Nowadays there is a growing demand for small- and medium-sized enterprises (SMEs) to improve their level of digitalisation. This situation becomes even more critical in cases when SMEs act in the role of a subcontractor of large enterprises who demand the utilisation of certain digital operations. This paper aims to identify the essential Industry 4.0 attributes for the requirements of SMEs that enterprises can purchase to deploy an adequate solution with a view of increasing their competitiveness in the market. By analysing research articles and statistical data from the worldwide Web of Science database, we identify the major Industry 4.0 attributes for SME: Internet of Things (IoT), Big Data, Artificial Intelligence (AI), Cloud Computing, Simulation and Cybersecurity. Based on the review results and a survey by the European Commission, we propose devices primarily designed to implement AI tasks in industrial environments that meet the essential attributes for SMEs and have low entry costs. The subject of IoT is thoroughly addressed. Its subsets and the relationship between Industrial Internet of Things (IIoT) and Artificial Intelligence of Things (AIoT) are introduced and described. The characteristics of the listed devices as related to usability in the identified attributes are verified. Therefore, the description of the devices is provided with respect to their usability in SMEs. The main purpose of this paper is to identify attributes for SMEs and to develop strategic plans for the digitalisation requirements, particularly in the development of Artificial Intelligence as part of the implementation of the IoT pillar.
1 January 2012 in International Journal of Computer Theory and Engineering
This paper aims at deeper exploration of the new field named auto-machine learning, as it shows promising results in specific machine learning tasks e.g. image classification. The following article is about to summarize the most successful approaches now available in the A.I. community. The automated machine learning method is very briefly described here, but the concept of automated task solving seems to be very promising, since it can significantly reduce expertise level of a person developing the machine learning model. We used Auto-Keras to find the best architecture on several datasets, and demonstrated several automated machine learning features, as well as discussed the issue deeper.
25 September 2016 in Artificial Intelligence Review
The design of control systems needs to ensure communication between multiple PLCs or external IoT devices. Furthermore, there are several ways of communication between them. This article dealt with the PLC communication based on TCP/IP protocol, and compared several communication options between two PLCs of the S7-300 and S7-1200 series connected using Profinet with a solution built in C# connected to the PLC via an OPC server. We used MODBUS TCP, TCON, and PUT/GET program blocks for comparison. We transmitted a digital Boolean data type and an analogue value of the integer data type via Profinet to read data from the S7-300 PLC and send data to the S7-1200. We compared the programming instructions standardly used as a client/server PLC programming with a Windows Forms application, and evaluated the advantages and disadvantages of this solution even when using external IoT devices. The solution was applied and successfully tested for communication between PLC S7-1200 and Nvidia Jetson Nano. We wrote program instructions for PLC in Siemens Tia Portal V15.
Today are used electrocardiograms with sensors, which require a wild-sprays to ensure electrical contact between sensor and skin. Such devices are for set to time-consuming and problematic for long term record. The lack of principle eliminates the use of non-contact sensing. The object was to construct such an ECG device, which has been designed and constructed under the project. On the other hand, non-contact sensing is burdened by relative high level of noise in the useful signal what is not suitable for medical purposes. This paper is focused just on issue of removing noise from the signal obtained from non-contact device. The aim is proposal of processing these signals, which is suitable for the another analysis. The aim is filtered ECG signals using suitable methods of linear filtering obtained from the non-contact device from the mains and battery. The aim is also to find signals that are suitable for medical purposes obtained from experiments involving the device. The results clearly show the noise reduction in ECG signals using low pass, high pass and notch filters.