Bhushan Nemade

Bio: Bhushan Nemade is an academic researcher from Thakur College of Engineering and Technology. The author has contributed to research in topics: Feature vector & Facial recognition system. The author has an hindex of 10, co-authored 18 publications receiving 259 citations. Previous affiliations of Bhushan Nemade include Tata Memorial Hospital & University of Mumbai.

A Review: Data Pre-Processing and Data Augmentation Techniques

Abstract: This review paper provides an overview of data pre-processing in Machine learning, focusing on all types of problems while building the machine learning problems. It deals with two significant issues in the pre-processing process (i). issues with data and (ii). Steps to follow to do data analysis with its best approach. As raw data are vulnerable to noise, corruption, missing, and inconsistent data, it is necessary to perform pre-processing steps, which is done using classification, clustering, and association and many other pre-processing techniques available. Poor data can primarily affect the accuracy and lead to false prediction, so it is necessary to improve the dataset's quality. So, data pre-processing is the best way to deal with such problems. It makes the knowledge extraction from the data set much easier with cleaning, Integration, transformation, and reduction methods. The issue with Data missing and significant differences in the variety of data always exists as the information is collected through multiple sources and from a real-world application. So, the data augmentation approach generates data for machine learning models. To decrease the dependency on training data and to improve the performance of the machine learning model. This paper discusses flipping, rotating with slight degrees and others to augment the image data and shows how to perform data augmentation methods without distorting the original data.

Cloud computing: Windows Azure platform

Abstract: Cloud computing is driving a fundamental shift in the way organizations build, deploy and use applications, and it's raising expectations on how quickly and cost-effectively new IT functionality can be made available to the business. And even though the delivery chain for these "borderless applications" now crosses organizational and geographic boundaries, users will still expect the applications to perform well, and they will hold IT accountable if they don't. For its part, IT is faced with managing an increasingly complex and diverse delivery chain, consisting of perhaps dozens of service and content providers spread around the world. Cloud computing is the set of technologies and infrastructure capabilities being offered in a utility based consumption model. Windows Azure is Microsoft's Cloud Computing offering to help its customers realize the benefits of cloud computing. This paper is an introduction on Windows Azure and provides insights into different aspects of Azure based development, especially for those who are interested in adopting Windows Azure within their Enterprise IT landscape. The key aspects we shall be discussing in this paper include overview of cloud computing, Windows Azure platform components, features, implementation, creating a cloud project in Windows Azure and developer's perspective about Azure.

Embryonal rhabdomyosarcoma of the biliary tree mimicking a choledochal cyst.

Abstract: Embryonal rhabdomyosarcoma (ERMS) of biliary tree is a rare type of mesenchymal neoplasm diagnosed at surgery or by preoperative liver biopsy. We present a one year eight months old child who mimicked a choledochal cyst and was eventually treated with surgery, chemotherapy with IRS IV protocol and adjuvant postoperative radiotherapy to surgical bed with 6 MV photons to a dose of 5040cGy in 28 fractions.

Person Recognition System Based on a Combination of Body Images from Visible Light and Thermal Cameras.

Abstract: The human body contains identity information that can be used for the person recognition (verification/recognition) problem. In this paper, we propose a person recognition method using the information extracted from body images. Our research is novel in the following three ways compared to previous studies. First, we use the images of human body for recognizing individuals. To overcome the limitations of previous studies on body-based person recognition that use only visible light images for recognition, we use human body images captured by two different kinds of camera, including a visible light camera and a thermal camera. The use of two different kinds of body image helps us to reduce the effects of noise, background, and variation in the appearance of a human body. Second, we apply a state-of-the art method, called convolutional neural network (CNN) among various available methods, for image features extraction in order to overcome the limitations of traditional hand-designed image feature extraction methods. Finally, with the extracted image features from body images, the recognition task is performed by measuring the distance between the input and enrolled samples. The experimental results show that the proposed method is efficient for enhancing recognition accuracy compared to systems that use only visible light or thermal images of the human body.

From the Archives of the AFIP: Pediatric Liver Masses: Radiologic-Pathologic Correlation Part 2. Malignant Tumors

Abstract: Benign hepatic tumors in children include lesions that are unique to the pediatric age group and others that are more common in adults. Infantile hemangioendothelioma, or infantile hepatic hemangioma, is a benign vascular tumor that may cause serious clinical complications. It is composed of vascular channels lined by endothelial cells. At imaging, large feeding arteries and draining veins and early, intense, peripheral nodular enhancement with centripetal filling on delayed images are characteristic features. Mesenchymal hamartoma of the liver occurs in young children and is characterized pathologically by mesenchymal proliferation with fluid-containing cysts of varying size and number. The mesenchymal component or cystic component may predominate; this predominance determines the imaging appearance of the tumor. Benign epithelial tumors that are common in adults may infrequently occur in childhood. These include focal nodular hyperplasia (FNH), hepatocellular adenoma, and nodular regenerative hyperplasia. All are composed of hyperplastic hepatocytes similar to surrounding liver parenchyma and may be difficult to discern at imaging. Preferential hepatic arterial phase enhancement helps distinguish FNH and hepatic adenoma from uninvolved liver. Hepatic adenoma often has intracellular fat and a propensity for intratumoral hemorrhage, neither of which are seen in FNH. Unlike adenoma, FNH often contains enough Kupffer cells to show uptake at sulfur colloid scintigraphy. Nodular regenerative hyperplasia is often associated with portal hypertension, which may be evident at imaging. Knowledge of how the pathologic features of these tumors affect their imaging appearances helps radiologists offer an appropriate differential diagnosis and management plan.

An improved face recognition algorithm and its application in attendance management system

Abstract: Face Recognition is a computer application that is capable of detecting, tracking, identifying or verifying human faces from an image or video captured using a digital camera. Although lot of progress has been made in domain of face detection and recognition for security, identification and attendance purpose, but still there are issues hindering the progress to reach or surpass human level accuracy. These issues are variations in human facial appearance such as; varying lighting condition, noise in face images, scale, pose etc. This research paper presents a new method using Local Binary Pattern (LBP) algorithm combined with advanced image processing techniques such as Contrast Adjustment, Bilateral Filter, Histogram Equalization and Image Blending to address some of the issues hampering face recognition accuracy so as to improve the LBP codes, thus improve the accuracy of the overall face recognition system. Our experiment results show that our method is very accurate, reliable and robust for face recognition system that can be practically implemented in real-life environment as an automatic attendance management system.

Utilizing deep neural nets for an embedded ECG-based biometric authentication system

Abstract: This work presents a low-power, embedded ECG pattern recognition system for the purpose of biometric authentication. We believe that ECG coupled with a secondary biometric marker such as fingerprint will play a key role in wearable security as wearables' popularity continues to grow. The key objective of this work is to implement a system that is reliable, robust, and fast while maintaining a low area and power footprint. A streamlined approach was devised that utilized neural networks to both identify QRS complex segments of the ECG signal and then perform user authentication on these segments. When tested on 90 individuals, the system is able to achieve 99.54% accuracy for QRS complex identification, and, on average, 99.85% sensitivity, 99.96% specificity, and 0.0582% EER for user identification. When implemented on an Artix-7 FPGA, the entire design occupies 1,712 slices (5%) and 978.7 KB of memory and dissipates 31.75 mW of total chip dynamic power when running at 12.5 MHz.