International Journal of Advanced Networking and Applications

4509-4518

Authors: Gajendra Sharma, UmeshHengaju

In Data mining, Classification and prediction are the two very essential forms of data analysis. They are widely used for extracting models for describing important data classes. This paper aims in designing classifier models based on five different classification algorithms namely, Decision Tree, K-Nearest Neighbors (KNN), Naive Bayes, Random Forest and Support Vector Machines (SVM), to classify and predict patients with diabetes. These classifiers are experimented with 10 fold Cross Validation and their performances are evaluated by computing Accuracy, Precision, F-Score, Recall and ROC measure. The test experiment shows that the accuracy given by classifier models developed by using Decision Tree, KNN, Naïve Bayes, SVM and Random Forest are 73.82%, 71.65%, 76.30%, 65.10% and 68.74 % respectively. Similarly, their precisions and recall are 0.705, 0.552, 0.759, 0.424, 0.538 and 0.738, 0.763, 0.82, 0.651, 0.804 respectively. Thus, this study shows that the Naïve Bayes algorithm provides the better accuracy in predicting diabetes as compared to other techniques. And, the data set chosen for this study is “Pima Indian Diabetic Dataset” taken from University of California, Irvine (UCI) Repository of Machine Learning databases.

4528-4531

Authors: Pshwang Wang, Zecheng Wang

In order to protect mobile social network users' privacy information, and promote the healthy development of the mobile social industry, This paper studies the types and ways of user privacy disclosure in mobile social networks, and proposes the privacy protection strategies for users in mobile social networks from the aspects of formulating national laws and regulations, building and managing mobile platforms, improving privacy protection technologies and enhancing personal protection awareness. It also briefly introduces the development trend and future research of access control policies in mobile social network.

4537-4541

Authors: Dr.K.R.R.MOHAN RAO, Dr K.KIRAN KUMAR, Prof. P.SUBBA RAO

In the fund world stock exchanging is one of the most significant exercises. Securities exchange expectation is a demonstration of attempting to decide the future estimation of a stock other money related instrument exchanged on a monetary trade. This paper clarifies the expectation of a stock utilizing Machine Learning[6]. The specialized and central or the time arrangement examination is utilized by the a large portion of the stockbrokers while making the stock forecasts. The programming language is utilized to anticipate the securities exchange utilizing AI is Python. Right now propose a Machine Learning[10] (ML) approach that will be prepared from the accessible stocks information and increase insight and afterward utilizes the gained information for a precise forecast. Right now study utilizes an AI system called Support Vector Machine (SVM)[1] to anticipate stock costs for the enormous and little capitalizations and in the three distinct markets, utilizing costs with both every day and regularly updated frequencies.

4429-4442

Authors: Vincent Omollo Nyangaresi, Anthony J. Rodrigues, Silvance O. Abeka

The motivations behind 5G networks include seamless handovers, higher data rates, lower latencies of about one millisecond, and enhanced coverage compared to 4G networks. To achieve these goals, network densification has been implemented to cope with increasing capacity demands. Networks with ultra-densification have large numbers of heterogeneous small cell deployments such as femto-cells, relays and microcells which complicate mobility management, resulting in unnecessary, frequent, and ping-pong handovers as UEs move within the network. To address these challenges, state of the art approaches using fuzzy logic, adaptive neuro-networks or their combination have been proposed. However, these approaches majorly address the QoS issues, ignoring the security aspect of handovers. In this paper, a handover protocol that incorporates both security and QoS in the handover process is proposed. The simulation results showed that this protocol reduced handover latency, packet losses, number of executed handovers and ping pong rate by 56.1%, 38.8 %, 74.6% and 24.1% respectively. In addition, the developed protocol yielded a 27.1% increase in the handover success rate, and a 27.3% reduction in handover failure rate. This protocol was also shown to be robust against de-synchronization and session hijacking attacks.

4451-4457

Authors: Mona Nasr, Omar Farouk, Ahmed Mohamedeen, Ali Elrafie, Marwan Bedeir, Ali Khaled

Solving an optimization task in any domain is a very challenging problem, especially when dealing with nonlinear problems and non-convex functions. Many meta-heuristic algorithms are very efficient when solving nonlinear functions. A meta-heuristic algorithm is a problem-independent technique that can be applied to a broad range of problems. In this experiment, some of the evolutionary algorithms will be tested, evaluated, and compared with each other. We will go through the Genetic Algorithm, Differential Evolution, Particle Swarm Optimization Algorithm, Grey Wolf Optimizer, and Simulated Annealing. They will be evaluated against the performance from many points of view like how the algorithm performs throughout generations and how the algorithm’s result is close to the optimal result. Other points of evaluation are discussed in depth in later sections.

4468-4474

Authors: 1 Yekini Nureni Asafe, 2 Oloyede Adetokunbo Olamide, 3 Akinwole Agnes Kikelomo

Computer and Internet-Based Communication Technologies aka Cybernetic Communication play important role in communication over a distance. This work gauged uses of cybernetic communication as major means of communication during COVID-19 outbreak based on measured (Social Distance, Self-Quarantine, Isolation, Lockdown) put in place by the government to curtail spreading of the disease in Nigeria. Data were randomly collected through online publication, newsprints, and telephone calls from 290 sampled population. Data Collected were discussed and analyses using Pie chart, Percentile, and Histogram as statistical tools. Findings shows that Cybernetic communication play major role to bridge the communication gaps between the Nigerian people during the outbreak of the Covid-19 outbreak as majority of Nigerians spent more hours using cybernetic tools to communicate and more money was spent on airtime and data to keep their mobile phone running during the trying period of COVID-19 rash. Majority of the sampled population spent their useful time on social medial as in Facebook, whattsapp, Instagram, YouTube and for social interactions and meetings. The implications of our findings are: majority of Nigeria may have computer linked diseases or syndrome such Sleeping Problems and others due to prolong uses of computers; the cybernetic tools (mobile phones, computer, laptop etc.) used by the infected people may be a carrier of the symptoms in the nearest future; Nigerians spent more on data and airtime credit in this trying period and it may affect their financial economy later. This work ends with proposal for roles to be played by Nigeria government and other stakeholders in cybernetic sustained communication processes for pandemic response and to prevent future outbreak of covid-19 after overcoming recent happenings, and also recommended organization strategy for workforce continuity and recovery.

4486-4493

Authors: Dr. M. N. Faruk, Dr. G. Lakshmi Vara Prasad, Dr. K. Lakshmi Prasad

Cloud computing is actually a developing ideal to provide on-demand IT services to end-users. The get accesses to command to information situated in the cloud is just one of the essential parts to enable service to change right into the cloud. Some latest works offer access management models ideal for the cloud; nonetheless, there are essential shortages that need to be resolved in this field. This work offers a progression in the state-of the-craft to get access to management for cloud processing. We illustrate a higher meaningful consent version that permits the management of state-of-the-art attributes such as role-based to get access to management (RBAC), hierarchical RBAC (hRBAC), relative RBAC (cRBAC) and also ordered objects (HO). The get access to management design takes benefit of the logic formalism delivered due to the Semantic Internet technologies to designate both the rooting framework and also the certification style, as well as the rules worked with to guard the get access to sources in the cloud. The access control style has actually been specially established taking into consideration the multi-tenancy model of this type of environment. Moreover, this rely on a style that allows a powdery meaning of what information is on call for every specific tenant has been actually illustrated. This multi-tenant endorsement model permits a fine-grained definition of information sets is being available for the individual tenants. Certainly this assures formation of business associations among cloud tenants resulting in confederation and association agreements. The suggested model has actually been confirmed via verification of concept implementation of the gain access to management device for OpenStack along with promising efficiency end results.

4501-4508

Authors: Mona Nasr, Rana Osama, Hussein Ayman, Nouran Mosaad, Nourhan Ebrahim, Adriana mounir

This paper explains how to detect the 2D pose of multiple people in an image. We use in this paper Part Affinity Fields for Part Association (It is non-parametric representation), Confidence Maps for Part Detection, Multi-Person Parsing using PAFs, Simultaneous Detection and Association, this method achieve high accuracy and performance regardless the number of people in the image. This architecture placed first within the inaugural COCO 2016 key points challenge. Also, this architecture exceeds the previous state-of-the-art result on the MPII Multi-Person benchmark, both in performance and efficiency.

4378-4385

Authors: He Hong, Wang Ning

The research on group mobility in the opportunity network concerns what nodes’ mobility may bring about, in contrast to the preciously-proposed group mobility approaches that are unilateral in the thoughts of the constitution of groups by nodes, resulting in, the distortion of reality to reflect group behavior characteristics that are revealed in the situations of their application. Based on the Spectral Clustering algorithm, this paper proposes the group mobility model (SCM), which takes the advantage of node’s own properties, such as its spatial position, to set up node’s affinity matrix, extract main characteristics from arbitrarily distributed nodes with the aid of spectral clustering algorithm, and regarding the needs of a task assigned cluster nodes dynamically in a fixed time. The model depicts truly and effectively the group characteristics of node’s mobility, accomplish the conducts of group mobility and clustering well.

4393-4398

Authors: Tang Zhi-hang, Guo Tao, Li Jun, Wu Shi-qi

Use python web crawler to collect data from Trade website. The collected data is down jacket information. The fields are shell material, structure type, filling material, process information and style information. This information can be used for data mining, using clustering algorithms, correlation algorithms, etc. to identify potential value, providing decision-making reference for the management of textile and garment enterprises, with strong practical value. This paper provides a new idea for the development of textile and garment enterprises. The employees of the company screen, deal with the missing data and standardize the data, and then conduct data mining. The management of the enterprise makes decisions based on the results of data mining to improve decision-making basis and correctness.

4407-4417

Authors: Dr.Vijay Arputharaj J, Ms.Pushpa Rega Ganesan, Mr.Ponsuresh Manoharan, Ms.P.Supraja

Gene is a basic component of DNA located in the nucleus of Human cell. Currently data mining technique has huge impact in fields of human genetic science and gene sequence data analysis. Gene sequence analysis is a method of subjecting DNA sequence to systematic methods in order to know the genes character, configuration, nature and characteristics. CBC and MNBC applied to gene sequence data analysis, aims to segregate diseased diabetic genes from a vast stream of DNA gene sequence elements present in group of copious statistical data. This techniques attempts to approve, determine methods and tools for analyzing diseased gene sequences. It also helps in classification and interpretation of results accurately and meaningfully. This study is a combination of supervised and unsupervised machine learning technique for data analysis. The clustering is done by CBC whereas classification done by MNBC techniques. It recognizes gene expressions by framing association rules in accordance with support measure and confidence measure on the input data set.It will extract and filter required data into clusters based on CBC technique thereby drafting association rules. These are then applied on testing dataset to filter required (diseased) gene sequences. Finally MLRC algorithm is applied as classification algorithm to identify class labels of test genes sequences in a big dataset. In medical diagnosis gene data mining techniques through gene discretization models helps to identify various associations between the DNA genes based progressions and inconsistency in disease infections transformations. Above all it overcomes the limitation of existing Support Vector Machine Classification technology which incurs high computational cost and increased iterations.

4423-4428

Authors: NaglaaSaeedShehata, Amira Hassan Abed

Due to the Era of Big Data with the large amount of distributed databases in the web and the rapid growth in the smart systems a rapid growth happening in database models and the relational database fails to dealing with such a big amount of data and have many limitations the need to new technologies comes up, which makes DBMS developers move towards column oriented NOSQL database. The main goal of this paper is to provide a survey on NOSQL Model especially a column oriented NOSQL database, providing the user with the benefit of using NOSQL database, Instead of using the (row database) relational to overcome the drawbacks of the relational database Model.

4321-4329

Authors: Amira Hassan Abed

Big data is becoming a very important concept nowadays as it can handle data in different formats and structures, velocity, and huge volume. NOSQL databases are used for handling the data with these characteristics as traditional database can’t be used in managing this type of data. NoSQL database design is based on horizontal scalability with the concept of BASE which supports eventual consistence and data is considered in a soft state and basically available. Although NoSQL has a lot to offer when used in big data it is still not mature enough and faces some challenges including low join performance, concurrency control and recovery. Not only this but also it is very challenging for organizations to know which NoSQL data model to use and how does it fit with its organizational needs. This paper mainly displays the different NOSQL data models and the opportunities and challenges alongside with some techniques for handling these challenges.

4336-4344

Authors: Bekan Kitaw, Fisseha Bayu, Gemechu Birhanu

Mobile Adhoc Networks are used in various areas each of which has its own set of requirements. In this paper we concentrate on application areas which require fast data delivery, less delay and high availability of the network. Fast delivery and less delay concepts are related to the relative position and status of nodes (links) while network availability is a direct cost of overall network lifetime. Our focus here is on developing a network layer strategy, i.e. one that uses routing protocols. For MANET, in some applications packets become useless as a result of delay and distance between nodes. Hence it is required to design Efficient-Path selection scheme using optimized ondemand Multipath routing protocol with goals of improving throughput, delay and data delivery. With this our new approach we are going to evaluate the performance of our protocol against the traditional AOMDV. The practical simulation is done using NS2 network simulator.

4350-4353

Authors: Dhirendra Pal Singh

There are several domains like medical, astronomical, hybrid techniques, remote sensing, pattern recognition, high resolution display etc., in which people want to get an image and store it so that the images may be used to extract some valuable information using image quality features in the future. Image quality estimation aims to evaluate the image information automatically by a computational model hence plays a significant role in digital image processing systems. In this paper to meet the need of accuracy and effectiveness for gray scale images, role of various image enhancement quality features are discussed.

4359-4366

Authors: Chandra Bhim Bhan Singh

A strong and insightful interpretation of scientific knowledge and practice must take into consideration how human cognitive skills and constraints enable as well restrict the scientific enterprise's activities and products. While existing deep learning systems are outstanding in functions such as object classification, language processing, and gameplay but few can create or transform a complex system like a Frame Pyramid. Assume that what these systems lack is a "Cognitive Inductive Prejudice": an ability to justify inter-object relationships and make decisions about an organized description of the incident. In order to assess this premise, this paper concentrated on a work involving stapling together stacks of frames to balance a castle and quantify how well hominids are doing. Then for analyzing contraption capability, our work introduce the Significant Stimulus Learning Tool that utilizes object-and interaction-centered scene and policy representations, these apply to the task. Our results shows that these structural portrayals enable the tool to perform both hominids and contraption for more naive methods, indicating that cognitive inductive effect is a significant element in solving structured reasoning issues and building more intelligent also flexible for machines.

4374-4377

Authors: Harikrishna Bommala, Dr. S. Kiran, T.Venkateswarlu, M. Asha Aruna Sheela

Cloud computing is increasingly popular in the distribution of the computing environment. Process and implement cloud storage data to become a global movement. Software as an organization Software as a Service (SaaS) has many commercial applications and in our day to day, we can only say that it is disruptive technology [1]. Data security has become a major problem in the field of cloud ecosystems because data is available in various parts of the world to access the Internet for free as it progresses. The global security record for mid-2018, with a cloud data migration of approximately 86.67%, a global analyst estimates that this range can be 100% [8,9]. Change the data of two or more people, so that unauthorized people can access real data. There are many different ways to perform this conversion, but the method there has proposed a text input method so that the recipient can access the original information. Encryption has become a solution and alternative encryption algorithms play an important role in the security of data in the cloud. In this process, the process investigation operation is designed to obtain data to avoid breaking an unauthorized person. In this way, you can protect any type of files using the Fibonacci series. The proposed algorithm s is encryption and decryption process takes a less of time compare with other traditional security algorithms.

4263-4269

Authors: Koffka Khan, Wayne Goodridge

Stochastic Dynamic Programming (SDP) is an important class of optimization which has recently been used in the area of dynamic adaptive streaming over HTTP (DASH). Though DASH is very popular method of video delivery in recent years it is plagued with problems when multiple players share a bottleneck link. Thus, this area has become a very active area of research. Two works which implement SDP in DASH are selected and their performances compared against the Conventional DASH player. It is shown that SDP works well for various network conditions.

4277-4282

Authors: Francisco Ángel Luna Hernández; Mayra Hernández Oramas; Victor Manuel Arias Peregrino

Nowadays there are serious global problems, among them, the bad air quality in urban zones stands out, and also the lack of healthy food to guarantee quality feeding. According with some information of the United Nations Organization for agriculture and feeding, the global population is expected to increase to reach 8300 millions, and for that reason objectives for the sustainable development were fixed in the 2030 Agenda. In Mexico, the 2013-2018 Development Plan in the goal National IV Mexico Prospero is looking to guarantee the security in feeding, that is why an opportunity area has been identified in which we can set innovations and new technology. The main objective of this project was to develop an Autonomous Urban Garden, which allows to plant and care for different daily consumption foods on the roofs or roofs of houses or buildings through the Arduino platform and various sensors (soil moisture, rain, humidity and temperature), they can convert a large part of the carbon dioxide into oxygen, they will provide food to a family, ensuring that they are consumable since they themselves would be in charge of planting and harvesting.

4289-4293

Authors: Ayax Israel Isidro Alvarado; Victor Manuel Arias Peregrino; Dulce María León de la O; Alejandro Hernández Cadena; Jose Ángel Jesus Magaña

Visual disability is a condition that affects 285 million people around the world, this sector of the society has a lot of tools for displacement, since a simple white cane that is the first thing that comes to our mind talking about visual disability to some technologic devices that assists them, nevertheless, these devices attack different difficulties, such as the detection of objects in front or the reading of signs in the public thoroughfare. However, there is a difficulty that has not been addressed; the detection of cavities or subsidence in the ground, this section must be taken into account as it can cause very serious accidents and for this reason a device designed to overcome this need is designed.

4298-4304

Authors: Amira Hassan Abed; Mona Nasr; Walaa Saber

Abnormal temperature of human body is a natural extensive indicator of illness. Infrared thermography (IRT) is a fast, non-invasive, non-contact and passive substitution to ordinary medical thermometers for monitoring and observation human body temperature. Aside from, IRT is able to chart body surface heat remotely. Last five decades testified a stationary development in thermal imaging cameras utilization to obtain relations between the thermal physiology and surface temperature. IRT has effectively used in diagnosis and detection of breast cancer, diabetes neuropathy and peripheral vascular disorders. It has been employed to detect issues related to gynecology, dermatology, heart, neonatal physiology, and brain imaging. With the advent of modern infrared cameras, data acquisition and processing techniques, it is now possible to have real time high resolution thermographic images, which is likely to surge further research in this field. The emergent technology known as the Internet of Things (IoT) has guided practitioners, physicians and researchers to design innovative solutions in different environments, particularly in medical and healthcare using smart sensors, computer networks and a remote server. This paper aims to propose IoT-enabled medical system enables diagnostics and detection for several medical anomalies remotely; in real-time and simultaneous depend on combination of IoT and Thermal Infrared imaging techniques. It will detect and diagnostics any abnormal and alert the user through IoT remotely and in real-time.

4309-4320

Authors: Sanaa Abou Elhamayed; Samah Osama M. Kamel

Spam Email messages have a big problem either for users or for the Internet service providers. The content of such messages may contain viruses and bad information. The spam messages also occupy a huge amount of space on the mail boxes. So, the process of Emails' classification is very important to be analyzed and discussed. This research work aims at classifying the email messages into either spam or non-spam. The E-mail messages or a dataset can be represented in a matrix form. The rows of the matrix are representing the instances (messages) while the columns are representing the features of such instances. K-Nearest Neighbor (KNN) and Naïve Bayes (NB) are two classifiers where they are used to classify the email messages. The proposed approach based on partitioning the dataset into segment and compared with the adopted approach. Moreover, feature selection methods are adopted to choose the significant features and eliminate the others to avoid processing overheads. The choice of the relevant features plays an important role of the classification accuracy. In this work, some feature selection methods are adopted, analyzed, and operated. The performance of such methods is compared. Moreover, a feature selection method is proposed and discussed. The performance of the proposed feature selection method is compared with the adopted ones. This work is operated on a chosen dataset taken from the Internet. The dataset contains about four-thousand messages with fifty-eight features. Moreover, the dataset is supported with a target feature representing the class labels. From the practical experiments it is shown that the performance of the proposed method is better than the adopted ones. It is also expected that the proposed method is applicable to other datasets for other application domains.