Network Engineering Research Articles

Wavelength-based Attributed Deep Neural Network for Underwater Image Restoration

Background: Underwater images, in general, suffer from low contrast and high color distortions due to the non-uniform attenuation of the light as it propagates through the water. In addition, the degree of attenuation varies with the wavelength, resulting in the asymmetric traversing of colors. Despite the prolific works for underwater image restoration (UIR) using deep learning, the above asymmetricity has not been addressed in the respective network engineering. Contributions: As the first novelty, this article shows that attributing the right receptive field size ( context ) based on the traversing range of the color channel may lead to a substantial performance gain for the task of UIR. Further, it is important to suppress the irrelevant multi-contextual features and increase the representational power of the model. Therefore, as a second novelty, we have incorporated an attentive skip mechanism to adaptively refine the learned multi-contextual features. The proposed framework, called Deep WaveNet , is optimized using the traditional pixel-wise and feature-based cost functions. An extensive set of experiments have been carried out to show the efficacy of the proposed scheme over existing best-published literature on benchmark datasets. More importantly, we have demonstrated a comprehensive validation of enhanced images across various high-level vision tasks, e.g., underwater image semantic segmentation and diver’s 2D pose estimation. A sample video to exhibit our real-world performance is available at https://tinyurl.com/yzcrup9n . Also, we have open-sourced our framework at https://github.com/pksvision/Deep-WaveNet-Underwater-Image-Restoration .

A Modeling Design Method for Complex Products Based on LSTM Neural Network and Kansei Engineering

Complex products (CPs) modeling design has a long development cycle and high cost, and it is difficult to accurately meet the needs of enterprises and users. At present, the Kansei Engineering (KE) method based on back-propagated (BP) neural networks is applied to solve the modeling design problem that meets users’ affective preferences for simple products quickly and effectively. However, the modeling feature data of CPs have a wide range of dimensions, long parameter codes, and the characteristics of time series. As a result, it is difficult for BP neural networks to recognize the affective preferences of CPs from an overall visual perception level as humans do. To address the problems above and assist designers with efficient and high-quality design, a CP modeling design method based on Long Short-Term Memory (LSTM) neural network and KE (CP-KEDL) was proposed. Firstly, the improved MA method was carried out to transform the product modeling features into feature codes with sequence characteristics. Secondly, the mapping model between perceptual images and modeling features was established based on the LSTM neural network to predict the evaluation value of the product’s perceptual images. Finally, the optimal feature sets were calculated by a Genetic Algorithm (GA). The experimental results show that the MSE of the LSTM model is only 0.02, whereas the MSE of the traditional Deep Neural Networks (DNN) and Convolutional Neural Networks (CNN) neural network models are 0.30 and 0.23, respectively. The results verified that the proposed method can effectively grapple with the CP modeling design problem with the timing factor, improve design satisfaction and shorten the R&D cycle of CP industrial design.

Blockchain Systems, Technologies, and Applications: A Methodology Perspective

In the past decade, blockchain has shown a promising vision to build trust without any powerful third party in a secure, decentralized and scalable manner. However, due to the wide application and future development from cryptocurrency to the Internet of Things, blockchain is an extremely complex system enabling integration with mathematics, computer science, communication and network engineering, etc. By revealing the intrinsic relationship between blockchain and communication, networking and computing from a methodological perspective, it provided a view to the challenge that engineers, experts and researchers hardly fully understand the blockchain process in a systematic view from top to bottom. In this article we first introduce how blockchain works, the research activities and challenges, and illustrate the roadmap involving the classic methodologies with typical blockchain use cases and topics. Second, in blockchain systems, how to adopt stochastic process, game theory, optimization theory, and machine learning to study the blockchain running processes and design the blockchain protocols/algorithms are discussed in details. Moreover, the advantages and limitations using these methods are also summarized as the guide of future work to be further considered. Finally, some remaining problems from technical, commercial and political views are discussed as the open issues. The main findings of this article will provide a survey from a methodological perspective to study theoretical model for blockchain fundamentals understanding, design network service for blockchain-based mechanisms and algorithms, as well as apply blockchain for the Internet of Things, etc.

COMPARATIVE ANALYSIS OF CF-MMIMO AND MMIMO SYSTEMS WITH DIVERSE ALGORITHMS IN URBAN AND RURAL ENVIRONMENTS: EVALUATION AND INSIGHTS

The rapid advancement of 6G wireless communication systems brings forth unprecedented opportunities for improving coverage, data rates, and quality of service. As the demand for higher capacity and enhanced reliability continues to escalate, it becomes imperative to develop novel techniques that address the challenges of future wireless networks. One such technique is Cell-Free massive multiple-input multiple-output (CF-mMIMO) [1], which holds immense potential for augmenting coverage and reducing bit error rates (BER) across diverse area types, including urban and rural environments. CF-mMIMO represents a state-of-the-art technology that harnesses the synergy between cloud computing and massive MIMO systems. By combining the scalability of cloud resources with the spatial multiplexing capabilities of massive MIMO, CF-mMIMO introduces substantial improvements in coverage and spectral efficiency. Nevertheless, to achieve optimal performance in varying area types, the selection of appropriate precoding techniques assumes paramount importance. This paper conducts a comprehensive investigation into the effects of different precoding schemes, such as channel inversion, block diagonalization, and dirty paper coding, on the performance of CF-mMIMO in urban and rural areas. The outcomes of this research hold significant implications for the design and deployment of 6G networks, providing valuable guidance to network planners and engineers aiming to optimize coverage and minimize bit error rates across diverse area types.

Performance Evaluation of Urban Water Environment Management Projects for the Protection of the Yangtze River Based on AHP-Fuzzy Comprehensive Evaluation Method

In order to promote the urban water environment management work for the protection of the Yangtze River, it is necessary to use a scientific evaluation index system to evaluate the governance effectiveness of completed management projects in pilot cities. Based on the characteristics of urban water environment management projects, this paper uses a constructed evaluation index system for the effectiveness of urban water environment management projects in the protection of the Yangtze River to evaluate the effectiveness of Phase I urban water environment management projects in Jiujiang City. The weights of each criterion layer and indicator layer were determined using the Analytic Hierarchy Process, and the fuzzy comprehensive evaluation method was used for comprehensive evaluation. The conclusions are as follows: (1) the engineering efficiency evaluation result is poor, mainly affected by the urban rain and sewage pipe network engineering criterion layer, in which the weight of the BOD5 concentration of domestic sewage in the influent of the sewage treatment plant is relatively large, and the membership degree result is poor, so attention should be paid to the BOD5 concentration of the sewage treatment plant within the scope of the project. (2) the engineering benefit evaluation result is generally good, and this evaluation result can reflect the overall benefits of the Phase I urban water environment comprehensive management project to the "plant-network-river-lake-shore" within the scope of Jiujiang City, but it is only reflected significantly by the surface water improvement contribution criterion. The reflection of social and economic aspects is not obvious, and follow-up research needs to increase the participation of residents through questionnaires or field surveys to make the results more reflective of the economic and social benefits.

Problem-Based Blended Learning Models in Vocational Education: A Developmental Research

This research was motivated by two main problems: (1) the ineffectiveness of courageous learning is often caused by technical problems; and (2) the learning model used by teachers so far has not been effective, innovative, and optimal because it still uses a textual-based problem-based learning model. The purpose of this study was to develop a problem-based blended learning model for computer network engineering subjects at vocational education and to test the validity, practicality, and effectiveness. The development model applied in this study is the 4D development model, namely: (1) define, (2) design, (3) develop, and (4) disseminate. Data collection techniques were carried out through questionnaires to get validation experts, the practicality of teachers and students. Furthermore, the effectiveness of the data was done through a comparison of pretest and posttest values. The results of the calculation of the acquisition of a score reached 0.53 in the moderate category. Therefore, it can be concluded that the learning model of blended learning based on problem based learning in the subjects of computer network engineering in Vocational High Schools has a high level of validity, practicality, effectiveness.

Pengenalan penggunaan teknologi kedirgantaraan drone untuk meningkatkan mutu siswa SMK Muhammadiyah Sentolo dalam bidang agroindustri

Sentolo Muhammadiyah Vocational School is located in the Kulon Progo area, more precisely on Sentolo-Magelang, Ngeplang, Sentolo, Kulon Progo roads. His areas of expertise are Motorcycle Business Engineering (TBSM), Automotive Light Vehicle Engineering (TKRO), Computer Network Engineering (TKJ). SMK Muhammadiyah Sentolo continues to carry out the process to improve and develop itself. One of them is by creating a Plus Program with the aim of preparing graduates who have resilience and independence. One of the plus programs is agroindustry Therefore, it is necessary to introduce agricultural processing methods using technology, especially technology that supports the fertilization process using liquid fertilizer. This Community Service Activity will introduce the use of fertilization technology using liquid media with the help of drones . The result of this service activity is that students know that the use of drones to help the fertilization process is meaningful for farmers, so students feel eager and enthusiastic to learn how to use the drone. On the farmer's side, they feel that the presence of drones applied by SMK Muhamaadiyah Sentolo students is a new hope that will be useful for helping farmers

Analysis of the Impact of Newly Built Grounding Grid on the Original Grounding Grid Based on the Method of Moments

On the basis of the method of moments, the resistive coupling effect between the newly built grounding network. When the horizontal distance between two grounding networks of a substation changes, this original grounding network of a certain substation is analyzed. And establish corresponding soil models based on actual engineering soil resistivity data. Use the grounding grid analysis function of CDEGS software and Powerstation software simulation software to simulate and calculate some parameters of the new and old grounding grids. The analysis parameters mainly include the grounding resistance, step voltage, and contact voltage of the grounding grid system. And the obtained parameter indicators are compared and analyzed with safety limits to determine the safety performance of the newly built grounding grid system in the substation. And the impact on the grounding performance of the original grounding network of the substation. Provide certain theoretical data support for the actual promotion of substation grounding network engineering.

Cybersecurity Alert Prioritization in a Critical High Power Grid With Latent Spaces

High-Power electric grid networks require extreme security in their associated telecommunication network to ensure protection and control throughout power transmission. Accordingly, supervisory control and data acquisition systems form a vital part of any critical infrastructure, and the safety of the associated telecommunication network from intrusion is crucial. Whereas events related to operation and maintenance are often available and carefully documented, only some tools have been proposed to discriminate the information dealing with the heterogeneous data from intrusion detection systems and to support the network engineers. In this work, we present the use of deep learning techniques, such as Autoencoders or conventional Multiple Correspondence Analysis, to analyze and prune the events on power communication networks in terms of categorical data types often used in anomaly and intrusion detection (such as addresses or anomaly description). This analysis allows us to quantify and statistically describe high-severity events. Overall, portions of alerts around 5-10% have been prioritized in the analysis as first to handle by managers. Moreover, probability clouds of alerts have been shown to configure explicit manifolds in latent spaces. These results offer a homogeneous framework for implementing anomaly detection prioritization in power communication networks.

Boosting the rate performance of primary Li/CFx batteries through interlayer conductive network engineering

The CFx cathode, with intercalated conductive networks, achieves improved rate performance in lithium primary batteries because of enhanced electron transfer rates and electrochemical kinetics.

Reform and Practice of Software Engineering Talents Training Program in Application-Oriented Universities Based on Asiin Certification

ASIIN is a non-profit organization established by universities, Universities of Applied Sciences, authoritative science and technology associations, professional education and further education associations and important industrial and commercial organizations under the initiative of German Engineers Association. Guided and promoted by the advanced concept of ASIIN certification, it is a systematic project for the school to certify the majors of traditional Chinese applied undergraduate colleges through ASIIN institutions according to the interdisciplinary characteristics of the majors in the process of cultivating applied talents. This paper introduces the significance of ASIIN certification, and summarizes the reform and practical thinking of software engineering talents training program in application-oriented universities. On the basis of setting professional goals and exploring and improving learning achievements, this paper puts forward the reform requirements and guiding ideology of revising professional course syllabus. The educational reform based on ASIIN certification can promote the cultivation of network engineering talents who adapt to engineering, nationalization and modernization in China.

Development of Crimping Trainer Learning Media in Basic Computer and Networking Subjects at Senior High School

This study develops a novel trainer learning media for computer subjects and basic networking, targeting class XI Computer and Network Engineering students. Employing the Research and Development (R&D) approach with the ADDIE model, the study demonstrates the suitability of the developed media through expert assessments. Validation scores of 90% and 93% from media and material experts respectively affirm its effectiveness. The trainer learning media enhances computer and network learning at SMK Yapenas Gempol, class XI, contributing to educational technology advancement in the field.
 Highlights:
 
 
 Development of innovative learning support: This study focuses on developing a trainer learning media with new innovations, aiming to enhance the learning experience for computer subjects and basic networking.
 
 
 Feasibility assessment: The research employs the ADDIE model and involves experts' evaluation to determine the suitability of the developed learning media for classroom implementation, with high validation scores obtained from both media and material experts.
 
 
 Implications for Computer and Network Engineering education: The findings of this study have significant implications for the field of Computer and Network Engineering, contributing to the advancement of educational technology and providing a valuable tool to support teaching and learning processes.
 
 
 Keywords: Trainer learning media, computer subjects, basic networking, Research and Development (R&D), feasibility.

Advances in Survivability-supported Framework for Traffic Engineering in Multi-service Backbone Networks

In this paper, optimisation models and heuristic algorithms that address the off-line survivability-supported Traffic Engineering (TE) problem in multi-service backbone networks are presented. In such networks traffic demands with different Quality of Service (QoS) and survivability requirements (e.g. existence of a node disjoint backup path for each primary path) inhere. The optimisation models for engineering the QoS traffic with different survivability prerequisites and the Best-Effort (BE) traffic are based on novel admission control/routing Integer Linear Programming (ILP) and Linear Programming (LP) optimisation sub-problems, which are solved sequentially. LP relaxations of the ILP sub-problems are also provided. The optimisation models and heuristic algorithms are tested on two different networks and their performance is compared.

Software Defined Network Implementation by Using OpenDayLight Centralized Controller

The most attractive study framework among academics is Software Define Networking Networking SDN, which aims to create the Internet with an architecture-independent architecture that will lead to the most significant advances in the network field. This can solve many network problems to deal with high demand changes and reduce Replenishment, changes and less manual work. Because of the limited architecture of traditional networks, which requires modifications in the basic design, network expansion has been mature and slow. Since 2010, until now, the ODL - OpenDayLight model has been proposed to solve most of the problems that guide network engineers in the process of managing complex high-volume networks by top research-oriented universities around the world. Now is the time to turn dreams into reality by putting the presented ideas into action, which will result in a solution that meets the expectations of the researcher regarding the process of managing complex networks and all forms of networks. This document is an attempt to assist researchers in implementing a software identification network infrastructure on which the research community may focus on further analysis and development. We demonstrated an incremental approach to implementing ODL - OpenDayLight Controller (ODL is a JVM program and can run from any operating system and device as long as it supports Java) from the Software Define Network, as well as creating and executing required scenarios, and illustrate the working nature of ODL - OpenDayLight compared to ryu contrlloer, in this paper Research. Index Terms— SDN, OpenDayLight, Mininet, Switch, Controller, Performance evaluation.

Research on the Integration of Innovation and Entrepreneurship Education and Higher Special Education Courses ——Taking the Network Engineering Course of the Technical College for the Deaf of Tianjin University of Technology as an Example

Under the background of "mass entrepreneurship and innovation", mass entrepreneurship and innovation education urgently need integration with professional education. This paper takes the Network Engineering course of the Technical College for the Deaf of Tianjin University of Technology as an example, analyzes the mass entrepreneurship education's research status, deeply studies the integration education of innovation and entrepreneurship education and the deaf network engineering professional course, and proposes the education path of "integration of expertise and innovation," it gives a new method for the organic combination of entrepreneurship and innovation education and professional education in China's higher special education.

Development of Auto-PIVOT: Automated Platform In Vitro for Cell Tissue Culture

Bioreactors are growing in popularity among network engineers. Bioreactors are generally chambers used for cell culture processes with predetermined parameters. Pivot is a bioreactor system for cell culture that is controlled automatically and remotely using multi-chambers that allow inflow of fresh liquid or output for sample collection. This system facilitates gas exchange between the culture medium and ambient gas. The system provides a storage bag for fresh media and a peristaltic pump is used to move the media in a closed loop during perfusion and stirring in the cell culture chamber. The flow rates used is 2 mL/min. The system has a container for direct sample measurement to obtain pH, oxygen, and carbon dioxide parameters. The bioreactor system is also equipped with a mixing vessel which allows the addition of desired nutrients or additives to the system. The results of a computational fluid dynamics (CFD) and shear stress-based flow analysis have been conducted. The simulation results demonstrate that the applied Pivot parameters correspond to an ideal environment to hepatocyte cell viability and growth. This research is expected to increase the number of cells produced without reducing the quality of each chamber and be carried out simultaneously, automatically, and remotely controlled.

IMPLEMENTATION OF WEB-BASED NAIVE BAYES ALGORITHM FOR DETERMINING DEPARTMENTS AT SMK 10 MUHAMMADIYAH KISARAN

Determination of majors is very important for the convenience of prospective students in the process and continuation of education so that they do not experience difficulties in the teaching and learning process in the future. SMK 10 Muhammadiyah Kisaran is one of the private vocational schools in Asahan that provides 3 majors including Audio Video Engineering (TAV), Computer and Network Engineering (TKJ), and Motorcycle Engineering and Business (TBSM). SMK 10 Muhammadiyah Kisaran does not yet have a special system for selecting majors so that prospective students are welcome to choose majors according to their own wishes, not a few students find it difficult because the students themselves do not understand their abilities.so that it’s not uncommon for students to choose majors in a random way or follow their friends' choices. Therefore we need a system that can help prospective students in selecting majors that match their interests and talents and reduce mistakes in choosing majors. The technique used for the classification data mining model in this study is the Naïve Bayes Algorithm. The dataset that will be used as training data and test data is data for new students for the 2021/2022 school year, to be precise, for class X SMK 10 Muhammadiyah Kisaran obtained from the results of documentation and questionnaires. The criteria used were school origin, gender, interests, major, influence of friends, parental suggestions, math scores, English grades, and science grades. The results of the classification modeling with the Naïve Bayes Algorithm produce an accuracy value of 89%.

IMPLEMENTATION OF FORECASTING EXPONENTIAL SMOOTHING IN THE NUMBER OF NEW STUDENT PREDICTION INFORMATION SYSTEM AT SMK AL MA'SHUM

SMK Al Ma'shum annually conducts socialization and promotions in junior high schools. Prediction of the number of prospective new students is one of the most important things in the evaluation process or high cognitive at SMK Al Ma'shum. This serves to determine the priority of how many prospective students will be accepted, where the number of students sometimes tends to decrease and increase. This makes the school must try to estimate the number of new students from each of these majors next year will increase or decrease. If this is not done by the school, it will have an impact on the operational costs of the school. The goal is to predict the number of prospective new students who will be accepted at the Al Ma'shum Vocational School next year using the forecasting exponential smoothing method. The prediction system for new students at the Al Ma'shum Vocational School uses the PHP and MySQL programming languages ​​to help the forecasting process be fast and accurate. The prediction results for 2022 are accounting majors as many as 19.23 new students with MAPE 20.52%, computer and network engineering majors as many as 102.73 new students with MAPE 9.12% and motorcycle engineering majors as many as 76 new students with MAPE 25.53 %. So it can be concluded that the forecasting exponential smoothing method can help predict new students at SMK Al Ma'shum.

Tanggapan Peserta Didik Kelas XII Jurusan Teknik Komputer dan Jaringan terhadap Penggunaan Google Classroom sebagai Upaya Peningkatan Kemandirian Belajar

Since revolution 4.0 and the outbreak of COVID 19, the world of education has been required to be able to transform from a face-to-face learning system to a distance learning system. Teachers have the flexibility of time to share scientific studies and provide independent assignments to students. In addition, teachers can also open discussion rooms for students online (Putri & Dewi, 2019). Independent learning is the readiness of individuals who are willing and able to learn on their own initiative , with or without the help of other parties in terms of determining learning objectives, learning methods, and evaluating learning outcomes. According to (Mujiman 2005 in (Aliyyah & Djuanda, 2020) the research was conducted using a descriptive quantitative approach. The subjects of this study were students majoring in Computer and Network Engineering, SMK Negeri 1 Ketapang class XII as many as 36 respondents. The results of the discussion show that the learning independence of students is lacking in indicators of not depending on others, discipline, responsibility, initiative and self-control it is proven that only indicators of self-confidence are in a good category Utilization of the application is felt to be less supportive because there are several billing assignments that are not known to have been collected or have not been collected or there is no system in place restrain students from being able to continue to the next material if there are assignments that have not been done. This is one of the declines in the percentage of independent learning. Until a positive value is obtained for future application development in order to increase the percentage of independent learning.

Penggunaan Media Teknologi Informasi dan Gaya Belajar Terhadap Hasil Belajar Mata Pelajaran Bahasa Inggris

This research looks at how interactive multimedia influences learning outcomes in English, especially considering different learning styles. This research approach is a quantitative approach to the type of quasi-experimental research. The subjects of this study were class XII students at SMKN 7 Jakarta for the 2020/2021 academic year. This study used purposive cluster sampling to select two majors at SMKN 7 Jakarta, Graphic Design as the control group and Computer and Network Engineering as the experimental group, based on the characteristics of the departments. The number of students majoring in Graphic Design is 35 students while the Department of Computer and Network Engineering is 39 students. In the control group learning using sophisticated tools such as PowerPoint and media presentations the experimental group uses interactive multimedia learning tools such as flash. This research uses a quantitative approach because it is considered easier to analyze data using numbers so that it makes it easier to measure achievement. The results of this study indicate that interactive multimedia can be used to improve the English learning outcomes of students with different learning styles.