can be confirmed. In the past researchers have proposed several methods for authentication of videos. This paper presents an algorithm that is divided in two parts: computing the repeated frames by processing the image pixels to produce a frame-by-frame motion energy time and computing the tampering attack and its location with the help of the Support Vector Machine. This helps to predict whether the given video has been tampered or not.

13 citations


Cited by
More filters
Proceedings Article
01 Jan 2010
TL;DR: In this article, a low power boost converter for thermoelectric energy harvesting that demonstrates an efficiency that is 15% higher than the state-of-the-art for voltage conversion ratios above 20.
Abstract: This paper presents a low power boost converter for thermoelectric energy harvesting that demonstrates an efficiency that is 15% higher than the state-of-the-art for voltage conversion ratios above 20. This is achieved by utilizing a technique allowing synchronous rectification in the discontinuous conduction mode. A low-power method for input voltage monitoring is presented. The low input voltage requirements allow operation from a thermoelectric generator powered by body heat. The converter, fabricated in a 0.13 μm CMOS process, operates from input voltages ranging from 20 mV to 250 mV while supplying a regulated 1 V output. The converter consumes 1.6 (1.1) μW of quiescent power, delivers up to 25 (175) μW of output power, and is 46 (75)% efficient for a 20 mV and 100 mV input, respectively.

412 citations

Journal ArticleDOI
TL;DR: This study presents a comprehensive review of traditional machine learning techniques and evolving deep learning techniques for brain tumor diagnosis and identifies the key achievements reflected in the performance measurement metrics of the applied algorithms in the three diagnosis processes.

147 citations

Journal ArticleDOI
TL;DR: An automated system is developed for tumor extraction and classification from MRI based on marker‐based watershed segmentation and features selection that outperforms existing methods with greater precision and accuracy.
Abstract: Brain tumor identification using magnetic resonance images (MRI) is an important research domain in the field of medical imaging. Use of computerized techniques helps the doctors for the diagnosis and treatment against brain cancer. In this article, an automated system is developed for tumor extraction and classification from MRI. It is based on marker-based watershed segmentation and features selection. Five primary steps are involved in the proposed system including tumor contrast, tumor extraction, multimodel features extraction, features selection, and classification. A gamma contrast stretching approach is implemented to improve the contrast of a tumor. Then, segmentation is done using marker-based watershed algorithm. Shape, texture, and point features are extracted in the next step and high ranked 70% features are only selected through chi-square max conditional priority features approach. In the later step, selected features are fused using a serial-based concatenation method before classifying using support vector machine. All the experiments are performed on three data sets including Harvard, BRATS 2013, and privately collected MR images data set. Simulation results clearly reveal that the proposed system outperforms existing methods with greater precision and accuracy.

115 citations