The past few decades have seen software and hardware growing more heterogeneous and layered in abstractions. This trend produced many benefits for hiding complexity and increasing efficiency and modularity. But it also makes reasoning about performance and identifying its underlying factors more challenging because of the presence of performance variability. Moreover, performance variability can prevent synchronous applications from scaling and server applications from meeting service-level agreements.

In modern computing environments, users may have multiple systems accessible to them such as local clusters, private clouds, or public clouds. This abundance of choices makes it difficult for users to select the system and configuration for running an application that best meet their performance and cost objectives. To assist such users, we propose a prediction tool that predicts the full performance-cost trade-off space of an application across multiple systems. Our tool runs and profiles a submitted application on a small number of configurations from some of the systems, and uses that information to predict the application's performance on all configurations in all systems. The prediction models are trained offline with data collected from running a large number of applications on a wide variety of configurations. Notable aspects of our tool include: providing different scopes of prediction with varying online profiling requirements, automating the selection of the small number of configurations and systems used for online profiling, performing online profiling using partial runs thereby make predictions for applications without running them to completion, employing a classifier to distinguish applications that scale well from those that scale poorly, and predicting the sensitivity of applications to interference from other users. We evaluate our tool using 69 data analytics and scientific computing benchmarks executing on three different single-node CPU systems with 8–9 configurations each and show that it can achieve low prediction error with modest profiling overhead.

The normalized cross-correlation coefficient is a standard metric that can be used to evaluate the relation of one vector with another. In machine learning and as part of feature selection, the coefficient can be used to evaluate the importance of each feature in relation to the required output. This work aims to utilize this coefficient or similar feature importance indicators to improve the accuracy of a neural network by first computing the corresponding coefficient of each of the input features with the required output and then by creating a specialized network layer that can be used to improve the accuracy of the network. The specialized and novel layer requires adding a number of parameters that depends on the number of input features to the network. These parameters are optimized through the learning algorithm utilized by the network. The proposed layer guides the network to perform better with little effect on the computational cost by initially weighing each feature according to its importance such as the correlation. It is possible to use meaningful coefficients such as the Pearson correlation, the Spearman coefficient or others. The results indicate a consistently enhanced performance with the accuracy gain often exceeding 1% to more than 5% in some cases. The work considers several types of data including regression datasets, multi-output and convolutional neural networks related problems with concentration on binary classification datasets.

The current landmine clearance methods mostly rely on the manual use of metal detectors (MDs) and on the deminer’s experience in differentiating between the sounds emitted due to the presence of a landmine or of harmless clutter. This process suffers from high false-alarm rates, which renders the demining effort slow and costly. In this paper, we report our attempts in using machine learning for decision making in the demining process. We have created our own database of the MD responses corresponding to landmines and/or clutter. A robotic rail is designed and assembled to accurately measure these responses and build the database. Several machine learning models are then developed using the database with the aim of detecting the presence of landmines and classifying them. It is shown that the classification algorithms lead to accurately discriminating the landmines and distinguishing between different buried objects including mines or other items based on the metal detector delivered data or signature.

A weighted mean square error (WMSE) approach to optimising digital filters is delineated. It is applied in the current work to optimising the classical Al‐Alaoui IIR differentiators to obtain new improved wideband differentiators of varying orders. These can be directly used for analog to digital conversion and in many digital signal processing applications. The weighted MSE approach is motivated by the Al‐Alaoui WMSE approach to pattern recognition. In addition, the differentiators are converted to integrators of similar orders that are further optimised. Various examples and comparisons are presented to demonstrate the viability of the proposed approach.