Submit to Special Issue Submit Abstract to Special Issue Review for Sensors Propose a Special Issue

Journal Browser

► Journal Browser

Innovations in AI and ML-Based Techniques for Image and Video Analysis from Sensors

Special Issue Editors
Special Issue Information
Keywords
Published Papers

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

Deadline for manuscript submissions: 15 July 2024 | Viewed by 4967

Share This Special Issue

Special Issue Editors

Prof. Dr. Hwa-Young Jeong

E-Mail Website
Guest Editor

Humanitas College, Kyung Hee University, Seoul 130-701, Republic of Korea
Interests: image data processing; multimedia based e-learning system and services; conversion service with multimedia; big data analysis
Special Issues, Collections and Topics in MDPI journals

Dr. Neil Yuwen Yen

E-Mail Website
Guest Editor

School of Computer Science and Engineering, The University of Aizu, Aizu-Wakamatsu 965-8580, Japan
Interests: human-centric computing; big data; anticipatory computing
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Artificial intelligence (AI) and machine learning (ML) are revolutionizing the field of image and video analysis by enabling computers to automatically interpret and extract meaningful information from visual data. Image and video analysis from sensors refers to the process of analyzing visual data captured by various sensors, such as cameras or thermal imaging devices. The goal of this analysis is to extract meaningful information from the visual data, such as identifying objects, tracking or detecting motion. Here are some common AI and ML-based techniques used for image and video analysis from sensors: Object Detection and Recognition, Image and Video Classification, Semantic Segmentation, Object Tracking, Action Recognition, Image and Video Generation, and Video Summarization. Example is, AI and ML algorithms can be trained to detect and recognize objects of interest within images or videos. These algorithms can use deep neural networks, such as convolutional neural networks (CNNs), to accurately identify objects based on their features, shapes, and textures. Additionally, these algorithms can classify images or videos into different categories based on their content, and be trained using large datasets and various ML techniques, such as support vector machines (SVMs), decision trees, or deep learning algorithms, to achieve high accuracy in classifying visual data. Additionally, CNNs can be trained to perform semantic segmentation, enabling precise pixel-level understanding of visual data. Recently, the rapid advancement of AI and ML is opening up new possibilities for extracting valuable insights and information from visual data, leading to numerous applications in various fields such as healthcare, transportation, drone, education, entertainment, and security.

Within this context, we invite manuscripts for this Special Issue on image and video analysis from sensors using AI and ML. We encourage prospective authors to submit related distinguished research papers on the subject of both theoretical approaches and practical case reviews.

Topics of Interests:

Object detection and recognition techniques from sensors;
Object detection using AI and ML algorithms;
Object recognition and processing using AI and ML;
Image and Video Classification from sensors;
Video Classification using large datasets and ML;
Semantic Segmentation using AI and ML algorithms;
Medical imaging, robotics, and augmented reality from sensors;
Object Tracking from sensors;
Surveillance, video analysis, and robotics using AI and ML algorithms;
Video surveillance and video content analysis;
Action Recognition from sensors;
Human–computer interaction;
Image and Video Generation from sensors;
Generative adversarial networks (GANs) techniques;
Video Summarization.

Prof. Dr. Hwa-Young Jeong
Dr. Neil Yuwen Yen
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.

Keywords

object detection and recognition techniques
artificial intelligence
machine learning
image classification
video classification
semantic segmentation
medical imaging
robotics
augmented reality
human-computer interaction

Published Papers (6 papers)

Download All Papers

Research

20 pages, 2765 KiB

Open AccessArticle

An Intelligent Thermal Compensation System Using Edge Computing for Machine Tools

by Endah Kristiani, Lu-Yan Wang, Jung-Chun Liu, Cheng-Kai Huang, Shih-Jie Wei and Chao-Tung Yang

Sensors 2024, 24(8), 2531; https://0-doi-org.brum.beds.ac.uk/10.3390/s24082531 - 15 Apr 2024

Viewed by 353

Abstract

This paper focuses on the use of smart manufacturing in lathe-cutting tool machines, which can experience thermal deformation during long-term processing, leading to displacement errors in the cutting head and damage to the final product. This study uses time-series thermal compensation to develop a predictive system for thermal displacement in machine tools, which is applicable in the industry using edge computing technology. Two experiments were carried out to optimize the temperature prediction models and predict the displacement of five axes at the temperature points. First, an examination is conducted to determine possible variances in time-series data. This analysis is based on the data obtained for the changes in time, speed, torque, and temperature at various locations of the machine tool. Using the viable machine-learning models determined, the study then examines various cutting settings, temperature points, and machine speeds to forecast the future five-axis displacement. Second, to verify the precision of the models created in the initial phase, other time-series models are examined and trained in the subsequent phase, and their effectiveness is compared to the models acquired in the first phase. This work also included training seven models of WNN, LSTNet, TPA-LSTM, XGBoost, BiLSTM, CNN, and GA-LSTM. The study found that the GA-LSTM model outperforms the other three best models of the LSTM, GRU, and XGBoost models with an average precision greater than 90%. Based on the analysis of training time and model precision, the study concluded that a system using LSTM, GRU, and XGBoost should be designed and applied for thermal compensation using edge devices such as the Raspberry Pi. Full article

(This article belongs to the Special Issue Innovations in AI and ML-Based Techniques for Image and Video Analysis from Sensors)

► Show Figures

Figure 1

17 pages, 7552 KiB

Open AccessArticle

Securing Infrared Communication in Nuclear Power Plants: Advanced Encryption for Infrared Sensor Networks

by Tae-Jin Park, Ki-il Kim and Sangook Moon

Sensors 2024, 24(7), 2054; https://0-doi-org.brum.beds.ac.uk/10.3390/s24072054 - 23 Mar 2024

Viewed by 439

Abstract

This study enhances infrared communication security in nuclear power plants’ secondary systems, addressing the risk of mechanical and cyber failures. A novel random address generator, employing an innovative S-box, was developed to secure IoT sensor data transmissions to gateway nodes, mitigating eavesdropping, interference, and replay attacks. We introduced a structured IR communication protocol, generating unique, encrypted addresses to prevent unauthorized access. Key-dependent S-boxes, based on a compound chaotic map system, significantly improved encryption, increasing data transmission randomness and uniqueness. Entropy analysis and reduced duplicated addresses confirmed the effectiveness of our method, with the Hash-CCM algorithm showing the highest entropy and fewest duplicates. Integrating advanced cryptographic techniques into IR systems significantly enhances nuclear power plants’ security, contributing to the protection of critical infrastructure from cyber threats and ensuring operational integrity. Full article

(This article belongs to the Special Issue Innovations in AI and ML-Based Techniques for Image and Video Analysis from Sensors)

► Show Figures

Figure 1

23 pages, 10067 KiB

Open AccessArticle

Video Classification of Cloth Simulations: Deep Learning and Position-Based Dynamics for Stiffness Prediction

by Makara Mao, Hongly Va and Min Hong

Sensors 2024, 24(2), 549; https://0-doi-org.brum.beds.ac.uk/10.3390/s24020549 - 15 Jan 2024

Viewed by 691

Abstract

In virtual reality, augmented reality, or animation, the goal is to represent the movement of deformable objects in the real world as similar as possible in the virtual world. Therefore, this paper proposed a method to automatically extract cloth stiffness values from video scenes, and then they are applied as material properties for virtual cloth simulation. We propose the use of deep learning (DL) models to tackle this issue. The Transformer model, in combination with pre-trained architectures like DenseNet121, ResNet50, VGG16, and VGG19, stands as a leading choice for video classification tasks. Position-Based Dynamics (PBD) is a computational framework widely used in computer graphics and physics-based simulations for deformable entities, notably cloth. It provides an inherently stable and efficient way to replicate complex dynamic behaviors, such as folding, stretching, and collision interactions. Our proposed model characterizes virtual cloth based on softness-to-stiffness labels and accurately categorizes videos using this labeling. The cloth movement dataset utilized in this research is derived from a meticulously designed stiffness-oriented cloth simulation. Our experimental assessment encompasses an extensive dataset of 3840 videos, contributing to a multi-label video classification dataset. Our results demonstrate that our proposed model achieves an impressive average accuracy of 99.50%. These accuracies significantly outperform alternative models such as RNN, GRU, LSTM, and Transformer. Full article

(This article belongs to the Special Issue Innovations in AI and ML-Based Techniques for Image and Video Analysis from Sensors)

► Show Figures

Figure 1

16 pages, 2814 KiB

Open AccessArticle

An Autoscaling System Based on Predicting the Demand for Resources and Responding to Failure in Forecasting

by Jieun Park and Junho Jeong

Sensors 2023, 23(23), 9436; https://0-doi-org.brum.beds.ac.uk/10.3390/s23239436 - 27 Nov 2023

Viewed by 685

Abstract

In recent years, the convergence of edge computing and sensor technologies has become a pivotal frontier revolutionizing real-time data processing. In particular, the practice of data acquisition—which encompasses the collection of sensory information in the form of images and videos, followed by their transmission to a remote cloud infrastructure for subsequent analysis—has witnessed a notable surge in adoption. However, to ensure seamless real-time processing irrespective of the data volume being conveyed or the frequency of incoming requests, it is vital to proactively locate resources within the cloud infrastructure specifically tailored to data-processing tasks. Many studies have focused on the proactive prediction of resource demands through the use of deep learning algorithms, generating considerable interest in real-time data processing. Nonetheless, an inherent risk arises when relying solely on predictive resource allocation, as it can heighten the susceptibility to system failure. In this study, a framework that includes algorithms that periodically monitor resource requirements and dynamically adjust resource provisioning to match the actual demand is proposed. Under experimental conditions with the Bitbrains dataset, setting the network throughput to 300 kB/s and with a threshold of 80%, the proposed system provides a 99% performance improvement in terms of the autoscaling algorithm and requires only 0.43 ms of additional computational overhead compared to relying on a simple prediction model alone. Full article

(This article belongs to the Special Issue Innovations in AI and ML-Based Techniques for Image and Video Analysis from Sensors)

► Show Figures

Figure 1

16 pages, 6951 KiB

Open AccessArticle

Multi-Cat Monitoring System Based on Concept Drift Adaptive Machine Learning Architecture

by Yonggi Cho, Eungyeol Song, Yeongju Ji, Saetbyeol Yang, Taehyun Kim, Susang Park, Doosan Baek and Sunjin Yu

Sensors 2023, 23(21), 8852; https://0-doi-org.brum.beds.ac.uk/10.3390/s23218852 - 31 Oct 2023

Viewed by 1136

Abstract

In multi-cat households, monitoring individual cats’ various behaviors is essential for diagnosing their health and ensuring their well-being. This study focuses on the defecation and urination activities of cats, and introduces an adaptive cat identification architecture based on deep learning (DL) and machine learning (ML) methods. The architecture comprises an object detector and a classification module, with the primary focus on the design of the classification component. The DL object detection algorithm, YOLOv4, is used for the cat object detector, with the convolutional neural network, EfficientNetV2, serving as the backbone for our feature extractor in identity classification with several ML classifiers. Additionally, to address changes in cat composition and individual cat appearances in multi-cat households, we propose an adaptive concept drift approach involving retraining the classification module. To support our research, we compile a comprehensive cat body dataset comprising 8934 images of 36 cats. After a rigorous evaluation of different combinations of DL models and classifiers, we find that the support vector machine (SVM) classifier yields the best performance, achieving an impressive identification accuracy of 94.53%. This outstanding result underscores the effectiveness of the system in accurately identifying cats. Full article

(This article belongs to the Special Issue Innovations in AI and ML-Based Techniques for Image and Video Analysis from Sensors)

► Show Figures

Figure 1

12 pages, 1320 KiB

Open AccessArticle

Ensemble Approach to Combining Episode Prediction Models Using Sequential Circadian Rhythm Sensor Data from Mental Health Patients

by Taek Lee, Heon-Jeong Lee, Jung-Been Lee and Jeong-Dong Kim

Sensors 2023, 23(20), 8544; https://0-doi-org.brum.beds.ac.uk/10.3390/s23208544 - 18 Oct 2023

Viewed by 921

Abstract

Managing mood disorders poses challenges in counseling and drug treatment, owing to limitations. Counseling is the most effective during hospital visits, and the side effects of drugs can be burdensome. Patient empowerment is crucial for understanding and managing these triggers. The daily monitoring of mental health and the utilization of episode prediction tools can enable self-management and provide doctors with insights into worsening lifestyle patterns. In this study, we test and validate whether the prediction of future depressive episodes in individuals with depression can be achieved by using lifelog sequence data collected from digital device sensors. Diverse models such as random forest, hidden Markov model, and recurrent neural network were used to analyze the time-series data and make predictions about the occurrence of depressive episodes in the near future. The models were then combined into a hybrid model. The prediction accuracy of the hybrid model was 0.78; especially in the prediction of rare episode events, the F1-score performance was approximately 1.88 times higher than that of the dummy model. We explored factors such as data sequence size, train-to-test data ratio, and class-labeling time slots that can affect the model performance to determine the combinations of parameters that optimize the model performance. Our findings are especially valuable because they are experimental results derived from large-scale participant data analyzed over a long period of time. Full article

(This article belongs to the Special Issue Innovations in AI and ML-Based Techniques for Image and Video Analysis from Sensors)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Innovations in AI and ML-Based Techniques for Image and Video Analysis from Sensors

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (6 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI