applsci-logo

Journal Browser

Journal Browser

Software Engineering for Machine Learning Systems

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: closed (20 September 2022) | Viewed by 5059

Special Issue Editor


E-Mail Website
Guest Editor
Department of Validation Intelligence for Autonomous Software Systems, Simula Research Laboratory, 0164 Oslo, Norway
Interests: artificial intelligence; machine learning; autonomous systems; autonomous shipping; software engineering/V&V
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

There has been growing interest regarding integrating machine learning (ML) into a wide range of software systems, from digital assistants to self-driving software. While the ML research community is rapidly progressing state-of-the-art ML technologies, such as deep learning, vision, speech, and NLP, building software systems that include these core ML technologies (also known as ML systems) can be challenging.

Specifically, developing ML systems requires compliance with the complex ML workflow, which includes several stages, such as ML model requirements, data collection, data cleaning, data labeling, feature engineering, model training, model evaluation, model deployment, and model monitoring. Because of this complexity, traditional software engineering (SE) practices need to evolve to support the effective development of ML systems.

Furthermore, ML systems are highly data-dependent and often prone to model drift (or decay), caused by changes in the model environment. There are two types of model drift: concept drift, where the joint distribution of the model’s inputs and outputs changes, and data drift, where the distribution of the model’s input changes. Both types, if not detected and handled properly, can significantly decrease the ML model’s prediction performance.

The purpose of this Special Issue is to present advancements in the area of software engineering for the development of machine learning systems.

Topics of interest include, but are not limited to, the following:

  • Methods for supporting ML system engineering at different stages of the ML workflow (model requirements, data collection, data cleaning, data labeling, feature engineering, model training, model evaluation, model deployment, and model monitoring).
  • Requirement engineering for ML systems.
  • Verification and validation methods for ML systems.
  • Empirically validated studies of applying SE methods for the development of ML systems.
  • Systematic reviews of the state-of-the-art and state of practice in software engineering for designing, developing, deploying, operating, maintaining, and evolving ML systems.

Dr. Dusica Marijan
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • software engineering for machine learning: techniques, methods, and tools
  • autonomous systems
  • self-managing systems
  • socio-technical systems
  • human aspects of software engineering for machine learning
  • trust and trustworthiness
  • artificial intelligence systems
  • artificial intelligence system engineering
  • human-centered AI

Published Papers (2 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Jump to: Review

16 pages, 5632 KiB  
Article
A Bug Triage Technique Using Developer-Based Feature Selection and CNN-LSTM Algorithm
by Jeongmin Jang and Geunseok Yang
Appl. Sci. 2022, 12(18), 9358; https://doi.org/10.3390/app12189358 - 18 Sep 2022
Cited by 3 | Viewed by 2036
Abstract
With an increase in the use of software, the incidence of bugs and resulting maintenance costs also increase. In open source projects, developer reassignment accounts for approximately 50%. Software maintenance costs can be reduced if appropriate developers are recommended to resolve bugs. In [...] Read more.
With an increase in the use of software, the incidence of bugs and resulting maintenance costs also increase. In open source projects, developer reassignment accounts for approximately 50%. Software maintenance costs can be reduced if appropriate developers are recommended to resolve bugs. In this study, features are extracted by applying feature selection for each developer. These features are entered into CNN-LSTM algorithm to learn the model and recommend appropriate developers. To compare the performance of the proposed model, open source projects (Google Chrome, Mozilla Core, and Mozilla Firefox) were used to compare the performance of the proposed method with a baseline for developer recommendation. In this paper, the performance showed 54% for F-measure and 52% for accuracy in open source projects. The proposed model has improved and showed about a 13% more effective performance improvement than with DeepTriage. It was discovered that the performance of the proposed model was better. Full article
(This article belongs to the Special Issue Software Engineering for Machine Learning Systems)
Show Figures

Figure 1

Review

Jump to: Research

29 pages, 1327 KiB  
Review
Computational Methods for Neuron Segmentation in Two-Photon Calcium Imaging Data: A Survey
by Waseem Abbas and David Masip
Appl. Sci. 2022, 12(14), 6876; https://doi.org/10.3390/app12146876 - 7 Jul 2022
Cited by 2 | Viewed by 2506
Abstract
Calcium imaging has rapidly become a methodology of choice for real-time in vivo neuron analysis. Its application to large sets of data requires automated tools to annotate and segment cells, allowing scalable image segmentation under reproducible criteria. In this paper, we review and [...] Read more.
Calcium imaging has rapidly become a methodology of choice for real-time in vivo neuron analysis. Its application to large sets of data requires automated tools to annotate and segment cells, allowing scalable image segmentation under reproducible criteria. In this paper, we review and summarize the most recent methods for computational segmentation of calcium imaging. The contributions of the paper are three-fold: we provide an overview of the main algorithms taxonomized in three categories (signal processing, matrix factorization and machine learning-based approaches), we highlight the main advantages and disadvantages of each category and we provide a summary of the performance of the methods that have been tested on public benchmarks (with links to the public code when available). Full article
(This article belongs to the Special Issue Software Engineering for Machine Learning Systems)
Show Figures

Figure 1

Back to TopTop