Search

This study focuses on the detection of seeded porosity during metal additive manufacturing by employing convolutional neural networks (CNN). The aim of the study is to demonstrate the application of Machine Learning (ML) in in-process monitoring. Laser Powder Bed Fusion (LPBF) is a selective laser melting technique used to build complex 3D parts. The current monitoring system in LPBF is inadequate to produce safety-critical parts due to the lack of automated processing of collected data. To assess the efficacy of applying ML to defect detection in LPBF by in-process images, a range of synthetic defects have been designed into cylindrical artefacts to mimic porosity occurring in different locations, shapes, and sizes. Empirical analysis has revealed insights into the importance of accurate labelling strategies required for data-driven solutions. Two labelling strategies based on the computer aided design (CAD) file and X-ray computed tomography (XCT) scan data was formulated. A novel CNN was trained from scratch and optimised by selecting the best values of an extensive range of hyper-parameters by employing Hyperband tuner. The accuracy of the model was 90% when trained using a CAD-assisted labelling, and 97% when using XCT-assisted labelling. The model successfully spotted pores as small as 0.2mm. Experiments revealed that balancing the data set improved the model's precision from 89% to 97% and recall from 85% to 97% when compared to training on an imbalanced data set. We strongly believed that the proposed model would significantly reduce post-processing cost and provide a better base model network for transfer learning of future ML models aimed at LPBF micro-defects detection.

Behavioural biometrics have the potential to provide an additional or alternative authentication mechanism to those involving a shared secret (i.e. a password). Keystroke timings are the focus of this study, where key press and release timings are acquired whilst monitoring a user typing a known phrase. Many studies exist in keystroke biometrics, but there is an absence of literature aiming to understand the relationship between characteristics of password policies and the potential of keystroke biometrics. Furthermore, benchmark datasets used in keystroke biometric research do not enable useful insights into the relationship between their capability and password policy. Herein, substitutions of uppercase, numeric, special characters, and their combination of passwords derived from English words are considered. Timings for 42 participants for the same 40 passwords are acquired. A matching system using the Manhattan distance measure with seven different feature sets is implemented, culminating in an Equal Error Rate of between 6% and 11% and accuracy values between 89% and 94%, demonstrating comparable accuracy to other threshold‐based systems. Further analysis suggests that the best feature sets are those containing all timings and trigraph press to press. Evidence also suggests that phrases containing fewer characters have greater accuracy, except for those with special character substitutions.

This work focuses on the problem of constructing accurate prediction models using an adaptive neuro-fuzzy inference system (ANFIS) from data that are scarce and poorly scaled. Many real-world problems have limited data to work with and yet require models with high prediction accuracy. Due to the fuzzy nature of many data sets, it is appropriate to construct prediction models using fuzzy inference systems (FIS), rather than traditional artificial neural network (ANN) models. However, the scarcity of the data raises serious concerns when attempting to construct models of this type. In this paper, we address the problem of constructing accurate prediction models using ANFIS in circumstances where capturing large amounts of data is difficult. We propose a new approach, using robust data expansion methods to enhance the data carefully. This approach provides the learning algorithm with enough representative data to allow all of the parameters (premise and consequent) to be optimised. We compare and contrast the effectiveness in reducing prediction error for three specific expansion models using radial basis function (RBF) kernels. When expanding data, for which the underlying smoothness properties are not known, there is often a danger of over-smoothing. This is usually noticeable at turning points and can occur when fitting the data using polynomials or cubic splines for example. To avoid over-smoothing, we introduce a modified multiquadric approach that allows smooth, near-interpolation while maintaining the desirable shape-preserving properties of the data. The proposed method is explained through two case studies — the first to predict gasoline consumption for the oil/fuel industry in Iraq and the second for predicting natural gas consumption in Iran. This is the first study that uses adjustable, shape-preserving re-sampling methods for optimising ANFIS models in low data environments.

SCADA (Supervisory Control and Data Acquisition) systems are a critical part of modern national critical infrastructure (CI) systems. Due to the rapid increase of sophisticated cyber threats with exponentially destructive effects, intrusion detection systems (IDS) must systematically evolve. Specific intrusion detection systems that reassure both high accuracy, low rate of false alarms and decreased overhead on the network traffic must be designed for SCADA systems. In this book chapter we present a novel IDS, namely K-OCSVM, that combines both the capability of detecting novel attacks with high accuracy, due to its core One-Class Support Vector Machine (OCSVM) classification mechanism and the ability to effectively distinguish real alarms from possible attacks under different circumstances, due to its internal recursive k-means clustering algorithm. The effectiveness of the proposed method is evaluated through extensive simulations that are conducted using realistic datasets extracted from small and medium sized HTB SCADA testbeds.

Ransomware is a continuing threat and has resulted in the battle between the development and detection of new techniques. Detection and mitigation systems have been developed and are in wide-scale use; however, their reactive nature has resulted in a continuing evolution and updating process. This is largely because detection mechanisms can often be circumvented by introducing changes in the malicious code and its behaviour. In this paper, we demonstrate a classification technique of integrating both static and dynamic features to increase the accuracy of detection and classification of ransomware. We train supervised machine learning algorithms using a test set and use a confusion matrix to observe accuracy, enabling a systematic comparison of each algorithm. In this work, supervised algorithms such as the Naive Bayes algorithm resulted in an accuracy of 96% with the test set result, SVM 99.5%, random forest 99.5%, and 96%. We also use Youden’s index to determine sensitivity and specificity.

The evolution in precision manufacturing has resulted in the requirement to produce and maintain more accurate machine tools. This new requirement coupled with desire to reduce machine tool downtime places emphasis on the calibration procedure during which the machine’s capabilities are assessed. Machine tool downtime is significant for manufacturers because the machine will be unavailable for manufacturing use, therefore wasting the manufacturer’s time and potentially increasing lead-times for clients. In addition to machine tool downtime, the uncertainty of measurement, due to the schedule of the calibration plan, has significant implications on tolerance conformance, resulting in an increased possibility of false acceptance and rejection of machined parts. The work presented in this paper is focussed on expanding a developed temporal optimisation model to reduce the uncertainty of measurement. Encoding the knowledge in regular PDDL requires the discretization of non-linear, continuous temperature change and implementing the square root function. The implementation shows that not only can domainindependent automated planning reduce machine downtime by 10.6% and the uncertainty of measurement by 59%, it is also possible to optimise both metrics reaching a compromise that is on average 9% worse that the best-known solution for each individual metric.

It is well established that file system permissions in large, multi-user environments can be audited to identify vulnerabilities with respect to what is regarded as standard practice. For example, identifying that a user has an elevated level of access to a system directory which is unnecessary and introduces a vulnerability. Similarly, the allocation of new file system permissions can be assigned following the same standard practices. On the contrary, and less well established, is the identification of potential vulnerabilities as well as the implementation of new permissions with respect to a system's current access control implementation. Such tasks are heavily reliant on expert interpretation. For example, the assigned relationship between users and groups, directories and their parents, and the allocation of permissions on file system resources all need to be carefully considered.\ud \ud This paper presents the novel use of statistical analysis to establish independence and homogeneity in allocated file system permissions. This independence can be interpreted as potential anomalies in a system's implementation of access control. The paper then presents the use of instance-based learning to suggest the allocation of new permissions conforming to a system's current implementation structure. Following this, both of the presented techniques are then included in a tool for interacting with Microsoft's New Technology File System (NTFS) permissions. This involves experimental analysis on six different NTFS directory structures within different organisations. The effectiveness of the developed technique is then established through analysing the true positive and true negative values. The presented results demonstrate the potential of the proposed techniques for overcoming complexities with real-world file system administration

Machine tool owners require knowledge of their machine’s capabilities, and the emphasis increases with\ud areas of high accuracy manufacturing. An aspect of a machine’s capability is its geometric accuracy. International\ud Standards and best-practice guides are available to aid understanding of the required measurements\ud and to advise on how to perform them. However, there is an absence of any intelligent method\ud capable of optimising the duration of a calibration plan, minimising machine down-time. In this work,\ud artificial intelligence in the form of automated planning is applied to the problem of machine tool\ud pseudo-static geometric error calibration. No prior knowledge of Artificial Intelligence (AI) planning is\ud required throughout this paper. The authors have written this paper for calibration engineers to see\ud the benefits that automated planning can provide. Two models are proposed; the first produces a sequential\ud calibration plan capable of finding the optimal calibration plan. The second model has the additional\ud possibility of planning for concurrent measurements, adding the possibility of further reducing machine\ud down-time. Both models take input regarding a machine’s configuration and available instrumentation.\ud The efficacy of both models is evaluated by performing a case study of a five-axis gantry machine,\ud whereby calibration plans are produced and compared against both an academic and industrial expert.\ud From this, the effectiveness of this novel method for producing optimal calibration plan is evaluated,\ud stimulating potential for future work.

The reliance on expert knowledge—required for analysing security logs and performing security audits—has created an unhealthy balance, where many computer users are not able to correctly audit their security configurations and react to potential security threats. The decreasing cost of IT and the increasing use of technology in domestic life are exacerbating this problem, where small companies and home IT users are not able to afford the price of experts for auditing their system configuration. In this paper, we present GraphBAD, a graph-based analysis tool that is able to analyse security configurations in order to identify anomalies that could lead to potential security risks. GraphBAD, which does not require any prior domain knowledge, generates graph-based models from security configuration data and, by analysing such models, is able to propose mitigation plans that can help computer users in increasing the security of their systems. A large experimental analysis, conducted on both publicly available (the well-known KDD dataset) and synthetically generated testing sets (file system permissions), demonstrates the ability of GraphBAD in correctly identifying security configuration anomalies and suggesting appropriate mitigation plans.

In this paper we are interested in the approximation of continuous surface texture profiles defined only at discretely obtained points. A continuous representation is required in order to be able to apply filtration methods that assume uniform data spacing to practical data that in general is not uniformly spaced. By reconstructing surface profiles as natural cubic spline interpolants accurately using numerically stable fitting algorithms, we can provide a mathematically sound basis on which to compute surface texture profile parameters. As an important direct benefit, parameters involving the integrals of surface profiles can be calculated directly from the spline interpolant. Examples are given to illustrate the advantages of using this reconstruction method.

Planning as satisfiability is one of the main approaches to finding parallel optimal solution plans for classical planning problems. Existing high performance SAT-based planners are able to exploit either forward or backward search\ud strategy; starting from an underestimation or overestimation of the optimal plan length, they keep increasing or decreasing the estimated plan length and, for each fixed length, they either find a solution or prove the nsatisfiability of the corresponding SAT instance.\ud In this paper we will discuss advantages and disadvantages of the underestimating and overestimating techniques, and we will propose an effective online decision system for selecting the most appropriate technique for solving a given planning problem. Finally, we will experimentally show that the exploitation of such a decision system improves the performance of the well known SAT-based planner SatPlan.

Administrating and monitoring New Technology File System (NTFS) permissions can be a cumbersome and convoluted task. In today’s data rich world there has never been a more important time to ensure that data is secured against unwanted access. This paper identifies the essential and fundamental requirements of access control, highlighting the main causes of their misconfiguration within the NTFS. In response, a number of features are identified and an efficient, informative and intuitive software-based solution is proposed for examining file system permissions. In the first year that the software has been made freely available it has been downloaded and installed by over four thousand users1.

—In this paper, we present a Monte-Carlo policy rollout technique (called MOCART-CGA) for path planning in dynamic and partially observable real-time environments such as Real-time Strategy games. The emphasis is put on fast action selection motivating the use of Monte-Carlo techniques in MOCART-CGA. Exploration of the space is guided by using corridors which direct simulations in the neighbourhood of the best found moves.\ud \ud MOCART-CGA limits how many times a particular stateaction pair is explored to balance exploration of the neighbourhood of the state and exploitation of promising actions. MOCART-CGA is evaluated using four standard pathfinding benchmark maps, and over 1000 instances. The empirical results show that MOCART-CGA outperforms existing techniques, in terms of search time, in dynamic and partially observable environments. Experiments have also been performed in static (and partially observable) environments where MOCARTCGA still requires less time to search than its competitors, but typically finds lower quality plans.

This paper introduces a novel path planning technique called MCRT which is aimed at non-deterministic, partially known, real-time domains populated with dynamically moving obstacles, such as might be found in a real-time strategy (RTS) game. The technique combines an efficient form of Monte-Carlo tree search with the randomized exploration capabilities of rapidly exploring random tree (RRT) planning. The main innovation of MCRT is in incrementally building an RRT structure with a collision-sensitive reward function, and then re-using it to efficiently solve multiple, sequential goals. We have implemented the technique in MCRT-planner, a program which solves non-deterministic path planning problems in imperfect information RTS games, and evaluated it in comparison to four other state of the art techniques. Planners embedding each technique were applied to a typical RTS game and evaluated using the game score and the planning cost. The empirical evidence demonstrates the success of MCRT-planner.

In this work, we explore two Monte-Carlo planning approaches: Upper Confidence Tree (UCT) and Rapidlyexploring Random Tree (RRT). These Monte-Carlo planning approaches are applied in a real-time strategy game for solving the path finding problem. The planners are evaluated using a grid-based representation of our game world. The results show that the UCT planner solves the path planning problem with significantly less search effort than the RRT planner. The game playing performance of each planner is evaluated using the mean, maximum and minimum scores in the test games. With respect to the mean scores, the RRT planner shows better performance than the UCT planner. The RRT planner achieves more maximum scores than the UCT planner in the test games.

This paper is concerned with addressing the problems experienced with the thermo-elastic behaviour of the disc - that of optimum heat dissipation, and equally important, even heating of the disc blade. The primary objective is to develop a more temperature-stable brake disc.\ud The work presented approaches the problems of thermal judder through benchmarking the current situation. This is approached by modelling the current brake and its validation by means of vehicle and laboratory testing. The empirical work is centred on a bespoke high speed brake dynamometer which incorporates the full vehicle suspension for an accurate yet controlled simulation of brake and vehicle operating conditions. The dynamometer is housed in a purpose built laboratory with both CCTV and direct visual access. It is capable of dynamic measurement of DTV, caliper pressure fluctuations, disc surface temperature and vibration measurements at discrete points about the rig. This information is presented and supported by thermal imaging of the brake during a heavy brake application and subsequent thermal judder. The results also include surface scanning of the disc which is carried out at appropriate stages during testing to identify disc deformation including disc warping, “ripple” and the effects of “hot spotting”.\ud Disc run-out measurements via non-contacting displacement transducers show the disc taking up varying orders of deformation ranging from first to third order during high speed testing. The state of cold deformation of the disc is also shown to vary with the disc returning to first or second order deformation upon cooling.\ud Thermal images of the brake disc have shown vane patterns to show through to the disc surface identifying uneven heat distribution.

Many commercial measurement processes are planned with little or no regard to optimality in terms of measurement time and the estimated uncertainty of measurement. This can be because the complexity of the planning problem makes optimality in a dynamic environment difficult to achieve, even with expert knowledge. This paper presents a novel approach to measurement planning using automated planning. Detailed information regarding the modelling and encoding of measurement processes are provided. The benefits of this approach are demonstrated through the results of applying it to machine tool calibration. A discussion is then formed around the development of future tools to further validate the approach.

Typically the design and production of metrology software is based upon a rigorous process of establishing the software requirements. Both the metrology and security requirements will be processed and normally evaluated in isolation, or at best simultaneously. With the use of cryptographic principles, and the more prominent object-oriented programming languages, a new security-centric philosophy to metrology software design and production is presented to provide secure, robust and functional metrology software.