Abstract
In this work, we develop a polymorphic record calculus with extensible records. Extensible records are records that can have new fields added to them, or preexisting fields removed from them. We also develop a static type system for this calculus and a sound and complete type inference algorithm. Most ML-style polymorphic record calculi that support extensible records are based on row variables. We present an alternative construction based on the polymorphic record calculus developed by Ohori. Ohori based his polymorphic record calculus on the idea of kind restrictions. This allowed him to express polymorphic operations on records such as field selection and modification. With the addition of extensible types, we were able to extend Ohori’s original calculus with other powerful operations on records such as field addition and removal.

Abstract
This paper presents the approach and results of an improvement project carried on by a company that provides business process outsourcing services based on customised software solutions. The critical objectives considered were to increase the efficiency and effectiveness of the processes involved in developing customised solutions. Thus, the focus of this research was to identify problems in current processes and practices and develop possible solutions to improve. The processes were mapped, the inefficiencies were identified, and suggestions for improvements were presented and analysed. It was concluded that the main problems with the project management and software development processes are related to the lack of visibility of the team load, lack of standardisation and inefficient management processes. These causes result in problems such as IT being unable to plan work and problems associated with quality that negatively influence the lead time of projects. Therefore, suggestions for improvement were formulated and prioritised to address each of these aspects. A more agile approach to software development and redesigning the processes for creating customised solutions were the solutions developed. There was also a need to develop the existing project management software changes to adapt it to these changes. © IEOM Society International.

Abstract
Real time series sometimes exhibit various types of "irregularities": missing observations, observations collected not regularly over time for practical reasons, observation times driven by the series itself, or outlying observations. However, the vast majority of methods of time series analysis are designed for regular time series only. A particular case of irregularly spaced time series is that in which the sampling procedure over time depends also on the observed values. In such situations, there is stochastic dependence between the process being modelled and the times of the observations. In this work, we propose a model in which the sampling design depends on all past history of the observed processes. Taking into account the natural temporal order underlying available data represented by a time series, then a modelling approach based on evolutionary processes seems a natural choice. We consider maximum likelihood estimation of the model parameters. Numerical studies with simulated and real data sets are performed to illustrate the benefits of this model-based approach.

Abstract

Abstract
Throughout this paper it is presented a novel elastic joint configuration, being compared with other similar joints found in recent literature. It is presented its modeling, being its estimation process developed offline, based on a proposed experimental setup. This setup enables to monitor and collect data from an absolute encoder and a load cell. Some data obtained from these sensors is then graphically represented, like angle and torque, obtaining some parameters. Finally, through an optimization process, where the error of the angle is minimized, the remaining parameters of the joint are estimated, thus obtaining a realistic model of the system. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021.

Abstract
Due to convenience and usability, many deep learning (DL) jobs resort to the available shared parallel file system (PFS) for storing and accessing training data when running in HPC environments. Under such a scenario, however, where multiple I/O-intensive applications operate concurrently, the PFS can quickly get saturated with simultaneous storage requests and become a critical performance bottleneck, leading to throughput variability and performance loss. We present MONARCH, a framework-agnostic middleware for hierarchical storage management. This solution leverages the existing storage tiers present at modern supercomputers (e.g., compute node's local storage, PFS) to improve DL training performance and alleviate the current I/O pressure of the shared PFS. We validate the applicability of our approach by developing and integrating an early prototype with the TensorFlow DL framework. Results show that MONARCH can reduce I/O operations submitted to the shared PFS by up to 45%, decreasing training time by 24% and 12%, for I/O-intensive models, namely LeNet and AlexNet.