Precise Marketing Strategy Optimization of E-Commerce Platform Based on KNN Clustering

With the development of computer technology and the arrival of the era of artificial intelligence, the analysis of user demand bias is of great significance to the operation optimization of e-commerce platforms. Combined with CS domain signaling data, IP packet data of PS domain, and customer CRM data provided by operators, this research studies each dimension index of operator user portrait, after that the operator user portrait platform is divided into some individual subunits, and then the corresponding data mining technology is carried out to study the implementation scheme of each subunit. The system can process and mine multidimensional data of operators’ users and form user portraits on the basis of user data aggregation. Finally, based on the operator user portrait platform studied in this paper, the operator user data are analyzed from both the user’s mobile phone use behavior and user consumption behavior. Furthermore, the application value of this research in the precision marketing and personalized service of operators is illustrated.

Evaluation of Routing Performance using OSPF and Multi-Controller Based Network Architecture

Newer mobile applications are increasingly being defined using Internet Protocol, resulting in increased use of Internet Protocol and subsequent upsurge of smartphones. However, many communication service provider core networks continue to use classical routing protocols and single controller-based networks if deployed. Controller-based networks built on the foundation of software-defined networks include centralization and separation of control plane and data plane, which can address the challenges experienced with the classical routing protocols. When single controllers are used, they tend to get overloaded with traffic. The ability to use multi-controller-based network architecture to improve quality of service in the mobile IP core network is still an open issue. This paper presents a performance evaluation of multi-controller-based network architecture, running OpenFlow and Open Shortest Path First protocol. The long-term evolution simulated network architecture is created using well-known network simulator Objective Modular Network Testbed running OpenFlow and simuLTE add-on. We test and analyze data traffic for Packet data ratio and Jitter and their associated effects on a multi-controller-based network running OpenFlow versus OSPF on a mobile core network. The experiment created two topologies; multi controller-based and Open Shortest path first network. Video and ping traffic is tested by the generation of traffic from User Equipment to the networkbased server in the data center and back, and traffic metrics recorded on an inbuilt integrated development environment. The simulation setup consisted of an OpenFlow controller, HyperFlow algorithm, OpenFlow switches, and Open Shortest Path First routers. The multi-controller-based network improved Jitter by 10 ms. The Open Shortest Path first showed packet data ratio values of 89% gain while the controller-based network registered a value of 86%. A standard deviation test revealed 0.7%, which shows that the difference is not significant when testing for Packet data ratio. We provided insight into the performance of multi-controller-based architecture and Open Shortest Path First protocol in the communication service provider's core network.

Evaluation of the Distance Education Model in the Coronavirus (Covid-19) Pandemia

Purpose:The aim of this study is to question and evaluate the perceptions of 3rd, 4thand 5thyear undergraduate dentalstudents towards distance education practices and the roles of faculty members in the implementation of educationduring the Covid-19 pandemic.Materials & Methods:An online survey was applied to 149 volunteers, consisting of 3rd, 4thand 5thyear undergraduatedental students. The survey composed of 12 questions about distance education and shared from "Google Forms"application. Data analysis was done with SPSS 22.0 Packet Data Program.Results:One hundred forty-nine undergraduate dental students, including 54 third-year students, 60 fourth-yearstudents and 35 fifth-year students, answered the survey on a voluntary basis. Upon this, each answer was examinedseparately, and efforts were made to reach conclusions about the distance education model. When results were evaluated,the majority of the students (40.9%) who participated in the survey reported that the distance education modelcontributed to the theoretical lessons, when adequacy of the practical training was assessed, it was concluded thatdistance education was "Absolutely Inadequate" at with a 79.9 percentageConclusion:As a result of the study, most of the students found the distance education model sufficient for theoreticalcourses, but insufficient for practical education and found traditional practical education more advantageous.

Packet Preprocessing in CNN-Based Network Intrusion Detection System

The proliferation of various connected platforms, including Internet of things, industrial control systems (ICSs), connected cars, and in-vehicle networks, has resulted in the simultaneous use of multiple protocols and devices. Chaotic situations caused by the usage of different protocols and various types of devices, such as heterogeneous networks, implemented differently by vendors renders the adoption of a flexible security solution difficult, such as recent deep learning-based intrusion detection system (IDS) studies. These studies optimized the deep learning model for their environment to improve performance, but the basic principle of the deep learning model used was not changed, so this can be called a next-generation IDS with a model that has little or no requirements. Some studies proposed IDS based on unsupervised learning technology that does not require labeled data. However, not using available assets, such as network packet data, is a waste of resources. If the security solution considers the role and importance of the devices constituting the network and the security area of the protocol standard by experts, the assets can be well used, but it will no longer be flexible. Most deep learning model-based IDS studies used recurrent neural network (RNN), which is a supervised learning model, because the characteristics of the RNN model, especially when the long-short term memory (LSTM) is incorporated, are better configured to reflect the flow of the packet data stream over time, and thus perform better than other supervised learning models such as convolutional neural network (CNN). However, if the input data induce the CNN’s kernel to sufficiently reflect the network characteristics through proper preprocessing, it could perform better than other deep learning models in the network IDS. Hence, we propose the first preprocessing method, called “direct”, for network IDS that can use the characteristics of the kernel by using the minimum protocol information, field size, and offset. In addition to direct, we propose two more preprocessing techniques called “weighted” and “compressed”. Each requires additional network information; therefore, direct conversion was compared with related studies. Including direct, the proposed preprocessing methods are based on field-to-pixel philosophy, which can reflect the advantages of CNN by extracting the convolutional features of each pixel. Direct is the most intuitive method of applying field-to-pixel conversion to reflect an image’s convolutional characteristics in the CNN. Weighted and compressed are conversion methods used to evaluate the direct method. Consequently, the IDS constructed using a CNN with the proposed direct preprocessing method demonstrated meaningful performance in the NSL-KDD dataset.

Evaluasi Kinerja Protokol Perutean AODV dan SDGR+R pada VANET dengan Studi Kasus Pelabuhan Lembar

The Vehicular ad-hoc Network (VANET) is a subclass of Mobile ad-hoc networks (MANETs).VANET is a wireless network created from the concept of building a vehicle network (node) toexchange data information (data communication). There is a new concept technique forVANET communication used, namely the use of the concept of Software Defined Network(SDN) on VANET. For data communication between vehicles, a routing protocol required. Themost common routing protocol used on VANET since 2003 is AODV. In 2014 several studieswere using the SDN paradigm tried on VANET technology to improve the performance ofQuality of Service (QoS), one of which is a Geographic-based SDN, called SDGR in 2016.Multicast is a method of routing data on a network that allows one node or a group of nodes tocommunicate efficiently with the receiving node. The multicast concept supports one-to-manyrouting in nodes that send packet data to a group of nodes. The development of the SDGRrouting protocol using the idea of multicast technique to SDGR based on the Direction calledSDGR + R carried out in 2019. This study uses a case study of vehicle transportationsimulations in the Lamber Port area of Lombok. The simulation results knew that SDGR + Ris better than AODV in terms of service quality (QoS) at a latency of 15.58% and packet deliveryratio (PDR) of 47.78%.