JOURNAL OF ADVANCED APPLIED SCIENTIFIC RESEARCH 2024-02-26T09:20:55+00:00 Editorial Manager Open Journal Systems <p>Journal of advanced applied scientific research (JOAASR) is an entrenched podium for scientific exchange among applied scientific research. The journal aims to publish papers dealing with novel experimental and theoretical aspects of applied scientific research. The focus is on fundamental and advance papers that understanding of applied scientific research. JOAASR incorporates innovations of the novel theoretical and experimental approaches on the quantitative, qualitative and modeling of advanced scientific concepts.</p> Optimizing Performance of Cloud Infrastructure Through Effective Resource Scheduling 2023-11-04T13:10:32+00:00 M.Abdullah Dr. M. Mohamed Surputheen <p>Cloud computing has emerged as a very promising technology that has garnered significant interest from both industry professionals and academic researchers. Cloud computing service models refer to the various types of services that are provided, including hardware and software infrastructure, platforms for application development, testing, and deployment, as well as enterprise software that is readily available for usage through subscription. Public cloud computing involves the delegation of IT infrastructure, storage, or applications to an external service provider. The presence of a cloud infrastructure also signifies the existence of geographically distributed computing resources. The utilisation of resources in conjunction with cloud computing is not exclusive to large-scale organisations, as it may be employed by entities of any size. Numerous services are offered based on a fee-for-use model, rendering them cost-effective for organisations of various sizes. Cloud service providers are obligated to provide consumers with cloud services on demand, as there is a growing need for such services. This requirement stems from the necessity to decrease the size of large data volumes, which in turn leads to cost savings in maintaining extensive storage systems. The overall effectiveness of cloud computing environments is directly related to the operational performance of cloud infrastructure. This phenomenon holds substantial significance in the realm of optimization, since it enhances the overall efficiency of the underlying cloud architecture. The proposed technique exhibits a significant effectiveness in enhancing cloud performance, as it manifests improvements for both service providers and cloud customers.</p> <p><strong>Key Words: </strong>Cloud Computing, Task Scheduling, Cloud Infrastructure, Resource Scheduling, Performance Analysis and Infrastructure as Service.</p> 2024-02-26T00:00:00+00:00 Copyright (c) 2024 JOURNAL OF ADVANCED APPLIED SCIENTIFIC RESEARCH Detection and Removal of Assymmetrical Skin Lesions Using DU-Net for Patch Extraction 2023-12-19T14:07:04+00:00 Gopikha S BalaMurugan M <p id="E253" class="x-scope qowt-word-para-2"><span id="E255" class="qowt-font2-TimesNewRoman">The incidence of melanoma, a highly </span><span id="E256" class="qowt-font2-TimesNewRoman">fatal</span><span id="E257" class="qowt-font2-TimesNewRoman"> kind of malignant </span><span id="E258" class="qowt-font2-TimesNewRoman">tumor</span><span id="E259" class="qowt-font2-TimesNewRoman">, is exhibiting an upward trend in its progression. Timely intervention and management of skin cancer significantly enhance the likelihood of survival. Analyzing </span><span id="E261" class="qowt-font2-TimesNewRoman">dermoscopic</span><span id="E263" class="qowt-font2-TimesNewRoman"> images poses challenges for dermatologists due to various distracting factors, including fluctuations in lighting and reflections on the skin's surface. Accurately delineating the area of skin pathology is crucial for diagnosing the specific skin condi</span><span id="E264" class="qowt-font2-TimesNewRoman">tion. This study introduces DU</span><span id="E265" class="qowt-font2-TimesNewRoman">-net, a method for identifying and removing </span><span id="E266" class="qowt-font2-TimesNewRoman">pigmented skin lesions. The DU</span><span id="E267" class="qowt-font2-TimesNewRoman">-net framework incorporates deep convolutional neural networks, notably YOLOv5, to perform patch detection. It also employs asymmetrical patch contouring methods to preserve edge information. Additionally, clustering algorithms are </span><span id="E268" class="qowt-font2-TimesNewRoman">utilized</span><span id="E269" class="qowt-font2-TimesNewRoman"> to identify pixel groups and extract patches from the image. </span><span id="E270" class="qowt-font2-TimesNewRoman">The De Trop Noise Exclusion technique, in conjunction with the process of in-painting, is employed to successfully eliminate hair from the images within the ISIC-2018 and 2019 datasets. </span><span id="E271" class="qowt-font2-TimesNewRoman">Rigorous annotation of skin images with lesions of various sizes and shapes using rectangle bounding is carried out, and YOLOv5 hyper</span><span id="E272" class="qowt-font2-TimesNewRoman">-</span><span id="E273" class="qowt-font2-TimesNewRoman">parameters are fine-tuned to achieve high-confidence multiple lesion detection in </span><span id="E275" class="qowt-font2-TimesNewRoman">dermoscopic</span><span id="E277" class="qowt-font2-TimesNewRoman"> images. Despite complex textures and unclear boundaries, our approach consistently detects and labels patches, accurately segmenting the areas of skin pathology. The model's performance is assessed on these datasets using various parameter metrics, the results of the study indicate that the segmentation strategies described in this research exhibit an average accuracy ranging from about 92% to 94%.</span></p> 2024-02-26T00:00:00+00:00 Copyright (c) 2024 JOURNAL OF ADVANCED APPLIED SCIENTIFIC RESEARCH