·         Table of Contents (Volume #3, Issue #4)

·         Cover Page (Volume #3, Issue #4)

·         Editorial (Volume #3, Issue #4)

Paper #1

Numerical Discrimination of the Generalisation Model from Learnt Weights in Neural Networks

Richard N M Rudd-Ortner and Lyudmilla Milhaylova

Abstract: This research demonstrates a method of discriminating the numerical relationships of neural network layer inputs to the layer outputs established from the learnt weights and biases of a neural network's generalisation model. It is demonstrated with a mathematical form of a neural network rather than an image, speech or textual translation application as this provides clarity in the understanding gained from the generalisation model. It is also reliant on the input format but that format is not unlike an image pixel input format and as such the research is applicable to other applications too. The research results have shown that weight and biases can be used to discriminate the mathematical relationships between inputs and make discriminations of what mathematical operators are used between them in the learnt generalisation model. This may be a step towards gaining definitions and understanding for intractable problems that a Neural Network has generalised in a solution. For validating them, or as a mechanism for creating a model used as an alternative to traditional approaches, but derived from a neural network approach as a development tool for solving those problems. The demonstrated method was optimised using learning rate and the number of nodes and in this example achieves a low loss at 7.6e-6, a low Mean Absolute Error at 1e-3 with a high accuracy score of 1.0. But during the experiments a sensitivity to the number of epochs and the use of the random shuffle was discovered, and a comparison with an alternative shuffle using a non-random reordering demonstrated a lower but comparable performance, and is a subject for further research but demonstrated in this "decomposition" class architecture.

Keywords: Weight capture; Information Assurance; Safety-Critical AI; Decomposition Rule-Extraction.

Download Full Text

Paper #2

Consideration of Quality Attribute Tradeoffs of the Blockchain Pattern in the Software Development Process

John M. Medellin and Mitchell A. Thornton

Abstract: The Blockchain (BC) design pattern has many variations and is a concept that is anticipated to lead many implementations in the years to come. The number of choices for a BC implementation continues to increase since new design and implementation patterns and applications are emerging. This increasing number of design patterns enables correspondingly increasing tradeoff opportunities at every evolutionary round of architecture elaboration. Key components of a BC include network nodes, blocks, and consensus methodologies. These components all possess critical characteristics that can be designed and implemented in a variety of different ways. A central thesis here is that the choice of the design methodologies has direct and varying impact with regard to resulting quality attributes such as performance, security, and availability. We describe the use of a tradeoff matrix during the initial design phase of a development cycle that identifies the quality attributes to be evaluated when designing software systems comprising a BC. We hypothesize that consideration of the quality attributes at this initial design stage via the use of the proposed tradeoff matrix enables designers to meet requirements more efficiently and accurately. This hypothesis is tested and the use of the tradeoff matrix is demonstrated by creating a consensus algorithm whose performance is evaluated through a simulation that compares the behaviour in a “bare-metal” versus a Cloud-based environment. This simulation approach drives the usage of one of the quality tradeoff parameters in achieving a more optimal solution.

Keywords: Blockchain (BC); Consensus; Quality Attributes; Design Tradeoffs; Software Development.

Download Full Text

Paper #3

E-mobile Acceptance Using Unified Theory of Acceptance and Use of Technology (UTAUT): Research on Universities in Jordan

Saleem Issa Al-Zoubi and Maaruf Ali

Abstract: An investigation into the variables that have a bearing on the acceptance of D-learning (Digital-learning) services such as E-learning and M-learning, in Jordanian universities is presented. This is followed with a discussion on modernising M-learning with emerging technologies. The study fuses the Unified Theory of Acceptance and Use of Technology (“UTAUT”) model with the cultural paradigm and educational variables. 100 valid questionnaires distributed to random Jordanian students in two cities were used to collect the primary data. The IBM SPSS® (Statistical Package for the Social Sciences) software platform was used to analyse the data. The validity of the overall model was proven statistically with an acceptable fit of the data to the measurement model. The findings show that the factor with the highest direct effect on “Intention to use M-learning” is the “Attitude toward using M-learning”. Whilst the factor with the highest indirect effect on “Intention to use M-learning” is “Compatibility”. The conclusions are that the: cultural factor has a significant and positive impact on the “perceived usefulness” and “perceived ease of use”. “Perceived usefulness” and “perceived ease of use” have the greater impact on the “customers’ attitude”, which consequently influences the students’ “intention to use M-learning services”. The findings also indicate that educational variables such as the attainment value, self-management of learning and the perceived enjoyment significantly affected M-learning adoption intention. Emerging technologies such as the Cloud, AI (Artificial Intelligence) and the Blockchain and how they may be utilised to enhance the delivery of M-learning is discussed throughout the paper.

Keywords: Unified Theory of Acceptance and Use of Technology Model; UTAUT; D-learning; Mobile Learning Services; Mobile Learning; M-learning; Culture; E-learning.

Download Full Text

Paper #4

A Method of Body Parts Force Displacements Calculation of Metal-Cutting Machine Tools Using CAD and CAE Technologies

Taras Chetverzhuk, Oleg Zabolotnyi, Viktor Sychuk, Roman Polinkevych and Anatolii Tkachuk

Abstract: This paper describes a developed new method of body parts force displacements calculation of metal-cutting machine tools using combination of CAD and CAE technologies. It was carried out the analysis of analytical methods and the method of finite elements of body parts force displacements calculation of metal-cutting machine tools. On the basis of it the requirements to the method of calculation of compound errors of processing and deviations of the form of the processed surfaces due to deformations of the body parts of metal-cutting machines are established. The method of designing metal-cutting machines is grounded, which is based on mathematical modeling of different processes. It gives an opportunity to evaluate the accuracy of the machine and the impact on it of the individual assembly already in the initial stages of designing. The calculation methodology was implemented using ANSYS finite element analysis. This technique was used in the calculations on the example of high-precision lathes.

Keywords: Structural Elements; Spindle; Calculation Scheme; Load; Rigidity; Finite Element Method; Deformation.

Download Full Text

Paper #5

Hardware Dynamic Memory Manager for Hard Real-Time Systems

Lukáš Kohútka, Lukáš Nagy and Viera Stopjaková

Abstract: This paper presents novel hardware architecture of dynamic memory manager providing memory allocation and deallocation operations that are suitable for hard real-time and safety-critical systems due to very high determinism of these operations. The proposed memory manager implements Worst-Fit algorithm for selection of suitable free block of memory that can be used by the external environment, e.g. CPU. The deterministic timing of the memory allocation and deallocation operations is essential for hard real-time systems. The proposed memory manager performs these operations in nearly constant time thanks to the adoption of hardware-accelerated max queue, which is a data structure that continuously provides the largest free block of memory in two clock cycles regardless of actual number or constellation of existing free blocks of memory. In order to minimize the overhead caused by implementing the memory management in hardware, the max queue was optimized by developing a new sorting architecture, called Rocket-Queue. The Rocket-Queue architecture as well as the whole memory manager is described in this paper in detail. The memory manager and the Rocket-Queue architecture were verified using simplified version of UVM and applying billions of randomly generated instructions as testing inputs. The Rocket-Queue architecture was synthesized into Intel FPGA Cyclone V with 100 MHz clock frequency and the results show that it consumes from 17,06% to 38,67% less LUTs than the existing architecture, called Systolic Array. The memory manager implemented in a form of a coprocessor that provides four custom instructions was synthesized into 28nm TSMC HPM technology with 1 GHz clock frequency and 0.9V power supply. The ASIC synthesis results show that the Rocket-Queue based memory manager can occupy up to 24,59% smaller chip area than the Systolic Array based manager. In terms of total power consumption, the Rocket-Queue based memory manager consumes from 15,16% to 42,95% less power.

Keywords: Hard Real-Time; Dynamic Memory Management; SRAM; ASIC; Worst-Fit.

Download Full Text