sensors-logo

Journal Browser

Journal Browser

Machine Learning Applications to Sensing, Internet of Things, and Imaging

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Sensing and Imaging".

Deadline for manuscript submissions: closed (15 May 2022) | Viewed by 1927

Special Issue Editors


E-Mail Website
Guest Editor
Department of Computer Science and Engineering, Oakland University, 318 Meadow Brook Rd, Rochester, MI 48309, USA
Interests: data mining; machine learning; healthcare computing; information and network security; graph databases

E-Mail Website
Guest Editor
School of Computing, College of Computing and Digital Media, DePaul University, 2400 N Sheffield Ave, Chicago, IL 60614, USA
Interests: biomedical and health informatics; medical imaging; computer vision; data mining; machine learning

Special Issue Information

Dear Colleagues,

The 20th IEEE International Conference on Machine Learning and Applications (ICMLA 2021) will be held on 13–16 December, Pasadena, CA, USA (https://www.icmla-conference.org/icmla21/index.html).

The aim of the conference is to bring researchers working in the areas of machine learning and applications together. The conference will cover both theoretical and experimental research results. Submission of machine learning papers describing machine learning applications in fields such as medicine, biology, industry, manufacturing, security, education, virtual environments, game playing, and problem-solving is strongly encouraged.

The main topics of this Special Issue include but are not limited to:

  • General machine learning (reinforcement learning, feature selection, etc.);
  • Deep learning (neural network models, deep reinforcement learning, etc.);
  • Machine learning performance and optimization;
  • Probabilistic inference (Bayesian methods, graphical models, Monte Carlo methods, etc.);
  • Trustworthy machine learning (security, privacy, adversarial learning, etc.);
  • Applications (gaming, problem-solving, virtual environments, industry, manufacturing, homeland security, medicine, bioinformatics and system biology, healthcare, neuroscience, economics, business, social good, web, mobile data, time series data, multimedia data, natural language processing, data mining, information retrieval, knowledge discovery, etc.).

Contributions describing applications of machine learning (ML) techniques to real-world problems, interdisciplinary research involving machine learning, experimental and/or theoretical studies yielding new insights into the design of ML systems, and papers describing development of new analytical frameworks are also welcome. Extended versions of conference papers that show significant improvement (minimum of over 50%) can also be considered for publication in this Special Issue.

Prof. Dr. Guangzhi Qu
Prof. Dr. Daniela Raicu
Guest Editors

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. Sensors 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 2600 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.

Published Papers (1 paper)

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

Research

12 pages, 3009 KiB  
Article
Instance Segmentation Based on Improved Self-Adaptive Normalization
by Sen Yang, Xiaobao Wang, Qijuan Yang, Enzeng Dong and Shengzhi Du
Sensors 2022, 22(12), 4396; https://0-doi-org.brum.beds.ac.uk/10.3390/s22124396 - 10 Jun 2022
Cited by 5 | Viewed by 1303
Abstract
The single batch normalization (BN) method is commonly used in the instance segmentation algorithms. The batch size is concerned with some drawbacks. A too small sample batch size leads to a sharp drop in accuracy, but a too large batch may result in [...] Read more.
The single batch normalization (BN) method is commonly used in the instance segmentation algorithms. The batch size is concerned with some drawbacks. A too small sample batch size leads to a sharp drop in accuracy, but a too large batch may result in the memory overflow of graphic processing units (GPU). These problems make BN not feasible to some instance segmentation tasks with inappropriate batch sizes. The self-adaptive normalization (SN) method, with an adaptive weight loss layer, shows good performance in instance segmentation algorithms, such as the YOLACT. However, the parameter averaging mechanism in the SN method is prone to problems in the weight learning and assignment process. In response to such a problem, the paper proposes to replace the single BN with an adaptive weight loss layer in SN models, based on which a weight learning method is developed. The proposed method increases the input feature expression ability of the subsequent layers. By building a Pytorch deep learning framework, the proposed method is validated in the MS-COCO data set and Autonomous Driving Cityscapes data set. The experimental results prove that the proposed method is effective in processing samples independent from the batch size. The stable accuracy for all kinds of target segmentation is achieved, and the overall loss value is significantly reduced at the same time. The convergence speed of the network is also improved. Full article
Show Figures

Figure 1

Back to TopTop