An important parameter assessed during the semen analysis is the overall morphology, or shape of the sperm. Currently, the morphological analysis of sperm is done manually and is based on visual observation of at least 200 spermatozoa in a microscope followed by a classification stage based on strict criteria. But this method has led to incorrect results due to various factors such as different staining procedures, experience of technicians and human errors. So this paper focuses on morphological classification of spermatozoon either as normal or abnormal using Matlab. The first stage is the image preprocessing stage which involves the conversion of RGB image to a gray scale image and then image noises are removed using median filter. The second stage is the detection and extraction of individual spermatozoon which involves the extraction of sperm objects from images using sobel edge detection algorithm. The third stage segments the spermatozoon into various region of interest such as sperm head, midpiece and tail. The fourth stage involves the statistical measurement of spermatozoon which classifies Spermatozoa as normal or abnormal.
A semen analysis evaluates certain characteristics of a male's semen and the sperm contained in the semen. The chance of pregnancy will be reduced, if more than 50 percent of a man's sperm lack movement. Assessing the ability of sperm to move forward through the cervix into the fallopian tubes is a widely used measure of male infertility. Since the examination is done by a person through a microscope, a fairly simple system is used for classifying the spermatozoa. This paper proposes a technique to evaluate the motility of human spermatozoon which includes moving object detection, tracking and behavioral analysis. The objective is to measure the speed and quality of movement by tracking video clips of individual sperm cells. The approach chosen was frame differencing on consecutive frames, which identifies moving objects from the portion of a video frame that differs significantly from the previous frame. This method has less computation complexity, high recognition rate and a faster processing speed.
Cloud computing is a model that points at streamlining the on-demand provisioning of software, hardware and data as services and providing end-users with flexible and scalable services accessible through the Internet. The main objective of the proposed approach is to maximize the resource utilization and provide a good balanced load among all the resources in cloud servers. Initially, a load model of every resource will be derived based on several factors such as, memory usage, processing time and access rate. Based on the newly derived load index, the current load will be computed for all the resources shared in virtual machine of cloud servers. Once the load index is computed for all the resources, load balancing operation will be initiated to effectively use the resources dynamically with the process of assigning resources to the corresponding node to reduce the load value. So, assigning of resources to proper nodes is an optimal distribution problem so that many optimization algorithms such as genetic algorithm and modified genetic algorithm are utilized for load balancing. These algorithms are not much effective in providing the neighbour solutions since it does not overcome exploration and exploration problem. So, utilizing the effective optimization procedure instead of genetic algorithm can lead to better load balancing since it is a traditional and old algorithm. Accordingly, I have planned to utilize a recent optimization algorithm, called firefly algorithm to do the load balancing operation in our proposed work. At first, the index table will be maintained by considering the availability of virtual servers and sequence of request. Then, load index will be computed based on the newly derived formulae. Based on load index, load balancing operation will be carried out using firefly algorithm. The performance analysis produced expected results and thus proved the proposed approach is efficient in optimizing schedules by balancing the loads. The average time obtained for the proposed approach is 0.934 ms.
Cloud computing is a new technology which supports resource sharing on a “Pay as you go” basis around the world. It provides various services such as SaaS, IaaS, and PaaS. Computation is a part of IaaS and the entire computational requests are to be served efficiently with optimal power utilization in the cloud. Recently, various algorithms are developed to reduce power consumption and even Dynamic Voltage and Frequency Scaling (DVFS) scheme is also used in this perspective. In this paper we have devised methodology which analyzes the behavior of the given cloud request and identifies the associated type of algorithm. Once the type of algorithm is identified, using their asymptotic notations, its time complexity is calculated. Using best fit strategy the appropriate host is identified and the incoming job is allocated to the victimized host. Using the measured time complexity the required clock frequency of the host is measured. According to that CPU frequency is scaled up or down using DVFS scheme, enabling energy to be saved up to 55% of total Watts consumption.
Medical Diagnosis is the utmost need of an hour. Gestational Diabetics in women represents the second leading cause of yielding children born with birth defects. The ultrasound images are usually low in resolution making diagnosis difficult. Specialized tools are required to assist the medical experts to categorize and diagnose diseases to accuracy. If the anomalies in the ultrasound images are detected in the preliminary screening of placenta, fetal loss could be minimized. This pilot study was carried out to find the feasibility for detecting anomalies in placental growth due to the implications of gestational diabetics by considering the stereo image mapping based on wavelet analysis for 2D reconstruction. The research uses waveletbased methods to extract features from the ultrasonic images of placenta. The shape of the placenta is generated using the Back Propagation Network. Euclidean Distance Classifier is used for classifying the ultrasonic images of placenta.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.