International Journal of Computer and Applications

Medical Image segmentation is an important image processing step. Comparing images to evaluate the quality of segmentation is an essential part of measuring progress in this research area. Some of the challenges in evaluating medical segmentation are: metric selection, the use in the literature of multiple definitions for certain metrics, inefficiency of the metric calculation implementations leading to difficulties with large volumes, and lack of support for fuzzy segmentation by existing metrics. First we present an overview of 20 evaluation metrics selected based on a comprehensive literature review. For fuzzy segmentation, which shows the level of membership of each voxel to multiple classes, fuzzy definitions of all metrics are provided. We present a discussion about metric properties to provide a guide for selecting evaluation metrics. Finally, we propose an efficient evaluation tool implementing the 20 selected metrics. The tool is optimized to perform efficiently in terms of speed and required memory, also if the image size is extremely large as in the case of whole body MRI or CT volume segmentation. An implementation of this tool is available as an open source project. We propose an efficient evaluation tool for 3D medical image segmentation using 20 evaluation metrics and provide guidelines for selecting a subset of these metrics that is suitable for the data and the segmentation task.

/pdf/metrics-for-evaluating-3d-medical-image-segmentation-9r93of3dkp.pdf

Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool

This review article through light on a highly promising & demanding technology, which is set to revolutionize nearly every product category in present era, while discussing the Concept, Design & Development, Fabrication techniques and applications of micro electro-mechanical systems (MEMS) based Devices or systems. Microelectromechanical system discloses outstanding flexibility and adaptability in miniaturization devices followed by their compact dimension, low power consumption, and fine performance. The MEMS devices have numerous and very high potentials of creating a new field of applications for mobile equipment’s with increased flexibility & more reliability. This work deals with research carried out for the development of MEMS based sensors & Actuators and appropriate uses of MEMS. This work carries information’s regarding subsequent commercial and real life applications of MEMS and discusses various recent technological innovations carried out with their advantages & disadvantages. This work also describes the historical development of micro-electromechanical system (MEMS) sensor technology.

/pdf/mems-technology-a-review-3ce419hf6o.pdf

MEMS Technology: A Review

Over the last couple of decades, the advancement in Microelectromechanical System (MEMS) devices is highly demanded for integrating the economically miniaturized sensors with fabricating technology. A sensor is a system that detects and responds to multiple physical inputs and converting them into analogue or digital forms. The sensor transforms these variations into a form which can be utilized as a marker to monitor the device variable. MEMS exhibits excellent feasibility in miniaturization sensors due to its small dimension, low power consumption, superior performance, and, batch-fabrication. This article presents the recent developments in standard actuation and sensing mechanisms that can serve MEMS-based devices, which is expected to revolutionize almost many product categories in the current era. The featured principles of actuating, sensing mechanisms and real-life applications have also been discussed. Proper understanding of the actuating and sensing mechanisms for the MEMS-based devices can play a vital role in effective selection for novel and complex application design.

/pdf/a-review-of-actuation-and-sensing-mechanisms-in-mems-based-450ftrxe90.pdf

A Review of Actuation and Sensing Mechanisms in MEMS-Based Sensor Devices

Cloud computing (CC) is on-demand accessibility of network resources, especially data storage and processing power, without special and direct management by the users. CC recently has emerged as a set of public and private datacenters that offers the client a single platform across the Internet. Edge computing is an evolving computing paradigm that brings computation and information storage nearer to the end-users to improve response times and spare transmission capacity. Mobile CC (MCC) uses distributed computing to convey applications to cell phones. However, CC and edge computing have security challenges, including vulnerability for clients and association acknowledgment, that delay the rapid adoption of computing models. Machine learning (ML) is the investigation of computer algorithms that improve naturally through experience. In this review paper, we present an analysis of CC security threats, issues, and solutions that utilized one or several ML algorithms. We review different ML algorithms that are used to overcome the cloud security issues including supervised, unsupervised, semi-supervised, and reinforcement learning. Then, we compare the performance of each technique based on their features, advantages, and disadvantages. Moreover, we enlist future research directions to secure CC models.

https://www.mdpi.com/2079-9292/9/9/1379/pdf

A Review of Machine Learning Algorithms for Cloud Computing Security

Information Security in cloud storage is a key trepidation with regards to Degree of Trust and Cloud Penetration. Cloud user community needs to ascertain performance and security via QoS. Numerous models have been proposed [2] [3] [6][7] to deal with security concerns. Detection and prevention of insider threats are concerns that also need to be tackled. Since the attacker is aware of sensitive information, threats due to cloud insider is a grave concern. In this paper, we have proposed an authentication mechanism, which performs authentication based on verifying facial features of the cloud user, in addition to username and password, thereby acting as two factor authentication. New QoS has been proposed which is capable of monitoring and detection of insider threats using Machine Learning Techniques. KNN Classification Algorithm has been used to classify users into legitimate, possibly legitimate, possibly not legitimate and not legitimate groups to verify image authenticity to conclude, whether there is any possible insider threat. A threat detection model has also been proposed for insider threats, which utilizes Facial recognition and Monitoring models. Security Method put forth in [6] [7] is honed to include threat detection QoS to earn higher degree of trust from cloud user community. As a recommendation, Threat detection module should be harnessed in private cloud deployments like Defense and Pharma applications. Experimentation has been conducted using open source Machine Learning libraries and results have been attached in this paper.

Insider Threat Detection with Face Recognition and KNN User Classification

Emotion recognition helps to recognize the internal expressions of the individuals from the speech database. In this paper, Dynamic time warping (DTW) technique is utilized to recognize speaker independent Emotion recognition based on 39 MFCC features. A large audio of around 960 samples of isolated words of five different emotions are collected and recorded at 20 to 300 KHz sampling frequency. Training and test templates are generated using 39 MFCC features. In the proposed work, we have extracted the MFCC coefficients from the speech database and DTW is used to store a prototypical version of each word in the vocabulary and compute incoming emotion with each word. For the classification of emotions SVM is used. The experimental results are provided using MFCC, Delta Coefficients (∆MFCC) and Delta Delta Coefficients(∆∆MFCC) . It is proposed that higher recognition rates can be achieved using MFCC features with DTW which is useful for different time varying speech utterances.

Emotion Recognition using Dynamic Time Warping Technique for Isolated Words

MEMS - Micro electro mechanical systems. It refers to machines with moving parts smaller than a human hair that contain both electrical and mechanical components on silicon. Also referred to as Microsystems, microstructures, microstructure technology (MST) and mechatronics. Micro electro mechanical Systems (MEMS) have gained acceptance as viable products for many commercial and government applications. This paper gives a brief review of history and components of MEMS. This paper will discuss current and future MEMS applications. It then gives the fabrication processes of MEMS. Further this paper discusses about the MEMS achievements, challenges and requirements. Next it discusses the future form of MEMS. Lastly it concludes saying that MEMS have enough potential to establish a second technological revolution of miniaturization that may create an industry that exceeds the IC industry in both size and impact on society

/pdf/review-on-break-through-mems-technology-2zwfs3dvor.pdf

Review on Break through MEMS Technology

The Semantic Web Technologies growing interest in human computer interactions where it enables the machines to interpret the data published in a machine interpretable form under web. Currently, E-Commerce is seriously vulnerable due to the lack of proper standards where HTML does not provide the syntax and semantics of information. Semantic Web has the potential to extremely influence the further development of the internet market, where e-commerce plays an important role. This paper discusses the semantic architecture for e-commerce using ontology language like RDF. This gives the overview about how the producer describes their resource in ontology content and how the consumer will retrieve the efficient data.

/pdf/perspectives-of-semantic-web-in-e-commerce-11pmb2ciyy.pdf

Perspectives of Semantic Web in E- Commerce

Today, modern technology led to a faster growth of digital media collection, and it contains both still images and videos. Storage devices contain large amount of digital images, increasing the response time of a system to retrieve images required from such collections, which degrades the performance. Various search skills are needed to find what we are searching for in such large collections. The annotations are given manually for images by describing with the set of keywords. By doing so, the contents of an image retrieve images of interest, but it is time-consuming. Also, different individuals may annotate the same image using different keywords, which make it difficult to create a suitable classification and annotate images with the exact keywords. To overcome all these reasons, content-based image retrieval (CBIR) is the area which is used for extracting images. The technique gray-level co-occurrence matrix (GLCM) is discussed and analyzed for retrieval of image. It considers the various features such as color histogram, texture, and edge density. In this paper, we mainly concentrate on texture feature for accurate and effective content-based image retrieval system.

Yarramalle Srinivas

Papers

Insider Threat Detection with Face Recognition and KNN User Classification

Emotion Recognition using Dynamic Time Warping Technique for Isolated Words

Review on Break through MEMS Technology

Perspectives of Semantic Web in E- Commerce

An Efficient Content-Based Image Retrieval (CBIR) Using GLCM for Feature Extraction