Transactions on Computational Collective Intelligence XXV

The main goal of the paper is to build a high-level model for the design of KPIs. Currently, the development and processes of cities have been checked by KPI indicators. The authors realized that there is a limited usability of KPIs for both the users and IT specialists who are preparing them. Another observation was that the process of the implementation of Smart Cities systems is very complicated. Due to this the concept of a trigger for organizational-technological changes in the design and implementation of Smart Cities was proposed. A dedicated Model for City Development (MCD) was presented. The paper consists of four main parts. First the structures of both city and business organizations were presented. Based on that, in the second part, the processes existing in cities and business organizations were presented to show how different they are. The third part presents the role of KPIs and their limitations with the example of the IOC. The last part consists of the presentation of the model and its verification based on two city decision-making examples. The proposed design model presented herein takes into account both the city indicators and their aggregate versions for the needs of city models.

The goal of the paper is to present the results of studies concerning the development of a method of implementation of business processes in Smart Cities systems. The method has been developed during studies carried out within the building of a Smart Cities system for Gdańsk, and is based on basic development project management mechanisms (drawing from best practices, and in particular from the RUP methodology) and business-oriented development principles, where the role of business process modeling is crucial for the implementation of functionalities of IT systems.

The aim of the paper is to present a concept of measuring the performance of city management processes by use of a concept of aggregate KPIs. In the management of organizations and, as a consequence of the use of a common design framework also in the management of cities, silo KPIs are commonly used to show the statuses of the processes of organizations/cities. Thus the question arises as to what extent aggregate KPIs, as proposed in the paper, can be used in the management processes of smart cities in place of the silo ones typical for organizations. The work is divided into four main parts. The first presents the problems of managing smart cities to introduce the reader to the problems of measuring processes and the need for aggregated measurements. The second section discusses KPIs and their place and role in management processes. The third part contains a description of the model of aggregate KPIs to support measurements of the status of city processes. In the fourth section the developed model is verified, demonstrating its applicability for city management processes. The summary includes a recommendation for the use of aggregate KPIs in the city.

The objective of this paper is to present the results of research carried out to develop a design method for Smart Cities systems. The method is based on the analysis of design cases of Smart Cities systems in cities, the selection of the city appropriate to the requirements for implementation and application. The Case Based Reasoning method was used to develop the proposed design methodology, along with mechanisms of the conversion of project processes and roles to Rational Unified Processes (RUP). The prerequisite for the proposed method is that the enterprise manager must be knowledgeable about high-level Smart Cities system architecture and the design framework applied. The authors, being themselves knowledgeable about architecture of this kind and about project environments which implement KPI models, propose a generic solution applicable to any environments and system architectures.

This paper presents a model of an integration bus used in the design of Smart Cities system architectures. The model of such a bus becomes necessary when designing high-level architectures, within which the silo processes of the organization should be seen from the perspective of its ontology. For such a bus to be used by any city, a generic solution was proposed which can be implemented as a whole or in part depending on the requirements posed by those cities with respect to the construction of such buses.

The work is divided into four main parts. The first part presents a model of high-level architectural design processes, using ontologies and a data integration bus, which constitutes the generalized experiences of the authors drawn from the design processes of Smart Cities systems. The second part contains a description of the environment in which Smart Cities systems are developed, illustrated with two guidelines and the implementation processes of these guidelines. In the third part, two components of that environment are identified: the data integration bus and the ontologies of city processes. This is done to demonstrate how Smart Cities systems are designed and to show the processes of the permeation of data and the ontologies of city processes in the creation of a high-level architecture. The fourth section contains a description of how the proposed model is applied in the construction of a common integration bus for data and ontologies. The paper summary presents recommendations concerning the applicability of the proposed model.

The paper presents the definition of the design pattern language of Smart Cities in the form of an ontology. Since the implementation of a Smart City system is difficult, expensive and closely linked with the problems concerning a given city, the knowledge acquired during a single implementation is extremely valuable. The language we defined supports the management of such knowledge as it allows for the expression of a solution which, based on best practices recorded in the form of design patterns, is also tailored to the requirements of the city seeking to implement the Smart City solution. The formal/ontological structure of the language in turn allows the automatic management of the properties of a solution recorded in this way. This final feature of the introduced language is extremely important in the decision-making process regarding the choice of a particular solution by the relevant authorities.

The work is divided into five main parts. In the first part we discuss the implementation issue of the integration bus using the example of the IOC. In the next part we talk about the validity of using semantic technologies in order to expand the spectrum of potential implementations. Then we discuss the ontological implementation of the Smart City pattern language which we created, a language which allows for both the saving of requirements and the validation of solutions specified in it. We also present an example of usage, which at the same time serves as a validation of the language in real-life conditions. In the last part we discuss certain aspects of the pattern language and the possible ways to develop research related to it.

The problem of Text Classification (TC) has been studied for decades, and this problem is particularly interesting because the features are derived from syntactic or semantic indicators, while the classification, in and of itself, is based on statistical Pattern Recognition (PR) strategies. Thus, all the recorded TC schemes work using the fundamental paradigm that once the statistical features are inferred from the syntactic/semantic indicators, the classifiers themselves are the well-established ones such as the Bayesian, the Naïve Bayesian, the SVM etc. and those that are neural or fuzzy. In this paper, we shall demonstrate that by virtue of the skewed distributions of the features, one could advantageously work with information latent in certain “non-central” quantiles (i.e., those distant from the mean) of the distributions. We, indeed, demonstrate that such classifiers exist and are attainable, and show that the design and implementation of such schemes work with the recently-introduced paradigm of Quantile Statistics (QS)-based classifiers(The foundational properties for CMQS (for generic and some straightforward distributions) were initially described in [17]. Their properties for uni-dimensional distributions of the exponential family are included in [9], and for multi-dimensional distributions in [18]. The authors of [17], [9] and [18] had initially proposed their results as being based on the Order-Statistics of the distributions. This was later corrected in [19], where they showed that their results were rather based on their Quantile Statistics.). These classifiers, referred to as Classification by Moments of Quantile Statistics (CMQS), are essentially “Anti”-Bayesian in their modus operandi. To achieve our goal, in this paper we demonstrate the power and potential of CMQS to describe the very high-dimensional TC-related vector spaces in terms of a limited number of “outlier-based” statistics. Thereafter, the PR task in classification invokes the CMQS classifier for the underlying multi-class problem by using a linear number of pair-wise CMQS-based classifiers. By a rigorous testing on the standard 20-Newsgroups corpus we show that CMQS-based TC attains accuracy that is comparable to the best-reported classifiers. We also propose the potential of fusing the results of a CMQS-based methodology with those obtained from a more traditional scheme.

Semi-supervised classification problem arises in the situation that we just have a small amount of labeled instances in the training set. One method to classify the new time series in such situation is that; firstly we need to use self-training to classify the unlabeled instances in the training set. Then, we use the output training set to classify the new time series. In this paper, we propose two novel improvements for Minimum Description Length-based semi-supervised classification of time series: an improvement technique for Minimum Description Length-based stopping criterion and a refinement step to make the classifier more accurate. Our first improvement applies the non-linear alignment between two time series when we compute Reduced Description Length of one time series exploiting the information from the other. The second improvement is a post-processing step that aims to identify the class boundary between positive and negative instances accurately. For the second improvement, we propose an algorithm called Refinement that attempts to identify the wrongly classified instances in the self-training step; then it reclassifies these instances. We compare our method with some previous methods. Experimental results show that our two improvements can construct more accurate semi-supervised time series classifiers.