529 research outputs found
Discrepancy detection between actual user reviews and numeric ratings of Google App store using deep learning
No full textNowadays online reviews play a significant role in influencing the decision of consumers. Consumers show their experience and information about product quality in their reviews. Product Reviews from Amazon to Restaurant Reviews from Yelp are facing problems with fake reviews and fake numeric ratings. Online reviews typically consist of qualitative (text format) and quantitative (rating) formats. In the case of Google Play store fake numeric ratings can play a big role in the success of apps. People tend to believe that a high-star rating may be significantly attached with a good review. However, user star level rating information does not usually match with text format of review. Despite many efforts to resolve this issue, Apple App Store and Google Play Store are still facing this problem. This study proposes a novel Google App numeric reviews & ratings contradiction prediction framework using Deep Learning approaches. The framework consists of two phases. In the first phase, the polarity of reviews are predicted using sentiment analysis tool to build ground truth. In the second phase, star ratings are predicted from text format of reviews after training deep learning models on ground truth obtained in the first phase. Experimental results demonstrate that based on actual user reviews the proposed framework significantly predicts unbiased star rating of app.No Full Tex
Improving the Prediction of Heart Failure Patients’ Survival Using SMOTE and Effective Data Mining Techniques
No full textCardiovascular disease is a substantial cause of mortality and morbidity in the world. In clinical data analytics, it is a great challenge to predict heart disease survivor. Data mining transforms huge amounts of raw data generated by the health industry into useful information that can help in making informed decisions. Various studies proved that significant features play a key role in improving performance of machine learning models. This study analyzes the heart failure survivors from the dataset of 299 patients admitted in hospital. The aim is to find significant features and effective data mining techniques that can boost the accuracy of cardiovascular patient’s survivor prediction. To predict patient’s survival, this study employs nine classification models: Decision Tree (DT), Adaptive boosting classifier (AdaBoost), Logistic Regression (LR), Stochastic Gradient classifier (SGD), Random Forest (RF), Gradient Boosting classifier (GBM), Extra Tree Classifier (ETC), Gaussian Naive Bayes classifier (G-NB) and Support Vector Machine (SVM). The imbalance class problem is handled by Synthetic Minority Oversampling Technique (SMOTE). Furthermore, machine learning models are trained on the highest ranked features selected by RF. The results are compared with those provided by machine learning algorithms using full set of features. Experimental results demonstrate that ETC outperforms other models and achieves 0.9262 accuracy value with SMOTE in prediction of heart patient’s survival.Full Tex
Experimental Validation of a Multi-Functional Metasurface for 5G and Satellite Communication
Get PDFIn this article, a single layer, ultrathin, multiband, and multifunctional reflective polarization converting metasurface (PCMS) is presented that can perform linear to linear (LTL) orthogonally with respect to the incident polarization, also called cross polarization conversion (CPC), and linear to circular (LTC) polarization conversion (PC). It consists of a periodic arrangement of an inclined H-shaped metallic patch, on the top of a F4B grounded dielectric substrate. The proposed configuration converts linear polarization (LP) to an orthogonal polarization in five frequency bands, i.e., 9-10.6, 15.9-16, 18.6-22.9, 23.7-23.8, and 25.9-26.9 GHz with more than 90% polarization conversion ratio (PCR). Furthermore, the proposed metasurface design accomplishes circular polarization (CP) in eight different frequency bands namely, 8.6-8.8, 10.9-11.4, 15.6-15.8, 16.8-17.7, 22.9-23, 23.3-23.4, 25.6-25.7, and 27.3-27.5 GHz, having the required axial ratio (AR dB). Multiple surface plasmonic resonances are the reason behind the different conversions. The experimental results are in good agreement with the simulated results. The ultrathin, simple structure, multiband, multifunctional characteristics, and compact size of the polarization converter make it an excellent option for 5G wireless systems, satellite communication, and stealth technologies
Design, Analysis and Applications of Wearable Antennas: A Review
Get PDFWearable antennas are the vital components for Body Centric Communication (BCC). These antennas have recently gained the attention of researchers and have received a great deal of popularity due to their attractive characteristics and opportunities. They are fundamental in the Wireless Body Area Networks (WBANs) for health care, military, sports, and identification purposes. Compared to traditional antennas, these antennas work in close proximity to the human body, so their performance in terms of return loss, gain, directivity, bandwidth, radiation pattern, efficiency, and Specific Absorption Rate (SAR) is influenced by the coupling and absorption of the human body tissues. Additionally, in the design of these antennas, size, power consumption, and speed can also play a paramount role. In most cases, these antennas are integrated into the clothes, or in some cases, they may be fixed over the skin of the users. When these characteristics are considered, the design of wearable antennas becomes challenging, particularly when textile materials are examined, high conductivity materials are used during the manufacturing process, and various deformation scenarios have an impact on the design’s performance. To enhance the overall performance of the wearable antennas and to reduce the backward radiation towards the human body, metamaterial surfaces are introduced that provide a high degree of isolation from the human body and significantly reduce the SAR. This paper discusses the state-of-the-art wearable/textile/flexible antennas integrated with metamaterial structures composed of wearable/flexible substrate materials, with a focus on single and dual band antenna designs. The paper also reviews the critical design issues, various fabrication techniques, and other factors that need to be considered in the design of wearable/textile/flexible antennas. All the designs presented in this work are of the recent developments in wearable technology
Wideband and High Gain Array Antenna for 5G Smart Phone Applications Using Frequency Selective Surface
Get PDFThis work presents an eight element array antenna with single layer frequency selective surface (FSS) to obtain high gain. The eight elements are fed by single port. The FSS consists of 14 × 6 unit cells with one unit cell size is 5 × 5 mm2 having wideband behavior. The antenna uses Rogers RT Duroid 5880 substrate and giving very wide bandwidth from 20 GHz to 65 GHz, covering millimeter wave 5G bands (including 28 GHz, 38 GHz and 60 GHz). The designed FSS is showing stop band transmission characteristics below −10 dB threshold from 25 GHz to 42 GHz and 59 GHz to 61 GHz. The eight element antenna integrated with the FSS reflector, which results an improvement in the gain level from 12 dB to 15 dB at 28 GHz, from 10 dB to 12 dB at 38 GHz, and from 9.5 to 11 dB at 60 GHz. The dimensions of the antenna are 65 × 27 × 0.857 mm3. The proposed antenna shows stable gain and directional radiation patterns. The simulation findings are experimentally confirmed, by testing the fabricated prototypes of the proposed antenna system
Design and SAR Analysis of AMC-Based Fabric Antenna for Body-Centric Communication
Get PDFThis study focused on the design and analysis of an artificial magnetic conductor (AMC)-based fabric antenna for body-centric communication. The antenna was made of felt and had a loss tangent of 0.044 and relative permittivity of 1.3. The proposed antenna was built to function in the frequency band centered at 2.45 GHz, widely used in wireless communication devices. The antenna’s performance was evaluated using the electromagnetic simulation software CST MWS. A 50 Ω SubMiniature version connector was used to excite the proposed antenna. A 2×2 AMC array was integrated into the antenna below it to improve its performance in terms of radiation efficiency, gain, and backward radiation reduction. The antenna and AMC array were fabricated on flexible fabric substrates. The total volume of the AMC-integrated antenna is 0.55λo×0.55λo×0.016λo . It was demonstrated that adding an AMC array enhanced the radiation properties of the antenna and significantly decreased its back lobes. The on- and off-body maximum gains of the AMC-integrated antenna are (≥ 4.11 dBi) and 5.23 dBi, respectively. Furthermore, employing the AMC array, a significant reduction in the specific absorption rate value, which is (≤ 0.43 W/kg) for human body tissue chest/back and (≤ 0.75 W/kg) for human body tissue arm, was obtained, ensuring safety for human use. The simulated and measured results were in agreement. The tested on- and off-body radiation efficiencies in the frequency band centered at 2.45 GHz is (>67%) and (>83%), respectively. The proposed antenna can potentially be used in various applications such as healthcare monitoring, wearable electronics, and Internet of Things (IoT) systems, where reliable and efficient communication is required in a body-centric environment
Robust Feedback Linearization Based Disturbance Observer Control of Quadrotor UAV
Get PDFThis paper presents a novel Robust Feedback Linearization (RFBL) controller for Quadrotor Unmanned Aerial Vehicle (UAV) when subjected to external disturbances. A Robust Feedback Linearization controller is achieved by augmenting the conventional Feedback Linearization-based control with the Supertwisting Algorithm in the outer loop. To estimate the external disturbances acting on a quadrotor a Nonlinear Harmonic Disturbance Observer (NHDO) is patched with the robust controller. The efficacy and superiority of the results can be seen in terms of tracking error, rise time and robustness to disturbances when comparing it with other three robust controllers i.e. Integral Sliding Mode Controller (ISMC), Terminal Synergetic Controller (TSC) and Finite-Time supertwisting controller. Lyapunov’s stability analysis is performed to prove stability while numerical simulation is carried out using MATLAB/Simulink. The results are also validated by testing the system in a Hardware-In-Loop (HIL) environment on the MicroLabBox dSPACE RTI-1202 platform
Predicting Household Electric Power Consumption Using Multi-step Time Series with Convolutional LSTM
No full textEnergy consumption prediction has become an integral part of a smart and sustainable environment. With future demand forecasts, energy production and distribution can be optimized to meet the needs of the growing population. However, forecasting the demand of individual households is a challenging task due to the diversity of energy consumption patterns. Recently, it has become popular with artificial intelligence-based smart energy-saving designs, smart grid planning and social Internet of Things (IoT) based smart homes. Despite existing approaches for energy demand forecast, predominantly, such systems are based on one-step forecasting and have a short forecasting period. For resolving this issue and obtain high prediction accuracy, this study follows the prediction of household appliances' power in two phases. In the first phase, a long short-term memory (LSTM) based model is used to predict total generative active power for the coming 500 hours. The second phase employs a hybrid deep learning model that combines convolutional characteristics of neural network with LSTM for household electrical energy consumption forecasting of the week ahead utilizing Social IoT-based smart meter readings. Experimental results reveal that the proposed convolutional LSTM (ConvLSTM) architecture outperforms other models with the lowest root mean square error value of 367 kilowatts for weekly household power consumption.(c) 2022 Elsevier Inc. All rights reserved
Industry 4.0 technologies and their applications in fighting COVID-19 pandemic using deep learning techniques
No full textThe disease known as COVID-19 has turned into a pandemic and spread all over the world. The fourth industrial revolution known as Industry 4.0 includes digitization, the Internet of Things, and artificial intelligence. Industry 4.0 has the potential to fulfil customized requirements during the COVID-19 emergency crises. The development of a prediction framework can help health authorities to react appropriately and rapidly. Clinical imaging like X-rays and computed tomography (CT) can play a significant part in the early diagnosis of COVID-19 patients that will help with appropriate treatment. The X-ray images could help in developing an automated system for the rapid identification of COVID-19 patients. This study makes use of a deep convolutional neural network (CNN) to extract significant features and discriminate X-ray images of infected patients from non-infected ones. Multiple image processing techniques are used to extract a region of interest (ROI) from the entire X-ray image. The ImageDataGenerator class is used to overcome the small dataset size and generate ten thousand augmented images. The performance of the proposed approach has been compared with state-of-the-art VGG16, AlexNet, and InceptionV3 models. Results demonstrate that the proposed CNN model outperforms other baseline models with high accuracy values: 97.68% for two classes, 89.85% for three classes, and 84.76% for four classes. This system allows COVID-19 patients to be processed by an automated screening system with minimal human contact
Design and performance investigation of metamaterial-inspired dual band antenna for WBAN applications
Get PDFThis paper presents the design and analysis of a metamaterial-based compact dual-band antenna for WBAN applications. The antenna is designed and fabricated on a 0.254 mm thick semi-flexible substrate, RT/Duroid (R) 5880, with a relative permittivity of 2.2 and a loss tangent of 0.0009. The total dimensions of the antenna are 0.26 lambda(o)x0.19 lambda(o)x0.002 lambda(o), where lambda(o) corresponds to the free space wavelength at 2.45 GHz. To enhance overall performance and isolate the antenna from adverse effects of the human body, it is backed by a 2x2 artificial magnetic conductor (AMC) plane. The total volume of the AMC integrated design is 0.55 lambda(o)x0.55 lambda(o)x0.002 lambda(o). The paper investigates the antenna's performance both with and without AMC integration, considering on- and off-body states, as well as various bending conditions in both E and H-planes. Results indicate that the AMC-integrated antenna gives improved measured gains of 6.61 dBi and 8.02 dBi, with bandwidths of 10.12% and 7.43% at 2.45 GHz and 5.80 GHz, respectively. Furthermore, the AMC integrated antenna reduces the specific absorption rate (SAR) to (>96%) and (>93%) at 2.45 GHz and 5.80 GHz, meeting FCC requirements for low SAR at both frequencies when placed in proximity to the human body. CST Microwave Studio (MWS) and Ansys High-Frequency Structure Simulation (HFSS), both full-wave simulation tools, are utilized to evaluate the antenna's performance and to characterize the AMC unit cell. The simulated and tested results are in mutual agreement. Due to its low profile, high gain, adequate bandwidth, low SAR values, and compact size, the AMC integrated antenna is considered suitable for WBAN applications
- …
