Intelligent Data Analysis for Connected Health Applications

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 December 2023) | Viewed by 4985

Special Issue Editor

College of Computer Science, Chongqing University, Chongqing 400044, China
Interests: recommender systems; social networking; information retrieval, machine learning; data mining

Special Issue Information

Dear Colleagues,

With the development of information technology, data from all walks of life are explosively generated. In this situation, the way to quickly and effectively mine valuable information and knowledge from the sea of data has become one of the important problems to be solved by all walks of life. Imbalanced data have become a research hotspot and direction for experts and scholars because they are very common in real life. Especially in the medical field, data imbalance is particularly prominent. It is highly feasible to mine effective information from medical data to assist doctors in decision making. This widespread data imbalance problem makes misclassification likely when dealing with the classification of imbalanced datasets. When the imbalance ratio is very high, it will cause a large classification loss. For the problem of class imbalance in medical data, the way to propose corresponding solutions from the data level and algorithm level, reduce the impact of data class imbalance on the model, and improve the prediction effect of the model are the topics that need to be studied.

Dr. Wei Zhou
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

  • imbalanced data mining
  • feature recognition
  • feature selection
  • feature extraction
  • medical image reconstruction
  • medical image segmentation
  • medical image classification
  • medical image processing and recognition
  • data mining
  • machine learning
  • deep learning

Published Papers (5 papers)

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

Research

26 pages, 7269 KiB  
Article
Enhancing CT Segmentation Security against Adversarial Attack: Most Activated Filter Approach
by Woonghee Lee and Younghoon Kim
Appl. Sci. 2024, 14(5), 2130; https://doi.org/10.3390/app14052130 - 04 Mar 2024
Viewed by 437
Abstract
This study introduces a deep-learning-based framework for detecting adversarial attacks in CT image segmentation within medical imaging. The proposed methodology includes analyzing features from various layers, particularly focusing on the first layer, and utilizing a convolutional layer-based model with specialized training. The framework [...] Read more.
This study introduces a deep-learning-based framework for detecting adversarial attacks in CT image segmentation within medical imaging. The proposed methodology includes analyzing features from various layers, particularly focusing on the first layer, and utilizing a convolutional layer-based model with specialized training. The framework is engineered to differentiate between tampered adversarial samples and authentic or noise-altered images, focusing on attack methods predominantly utilized in the medical sector. A significant aspect of the approach is employing a random forest algorithm as a binary classifier to detect attacks. This method has shown efficacy in identifying genuine samples and reducing false positives due to Gaussian noise. The contributions of this work include robust attack detection, layer-specific feature analysis, comprehensive evaluations, physician-friendly visualizations, and distinguishing between adversarial attacks and noise. This research enhances the security and reliability of CT image analysis in diagnostics. Full article
(This article belongs to the Special Issue Intelligent Data Analysis for Connected Health Applications)
Show Figures

Figure 1

19 pages, 4520 KiB  
Article
A Visual User Interfaces for Constant Checking of Non-Invasive Physiological Parameters
by Sara Jelbeb and Ahmad Alzubi
Appl. Sci. 2023, 13(16), 9192; https://doi.org/10.3390/app13169192 - 12 Aug 2023
Cited by 1 | Viewed by 853
Abstract
Objective: this study proposes the development of a wireless graphical interface with a monitoring system that allows for extensive integration with a variety of non-invasive devices. Method: an evaluation framework was created using ISO/IEC25012 parameters to evaluate each of the physiological parameters. Using [...] Read more.
Objective: this study proposes the development of a wireless graphical interface with a monitoring system that allows for extensive integration with a variety of non-invasive devices. Method: an evaluation framework was created using ISO/IEC25012 parameters to evaluate each of the physiological parameters. Using an ISO standard as a framework to evaluate the quality of the results and analysis parameters such as consistency, accessibility, compressibility, and others, the Cayenne myDevices platform is used to develop a variety of IoT projects. Results: the successful prototype shows that the temperature sensor’s technical capabilities were found to be insufficient for accurately measuring a human’s body temperature, requiring a calibration algorithm. The Cayenne myDevices platform provides a web dashboard for continuous tracking and storage of physiological data. Blynk, an IoT-based application with a graphical user interface, enables real-time visualization and tracking of data from the server and the electronic prototype. Conclusion: findings concluded that free software tools such as Cayenne myDevices, the Blynk App, and Arduino enable integration and reduce the need for expensive applications. Electronic prototypes monitor parameters (e.g., temperature, heart rate, oxygen saturation) were used to monitor COVID-19, cardiovascular, and diabetic patients during exercise. Successful prototypes used Max30100, Mlx90614 sensors, and Esp8266 microcontroller. To avoid giving the patient inaccurate results, the instruments must be carefully selected, so they were assessed to ensure a 95% effectiveness level. Full article
(This article belongs to the Special Issue Intelligent Data Analysis for Connected Health Applications)
Show Figures

Figure 1

19 pages, 3103 KiB  
Article
Enhancing Feature Selection for Imbalanced Alzheimer’s Disease Brain MRI Images by Random Forest
by Xibin Wang, Qiong Zhou, Hui Li and Mei Chen
Appl. Sci. 2023, 13(12), 7253; https://doi.org/10.3390/app13127253 - 18 Jun 2023
Viewed by 1148
Abstract
Imbalanced learning problems often occur in application scenarios and are additionally an important research direction in the field of machine learning. Traditional classifiers are substantially less effective for datasets with an imbalanced distribution, especially for high-dimensional longitudinal data structures. In the medical field, [...] Read more.
Imbalanced learning problems often occur in application scenarios and are additionally an important research direction in the field of machine learning. Traditional classifiers are substantially less effective for datasets with an imbalanced distribution, especially for high-dimensional longitudinal data structures. In the medical field, the imbalance of data problem is more common, and correctly identifying samples of the minority class can obtain important information. Moreover, class imbalance in imbalanced AD (Alzheimer’s disease) data presents a significant challenge for machine learning algorithms that assume the data are evenly distributed within the classes. In this paper, we propose a random forest-based feature selection algorithm for imbalanced neuroimaging data classification. The algorithm employs random forest to evaluate the value of each feature and combines the correlation matrix to choose the optimal feature subset, which is applied to imbalanced MRI (magnetic resonance imaging) AD data to identify AD, MCI (mild cognitive impairment), and NC (normal individuals). In addition, we extract multiple features from AD images that can represent 2D and 3D brain information. The effectiveness of the proposed method is verified by the experimental evaluation using the public ADNI (Alzheimer’s neuroimaging initiative) dataset, and results demonstrate that the proposed method has a higher prediction accuracy and AUC (area under the receiver operating characteristic curve) value in NC-AD, MCI-AD, and NC-MCI group data, with the highest accuracy and AUC value for the NC-AD group data. Full article
(This article belongs to the Special Issue Intelligent Data Analysis for Connected Health Applications)
Show Figures

Figure 1

25 pages, 3514 KiB  
Article
DKFD: Optimizing Common Pediatric Dermatoses Detection with Novel Loss Function and Post-Processing
by Dandan Fan, Hui Li, Mei Chen, Qingqing Liang and Huarong Xu
Appl. Sci. 2023, 13(10), 5958; https://doi.org/10.3390/app13105958 - 12 May 2023
Viewed by 1155
Abstract
Using appropriate classification and recognition technology can help physicians make clinical diagnoses and decisions more effectively as a result of the ongoing development of artificial intelligence technology in the medical field. There are currently a number of issues with the detection of common [...] Read more.
Using appropriate classification and recognition technology can help physicians make clinical diagnoses and decisions more effectively as a result of the ongoing development of artificial intelligence technology in the medical field. There are currently a number of issues with the detection of common pediatric dermatoses, including the challenge of image collection, the low resolution of some collected images, the intra-class variability and inter-class similarity of disease symptoms, and the mixing of disease symptom detection results. To resolve these problems, we first introduced the Random Online Data Augmentation and Selective Image Super-Resolution Reconstruction (RDA-SSR) method, which successfully avoids overfitting in training, to address the issue of the small dataset and low resolution of collected images, increase the number of images, and improve the image quality. Second, for the issue of an imbalance between difficult and simple samples, which is brought on by the variation within and between classes of disease signs during distinct disease phases. By increasing the loss contribution of hard samples for classification on the basis of the cross-entropy, we propose the DK_Loss loss function for two-stage object detection, allowing the model to concentrate more on the learning of hard samples. Third, in order to reduce redundancy and improve detection precision, we propose the Fliter_nms post-processing method for the intermingling of detection results based on the NMS algorithm. We created the CPD-10 image dataset for common pediatric dermatoses and used the Faster R-CNN network training findings as a benchmark. The experimental results show that the RDA-SSR technique, while needing a similar collection of parameters, can improve mAP by more than 4%. Furthermore, experiments were conducted over the CPD-10 dataset and PASCAL VOC2007 dataset to evaluate the effectiveness of DK_Loss over the two-stage object detection algorithm, and the results of cross-entropy loss-function-based training are used as baselines. The findings demonstrated that, with DK_Loss taken into account, its mAP is 1–2% above the baseline. Furthermore, the experiments confirmed that the Fliter_nms post-processing method can also improve model precision. Full article
(This article belongs to the Special Issue Intelligent Data Analysis for Connected Health Applications)
Show Figures

Figure 1

12 pages, 1330 KiB  
Article
Directed Search for Non-Dominated Emergency Medical System Designs
by Marek Kvet and Jaroslav Janáček
Appl. Sci. 2023, 13(8), 4810; https://doi.org/10.3390/app13084810 - 11 Apr 2023
Cited by 1 | Viewed by 804
Abstract
This research paper is aimed at a specific group of emergency medical service location problems, which are solved to save people’s lives and reduce the rate of mortality and morbidity. Since searching for the optimal service center deployment is a big challenge, many [...] Read more.
This research paper is aimed at a specific group of emergency medical service location problems, which are solved to save people’s lives and reduce the rate of mortality and morbidity. Since searching for the optimal service center deployment is a big challenge, many operations researchers, programmers, and healthcare practitioners have been making a great effort to find effective solutions since the 1960s. Within this paper, we study such a system design problem in which two contradictory objectives are taken into account. Since the optimization of one criterion causes deterioration in the value of the other, a specific small finite set of solutions seems to be a sufficient output of the associated solving process for further decision-making. Therefore, we study here several heuristic approaches that enable us to approximate the original Pareto fronts of non-dominated system designs. In addition to the theoretical explanation, we provide the readers with the results of numerical experiments in order to evaluate the quality of the proposed algorithms. Based on the presented results, it can be stated that the suggested approach is able to produce a good approximation of the Pareto front of emergency medical service system designs in acceptable computational time, which is in orders shorter than the one required by the former exact method. Full article
(This article belongs to the Special Issue Intelligent Data Analysis for Connected Health Applications)
Show Figures

Figure 1

Back to TopTop