Human Activity Recognition (HAR) systems are devised for continuously observing human behavior - primarily in the fields of environmental compatibility, sports injury detection, senior care, rehabilitation, entertainment, and the surveillance in intelligent home settings. Inertial sensors, e.g., accelerometers, linear acceleration, and gyroscopes are frequently employed for this purpose, which are now compacted into smart devices, e.g., smartphones. Since the use of smartphones is so widespread now-a-days, activity data acquisition for the HAR systems is a pressing need. In this article, we have conducted the smartphone sensor-based raw data collection, namely H-Activity , using an Android-OS-based application for accelerometer, gyroscope, and linear acceleration. Furthermore, a hybrid deep learning model is proposed, coupling convolutional neural network and long-short term memory network (CNN-LSTM), empowered by the self-attention algorithm to enhance the predictive capabilities of the system. In addition to our collected dataset ( H-Activity ), the model has been evaluated with some benchmark datasets, e.g., MHEALTH, and UCI-HAR to demonstrate the comparative performance of our model. When compared to other models, the proposed model has an accuracy of 99.93% using our collected H-Activity data, and 98.76% and 93.11% using data from MHEALTH and UCI-HAR databases respectively, indicating its efficacy in recognizing human activity recognition. We hope that our developed model could be applicable in the clinical settings and collected data could be useful for further research.
One of the common types of cancer for women is ovarian cancer. Still, at present, there are no drug therapies that can properly cure this deadly disease. However, early-stage detection could boost the life expectancy of the patients. The main aim of this work is to apply machine learning models along with statistical methods to the clinical data obtained from 349 patient individuals to conduct predictive analytics for early diagnosis. In statistical analysis, Student’s t-test as well as log fold changes of two groups are used to find the significant blood biomarkers. Furthermore, a set of machine learning models including Random Forest (RF), Support Vector Machine (SVM), Decision Tree (DT), Extreme Gradient Boosting Machine (XGBoost), Logistic Regression (LR), Gradient Boosting Machine (GBM) and Light Gradient Boosting Machine (LGBM) are used to build classification models to stratify benign-vs.-malignant ovarian cancer patients. Both of the analysis techniques recognized that the serumsamples carbohydrate antigen 125, carbohydrate antigen 19-9, carcinoembryonic antigen and human epididymis protein 4 are the top-most significant biomarkers as well as neutrophil ratio, thrombocytocrit, hematocrit blood samples, alanine aminotransferase, calcium, indirect bilirubin, uric acid, natriumas as general chemistry tests. Moreover, the results from predictive analysis suggest that the machine learning models can classify malignant patients from benign patients with accuracy as good as 91%. Since generally, early-stage detection is not available, machine learning detection could play a significant role in cancer diagnosis.
The gamma mass (µm) and linear (µ) attenuation coefficients of polycarbonate-bismuth oxide composites (PC-Bi2O3) with different bismuth oxide weight factors were investigated theoretically using EpiXS and a Monte Carlo simulation-based toolkit and Geant4 within an energy range between 0.1 and 2 MeV. The wide energy ranges of gamma rays and neutrons were chosen to cover as many applications as possible. The attenuation coefficients were then used to compute the half-value layers. The effective atomic numbers and effective electron densities of the studied samples obtained by EpiXS were compared as well. In order to further evaluate the shielding effectiveness of the studied samples, the thicknesses of all the investigated samples equivalent to 0.5 mm lead at a gamma energy of 511 keV were compared using a Geant4 code simulating a female numerical phantom with a gamma source placed facing the chest and a cylinder-shaped shield wrapped around the trunk area. The fast neutron removal cross sections of the investigated samples were studied to evaluate the effect of the weight factor of nanocomposites on the neutron shielding capabilities of the polymer as well.
Polymers are widely used materials that have many medical and industrial applications. Some polymers have even been introduced as radiation-shielding materials; therefore, many studies are focusing on new polymers and their interactions with photons and neutrons. Research has recently focused on the theoretical estimation of the shielding effectiveness of Polyimide doped with different composites. It is well known that theoretical studies on the shielding properties of different materials through modeling and simulation have many benefits, as they help scientists to choose the right shielding material for a specific application, and they are also much more cost-effective and take much less time compared to experimental studies. In this study, Polyimide (C35H28N2O7) was investigated. It is a high-performance polymer, well known for its outstanding chemical and thermal stability, as well as for its high mechanical resistance. Because of its exceptional properties, it is used in high-end applications. The performance of Polyimide and Polyimide doped with different weight fractions of composites (5, 10, 15, 20 and 25 wt.%) as a shielding material against photons and neutrons were investigated using a Monte Carlo-based simulation toolkit Geant4 within a wide range of energies of both photons and neutrons from 10 to 2000 KeVs. Polyimide can be considered a good neutron shielding material, and its photon shielding abilities could be further enhanced when adding different high atomic number composites to it. The results showed that Au and Ag gave the best results in terms of the photon shielding properties, while ZnO and TiO2 had the least negative effect on the neutron shielding properties. The results also indicate that Geant4 is a very reliable tool when it comes to evaluating the shielding properties against photons and neutrons of any material.
Background: Inherently ultrasound images are susceptible to noise which leads to several image quality issues. Hence, rating of an image's quality is crucial since diagnosing diseases requires accurate and high-quality ultrasound images. Methods: This research presents an intelligent architecture to rate the quality of ultrasound images. The formulated image quality recognition approach fuses feature from a Fuzzy convolutional neural network (fuzzy CNN) and a handcrafted feature extraction method. We implement the fuzzy layer in between the last max pooling and the fully connected layer of the multiple state-of-the-art CNN models to handle the uncertainty of information. Moreover, the fuzzy CNN uses Particle swarm optimization (PSO) as an optimizer. In addition, a novel Quantitative feature extraction machine (QFEM) extracts hand-crafted features from ultrasound images. Next, the proposed method uses different classifiers to predict the image quality. The classifiers categories ultrasound images into four types (normal, noisy, blurry, and distorted) instead of binary classification into good or poor-quality images. Results:The results of the proposed method exhibit a significant performance in accuracy (99.62%), precision (99.62%), recall (99.61%), and f1-score (99.61%). Conclusion: This method will assist a physician in automatically rating informative ultrasound images with steadfast operation in real-time medical diagnosis. INDEX TERMSUltrasound image, Quantitative feature extraction machine (QFEM), Particle swarm optimization (PSO), Feature fusion, Fuzzy convolutional neural network, Feature extraction. Clinical translation statement: This research has not been trialed in any real-life diagnosis. The whole research has been experimented with in our Lab setup. However, the research is designed to assist a physician.
Polymers are widely used materials that have many medical and industrial applications. Some polymers have even been introduced as radiation-shielding materials; therefore, many studies are focusing on new polymers and their interactions with photons and neutrons. Research has focused on theoretical estimation of the shielding effectiveness of different materials. It is well known that theoretical studies on the shielding properties of different materials through modeling and simulation have many benefits, as they help scientists to choose the right shielding material for a specific application, and they are also much more cost-effective and take much less time compared to experimental studies. In this study, polysulfone (PSU) was investigated. PSU is a high-temperature, amber-colored, semi-transparent plastic material with good mechanical properties. It is resistant to degradation from hot water and steam and is often used in medical and food preparation applications, where repeated sterilization is required. The interactions of photons and neutrons with PSU were investigated using a Monte Carlo-based simulation toolkit, Geant4, within a wide range of energies of both photons and neutrons. The mass attenuation coefficients (µm), the half-value layers (HVL), the effective atomic numbers (Zeff), and the effective electron densities (Neff) of gammas were investigated. In addition, the effective removal cross-sections (ΣR) and the mean free paths (λ) of neutrons were also studied. The results were then compared to other commonly used polymer materials.
Despite many dedicated efforts, the fabrication of high-quality ZnO-incorporated Zinc@Silicon (Zn@Si) core–shell quantum dots (ZnSiQDs) with customized properties remains challenging. In this study, we report a new record for the brightness enhancement of ZnSiQDs prepared via a unified top-down and bottom-up strategy. The top-down approach was used to produce ZnSiQDs with uniform sizes and shapes, followed by the bottom-up method for their re-growth. The influence of various NH4OH contents (15 to 25 µL) on the morphology and optical characteristics of ZnSiQDs was investigated. The ZnSiQDs were obtained from the electrochemically etched porous Si (PSi) with Zn inclusion (ZnPSi), followed by the electropolishing and sonication in acetone. EFTEM micrographs of the samples prepared without and with NH4OH revealed the existence of spherical ZnSiQDs with a mean diameter of 1.22 to 7.4 nm, respectively. The emission spectra of the ZnSiQDs (excited by 365 nm) exhibited bright blue, green, orange-yellow, and red luminescence, indicating the uniform morphology related to the strong quantum confinement ZnSiQDs. In addition, the absorption and emission of the ZnSiQDs prepared with NH4OH were enhanced by 198.8% and 132.6%, respectively. The bandgap of the ZnSiQDs conditioned without and with NH4OH was approximately 3.6 and 2.3 eV, respectively.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.