Stand-alone Machines Research Articles

Predicting daily global solar radiation in various climatic regions of China based on hybrid support vector machines with meta-heuristic algorithms

Accurate prediction of global solar radiation (Rs) is vital for investment decisions and solar energy distribution. In this study, three hybrid models (ACO-SVM, CS-SVM, and GWO-SVM) based on ant colony optimization (ACO), cuckoo search (CS) and grey wolf optimization (GWO) algorithms were proposed to optimize support vector machine (SVM) for predicting Rs in four climate zones of China (temperate continental zone TCZ, mountain plateau zone MPZ, temperate monsoon zone TMZ, and subtropical monsoon zone SMZ). They were compared with the standalone backpropagation neural network model, decision tree, and support vector machines. The results demonstrated that among the standalone models, support vector machines performed best with the highest accuracy in Rs estimation in each climate zone of China, followed by the decision tree and backpropagation neural network models, with a coefficient of determination (R2) in 0.707–0.882, 0.694–0.881, and 0.681–0.850, respectively. In contrast, the hybrid models exhibited higher accuracy than standalone support vector machines in four climatic regions of China, with the coefficient of determination (R2) increasing by 5.361%, 5.476%, 7.382%, and 10.965%, respectively. Among hybrid models, GWO-SVM performed better than CS-SVM, and both had higher accuracy than ACO-SVM, with the coefficient of determination (R2) in 0.809–0.927, 0.804–0.926, and 0.793–0.930, respectively. Therefore, the hybrid models (ACO-SVM, CS-SVM, and GWO-SVM), especially GWO-SVM and CS-SVM, can significantly improve the accuracy for predicting Rs in various regions of China.

Prediction of Cardiovascular Risk Using Extreme Learning Machine-Tree Classifier on Apache Spark Cluster

Introduction: In the recent scenario, machine learning is considered a prevailing area in the diverse fields of science and technology include image processing, automobiles, banking, finance, etc. The availability of data and adverse improvements over machine learning techniques have become more feasible to understand and to work on various channels of real-time health analytics. Method: In this paper, a health status prediction system is proposed to detect cardiovascular diseases through patients’ tweets. Further, analytics will be carried on a distributed Apache Spark framework to reduce the time taken for both training and testing when compared with regular standalone machines. Results: Performance of the proposed framework with Extreme Learning Machine (ELM) - Tree classifier is evaluated on two different corpora, and which outperforms other classifiers such as Decision Trees, Naïve Bayes, and Linear SVC, DNN, etc. in both accuracy and time. Discussion: Social media streaming data is considered as one of the major sources for data in the proposed system. Based on the model, the attributes of the incoming user tweets are analyzed, and accordingly cardiovascular risk is predicted. Further, current health status is tweeted back as a reply to the respective user along with a copy to the family and caretakers. Conclusion: This proposed work provides the development of the alert-based system for heart status prediction by adding some additional features impacting the accuracy besides reducing the response time by using Big data Apache Spark Distributed Framework.

Home hemodialysis

Heimhämodialyse (HHD) ist der Grundstein der Nierenersatztherapie in Deutschland. Sie ermöglichte ab 1969 das Überleben mit einer bis dahin tödlichen Diagnose. Mit dem Ausbau eines guten Netzes von Dialysezentren gingen das Wissen und die Erfahrung der HHD jedoch zunehmend verloren. In der Ausbildung kommt die HHD heute praktisch nicht mehr vor. Ungenügende Aufklärung und fehlendes Angebot der HHD sind die Folge. Aktuell werden in Deutschland weniger als 0,8 % der Patienten mit HHD behandelt. Die Industrie orientierte sich bei der Entwicklung von Dialysegeräten auf Standgeräte für die Zentren. Diese Form der Therapie behindert die Mobilität und schränkt die Aktivitäten von Patienten mit dialysepflichtiger Niereninsuffizienz ein. Ausgehend von der Advancing American Kidney Health Initiative hat sich eine erfreuliche Dynamik in der Entwicklung innovativer, tragbarer und implantierbarer künstlicher Nieren entwickelt. Damit kann die Lebensqualität verbessert und die Sterblichkeitsrate gesenkt werden. Auch in Deutschland und Europa sind erste Initiativen entstanden. Diese innovativen Geräte und der damit zusammenhängende Wandel in der Nierenersatztherapie werden viele Probleme der nephrologischen Community, wie Personalmangel oder den Mangel an Spenderorganen und Tod auf der Warteliste lösbar machen und den Patienten Unabhängigkeit und Mobilität schenken. Die Kostenbelastung der Gesundheitssysteme kann reduziert werden. Darüber hinaus werden der immense Wasser- und Stromverbrauch durch die regenerativen Techniken der neuen Geräte dramatisch verringert.

Econometrics at Scale: Spark up Big Data in Economics

This paper provides an overview of how to use “big data” for social science research (with an emphasis on economics and finance). We investigate the performance and ease of use of different Spark applications running on a distributed file system to enable the handling and analysis of data sets which were previously not usable due to their size. More specifically, we explain how to use Spark to (i) explore big data sets which exceed retail grade computers memory size and (ii) run typical statistical/econometric tasks including cross sectional, panel data and time series regression models which are prohibitively expensive to evaluate on stand-alone machines. By bridging the gap between the abstract concept of Spark and ready-to-use examples which can easily be altered to suite the researchers need, we provide economists and social scientists more generally with the theory and practice to handle the ever growing datasets available. The ease of reproducing the examples in this paper makes this guide a useful reference for researchers with a limited background in data handling and distributed computing.

Home hemodialysis

Heimhämodialyse (HHD) ist der Grundstein der Nierenersatztherapie in Deutschland. Sie ermöglichte ab 1969 das Überleben mit einer bis dahin tödlichen Diagnose. Mit dem Ausbau eines guten Netzes von Dialysezentren gingen das Wissen und die Erfahrung der HHD jedoch zunehmend verloren. In der Ausbildung kommt die HHD heute praktisch nicht mehr vor. Ungenügende Aufklärung und fehlendes Angebot der HHD sind die Folge. Aktuell werden in Deutschland weniger als 0,8 % der Patienten mit HHD behandelt. Die Industrie orientierte sich bei der Entwicklung von Dialysegeräten auf Standgeräte für die Zentren. Diese Form der Therapie behindert die Mobilität und schränkt die Aktivitäten von Patienten mit dialysepflichtiger Niereninsuffizienz ein. Ausgehend von der Advancing American Kidney Health Initiative hat sich eine erfreuliche Dynamik in der Entwicklung innovativer, tragbarer und implantierbarer künstlicher Nieren entwickelt. Damit kann die Lebensqualität verbessert und die Sterblichkeitsrate gesenkt werden. Auch in Deutschland und Europa sind erste Initiativen entstanden. Diese innovativen Geräte und der damit zusammenhängende Wandel in der Nierenersatztherapie werden viele Probleme der nephrologischen Community, wie Personalmangel oder den Mangel an Spenderorganen und Tod auf der Warteliste lösbar machen und den Patienten Unabhängigkeit und Mobilität schenken. Die Kostenbelastung der Gesundheitssysteme kann reduziert werden. Darüber hinaus werden der immense Wasser- und Stromverbrauch durch die regenerativen Techniken der neuen Geräte dramatisch verringert.

A Clustered Approach for Load Balancing in Distributed Systems

Distributed systems are increasingly becoming the dominant and rapidly expanding computational paradigm of tomorrow. A cluster is really a form of parallel or distributed processing system that consists of a set of intertwined stand-alone machines that function together like truly coherent computing and storage resources with a single system image (SSI) which means that perhaps the clusters are viewed as a single platform by the consumers. Global resource management, on the other hand, poses several concerns due to the sheer complexity and range of tools, as well as the need for user accountability. The possible advantages of load balancing in addressing the occasional congestion faced by some nodes when everyone else is idle or congested are widely agreed on a level of performance. This is also widely acknowledged that neither specific load balancing algorithm can adequately address evolving device characteristics and complex capacity management in a distributed ecosystem. To have a systematic approach and also in distributed systems, a proposed approach is created for a holistic view of element load balancing and also the qualities features of load balancing algorithms. The nomenclature has been expanded. In order for adaptive algorithms to understand the problem and manner of prefixing resilience along with different components in distributed systems, they must first recognize the concerns. In addition, a proposed approach is specified. The much more effective load balancing techniques and the modeling hypotheses used in prior load balancing experiments are established through a study of related research. We consider the most appropriate load balancing algorithm and optimum metrics for parameter estimation of the algorithm as a consequence of and output of this assessment for a range of formulations of resulting goals, distributed system features, and workload balancing framework.

Delineating fragmented grassland patches in the tropical region using multi-seasonal synthetic aperture radar (SAR) and optical satellite images

ABSTRACT Globally, grasslands are declining and are in highly degraded conditions. In South Asia, grasslands are neglected and treated as wastelands. They remain unprotected, highly fragmented, and poorly understood, which has led to a loss of unique biodiversity and livelihoods. Mapping grasslands accurately is a challenge and current maps based on optical remote sensing often over- or underestimate grasslands in South Asia due to the prevalent complex landscape matrix, small patch sizes, and obscuring monsoonal clouds. Synthetic Aperture Radar (SAR), fused with moderate spatial resolution optical data, has been used to delineate grasslands, but the high-resolution, freely available European Space Agency (ESA)’s Sentinel-1 (SAR) and Sentinel-2 (Optical) provide an opportunity to map small and fragmented patches. Further, high-resolution imageries require high computing power, which is often limited to stand-alone machines. Here, we demonstrate that using cloud computing and optimal use of multi-seasonal imagery, one can obtain a highly accurate land-cover land use (LCLU) classification for a complex habitat matrix. We performed LCLU classification using the Support Vector Machine (SVM) algorithm of Sentinel-1, Sentinel-2, and Sentinel-1 and Sentinel-2 (Combined) in Google Earth Engine (GEE). GEE is a freely accessible cloud computing platform. We compared the accuracy of grassland classes between a) Sentinel-1 seasonal (pre-, during, and post-monsoon), b) Sentinel-2 post-monsoon, and c) combined Sentinel-1 and Sentinel-2. We tested this method at two sites in a highly fragmented habitat matrix in arid and semi-arid areas of Western and Southern India. The classification results have shown that the overall accuracy for the combined image classification was higher than only Sentinel-2 or Sentinel-1 alone for both sites. Grassland class accuracy was also consistent with combined image classification across the sites. Our results identified newer grassland areas that coarse land use management maps used by the government did not. Since the computation was conducted in GEE, a regular laptop was sufficient for the user and processing was completed rapidly. We, therefore, suggest that this approach of using cloud computing and optimal use of resource-hungry (computation and storage) high-resolution Sentinel-1 and Sentinel-2 data can be used to identify major LCLU classes and patchy grasslands in the arid and semi-arid regions of India and has the potential to map at a continent level.

Multiple Access Control in a Centralized Full-Duplex Cognitive Machine Type Network with RF Energy Harvesting

Machine type communication connecting machines in the Internet of Things (IoT) brings massive traffic and rapidly increases the demand for radio spectrum in wireless networks. To transmit the traffic in limited spectra, a time division multiple access (TDMA) based interface with a reservation scheme, which is spectrum-efficient, energy-efficient, and deployment-economical, was proposed in cognitive radio based machine type communication. Since radio frequency (RF) energy harvesting is a way to charge stand-alone or low-power machines in IoT and full-duplex communication potentially doubles spectral efficiency, this paper proposes a multiple access control that incorporates RF energy harvesting and full-duplex communication into the TDMA based interface with a reservation scheme. The proposed multiple access control elaborately uses the full-duplex functionality with a mechanism of detecting primary users to appropriately turn on/off RF charging such that the trade-off between the interference of primary users and RF charging is balanced. Extensive simulation results show that the proposed multiple access control produces high system throughput while the interference of primary users is kept at a low level.

Networked Intelligence

The second part of this article focuses on the transformation of the production systems in manufacturing and agriculture as a result of the convergence in the I4.0 technologies detailed in Part I. The category of general-purpose production machines is presented in detail. The interconnection of these machines and our ability to operate them remotely turn the stand-alone machines into production systems. The characteristics of these systems are studied separately for the cases of manufacturing and agriculture, showing the interrelation of the transformations in the two sectors. The I4.0 production systems give a tremendous boost in productivity as they allow the user of these systems to switch between different activities dynamically, cutting down costs and inefficiencies. The widespread deployment of such production systems fosters the emergence of a new social entity, the “prosumer.” The subsequent rationalization in the production creates the conditions where overproduction gradually dies out while it shifts the balance from mass consumption to mass customization.

Deep support vector machine for hyperspectral image classification

To improve on the robustness of traditional machine learning approaches, emphasis has recently shifted to the integration of such methods with Deep Learning techniques. However, the classification problems, complexity and inconsistency in several spectral classifiers developed for hyperspectral images are some reasons warranting further research. This study investigates the application of Deep Support Vector Machine (DSVM) for hyperspectral image classification. Two hyperspectral images, Indian Pines and University of Pavia are used as tentative test beds for the experiment. The DSVM is implemented with four kernel functions: Exponential Radial Basis Function (ERBF), Gaussian Radial Basis Function (GRBF), neural and polynomial. Stand-alone Support Vector Machines form the interconnecting weights of the entire network. The network is trained with one hundred input datasets, and the interconnecting weights of the network are initialised using the regularisation parameter of the model. Numerical results show that the classification accuracies of the DSVM for Indian Pines and University of Pavia based on each DSVM kernel functions are: ERBF (98.87%, 98.16%), GRBF (98.90%, 98.47%), neural (98.41%, 97.27%), and polynomial (99.24%, 98.79%). By comparing the DSVM algorithm against well-known classifiers, Support Vector Machine (SVM), Deep Neural Network (DNN), Gaussian Mixture Model (GMM), K Nearest Neighbour (KNN), and K Means (KM) classifiers, the mean classification accuracies for Indian Pines and University of Pavia are: DSVM (98.86%, 98.17%), SVM (76.03%, 73.52%), DNN (94.45%, 93.79%), GMM (76.82%, 78.35%), KNN (76.87%, 78.80%), and KM (21.65%, 18.18%). These results indicate that the DSVM outperformed the other classification algorithms. The high accuracy obtained with the DSVM validates its efficacy as state-of-the-art algorithm for hyperspectral image classification.

Multimedia system and database simulation based on internet of things and cloud service platform

The existing stand-alone multimedia machines and online multimedia machines in the market have certain deficiencies, so they cannot meet the actual needs. Based on this, this research combines the actual needs to design and implement a multi-media system based on the Internet of Things and cloud service platform. Moreover, through in-depth research on the MQTT protocol, this study proposes a message encryption verification scheme for the MQTT protocol, which can solve the problem of low message security in the Internet of Things communication to a certain extent. In addition, through research on the fusion technology of the Internet of Things and artificial intelligence, this research designs scheme to provide a LightGBM intelligent prediction module interface, MQTT message middleware, device management system, intelligent prediction and push interface for the cloud platform. Finally, this research completes the design and implementation of the cloud platform and tests the function and performance of the built multimedia system database. The research results show that the multimedia database constructed in this paper has good performance.

Decentralized iterative approaches for community clustering in the networks

In this era of big data, as the data size is scaling up, the need for computing power is exponentially increasing. However, most of the community detection algorithms in the literature are classified as global algorithms, which require access to the entire information of the network. These algorithms designed to work on a single machine cannot be directly parallelized. Hence, it is impossible for such algorithms working in stand-alone machines to find communities in large-scale networks and also the required processing power far exceeds the processing capabilities of single machines. In this paper, a set of novel Decentralized Iterative Community Clustering Approaches to extract an efficient community structure for large networks are proposed and devalued using the LFR benchmark model. The approaches have the ability to identify the community clusters from the entire network without global knowledge of the network topology and will work with a range of computer architecture platforms (e.g., cluster of PCs, multi-core distributed memory servers, GPUs). Detecting and characterizing such community structures is one of the fundamental topics in network systems’ analysis, and it has many important applications in different branches of science including computer science, physics, mathematics and biology ranging from visualization, exploratory and data mining to building prediction models.

Framework for energy efficiency optimization of industrial systems based on the Control Layer Model

Abstract In the context of sustainable manufacturing, the energy efficient operation of industrial systems is of major interest. This paper presents a modular framework for practical research about energy efficiency optimization of complex technical systems. Whereas many approaches focus on stand-alone machines or processes, this approach is concerned with energy-related coupling of several entities. Using a method for energy-related key performance indicators, the overall efficiency is deduced from all subsystems. A given topology is modeled in an XML-based format, inspired by AutomationML. The framework gives the opportunity to analyze and compare optimization algorithms. First experiments with two optimization algorithms were applied to a simulated cooling system.

Time Series Econometrics at Scale: A Practical Guide to Parallel Computing in (Py)Spark

This paper provides an overview of how to use “big data” for economic research. We investigate the performance and ease of use of different Spark applications running on a distributed file system to enable the handling and analysis of data sets which were previously not usable due to their size. More specifically, we explain how to use Spark to (i) explore big data sets which exceed retail grade computers memory size and (ii) run typical econometric tasks including microeconometric, panel data and time series regression models which are prohibitively expensive to evaluate on stand-alone machines. By bridging the gap between the abstract concept of Spark and ready-to-use examples which can easily be altered to suite the researchers need, we provide economists and social scientists more generally with the theory and practice to handle the ever growing datasets available. The ease of reproducing the examples in this paper makes this guide a useful reference for researchers with a limited background in data handling and distributed computing.

(Invited) Soft Electronics and Machines with Tough Hydrogels

Introducing methods for instant strong bonding between hydrogels and antagonistic materials – from soft to hard – allows us to demonstrate elastic, yet tough biomimetic devices and machines with a high level of complexity [1]. Tough hydrogels strongly attach, within seconds, to plastics, elastomers, leather, bone and metals reaching unprecedented interfacial toughness exceeding 2000 J/m2. Our approach is applicable in rapid prototyping and in delicate environments inaccessible for extended curing and cross-linking. The combination of ionic hydrogels with antagonistic materials such as elastomers, polymers and metals allows to create soft electronics and hybrid machines. We demonstrate stretchable batteries for self-powered soft devices, adaptive lenses, and autonomous electronic skin for triggered drug delivery (Figure 1). We further introduce a new family of biodegradable hydrogels that are able to self-heal and are resistant to dehydration. Soft machines and robots – built from hydrogels with tuned mechanical properties – are designed to be operated in ambient conditions and degrade after use. Besides progressing standalone soft machines, our advances in the synthesis of biodegradable hydrogels bring bionic soft robots a step closer to nature. [1] D. Wirthl, R. Pichler, M. Drack, G. Kettlgruber, R. Moser, R. Gerstmayr, F. Hartmann, E. Bradt, R. Kaltseis, C. M. Siket, S. E. Schausberger, S. Hild, S. Bauer, M. Kaltenbrunner, „Instant tough bonding of hydrogels for soft machines and electronics”, Science Advances, 3(6), e1700053 (2017). Caption Figure 1: Hydrogel electronic skin. (left) Concept of a hydrogel smart skin, with a flexible unit bearing power supply, control, readout and communication units, and a stretchable transducer batch. (right) Photograph of an untethered electronic hydrogel with four stretchable heating elements and adjoined temperature sensors strongly bonded to a PVA hydrogel. Battery, control, readout and Bluetooth Low Energy communication electronics are hosted on a flexible circuit board. Figure 1

Virtual Process Data Linkage of Assembly Stations in High Variance Workshop Production

The advance of digitalization changes the requirements of processes in industrial production and assembly. For this reason, production and assembly must now be able to execute complex process steps. This is about quality and productivity expectations, as well as flexibility and reliability of production, lines and plants [1]. Today, data is generated by almost every system, machine and sensor, yet it is hardly used for process optimization. Manufacturing processes are usually organized as workshop production or chained production systems, in addition to standalone machines [2,3]. Most analytic projects focus on chained systems and serial production, unlike individual machines and specific workshop production. Depending on manufacturing IT, process data from serial production is stored in data bases, which are usually optimized for traceability. Standalone machines and machines within workshop production are scarcely connected to a common data base. The required process data is stored either on the module itself or inside a local data base [4]. The identification of dependencies between individual assembly processes, energy data and the quality of the finished product is necessary for an extended optimization. These optimizations can be process-specific, as well as environmental and resource related. Due to decentralized process data storages, an overall view of a dynamic order-oriented value chain is denied. Therefore, the potential of the machines is largely unused. Based on Data Mining, this advanced development can be counteracted by process monitoring and optimization. Therefore, this paper provides a solution for a virtual process data linkage of assembly stations. This enables the acquisition, processing, transformation and storage of unstructured raw data by special software and methods, which is also able to cope with chained production systems and standalone machines. For further analysis of interdependencies, a visualization is developed for advanced monitoring and optimization [5,6].

A differentiated approach for justification of advanced manufacturing technologies

European companies rely on advanced manufacturing technologies (AMTs) in order to succeed in an environment of high labour costs, increasing competition and rising customer expectations. AMT implementation is often a high-risk investment. Many companies experience a misalignment between the installed functionality and production needs. There is a need for decision support in order to take into account all possible advantages and disadvantages of the technology implementation, and ensure that the technology meets the requirements of the production processes. In this article, a differentiated technology justification approach is introduced. The approach suggests a combination of strategic, financial and risk justification methods. The recommended number and type of methods depend on the integration level of the technical system under consideration, ranging from stand-alone machines to large and integrated production systems. The approach was developed based on a literature review and a case study. The application of the approach was presented in a case where several types of pipe bending technology were evaluated.

A cloud computing based Big-Bang Big-Crunch fuzzy logic multi classifier system for Soccer video scenes classification

Soccer video summarization and classification is becoming a very important topic due to the world wide importance and popularity of soccer games which drives the need to automatically classify video scenes thus enabling better sport analysis, refereeing, training, advertisement, etc. Machine learning has been applied to the task of sports video classification. However, for some specific image and video problems (like sports video scenes classification), the learning task becomes convoluted and difficult due to the dynamic nature of the video sequence and the associated uncertainties relating to changes in light conditions, background, camera angle, occlusions and indistinguishable scene features, etc. The majority of previous techniques (such as SVM, neural network, decision tree, etc.) applied to sports video classifications did not provide a consummate solution, and such models could not be easily understood by human users; meanwhile, they increased the complexity and time of computation and the associated costs of the involved standalone machines. Hence, there is a need to develop a system which is able to address these drawbacks and handle the high levels of uncertainty in video scenes classification and undertake the heavy video processing securely and efficiently on a cloud computing based instance. Hence, in this paper we present a cloud computing based multi classifier systems which aggregates three classifiers based on neural networks and two fuzzy logic classifiers based on type-1 fuzzy logic and type-2 fuzzy logic classification systems which were optimized by a Big-Bang Big crunch optimization to maximize the system performance. We will present several real world experiments which shows the proposed classification system operating in real-time to produce high classification accuracies for soccer videos which outperforms the standalone classification systems based on neural networks, type-1 and type-2 fuzzy logic systems.

IoT safety and security as shared responsibility

Vinton G. Cerf - Vice President and Chief Internet Evangelist, Alphabet Inc.Address: 1600 Amphitheatre Parkway, Mountain View, CA 94043, USAE-mail: vint@google.comPatrick S. Ryan - Strategy & Operations Principal, Alphabet Inc.Address: 1600 Amphitheatre Parkway, Mountain View, CA 94043, USAE-mail: patrickryan@google.comMax Senges - Research Program Manager, Alphabet Inc.Address: 1600 Amphitheatre Parkway, Mountain View, CA 94043, USAE-mail: maxsenges@google.comRichard S. Whitt - Corporate Director for Strategic Initiatives, Alphabet Inc.Address: 1600 Amphitheatre Parkway, Mountain View, CA 94043, USAE-mail: whitt@google.com What happens when everyday standalone devices and machines acquire network interfaces? The somewhat obvious result will be an unprecedented number of “things” connected to the Internet. It is less obvious what this means for the governance of the Internet when this occurs. With the “Internet of Things” (IoT) the Internet’s loosely coupled governance structures are already adapting to accommodate the evolution of the Internet’s use. As the governance structure continues to develop, users’ safety must be the first priority for all hardware and software providers. In the context of the Internet of Things, this paper proposes a definition of digital safety as distinct from security and discusses how multistakeholder governance can be applied to address safety challenges. The paper also considers the integration of “old” industries and the transformation of their governance into the multistakeholder model as their products and services are coming online. We consider how the thousands of manufacturers who traditionally produced analog, not-connected physical “things” adapt to become stakeholders in the Internet and how that changes the way that we think about Internet Governance. The particular interest of this paper is how to address safety issues that become much more prominent with the spread of Internet-enabled physical environments. The authors of this paper have written this project in their personal capacities as an academic contribution. The views reflected may not be the official position of the authors’ employer.

A granularity model for balancing the structural complexity of manufacturing systems equipment and layout

The structural complexity of a manufacturing system results primarily from the complexity of its equipment and their layout. The balance between both complexity sources can be achieved by searching for the best system granularity level, which yields a manufacturing system with the least overall structural complexity. A new system granularity complexity index is developed to sum up and normalize the complexity resulting from the system layout complexity and the equipment structural complexity. A previously developed layout complexity index together with a code-based structural complexity assessment are used to determine the structural complexity of standalone pieces of equipment and to arrive at a balance between the two sources of complexity. Cladistics analysis is used to hierarchically cluster required pieces of equipment and bundle them into more integrated equipment and machines and demonstrate the possible different system granularity levels. The new developed model is a useful tool to create specific system configuration and layout alternatives based on system components adjacency, and then select the system design with the least overall structural complexity among those alternatives. The results of the presented case study clearly demonstrated this trade-off where decomposing manufacturing systems into a highly granular configuration with standalone machines maximizes system layout complexity and minimizes equipment complexity, while at a low level of granularity pieces of equipment are bundled into complex integrated machines, lines or cells but with a very simple system layout.