Model of Evaluation and Selection of Expert Group Members for Smart Cities, Green Transportation and Mobility: From Safe Times to Pandemic Times

Research on Architectural Planning and Landscape Design of Smart City Based on Computational Intelligence

City brain is a complex system, including online center, server network, and system with given algorithm. The core of the city brain is the intelligent system. After putting the urban brain into the intelligent nerve center, on the basis of not changing its original data structure, combining its own characteristics for design and then integrating into application, it can intelligently change the urban management mode. Urban planning leads the development of smart cities on a certain meaning, and smart city planning must have scientific and rational urban planning. The intelligent model is used to make urban planning form a more modern, convenient, and reasonable urban architectural planning. Some influential books on classical architectural theory are the theoretical basis of intelligent urban planning and even the trend and implementation blueprint of how smart cities will develop in the future. In this paper, four algorithms, ant colony algorithm, particle swarm optimization algorithm, genetic algorithm, and improved ant colony algorithm, are proposed to optimize the characteristics of urban architectural planning and landscape design; especially the security research of architecture and landscape characteristics is very important. The improved ant colony algorithm has the shortcoming of insufficient optimization ability in the face of complex path selection. By improving the influencing factors, a new ant colony algorithm is created. The improved ant colony algorithm achieves the best in security features, so it is advocated to use this algorithm for planning and design. The urban form in smart city aims to create a beautiful and comfortable urban environment, improve the competitiveness of cities in the rapid urbanization process, improve the living standards of the public, and shape the image of this beautiful city.

Model for Sustainable Financial Planning and Investment Financing Using Monte Carlo Method

The article deals with current issues of finance and investment planning with a selective focus on financial decision-making processes using sophisticated software tools. The article has a special significance in this period when it is necessary to re-evaluate and consider ways of appropriate and effective investment and financial policy in view of the restrictions in enterprises in Slovakia, which brings with it the global pandemic COVID-19 or another crisis in enterprises. The aim of the article is to propose a methodology as a tool for streamlining the investment activities of companies. The proposed methodology combines the usability of traditional and modern economic methods, making it an important tool for the sustainability and competitiveness of enterprises. Three variants of investment decisions in the enterprise were simulated using simulation in terms of two approaches. The first approach focuses on mathematical–economic calculations of deterministic modeling through traditional software tools. The second stochastic modeling uses the simulation of financial risks using a modern software tool using the Monte Carlo method. The output is the creation of a graphical management model in the form of an algorithm.

Adaptation and Learning to Learn (ALL): An Integrated Approach for Small-Sample Parking Occupancy Prediction

Parking occupancy prediction (POP) plays a vital role in many parking-related smart services for better parking management. However, an issue hinders its mass deployment: many parking facilities cannot collect enough data to feed data-hungry machine learning models. To tackle the challenges in small-sample POP, we propose an approach named Adaptation and Learning to Learn (ALL) by adopting the capability of advanced deep learning and federated learning. ALL integrates two novel ideas: (1) Adaptation: by leveraging the Asynchronous Advantage Actor-Critic (A3C) reinforcement learning technique, an auto-selector module is implemented, which can group and select data-scarce parks automatically as supporting sources to enable the knowledge adaptation in model training; and (2) Learning to learn: by applying federated meta-learning on selected supporting sources, a meta-learner module is designed, which can train a high-performance local prediction model in a collaborative and privacy-preserving manner. Results of an evaluation with 42 parking lots in two Chinese cities (Shenzhen and Guangzhou) show that, compared to state-of-the-art baselines: (1) the auto-selector can reduce the model variance by about 17.8%; (2) the meta-learner can train a converged model 102× faster; and (3) finally, ALL can boost the forecasting performance by about 29.8%. Through the integration of advanced machine learning methods, i.e., reinforcement learning, meta-learning, and federated learning, the proposed approach ALL represents a significant step forward in solving small-sample issues in parking occupancy prediction.

Proposal of a Methodology for Assessing Financial Risks and Investment Development for Sustainability of Enterprises in Slovakia

Investments are a demanding and, at the same time, threatening indicator for enterprises not only in the time of depression such as the current coronavirus pandemic but also under normal market conditions. The goal of this article is to propose a methodology for assessing financial risks and investment development. The proposed methodology integrates the use of new modern and classical economic-statistical methods, which makes it an effective tool for the sustainability of enterprises. At the same time, the methodology can be used as an auxiliary tool for enterprise management in the investment decision-making process. In the first step, a methodology was created using a commercial software tool where the pdevelopment of the cash-flow indicator and the accumulated cash flow were modeled in order to calculate the net present value (NPV). The statistical modeling was performed using the one-way analysis of variance (ANOVA). The normality was monitored using the Shapiro–Wilk test, and the Kruskal–Wallis test was chosen as the non-parametric test. The deliverable of the applied methods was the creation of a mathematical model in the form of an algorithm that is applicable in different enterprises in Slovakia.