International Journal of Advanced Networking and Applications

4668-4676

Authors: Wu Shiqi 1, Zhao Xing-yu 2, Qiu Fenglin 1, Tang Zhi-hang 1

This project is the design of word cloud analysis program based on web crawler. Taking Jingdong Mall as the platform, it crawls all comment information of designated products, conducts data cleaning and data analysis on the information obtained from the review and crawler, and generates word cloud map.At the same time, the visual analysis of review data can clearly show the advantages and disadvantages of customer-centered evaluations and commodities, and provide an important reference for consumers to choose commodities and businesses to improve decision-making and optimize services. This project is developed by using Python3 language, using PyChart as the IDE, using the requests library, JSON library, World Cloud library and PyMongo library, using Navicat to connect MongoDB, using PyQT5 library to achieve visual interface, and JavaScript+HTML5+ CSS3 +MySQL+ word cloud + Boozing and Bagging algorithm for data analysis and algorithm optimization. In addition to providing consumers with cost-effective, highly evaluated and highly rated goods, it also provides the sellers with more specific data to improve their own defects.

4691-4696

Authors: S.G.Hymlin Rose, Thilothi.R, Rubiya Banu.N, Sandhiya.A, Sumithra

Wireless Sensor Networks (WSNs) in recent times, have become one of the most promising network solutions with a wide variety of applications in the areas of agriculture, environment, healthcare and the military. Notwithstanding these promising applications, sensor nodes in WSNs are vulnerable to different security attacks due to their deployment in hostile and unattended areas and their resource constraints. One of such attacks is the DoS jamming attack that interferes and disrupts the normal functions of sensor nodes in a WSN by emitting radio frequency signals to jam legitimate signals to cause a denial of service. In this work a step-wise approach using a statistical process controls technique to detect these attacks. We deploy an Improved Exponentially Weighted Moving Average (IEWMA) to detect anomalous changes in the intensity of a jamming attack event by using the packet Break Advent Time (BAT) feature of the received packets from the sensor nodes. Results obtained from a trace-driven simulation show that the proposed solution can efficiently and accurately detect jamming attacks in WSNs with little or no overhead.

4706-4713

Authors: Dipendra Pant, Santosh Bhattarai, SanjayaPoudel

People with disabilities, the elderly, those who are sick, and children all need assistance. Staying with them 24 hours a day, seven days a week is impractical, and it also has an effect on the care receiver's psyche, making them feel overly reliant. Various architectures have been proposed, but none of them discuss generalization, feasibility questions, which are important for any care seeker, and also lacks focus on elderly people and non-critical patients care. As a result, an accessible, efficient architecture that allows our loved ones, especially the elderly and non-critical patients, to live healthier lives is required. It is important for health practitioners to be able to monitor the body status of those receiving care in real-time and to provide them with timely input on their health. As a result, the proposed generalizable architecture recognizes all stakeholders, as well as vital signs in the human body. Consolidates all of them into an IoT-based smart care infrastructure comprising a non-invasive hybrid body area sensor networks supported by cloud computing platforms, machine learning, and data analytics models, with the aim of assisting in the provision of high-quality, low-cost care to the elderly and non-critical patients. Finally, the design was validated through a survey and professional consultation with 45 experts, who agreed with the proposed architecture 82.2 percent of the time.

4719-4724

Authors: Salahuddin Shaikh, Liu Changan, Maaz Rasheed Malik

The few researchers have put their ideas about class-imbalance during analysis of datasets, two types of class imbalances are present in datasets. First type in which some classes have many models than others and that is called between class imbalance. Second type in which few subsets of one class have less models than other subsets of similar class and that is within class-imbalance. Over-sampling and Under-sampling innovation assume noteworthy jobs in tackling the class-imbalance issue. There are numerous dissimilarities of over-sampling and under-sampling methods which utilized for class imbalanced dataset model. We have used two sampling techniques in our research paper for our imbalanced datasets models. One is over-sampling using SMOTE technique and another one is under-sampling using spread-sub-sample. During experiments, all results are measured in evaluation performance measure. Mostly they all are class imbalanced measurements, in which precision, recall, f-measure, area under curve and 12 different classifiers we have used in our experiments to get the comparatively results of both sampling techniques. The over-all analysis showed that the efficiency of correctly classified in over-sampling techniques is enhanced in few classifiers as compared to under-sampling techniques. The TP-rate and positive accuracy of both techniques, the stacking is worst classifier in these experiments and multi classification and LMT couldn’t increase the TP-rate in under-sampling techniques. The over-all comparative analysis of both techniques as compared with without using sample techniques have increased but over-sampling technique is more valuable to use for solving the class imbalance issue.