Machine Learning Systems and Intelligent Applications

A software engineering perspective on engineering machine learning systems: State of the art and challenges

“…While Anderson [48] emphasizes the paramount significance of data modeling in engineering data-intensive systems that are scalable, robust, and efficient, de Souza Nascimento et al [P12] state the difficulty of succeeding in doing this. Benton [54] proposes an architecture for an ML system that deals with high-volume data. This architecture includes a component for data federation to deal with structured, unstructured, and streaming data.…”

“…Therefore, we need a holistic view of engineering softwareintensive systems with ML capabilities (ML systems) in real-world settings. Many researchers from software engineering (SE) [18], [23] and ML [20], [21], as well as industry practitioners [19], [22], [54], have stated the requirement of such a holistic view.…”

Bias and ethical considerations in machine learning and the automation of perioperative risk assessment

“…Underlying populations, decision, and outcome characteristics can change over time leading to concept drift, such that the original mappings of features to outcomes become less and less valid, and require updated training cycles to maintain accuracy and fairness. 15…”

A Novel Approach for Fault Detection in Integrated Navigation Systems

“…(4). The unbiased estimates of innovation ˆk r can be obtained by machine learning [26][27][28][29], such as Gaussian process regression (GPR) [30], support vector regression (SVR), neural network (NN) and so on. Users can freely choose their familiar way of algorithm to realize the fast fault detection.…”