Multi-Agent System Development and Application for Supply Chain Management Tasks

In today’s dynamically changing environment, we need to be able to respond in a timely manner to changes in supply chain processes. Software agents are successfully used in supply chain management tasks for a variety of purposes. The behaviour of agents is determined by the purpose of their development, and the effectiveness of the use of agents is considered in accordance with the purpose of their development. The paper presents research on the development of a multi-agent system for supply chain management, focusing on the steps of developing a multi-agent system. The choice of each algorithm for agents is analysed and argued. The application of the developed multi-agent system for supply chain management is also described in the paper. The efficiency of application of the developed multi-agent system is presented as well.

NFC-Blockchain Based COVID-19 Immunity Certificate: Proposed System and Emerging Issues

Vaccine requirements are becoming more mandatory in several countries as public health experts and governments become more concerned about the COVID-19 pandemic and its variants. In the meantime, as the number of vaccine requirements grows, so does the counterfeiting of vaccination documents. Fake vaccination certificates are steadily growing, being sold online and on the dark web. Due to the nature of the COVID-19 pandemic, there is a need of robust authentication mechanisms that support touch-less technologies like Near Field Communication (NFC). Thus, in this paper, a blockchain-NFC based COVID-19 Digital Immunity Certificate (DIC) system is proposed. The vaccination data are first encrypted by the Advanced Encryption Standard (AES) algorithm on Hadoop Distributed File System (HDFS) and then uploaded to the blockchain. The proposed system is based on the amalgamation of NCF and blockchain technologies which can mitigate the issue of fake vaccination certificates. Furthermore, the emerging issues of employing the proposed system are discussed with future directions.

Batch Order and Discrete Order Picking Integrated with Vehicle Routing Decisions

In a business-to-consumer (B2C) context, customers order more frequently and in smaller quantities, resulting in a high number of consignments. Moreover, online shoppers expect a fast and accurate delivery at low cost or even free. To survive in such a market, companies can no longer optimise individual supply chain processes, but need to integrate several activities. In this article, the integrated order picking-vehicle routing problem is analysed in an e-commerce environment. In previous research, a mathematical programming formulation has been formulated in literature but only small-size instances can be solved to optimality. Two picking policies are studied: discrete order picking and batch order picking. The influence of various problem contexts on the value of integration is investigated: a small picking time period, outsourcing to 3PL service providers, and a dynamic environment context.

Variability of Classification Results in Data with High Dimensionality and Small Sample Size

The study focuses on the analysis of biological data containing information on the number of genome sequences of intestinal microbiome bacteria before and after antibiotic use. The data have high dimensionality (bacterial taxa) and a small number of records, which is typical of bioinformatics data. Classification models induced on data sets like this usually are not stable and the accuracy metrics have high variance. The aim of the study is to create a preprocessing workflow and a classification model that can perform the most accurate classification of the microbiome into groups before and after the use of antibiotics and lessen the variability of accuracy measures of the classifier. To evaluate the accuracy of the model, measures of the area under the ROC curve and the overall accuracy of the classifier were used. In the experiments, the authors examined how classification results were affected by feature selection and increased size of the data set.

Organizational Cost and Complexity Saving Opportunities via the Development, Deployment, and Implementation of Blockchain Networks

Blockchain is being promoted as the platform to disrupt business as usual in many transaction-heavy sectors. Questions remain about the future standards of blockchain, their feature set, functionality, and the willingness of organisations to disrupt their existing revenue streams via blockchain. The most significant near-term promise that affords industry is the cost and complexity savings via the standardization of their technology infrastructure stacks. This paper explores the benefits available of reduced costs and complexity via the adoption of blockchain.

The Practice of Implementing ML Service into an Internet Business Application

Currently, there are a large number of articles describing the theoretical aspects of development in the field of machine learning. However, the experience of their practical application in real systems is described much less often. Basically, authors describe the efficiency, accuracy, and other performance metrics of the resulting solution, but everything stops at the prototype stage. At the same time, how the trained model will behave not on test data, but in real conditions, can be very different from the indicators obtained at the development stage. This article describes the experience of the implementation and real use of a classification service based on machine learning techniques.

Matrix Neo-Fuzzy-System and its Online Learning in Image Recognition Task

The paper proposes a 2D-hybrid system of computational intelligence, which is based on the generalized neo-fuzzy neuron. The system is characterised by high approximate abilities, simple computational implementation, and high learning speed. The characteristic property of the proposed system is that on its input the signal is fed not in the traditional vector form, but in the image-matrix form. Such an approach allows getting rid of additional convolution-pooling layers that are used in deep neural networks as an encoder. The main elements of the proposed system are a fuzzified multidimensional bilinear model, additional softmax layer, and multidimensional generalized neo-fuzzy neuron tuning with cross-entropy criterion. Compared to deep neural systems, the proposed matrix neo-fuzzy system contains gradually fewer tuning parameters – synaptic weights. The usage of the time-optimal algorithm for tuning synaptic weights allows implementing learning in an online mode.

Automated System for Restaurant Services

The study proposes a smart restaurant system and analyses its benefits to be able to determine system potential advantages in restaurants. Service time is one of the main criteria that can be improved to enhance the speed of the customer service as well as to increase the number of restaurant visitors. To develop the system, solutions found in scientific literature, software and their different architectures are analysed. It has been found out that it is possible to decrease the average restaurant service load time by 52.76 %. Two hypotheses have been proposed for further research in order to determine how a smart restaurant service system can increase chef’s efficiency and how the use of different algorithms can decrease chef’s workload during peak hours.

A Fuzzy Version of the TOPSIS Method in Multi-Criteria Decision-Making Tasks

Choice and decision making are an integral part of the purposeful activities of people in all areas of public and private life. Tasks of multi-criteria decision making are characterised by the fact that alternative decisions are evaluated by a set of criteria and the concept of a decision and its outcome coincide. The defining concept in such problems is the concept of a set of Pareto optimal decisions (Pareto set). This set forms alternative decisions that are not comparable in terms of the set of evaluation criteria. The choice of the optimal decision in the Pareto set can be performed only on the basis of the subjective preferences of the decision maker. In recent decades, extensions of traditional methods of multi-criteria decision making to a fuzzy environment have been proposed. One of the well-known approaches to multi-criteria decision making is the TOPSIS method. In the paper, a fuzzy version of this method is considered in situations where the values of evaluation criteria are set in the form of fuzzy numbers.

Initial Dataset Dimension Reduction Using Principal Component Analysis

Any data in an implicit form contain information of interest to the researcher. The purpose of data analysis is to extract this information. The original data may contain redundant elements and noise, distorting these data to one degree or another. Therefore, it seems necessary to subject the data to preliminary processing. Reducing the dimension of the initial data makes it possible to remove interfering factors and present the data in a form suitable for further analysis. The paper considers an approach to reducing the dimensionality of the original data based on principal component analysis.