Three-layer Architecture Research Articles

Predicting LQ45 financial sector indices using RNN-LSTM

As one of the most popular financial market instruments, the stock has formed one of the most massive and complex financial markets in the world. It could handle millions of transactions within a short period of time and highly unpredictable. In this study, we aim to implement a famous Deep Learning method, namely the long short-term memory (LSTM) networks, for the stock price prediction. We limit the stocks to those that are included in the LQ45 financial sectors indices, i.e., BBCA, BBNI, BBRI, BBTN, BMRI, and BTPS. Rather than using too deep network architecture, we propose using a simple three-layer LSTM network architecture to predict the stocks’ closing prices. We found that the prediction results fall in the reasonable forecasting category. Moreover, it is worth noting that two of the considered stocks, namely, BBCA and BMRI, have the lowest MAPE values at 19.1020 and 18.6135, which fall in the good forecasting results. Hence, the proposed LSTM model is most recommended to be used on those two stocks.

Internet of Things-Based Smart Farming Monitoring System for Bolting Reduction in Onion Farms

According to the Pakistan Bureau of Statistics, Pakistan is amongst the top ten onion-producing countries in the world. Though in Pakistan, most of the districts of Khyber Pakhtunkhwa produce onions, Malakand division lonely contributes 60% of the total onion production of the country. In onion farming, bolting is an insidious phenomenon that occurs in onion plants due to fluctuations in environmental factors such as temperature, humidity, and light intensity. Due to bolting, the flowering stem of an onion plant is produced before the crop is harvested, resulting in a poor-quality harvest and yield. Therefore, from a farmer’s perspective, it is highly desirable to monitor and control the environmental factors to avoid bolting. In this paper, we propose and design a new prototype, namely, a smart farming monitoring system (SFMS) for bolting reduction, which is based on the generic three-layered IoT architecture. By using IoT (Internet of things) technology and careful remote monitoring, a more favorable environment can be provided to reduce and avoid onion bolting. To analyze the efficacy and performance of the proposed SFMS, a real test-bed implementation was carried out. The SFMS prototype was installed both in the open and in a greenhouse environment to monitor onion crops. Based on the data received via sensors, the percentage of onion bolting was recorded as 16.7% in the open environment while 3% in the closed environment. In the closed environment, optimal temperature, humidity, and light intensity were provided to the onion crops using the SFMS. For this reason, the percentage of onion bolting was reduced from 16.7% to 3%, consequently yielding better onion production. Moreover, the SFMS is a low-cost, easy-to-install solution that is developed with locally available hardware and resources, and we believe that this new solution can transform conventional onion farming into a more productive and convenient smart farming in the region.

Intelligent public transport cloud platform dispatching operation management system development

In recent years, with the rapid development of various cities, the operation and maintenance of the public transport system has become increasingly prominent problems, the development of the intelligent public transport system has been imperative. This paper takes the intelligent public transport system as the research object, using wireless network transmission technology, big data retrieval and processing, cloud computing platform and other technologies, analyzes the main requirements of the intelligent public transport system. This system adopts the classic three-layer architecture of the Internet of Things, namely, the perception layer, the network layer and the platform layer. Intelligent public transport dispatching system is the core system of intelligent public transport. The paper uses frog leaping algorithm as the dispatching algorithm to realize the function of public transport dispatching. Through the test, it can complete the task of adding or reducing vehicles according to the increase or decrease of passenger flow. The design and implementation of the cloud platform provides a strong support for the renewal and development of modern urban public transportation system, and has a certain guiding significance. As a complete system with more rapid and accurate management, more convenient and efficient operation, it improves the public transport dispatching ability and improves the travel experience of passengers, and has a cross-era significance for the development of urban public transportation.

One-pot synthesis and microstructure of multi-layered nanospheres via plasma electrolytic oxidation

In the present work, plasma electrolytic oxidation (PEO) is creatively introduced as a novel method to fabricate multi-layered nanospheres. Titanium (Ti) was oxidized in a phosphate-based electrolyte containing ZnO nanoparticles (NPs), which results in the formation of nanospheres on the ceramic coating. The as-fabricated nanosphere is amorphous with a three-layered architecture. The inner layer of the nanosphere contains Zn, Ca and P whereas Cu and P were detected in the medium layer with the outer layer enriched in Cu, O and Ti, which is promising in the field of bio-medical implanted devices. Herein, a novel one-pot synthesis strategy is proposed to fabricate multi-layered nanospheres, which could enlighten the preparation of hierarchical structures in various fields.

Structure of the Arabidopsis thaliana glutamate receptor-like channel GLR3.4

Glutamate receptor-like channels (GLRs) play vital roles in various physiological processes in plants, such as wound response, stomatal aperture control, seed germination, root development, innate immune response, pollen tube growth, and morphogenesis. Despite the importance of GLRs, knowledge about their molecular organization is limited. Here we use X-ray crystallography and single-particle cryo-EM to solve structures of the Arabidopsis thaliana GLR3.4. Our structures reveal the tetrameric assembly of GLR3.4 subunits into a three-layer domain architecture, reminiscent of animal ionotropic glutamate receptors (iGluRs). However, the non-swapped arrangement between layers of GLR3.4 domains, binding of glutathione through S-glutathionylation of cysteine C205 inside the amino-terminal domain clamshell, unique symmetry, inter-domain interfaces, and ligand specificity distinguish GLR3.4 from representatives of the iGluR family and suggest distinct features of the GLR gating mechanism. Our work elaborates on the principles of GLR architecture and symmetry and provides a molecular template for deciphering GLR-dependent signaling mechanisms in plants.

DESIGN OF THE ARCHITECTURE OF AN AUTOMATED BIBLIOGRAPHIC SYSTEM

The development of information and computer technologies has led to the need to evolve the concept of universal bibliographic control. The creation of the Internet and web technologies has allowed this concept to reach a new level by creating a number of common international standards. In addition, to ensure control and exchange of bibliographic information public bibliographic and scientometric databases were created. Today, software for managing bibliographic records is in demand in various countries in Europe and America. The most popular software in these countries is EndNote, RefWorks, BibTeX and Zotero. The development of such automated bibliographic system and the adaptation of its functionality to standards and requirements within Ukraine is relevant for a number of reasons. The main reasons are the need for every scientist and lecturer of higher education institutions to confirm their scientific achievements when hiring, submitting scientific work to various competitions, to obtain a scientific degree and so on. Today the rapid development of information and computer technology allows us to abandon the list of scientific papers in manual mode and move to the use of specialized software on smartphones. That is why the architecture of an automated bibliographic system, which is developed as a mobile application based on the Android operating system, was designed. Java is chosen as the programming language in which the software will be written, as the vast majority of the Android operating system is written in this language. A number of technologies were chosen for the selected operating system. They will simplify the process of developing a mobile application. The three-layer architecture of the automated bibliographic system is designed on the basis of the multilevel model of architecture and the MVVM template. This architecture allows to provide the main non-functional characteristics of the quality of the developed software, as well as to effectively implement the rules of business logic within the object-oriented programming paradigm.

Web remote ideological and political education system constructed by using agent technology

In order to improve the effect of remote ideological and political education, this paper builds a Web ideological and political education system based on Agent technology, and adopts a three-layer abstract system architecture including Web service layer, Agent processing layer and service process layer. Moreover, based on this architecture foundation, this paper proposes an Agent-based Web service integration structure, and illustrates the overall execution process of the system through the execution process of the system integration structure. Then, this paper proposes the organization structure of multi-agent in the Agent processing layer and the organization structure of service process in the service process layer of the system. In addition, this paper uses multi-agent system design to ensure the efficient operation of the entire system, and combines algorithms to implement system resource recommendation modules and practical teaching functions. Finally, this paper designs a control experiment to test the performance of the distance ideological and political education system constructed in this paper. The research results show that the system constructed in this paper has certain practical effects.

Open Relation Extraction for Chinese Noun Phrases

Relation Extraction (RE) aims at harvesting relational facts from texts. A majority of existing research targets at knowledge acquisition from sentences, where subject-verb-object structures are usually treated as the signals of existence of relations. In contrast, relational facts expressed within noun phrases are highly implicit. Previous works mostly relies on human-compiled assertions and textual patterns in English to address noun phrase-based RE. For Chinese, the corresponding task is non-trivial because Chinese is a highly analytic language with flexible expressions. Additionally, noun phrases tend to be incomplete in grammatical structures, where clear mentions of predicates are often missing. In this article, we present an unsupervised Noun Phrase-based Open RE system for the Chinese language (NPORE), which employs a three-layer data-driven architecture. The system contains three components, i.e., Modifier-sensitive Phrase Segmenter, Candidate Relation Generator and Missing Relation Predicate Detector. It integrates with a graph clique mining algorithm to chunk Chinese noun phrases, considering how relations are expressed. We further propose a probabilistic method with knowledge priors and a hypergraph-based random walk process to detect missing relation predicates. Experiments over Chinese Wikipedia show NPORE outperforms state-of-the-art, capable of extracting 55.2 percent more relations than the most competitive baseline, with a comparable precision at 95.4 percent.

Hybrid time series forecasting methods for travel time prediction

Providing accurate information about travel time to passengers is important in public transportation. In this aspect, the travel time of buses between two consecutive stops can be handled as time series. Then, the future travel time can be predicted using time series forecasting methods. In this study, we propose a novel method with three-layer architecture to predict bus travel time between two stops. In the first layer of the proposed method, initial prediction is made by processing measured data. In the second layer, residuals are predicted in the specified depth. In the third layer, the final prediction is made by integrating the results of two previous layers with three different approach. The experiments were performed on the data, which were obtained from public transportation of Istanbul, using various time series forecasting methods in form of traditional and proposed architecture. The results show that proposed method outperforms traditional approach with approximately MAPE of 6.

Marvin: A parallel three-dimensional transport code based on the discrete ordinates method for reactor shielding calculations

Marvin is a parallel three-dimensional discrete ordinates (SN) code dedicated for reactor shielding calculations. It employs the multi-group and SN approximations to discretize the energy and angular variables, respectively. Multiple discretization methods, namely weighted diamond difference, theta-weighted diamond difference and step-characteristic, have been implemented to discretize the spatial variables. The within-group transport equation is solved by the source iteration or Krylov subspace solvers, both of which employ the Koch-Baker-Alcouffe (KBA) algorithm to parallelize the transport sweep process. The upscattering in the thermal energy range is treated with thermal upscattering iteration scheme. The code design of Marvin features the mixed programming model and a three-layer architecture design. Two benchmark problems devised from realistic reactor core configurations, namely the VENUS-3 and HBR-2 problems, were calculated to evaluate the correctness, accuracy and parallel computing performance of Marvin. The calculation results were compared against TORT solutions as well as measured data. The validation results indicate that: Marvin is properly implemented and can faithfully produce solutions to the reactor shielding problems; the computing efficiency of Marvin can be significantly enhanced via the KBA parallel transport sweep algorithm.

A Case Study on the Deployment of a Tactile Internet Application in a Hybrid Cloud, Edge, and Mobile Ad Hoc Cloud Environment

The tactile Internet is the next step after the Internet of Things (IoT). It enables the steering and control of virtual and real objects through the Internet and requires a very low round trip latency. This article is devoted to a case study on the deployment of a tactile Internet application in a hybrid cloud, edge, and mobile <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ad hoc</i> cloud environment. We deploy a remote phobia-treatment application as a set of components. Remote phobia treatment allows phobia patients to have therapy sessions under the guidance of an expert therapist located remotely, with patients and therapist sharing the same virtual reality (VR) environment. A three-layer architecture (cloud, edge, and mobile <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ad hoc</i> cloud) is proposed for the deployment. A prototype is built with Microsoft Azure at the cloud layer, laptops at the edge layer, and smartphones at the mobile <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ad hoc</i> cloud layer. End-users are equipped with an HTC VIVE headset for VR rendering and Gloveone gloves for haptic sensations rendering. Extensive performance measurements are made by varying the component deployment patterns as well as the distance between the therapist and patient. Our results demonstrate clearly that the addition of mobile <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ad hoc</i> cloud to the edge and cloud does bring added value in terms of latency reduction when deploying tactile Internet applications.

Intelligent Coordination Distribution of the Whole Supply Chain Based on the Internet of Things

In this paper, through the intelligent research of the whole process of logistics and distribution with the Internet of Things supply chain, we study how to improve the development of the cold chain, reduce the loss in circulation, improve the social and economic benefits, and carry out intelligent information collection, monitoring, management, and information tracing of the whole cold chain. This paper analyzes and empirically studies the impact of key technologies of the Internet of Things in cold chain coordination from the perspective of building an intelligent cold chain coordination system with the Internet of Things technology. This paper analyzes the current situation of cold chain logistics and the impact that the application of IoT technology will have, explains that IoT technology can improve the intelligence level of the cold chain, and then introduces the application of intelligent cold chain logistics under IoT orientation, combining the process of cold chain logistics with the three-layer architecture of IoT technology. By extracting the key technologies of IoT perception layer, network layer, and intelligence layer, the intelligent cold chain coordination system based on IoT technology is constructed, and then, the correctness of the system is verified, to have some reference and evaluation for the cold chain construction. The system was then verified to have some reference and guidance significance for the construction and evaluation of the cold chain. The results of this paper are more accurate and more efficient.

AMVchain: authority management mechanism on blockchain-based voting systems.

As blockchain technology booms, modern electronic voting system leverages blockchain as underlying storage model to make the voting process more transparent, and guarantee immutability of data. However, the transparent characteristic may disclose sensitive information of candidate for all system users have the same right to their information. Besides that, the pseudo-anonymity of blockchain will lead to the disclosure of voters’ privacy and the third-parties such as registration institutions involved in voting process also have possibility of tampering data. To overcome these difficulties, we apply authority management mechanism into blockchain-based voting systems. In this paper, we put forward AMVchain, a fully decentralized and efficient blockchain-based voting system. AMVchain has a three-layer access control architecture, and on each layer, smart contracts are responsible for validation and granting permissions. Linkable ring signature is adopted in the process of voting to protect ballot-privacy. AMVchain also makes a tradeoff between efficiency and concurrency by introducing proxy nodes. The experiments results show that our system meets the basic requirements under the high concurrent users circumstance.

Nanoscale Architecture of Polymer-Organolead Halide Perovskite Films and the Effect of Polymer Chain Mobility on Device Performance.

The integration of polymer chains with organolead halide perovskite (MAPbI3) films, leading to enhanced stability and electro-optical performance, is critically affected by the molecular weight of chains. The molecular weight determines the mobility and volume of the chains, which affects the crystallization kinetics and, hence, perovskite grain size. The insulating nature of the chains is another critical factor that affects both ion migration and conduction of electronic charge. The combined effect of these factors leads to optimal performance with the use of medium-length chains. A simple model integrating the two effects accurately fits the response of the polymer-perovskite composite. Further characterization results show that the polymer-perovskite films have a three-layer architecture consisting of nanoscale polymer-rich top and bottom layers. These combined results show that the optimization of performance in polymer-perovskite devices depends critically on the size of the chains due to their multiple effects on the perovskite matrix.

Toward Road Safety Recommender Systems: Formal Concepts and Technical Basics

Worldwide, traffic accidents are recognized as one of the leading causes of death. This phenomenon leads to significant daily losses affecting both road users and road authorities. Therefore, the need for effective dynamic road security systems is highly considered. Traffic accident data analysis is one of the promising approaches for improving road safety. By taking into account multiple factors (e.g., infrastructure, weather, driver behavior, etc.), it allows measuring the impact of traffic accidents on road security. However, reformulating this impact into practical road safety decisions remains limited and unstructured. To overcome the mentioned limitations, this paper proposes the first end-to-end recommendation framework for road safety. Our framework introduces a three-layered architecture, designed to handle data analysis and action recommendation tasks. For data analysis, we adopt a baseline of state-of-the-art machine and deep learning algorithms to build different traffic accident prediction models. For the action recommendation task, we developed a new approach involving model predictions, model interpretations, actions definition, and road-action interactions matrix annotation. The proposed framework has been successfully experimented and evaluated using two real-world datasets of historical traffic accidents of France (2006-2017) and Morocco (2010-2014), achieving interesting ROC-AUC scores of 0.93 and 0.96, respectively.

Distributed Optimization of Nonlinear Multiagent Systems: A Small-Gain Approach

This article studies the distributed optimal output agreement problem for multiagent systems described by uncertain nonlinear models. By using the partial information of an objective function, the design aims to steer the outputs of the agents to an agreement on the optimal solution to the objective function. To solve this problem, this article introduces distributed coordinators to calculate the desired outputs, and designs reference-tracking controllers for the agents to follow the desired outputs. To deal with the nonlinear uncertain dynamics, the closed-loop multiagent system is considered as a dynamical network, and Sontag's input-to-state stability is employed to characterize the interconnections. It is shown that output agreement in multiagent nonlinear systems is achievable by means of distributed optimal controllers via a small-gain approach. The proposed design features a three-layer architecture, and the reference-tracking controllers can be implemented as successive nonlinear proportional-integral loops. A numerical example is employed to show the effectiveness of the design.

A Multi-layered Framework for Internet of Everything (IoE) via Wireless Communication and Distributed Computing in Industry 4.0

Background: In the recent years, due to proliferation of the internet and smart computing there has been progress in the areas of energy, manufacturing, oil and gas, smart grid and other industrial applications. The progress in these areas is due to the advances in the emerging areas such as Big data, cloud computing, fog computing and wireless networks. The advancement in these areas has paved the way for new industrial evolution, Industry 4.0 or smart factory or Industrial Internet of Things (IIoT). IIoT is made up of a collection of devices, with each device being able to monitor, collect, exchange, analyze and take decisions intelligently based on the environment through proper communication channels. IIoT consists of smart solutions in the fields of electricity (smart-grid), home automation (smart-home), supply-chains (smart-automation) and agriculture (smart-agriculture). The interconnection among the different smart components of IIoT is a key requirement for IIoT systems. We revised all the patents relating to industry 4.0 and its application in Internet of Services (IoS). Methods: In this paper, a novel three-layered architecture is proposed to handle the heterogeneity of components of IIoT, thus providing a way for the digital transformation of IIoT systems. Results: The paper also provides an overview of underlying components, principles, communication standards and enabling technologies for IIoT or smart factory. There is no patent information used in the paper for discussing the framework. Conclusion: Recent technologies such as cloud computing, fog computing, and big data are the key enablers for IIoT systems and are transforming the way in which the industrial systems work and operate.

Integrated Design of Graduate Education Information System of Universities in Digital Campus Environment

This study takes the digital campus construction planning of the high school as an example and determines the requirements of the postgraduate management information system under the digital campus environment through the analysis of the overall framework and technology of the digital campus. Combining the current situation of computer technology, network technology, and the actual situation of our university, the current mainstream B/S three‐layer architecture is adopted, the web adopts the current popular Java Server Pages technology, and the struts framework connects to the Oracle backend database through the Java Database Connectivity interface to design the browser‐side and server‐side programs. The struts framework connects to the Oracle backend database through the Java Database Connectivity interface to design browser‐side and server‐side programs. The functional model and data flow model of the system were established through a detailed and effective analysis of the entire workflow of postgraduate students’ training management during their school years. Then, the system analysis, design, and drawing of the swim lane diagram and data business flow diagram were carried out. The system was designed in detail in terms of system architecture, development tools, functional modules, and database design, and the core module of training program making in postgraduate training management was highlighted as an example to discuss the principles and methods in the construction of departmental business systems and informatization under the digital campus environment, and a flexible and efficient postgraduate management information system was realized. It standardizes the construction of data standardization in universities; does a good job of standardizing and normalizing information; improves the accuracy, validity, and real‐time production of data collection and the real and safe unified management of historical data; and provides scientific and reasonable data support for the leadership to make relevant decisions.

FinRL: Deep Reinforcement Learning Framework to Automate Trading in Quantitative Finance

Deep reinforcement learning (DRL) has been envisioned to have a competitive edge in quantitative finance. However, there is a steep development curve for quantitative traders to obtain an agent that automatically positions to win in the market, namely \textit{to decide where to trade, at what price} and \textit{what quantity}, due to the error-prone programming and arduous debugging. In this paper, we present the first open-source framework \textit{FinRL} as a full pipeline to help quantitative traders overcome the steep learning curve. FinRL is featured with simplicity, applicability and extensibility under the key principles, \textit{full-stack framework, customization, reproducibility} and \textit{hands-on tutoring}. Embodied as a three-layer architecture with modular structures, FinRL implements fine-tuned state-of-the-art DRL algorithms and common reward functions, while alleviating the debugging workloads. Thus, we help users pipeline the strategy design at a high turnover rate. At multiple levels of time granularity, FinRL simulates various markets as training environments using historical data and live trading APIs. Being highly extensible, FinRL reserves a set of user-import interfaces and incorporates trading constraints such as market friction, market liquidity and investor's risk-aversion. Moreover, serving as practitioners' stepping stones, typical trading tasks are provided as step-by-step tutorials, e.g., stock trading, portfolio allocation, cryptocurrency trading, etc.

A Cyber-Physical Systems Approach to Collaborative Intersection Management and Control

As urban population increases steadily, current mobility and transportation services become inefficient, needing an urgent improvement since they represent a major source of discomfort and economic losses. In this context, the concept of intelligent transportation systems takes relevance as a way of optimizing those services with the use of technology. This work proposes a cyber-physical systems approach to collaborative urban traffic control. Specifically, a three-layer architecture is proposed to address the intersection management problem, making use of modular cyber-physical object abstractions and timed Petri nets. Preliminary implementations in a pseudo-real environment show that the proposed system is capable of handling the communication and processing loads, while improving traffic performance with respect to classical solutions for traffic signals, outperforming timed, Webster and coordinated control methods in pilot-scale tests.