Please wait a minute...
, No 3

■ Cover page(PDF 3172 KB) ■  Table of Content, March 2023(PDF 34 KB)

  • SERIGO: Development and Implementation of a Peer-to-Peer Self-Driving Car Rental App using Flutter Framework
    Zarak Jahan, Manav Chauhan, Nazia Parween, and Megha Chhabra
    2023, 19(3): 155-166.  doi:10.23940/ijpe.23.03.p1.155166
    Abstract    PDF (513KB)   
    References | Related Articles
    One of the unique transportation systems that are developing today is peer-to-peer self-driving car sharing, although fewer people are aware of it and its advantages. This transportation system targets individuals who may profit by using underutilised automobiles to generate extra income. In this paper, we present an Android app for peer-to-peer self-driving car rentals that allows users to register as Renters or Hosts, with the latter having the option to market their vehicle for rent. We use Flutter, Android Studio, and Firebase for backend and database management when developing for Android. Along with the system architecture and programme design, the graphical user interface (GUI) and the working of the software system are described. Future IOS application development and field testing are our goals.
    Low Power Full Adders based on Proposed Hybrid and GDI Designs: A Novel Approach
    Anubhav Anand, Satyam Singh, Sandeep Dhariwal, Reeba Korah, and Gaurav Kumar
    2023, 19(3): 167-174.  doi:10.23940/ijpe.23.03.p2.167174
    Abstract    PDF (898KB)   
    References | Related Articles
    This research article provides proposed designs of hybrid and GDI-based full adders with better performance parameters, such as power dissipation, propagation delay, and power delay product. Performance analysis of the existing designs and proposed designs are carried out for one-bit full adder using industry standard Cadence tool, Virtuoso at 45nm with a 1V supply. Based on the survey of performance, the best existing full adder designs are taken into consideration. These existing designs are based on GDI and hybrid techniques. The simulation results show that the proposed design performs better in terms of power dissipation and delay. The GDI-based proposed full adder exhibits less power dissipation compared to the existing GDI full adder. On the other hand, the hybrid-based proposed full adder also exhibits less power dissipation compared to the existing hybrid full adder. Among these two proposed techniques, the hybrid technique is much better in terms of power consumption, and the delay is less compared to existing designs. Therefore, these proposed designs can be considered for power efficient ALUs and processors.
    Boosting X-Ray Scans Feature for Enriched Diagnosis of Pediatric Pneumonia using Deep Learning Models
    Vaishali Arya and Tapas Kumar
    2023, 19(3): 175-183.  doi:10.23940/ijpe.23.03.p3.175183
    Abstract    PDF (1038KB)   
    References | Related Articles
    A range of infectious bacteria and non-infectious factors can both induce and lead to pneumonia, which is an illness of the pulmonary parenchyma. Several age categories are vulnerable, but children under the age of five tend to be especially vulnerable. Chest x-rays, the most frequent radiological test, are a highly significant modality for which numerous uses have been studied. Additionally, x-ray equipment has an upside due to their reduced radiation exposure over imaging technologies like tomography and their potential for accessibility from remote locations. Unfortunately, it might be challenging for physicians to identify pediatric pneumonia because x-ray scans are not always clear or because of human traits like weariness and inattentiveness. In this research, the authors provide a framework for brightness preserving and contrast boosting to strengthen the precision of existing deep learning models. Different cutting-edge deep learning models including VGG16, GoogLeNet, AlexNet, DenseNet-121, InceptionV3, ResNet-18, ResNet-50, ResNet-101, and SqueezeNet are tested both with and without the improvement suggested in this research. The results obtained clearly show the improvement in classification accuracy attained after implementing the proposed image enhancement. The experiments exhibit a maximum of 10.57% improvement in the overall accuracy attained without enhancing the image with the proposed framework. The highest accuracy recorded is 91.05% with RestNet-101.
    A Survey of Distributed Data Storage in the Cloud for Multitenant Applications
    Aditi Sharma and Parmeet Kaur
    2023, 19(3): 184-192.  doi:10.23940/ijpe.23.03.p4.184192
    Abstract    PDF (253KB)   
    References | Related Articles
    Cloud services are generally based on multitenancy, which refers to sharing of virtualized hardware infrastructure and application servers between the users, also known as tenants. Multi-tenancy lowers the cost of services for both the providers as well as the tenants. In the context of storage services utilized by software-as-a-service applications, data of all tenants is stored in cloud-based but shared servers, storage, or databases. The sharing of the resources among tenants can result in the co-location of their data within the same storage solution. This can further lead to risks of data tampering or data leaks that must be handled by the provider to ensure the trust of tenants. The separation of various customer data is mandatory to ensure any data stored is not accessible or viewable by another tenant user. This survey investigates the implementation of multitenancy in distributed, cloud-based storage services. It discusses the existing approaches and models employed by commercial cloud service providers. The perspective and solutions presented by researchers are also put forth. Finally, a few open problems and directions for further research are listed.
    DCADS: Data-Driven Computer Aided Diagnostic System using Machine Learning Techniques for Polycystic Ovary Syndrome
    Harshita Batra and Leema Nelson
    2023, 19(3): 193-202.  doi:10.23940/ijpe.23.03.p5.193202
    Abstract    PDF (982KB)   
    References | Related Articles
    Background: In recent years, humans have faced many diseases because of their lifestyle and environmental changes. One of these is polycystic ovary syndrome (PCOS), a hormonal condition that affects a large percentage of women of reproductive age. One in five (20%) Indian women have PCOS, making it one of the most prevalent causes for female infertility in women. Causes: The ovaries create small fluid-filled sacs called follicles, which fail to discharge eggs regularly, resulting in an imbalanced menstrual cycle. It is challenging for doctors to manually analyze disease symptoms, but this might be accomplished by utilizing machine-learning approaches to confirm that this category accurately identifies individuals with chronic diseases. Early identification and diagnosis of these diseases are important as they can prevent them from reaching their worst stage. Methods: This work aims to develop a Data-driven Computer Aided Diagnostic System (DCADS) using Synthetic Minority Oversampling Technique (SMOTE), correlation-based feature selection, and Machine Learning techniques to diagnose PCOS without the need for clinical testing. SMOTE oversamples the minority samples in the dataset and the important features are selected above the threshold value of 0.25 using the correlation-based feature selection method. Random Forest (RF), Support Vector Machine (SVM) and Logistic Regression (LR) are three machine-learning algorithms used to learn from the selected input features. The classification accuracy serves as the basis for the performance of the ML classifier. Because RF classifiers are more accurate than the other classifiers in this study, they have been employed in DCADS for non-clinical testing. The developed DCADS was tested using the PCOS dataset obtained from Kaggle and owned by Prasoon Kottarathil. Conclusion: Random forest achieves an overall accuracy of 92.024%, logistic regression achieves 90.18%, and SVM achieves 70.55% for the PCOS dataset. Gynecologists and women can diagnose PCOS using the developed DCADS without the need of clinical tests.
    AI-Powered Workforce Analytics: Maximizing Business and Employee Success through Predictive Attrition Modelling
    Shobhanam Krishna and Sumati Sidharth
    2023, 19(3): 203-215.  doi:10.23940/ijpe.23.03.p6.203215
    Abstract    PDF (477KB)   
    References | Related Articles
    The purpose of the paper is to introduce a machine learning model that utilizes the Logistics Regression algorithm to analyze the likelihood of employees leaving an organization. The paper seeks to identify key motivators that contribute to employee turnover and provide insights into how to reduce employee attrition rates. To accomplish this, the research delves into the factors that impact employee contentment and involvement, such as job security, opportunities for career advancement, maintaining a healthy work-life balance, and remuneration. Moreover, the effectiveness of the Logistics Regression algorithm in predicting employee turnover is being evaluated. The methodology used in the study involves the application of the Logistics Regression algorithm to evaluate important parameters related to employee retention. The model achieves an accuracy rate of 84.12 percent, a precision of 84 percent, and a recall rate of 100 percent. The study's findings can assist management in making informed decisions and implementing changes to retain employees, ultimately enhancing productivity and loyalty and increasing the organization's competitiveness. Focusing too much on predicting employee attrition may take attention away from other important aspects of managing employees, and different organizations may require different approaches to employee retention. However, using prediction models to identify potential flight risks and develop retention strategies can lead to a stable and productive workforce, positively impacting overall organizational performance. The paper's originality lies in its use of machine learning and predictive analytics to address a critical issue affecting organizational competitiveness.
    A Novel Multi-Objective Cat Swarm Technique for an Efficient Cloud Manager for Data Handling in Cloud Environment
    Megha Gupta, Laxmi Ahuja, and Ashish Seth
    2023, 19(3): 216-222.  doi:10.23940/ijpe.23.03.p7.216222
    Abstract    PDF (359KB)   
    References | Related Articles
    The three key advantages of cloud computing are adaptability, scale, and availability. These features were produced by combining virtualization techniques with internet services. The conventional management techniques and tools, unfortunately, appear inadequate in comparison to the scalability and flexibility of cloud services since they often require local software installation with ongoing upgrades and modifications. System administrators still do a major portion of the manual work involved in deploying and managing cloud configurations. Working with cloud services from multiple providers is also challenging since the solutions are sometimes private and only adhere to the cloud service capabilities of certain service providers. Incorporating autonomy into cloud management would mean giving the cloud manager the capacity to autonomously upgrade or decrease the variety of deployed images and virtual machines to fulfill Customer service contracts for efficiency, etc. In this paper, we introduce Multi-objective Cat Swarm - Aurora (MCS-Aurora), a highly scalable infrastructure as a service (IaaS) cloud manager that enables access to cloud services even in the scenario that the manager itself fails. By providing network automation, MCS-Aurora and the role-based access control mechanism provide flexible and effective resource management. Enhancing user authentication, data access mechanisms, and data security are the main goals of the suggested manager. The manager is in charge of achieving the cloud's service level agreement for handling and storing data. To demonstrate the effectiveness of the system, the suggested technique is contrasted with current methods.
ISSN 0973-1318