Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

This study proposed a hybrid decision support method (ANN and Fuzzy_AHP) for heart failure prediction.The performance of the proposed method was examined using three performance metrics.From the evaluations results, the proposed method performed better than the conventional ANN approachThe proposed method would provide improved and realistic result for efficient therapy administration. Heart failure (HF) has been considered as one of the deadliest human diseases worldwide and the accurate prediction of HF risks would be vital for HF prevention and treatment. To predict HF risks, decision support systems based on artificial neural networks (ANN) have been widely proposed in previous studies. Generally, these existing ANN-based systems usually assumed that HF attributes have equal risk contribution to the HF diagnosis. However, several previous investigations have shown that the risk contributions of the attributes would be different. Thus the equal risk assumption concept associated with existing ANN methods would not properly reflect the diagnosis status of HF patients. In this study, the commonly used 13 HF attributes were considered and their contributions were determined by an experienced cardiac clinician. And Fuzzy analytic hierarchy process (Fuzzy_AHP) technique was used to compute the global weights for the attributes based on their individual contribution. Then the global weights that represent the contributions of the attributes were applied to train an ANN classifier for the prediction of HF risks in patients. The performance of the newly proposed decision support system based on the integration of ANN and Fuzzy_AHP methods was evaluated by using online clinical dataset of 297 HF patients and compared with that of the conventional ANN method. Our result shows that the proposed method could achieve an average prediction accuracy of 91.10%, which is 4.40% higher in comparison to that of the conventional ANN method. In addition, the newly proposed method also had better performance than seven previous methods that reported prediction accuracies in the range of 57.85-89.01%. The improvement of the HF risk prediction in the current study might be due to both the various contributions of the HF attributes and the proposed hybrid method. These findings suggest that the proposed method could be used to accurately predict HF risks in the clinic.

An integrated decision support system based on ANN and Fuzzy_AHP for heart failure risk prediction

Machine learning (ML) is used increasingly in real-world applications. In this paper, we describe our ongoing endeavor to define characteristics and challenges unique to Requirements Engineering (RE) for ML-based systems. As a first step, we interviewed four data scientists to understand how ML experts approach elicitation, specification, and assurance of requirements and expectations. The results show that changes in the development paradigm, i.e., from coding to training, also demands changes in RE. We conclude that development of ML systems demands requirements engineers to: (1) understand ML performance measures to state good functional requirements, (2) be aware of new quality requirements such as explainability, freedom from discrimination, or specific legal requirements, and (3) integrate ML specifics in the RE process. Our study provides a first contribution towards an RE methodology for ML systems.

Requirements Engineering for Machine Learning: Perspectives from Data Scientists

We describe a debugger that is being developed for distributed programs in Amoeba. A major goal in our work is to make the debugger independent of the Amoeba kernel. Our design integrates many facilities found in other debuggers, such as execution replay, breakpointing, and an event-based view of the execution of the target program. This paper discusses the influence of Amoeba's architecture on the attainability of our goals and the desired functionality of the debugger. We also consider such problems as how to deal with timeouts and interactions between the target program and its environment.

A distributed debugger for Amoeba

Recently, we witness a rapid increase in the use of machine learning in self-adaptive systems. Machine learning has been used for a variety of reasons, ranging from learning a model of the environment of a system during operation to filtering large sets of possible configurations before analysing them. While a body of work on the use of machine learning in self-adaptive systems exists, there is currently no systematic overview of this area. Such overview is important for researchers to understand the state of the art and direct future research efforts. This paper reports the results of a systematic literature review that aims at providing such an overview. We focus on self-adaptive systems that are based on a traditional Monitor-Analyze-Plan-Execute feedback loop (MAPE). The research questions are centred on the problems that motivate the use of machine learning in self-adaptive systems, the key engineering aspects of learning in self-adaptation, and open challenges. The search resulted in 6709 papers, of which 109 were retained for data collection. Analysis of the collected data shows that machine learning is mostly used for updating adaptation rules and policies to improve system qualities, and managing resources to better balance qualities and resources. These problems are primarily solved using supervised and interactive learning with classification, regression and reinforcement learning as the dominant methods. Surprisingly, unsupervised learning that naturally fits automation is only applied in a small number of studies. Key open challenges in this area include the performance of learning, managing the effects of learning, and dealing with more complex types of goals. From the insights derived from this systematic literature review we outline an initial design process for applying machine learning in self-adaptive systems that are based on MAPE feedback loops.

Applying Machine Learning in Self-Adaptive Systems: A Systematic Literature Review

Use case model is normally used to model software requirement. Reverse engineering of the high-level requirement model from the source code of target system is an important way to promote the program comprehension. In this paper, an approach of discovering and mining the use case model from the source code of object-oriented software is presented. Based on dynamic information, which could be obtained based on instrumentation techniques during the execution of target system, the approach discovers the basic use cases by specifying the beginning methods of method calling sequences of the dynamic information, and then utilizes some rules to mine the relations among basic use cases to build the whole use case model. This approach has been implemented in the XDRE (XiDian reverse engineering) tool. At the end a case study is provided to show the accuracy and usefulness of discovered use case model.

Discovering and Mining Use Case Model in Reverse Engineering

Planning a suitable solution to adapt to software changes is the most important and fundamental ability of self-adaptive software (SAS). However, with the increasing complexities of managed resources, context and user preferences, existing self-adaptive planning approaches need to be improved to deal with the complex changes which are multiple, interrelated and evolving. Search-based optimization (SBO) is well-suited to deal with multiple and complex problems. Hence, using SBO as a new self-adaptive planning approach may be a particularly promising research trajectory. This paper proposes a multi-agent framework for SAS with SBO to deal with complex changes, reduce maintenance time and cost, and enhance software quality. This framework defines a special software architecture of SAS to choose different planning approaches, uses the SBO to plan solutions for complex changes, and supports the online planning by multi agents. In addition, a corresponding workbench is being established to develop SAS according to this framework.

A Multiagent-Based Framework for Self-Adaptive Software with Search-Based Optimization

The paper gives an overview of a Ph.D. thesis and describes the main contents of the thesis. The thesis makes research on reverse engineering of object-oriented software at source codes level. According to the dynamic property of object-oriented software system, a group of models, mechanisms and algorithms that can be used to extract dynamic information and abstract high-level models of such systems are provided in the thesis. A group of systematic experiments are also conducted in the thesis so as to verify the correctness, validity and other related performance of these dynamic model design recovery and architecture abstraction algorithms.

Dynamic model design recovery and architecture abstraction of object oriented software

This paper provides a kind of agent wrapper mechanism used in legacy system integration First, it presents the agent-based system integration hierarchy model, which, according to the abstract level from low to high, is divided into inheritance function unit layer, agent capability component layer, agent layer and multi-agent system (MAS) layer Then, it provides the wrapper agent model which includes agent capability component, agent definition file and agent template code The capability component wraps the inheritance function unit The loosely coupled wrapper mechanism decouples the agent capability representation and implementation It is flexible for users to wrap the inheritance function units to be an agent and develop a new agent

An Agent Based Wrapper Mechanism Used in System Integration

The growth of scale and complexity of software as well as the complex environment with high dynamic lead to the uncertainties in self-adaptive software’s decision making at run time. Self-adaptive software needs the ability to avoid negative effects of uncertainties to the quality attributes of the software. However, existing planning methods cannot handle the two types of runtime uncertainties caused by complexity of system and running environment. This paper proposes a planning method to handle these two types of runtime uncertainties based on reinforcement learning. To handle the uncertainty from the system, the proposed method can exchange ineffective self-adaptive strategies to effective ones according to the iterations of execution effects at run time. It can plan dynamically to handle uncertainty from environment by learning knowledge of relationship between system states and actions. This method can also generate new strategies to deal with unknown situations. Finally, we use a complex distributed e-commerce system, Bookstore, to validate the ability of proposed method.

Qingshan Li

Papers

Discovering and Mining Use Case Model in Reverse Engineering

A Multiagent-Based Framework for Self-Adaptive Software with Search-Based Optimization

Dynamic model design recovery and architecture abstraction of object oriented software

An Agent Based Wrapper Mechanism Used in System Integration

Using Reinforcement Learning to Handle the Runtime Uncertainties in Self-adaptive Software