Search

Real-time flood forecasting is crucial for early flood warnings. It relies on real-time hydrological and meteorological data. Satellite Precipitation Products offer real-time global precipitation estimates and have emerged as a suitable option for rainfall input in flood forecasting models. This study first compared the daily Satellite Precipitation Products of Integrated Multi-Satellite Retrievals for Global Precipitation Measurement (IMERG) with observed rainfall data of India Meteorological Department from the year 2001 to 2009 using contingency tests. Rainfall data of IMERG are used to build four Real-time flood forecasting models based on machine learning: feedforward neural network (FFNN), extreme learning machine (ELM), wavelet-based feedforward neural network, and wavelet-based extreme learning machine. The models consider the IMERG gridded data at 1 h resolution as input to predict water level at Hayaghat gauging station of Bagmati River with lead times from 1 h to 10 days. These models have been trained and tested with the observed water level data. The model performance was also evaluated using various statistical criteria. Results showed good correlation between IMERG and observed data with a probability of detection of 85.42%. Overall, wavelet-based models outperformed their singular counterparts. Among the singular models, the FFNN model performed better than ELM with satisfactory predictions up to 5 days of lead time. For a 7 days lead time, only wavelet-based-FFNN performs well, whereas none of the models produced satisfactory results for 10 days lead time. [ABSTRACT FROM AUTHOR]

Breast cancer is one of the paramount causes of new cancer cases worldwide annually. It is a malignant neoplasm that develops in the breast cells. The early screening of this disease is essential to prevent its metastasis. A mammogram X-ray image is the most common screening tool practiced currently when this disease is suspected; all the breast lesions identified are not malignant. The invasive fine needle aspiration (FNA) of a breast mass sample is the secondary screening tool to clinically examine cancerous lesions. The visual image analysis of the stained aspirated sample imposes a challenge for the cytologist to identify the malignant cells accurately. The formulation of an artificial intelligence-based objective technique on top of the introspective assessment is essential to avoid misdiagnosis. This paper addresses several artificial intelligence (AI)-based techniques to diagnose breast cancer from the nuclear features of FNA samples. The Wisconsin Breast Cancer dataset (WBCD) from the UCI machine learning repository is applied for this investigation. Significant statistical parameters are measured to evaluate the performance of the proposed techniques. The best detection accuracy of 98.10% is achieved with a two-layer feed-forward neural network (FFNN). Finally, the developed algorithm's performance is compared with some state-of-the-art works in the literature. [ABSTRACT FROM AUTHOR]

For high-precision positioning applications, various GNSS errors need to be mitigated, including the tropospheric error, which remains a significant error source as it can reach up to a few meters. Although some commercial GNSS correction data providers, such as the Quasi-Zenith Satellite System (QZSS) Centimeter Level Augmentation Service (CLAS), have developed real-time precise regional troposphere products, the service is available only in limited regional areas. The International GNSS Service (IGS) has provided precise troposphere correction data in TRO format post-mission, but its long latency of 1 to 2 weeks makes it unable to support real-time applications. In this work, a real-time troposphere prediction method based on the IGS post-processing products was developed using machine learning techniques to eliminate the long latency problem. The test results from tropospheric predictions over a year using the proposed method indicate that the new method can achieve a prediction accuracy (RMSE) of 2 cm, making it suitable for real-time applications. [ABSTRACT FROM AUTHOR]

The Ionospheric Total Electron Content (TEC) measured in the ray path of the signals directly contributes to the Range Error (RE) of the satellite signals, which affects positioning and navigation. Employing the Co-Kriging-based Surrogate Model (COKSM) to predict TEC and RE correction has proven prolific. This research attempted to test and compare the prediction capability of COKSM with an Artificial Intelligence-based Feed Forward Neural Network model (FFNN) during five X-Class Solar Flares of 2021–22. Also, the results are validated by comparing them with the IRI PLAS 2017 model. TEC, solar, and geomagnetic parameters data for Hyderabad GPS station located at 17.31° N latitude and 78.55° E longitude were collected from IONOLAB & OMNIWEB servers. The COKSM uses six days of input data to predict the 7th day TEC, whereas prediction using the FFNN model is done using 45 days of data before the prediction date. The performance evaluation is done using RMSE, NRMSE, Correlation Coefficient, and sMAPE. The average RMSE for COKSM varied from 1.9 to 9.05, for FFNN it varied from 2.72 to 7.69, and for IRI PLAS 2017 it varied from 7.39 to 11.24. Likewise, evaluation done for three different models over five different X-class solar flare events showed that the COKSM performed well during the high-intensity solar flare conditions. On the other hand, the FFNN model performed well during high-resolution input data conditions. Also, it is notable that both models performed better than the IRI PLAS 2017 model and are suitable for navigational applications. [ABSTRACT FROM AUTHOR]

Pulsed thermography is a technique of significant interest in non-destructive testing, particularly in defect detection and depth characterisation of composite materials. This study presents an innovative methodology for simultaneously detecting defects and estimating depth using a combination of sequenced thermal signal encoding and a two-dimensional convolution neural network (CNN) model. We compare the results of the proposed method with those obtained from the feed-forward neural network (FFNN), a one-dimensional CNN, and a long short-term memory recurrent neural network (LSTM-RNN). The findings demonstrate that the proposed approach exhibits superior accuracy and robustness compared to the benchmarks. [ABSTRACT FROM AUTHOR]

People across the world have been fascinated by solar eclipses for thousands of years. Solar eclipses are not only fascinating to observe but also provide opportunities for scientific research. During a solar eclipse, the quantity of solar energy reaching the Earth's surface is reduced as the Moon passes in front of the Sun. This reduction in solar energy can have an effect on the Total Electron Content of the Earth's ionosphere. In this paper, prediction and analysis of TEC variations in the Ionosphere during the solar eclipses happened on 26.12.2019 between 04:51 to 7:34 hours (UTC) and 09.03.2016 between 12:18 to 1:02 hours (UTC) over the Indonesia region were done by using two models: Ordinary Kriging based Surrogate Model (OKSM) and Feed-Forward Neural Network (FFNN). During the eclipse period, the TEC values were predicted by the OKSM and FFNN models and it is validated using literature. For this study, the GPS data belonging to the BAKO station situated in Indonesia were collected from IONOLAB servers and the input parameters were collected from the OMNIWEB servers. Forty days prior TEC data and input parameters were used to predict the TEC values. The credibility of the predicted results is assessed using statistical factors such as RMSE, CC, MAE, MAPE, sMAPE and R-Square. The statistical results show OKSM has performed well when compared to the FFNN model over the annular and total solar eclipse period. The study suggests that combining multiple modelling methods, such as OKSM and FFNN can improve our understanding of ionospheric variability during solar eclipses and provide more accurate predictions of TEC variations. This has important implications for satellite communications and navigation systems that rely on accurate TEC measurements for positioning and timing. [ABSTRACT FROM AUTHOR]

Tuberculosis is a severe and contagious lung disease that kills more than one million people annually, representing a real public health problem worldwide. Meanwhile, researchers and industry have highlighted the potential of analyzing and classifying chest radiographs (CXR) with artificial intelligence (AI). However, although high-performance industry solutions to aid in diagnosing have become a reality, vulnerable populations and underdeveloped countries have struggled to access them. In this sense, accessible and low-cost alternatives are essential to reach the needs of those populations that rely on public actions and services. Therefore, we propose a method to assist in the screening, diagnosing, and classifying of tuberculosis cases with a low-cost and high-efficiency computational approach. Our method uses a novel feature extraction approach based on binary patterns of phase congruence (BPPC) to describe CXR images that are represented in a feature vector of 1062 values. The extraction strategy maintains and recovers descriptive textural information of the TB, captured in 6 different directions of the CXR image, being invariant in the illumination and contrast of the CXR. The vector is then used to build a feed-forward neural network (FFNN) model capable of identifying and classifying TB cases. Our model experimented with three classification scenarios with CXR images from the TBX11K public dataset, and our results achieved exceptional performance, with greater than 99% accuracy, outperforming models from related work.

Breast cancer is one of the paramount causes of new cancer cases worldwide annually. It is a malignant neoplasm that develops in the breast cells. The early screening of this disease is essential to prevent its metastasis. A mammogram X-ray image is the most common screening tool practiced currently when this disease is suspected; all the breast lesions identified are not malignant. The invasive fine needle aspiration (FNA) of a breast mass sample is the secondary screening tool to clinically examine cancerous lesions. The visual image analysis of the stained aspirated sample imposes a challenge for the cytologist to identify the malignant cells accurately. The formulation of an artificial intelligence-based objective technique on top of the introspective assessment is essential to avoid misdiagnosis. This paper addresses several artificial intelligence (AI)-based techniques to diagnose breast cancer from the nuclear features of FNA samples. The Wisconsin Breast Cancer dataset (WBCD) from the UCI machine learning repository is applied for this investigation. Significant statistical parameters are measured to evaluate the performance of the proposed techniques. The best detection accuracy of 98.10% is achieved with a two-layer feed-forward neural network (FFNN). Finally, the developed algorithm’s performance is compared with some state-of-the-art works in the literature.

Accurate hydraulic conductivity (K) estimation of porous media is crucial in hydrological studies. Recently, groundwater investigators have utilized neural computing techniques to indirectly estimate soil sample K instead of time-consuming direct methods. The present study utilizes easily measurable characteristics, i.e., grain size at 10 and 50% finer by weight, porosity, and uniformity coefficient as input variables to examine the efficacy of feed-forward neural network (FFNN), Kohonen self-organizing maps (KSOM), and multiple linear regression (MLR) models in estimating the K of soil samples. Model development and validation used 70 and 30% of datasets, respectively. The determination coefficient (R2), root mean square error (RMSE), and mean bias error (MBE) were used to compare the model performance with the measured K values. The study's outcome indicates that the FFNN and KSOM models better estimate the K value, while the MLR model performs merely satisfactorily. Overall, during validation, the FFNN model correlates better with the measured values having R2, RMSE, and MBE of 0.94, 0.016, and 0.006, whereas the corresponding values for KSOM are 0.91, 0.024, and −0.004, and that for MLR are 0.87, 0.024, and 0.013, respectively. Notably, the FFNN model exhibits superior prediction performance and can be employed in aquifers for precise K estimation. HIGHLIGHTS The study examines the efficacy of FFNN, KSOM, and MLR models in estimating the K of porous media.; The statistical indicators reveal that the FFNN model performs better in estimating the K of porous media and can be employed in sub-surface flow studies for precise K estimation.;

Diabetic retinopathy (DR) is a complication of diabetes that damages the delicate blood vessels of the retina and leads to blindness. Ophthalmologists rely on diagnosing the retina by imaging the fundus. The process takes a long time and needs skilled doctors to diagnose and determine the stage of DR. Therefore, automatic techniques using artificial intelligence play an important role in analyzing fundus images for the detection of the stages of DR development. However, diagnosis using artificial intelligence techniques is a difficult task and passes through many stages, and the extraction of representative features is important in reaching satisfactory results. Convolutional Neural Network (CNN) models play an important and distinct role in extracting features with high accuracy. In this study, fundus images were used for the detection of the developmental stages of DR by two proposed methods, each with two systems. The first proposed method uses GoogLeNet with SVM and ResNet-18 with SVM. The second method uses Feed-Forward Neural Networks (FFNN) based on the hybrid features extracted by first using GoogLeNet, Fuzzy color histogram (FCH), Gray Level Co-occurrence Matrix (GLCM), and Local Binary Pattern (LBP); followed by ResNet-18, FCH, GLCM and LBP. All the proposed methods obtained superior results. The FFNN network with hybrid features of ResNet-18, FCH, GLCM, and LBP obtained 99.7% accuracy, 99.6% precision, 99.6% sensitivity, 100% specificity, and 99.86% AUC. [ABSTRACT FROM AUTHOR]

For high-precision positioning applications, various GNSS errors need to be mitigated, including the tropospheric error, which remains a significant error source as it can reach up to a few meters. Although some commercial GNSS correction data providers, such as the Quasi-Zenith Satellite System (QZSS) Centimeter Level Augmentation Service (CLAS), have developed real-time precise regional troposphere products, the service is available only in limited regional areas. The International GNSS Service (IGS) has provided precise troposphere correction data in TRO format post-mission, but its long latency of 1 to 2 weeks makes it unable to support real-time applications. In this work, a real-time troposphere prediction method based on the IGS post-processing products was developed using machine learning techniques to eliminate the long latency problem. The test results from tropospheric predictions over a year using the proposed method indicate that the new method can achieve a prediction accuracy (RMSE) of 2 cm, making it suitable for real-time applications.

The change in the electricity demand pattern globally due to sudden extreme weather conditions or situations like COVID 19 pandemic has brought unanticipated challenges for the electric utilities and operators around the world. This work primarily deals with the issue of load forecasting during such type of high impact low frequency (HILF) events. In this paper, we propose a novel resilient short-term load forecasting model capable of producing good forecasting performance for normal as well as critical situations during the COVID 19 pandemic and will also be useful for load forecasting for other HILF situations like natural calamity effect on load demand of the power system. The proposed method uses a feed-forward neural network (FFNN) with an added training feature named resiliency factor to forecast load in both regular and special scenarios. The resiliency factor for any type of node in the distribution system is decided by the power utility using the historical data and declared in advance. The proposed model is tested using the smart metered data available from a real-life distribution grid of an academic cum residential campus. The model is giving satisfactory results for both normal as well as COVID scenario for the said network. [ABSTRACT FROM AUTHOR]

Deep learning (DL) is a subdivision of machine learning (ML) that employs numerous algorithms, each of which provides various explanations of the data it consumes; mobile ad-hoc networks (MANET) are growing in prominence. For reasons including node mobility, due to MANET's potential to provide small-cost solutions for real-world contact challenges, decentralized management, and restricted bandwidth, MANETs are more vulnerable to security threats. When protecting MANETs from attack, encryption and authentication schemes have their limits. However, deep learning (DL) approaches in intrusion detection systems (IDS) can adapt to the changing environment of MANETs and allow a system to make intrusion decisions while learning about its mobility in the environment. IDSs are a secondary defiance system for mobile ad-hoc networks vs. attacks since they monitor network traffic and report anything unusual. Recently, many scientists have employed deep neural networks (DNNs) to address intrusion detection concerns. This paper used MANET to recognize complex patterns by focusing on security standards through efficiency determination and identifying malicious nodes, and mitigating network attacks using the three algorithms presented Cascading Back Propagation Neural Network (CBPNN), Feedforward-Neural-Network (FNN), and Cascading-Back-Propagation-Neural- Network (CBPNN) (FFNN). In addition to Convolutional-Neural-Network (CNN), these primary forms of deep neural network (DNN) building designs are widely used to improve the performance of intrusion detection systems (IDS) and the use of IDS in conjunction with machine learning (ML). Furthermore, machine learning (ML) techniques than their statistical and logical methods provide MANET network learning capabilities and encourage adaptation to different environments. Compared with another current model, The proposed model has better average receiving packet (ARP) and end-to-end (E2E) performance. The results have been obtained from CBP, FFNN and CNN 74%, 82% and 85%, respectively, by the time (27, 18, and 17 s). [ABSTRACT FROM AUTHOR]

White blood cells (WBCs) are one of the main components of blood produced by the bone marrow. WBCs are part of the immune system that protects the body from infectious diseases and an increase or decrease in the amount of any type that causes a particular disease. Thus, recognizing the WBC types is essential for diagnosing the patient's health and identifying the disease. Analyzing blood samples to determine the amount and WBC types requires experienced doctors. Artificial intelligence techniques were applied to analyze blood samples and classify their types to help doctors distinguish between types of infectious diseases due to increased or decreased WBC amounts. This study developed strategies for analyzing blood slide images to classify WBC types. The first strategy is to classify WBC types by the SVM-CNN technique. The second strategy for classifying WBC types is by SVM based on hybrid CNN features, which are called VGG19-ResNet101-SVM, ResNet101-MobileNet-SVM, and VGG19-ResNet101-MobileNet-SVM techniques. The third strategy for classifying WBC types by FFNN is based on a hybrid model of CNN and handcrafted features. With MobileNet and handcrafted features, FFNN achieved an AUC of 99.43%, accuracy of 99.80%, precision of 99.75%, specificity of 99.75%, and sensitivity of 99.68%. [ABSTRACT FROM AUTHOR]

In this study, rainfall–runoff (R–R) models were developed by assembling Particle Swarm Optimization (PSO) with the Feed Forward Neural Network (FFNN) and the Wavelet Neural Network (WNN). Performances of the model were compared with the wavelet ensembled neural network (WNN) and the conventional FFNN. The data from 1981 to 2005 were used for calibration and from 2006 to 2014 for validation of the models. Different combinations of rainfall and runoff were considered as inputs to the PSO–FFNN model. The fitness value and computational time of all the combinations were computed. Input combination was selected based on the lowest fitness value and lowest computational time. Four R–R models (FFNN, WNN, PSO–FFNN and PSO–WNN) were developed with the best input combination. The performance of the models was evaluated using statistical parameters (Nash–Sutcliffe Efficiency (NSE), D and root mean square error (RMSE)) and parameters vary in the range of (0.86–0.90), (0.95–0.97) and (68.87–84.37), respectively. After comparing the performance parameters and computational time of all four models, it was found that the PSO–FFNN model gave better values of NSE (0.89), D (0.97), RMSE (68.87) and less computational time (125.42 s) than other models. Thus, the PSO–FFNN model was better than the other three models (FFNN, WNN and PSO–WNN). HIGHLIGHTS The goals of this research are selection of input combination based on fitness value and computational time.; Four R-R models (FFNN, WNN, PSO-FFNN and PSO-WNN) were developed with the best input combination. The performance of the models was evaluated using statistical parameters (NSE, D and RMSE).;

هدف از این پژوهش ارزیابی اثرات تغییر اقلیم بر دما، بارش و خشکسالی‌های آینده در ایستگاه‌های الشتر و خرم‌آباد می‌باشد، ‏که به این منظور از خروجی مدل گردش عمومی ‏MRI-ESM2‎‏ مطابق جدیدترین گزارش‎ IPCC‏(گزارش ششم)‏‎ ‎و سناریوهای ‏انتشار ‏SSP 1.2.6 ‎، ‏SSP 2.4.5‎، ‏SSP 3.7.0 ‎‏ و ‏‎ SSP 5.8.5‎‏در این مناطق مطالعاتی استفاده شد. با کاربرد مدل درخت تصمیم ‏‏(‏‎M5 Tree‎)، غالب‌ترین متغیرهای پیشبینی‌کننده مدل ‏MRI-ESM2‎‏ انتخاب شدند. در ادامه متغیرهای پیشبینی‌کننده به‌عنوان ‏ورودی در مدل ریزمقیاس‌نمایی آماری شبکه عصبی مصنوعی پیشرو‎ ‎‏(‏FFNN‏) قرار گرفتند و با الگوریتم بهینه‌سازی کرم‌شب‌تاب ‏‏(‏FFA‏)، فرایند‎ ‎ریزمقیاس نمایی پارامترهای بارش، دمای حداکثر و دمای حداقل برای دوره پایه (2014-1970) با نتایج مطلوب ‏انجام شد. پس از اثبات قابلیت مدل شبکه عصبی، پیشبینی تغییرات متوسط دما و بارش ماهانه در طی دوره‌های آینده نزدیک ‏‏(2062-2023) و آینده دور (2100-2063) تحت سناریوهای خط سیرهای مشترک اجتماعی-اقتصادی (‏SSP‏) مربوط به مدل ‏جفت‌شده فاز ششم (‎CMIP6‎‏) به انجام رسید. به‌طورکلی، نتایج نشان داد که این متغیرها در هر دو دوره آتی در مقیاس ماهانه ‏دارای نوسان‌های متعددی خواهند بود، به‌طوری‌که در دو ایستگاه الشتر و خرم‎آباد طی دوره‌های آینده نزدیک و آینده دور دمای ‏حداکثر و دمای حداقل نسبت به دوره مشاهداتی در تمام سناریوهای ‏SSP‏ روندی افزایشی خواهند داشت و تغییرات دمای حداقل ‏نسبت به دمای حداکثر بیش‌تر خواهد بود. در آینده نزدیک میانگین بارش سالانه ایستگاه الشتر بین سه دهم تا 16 درصد و ‏ایستگاه خرم‌آباد بین هفت تا 12 درصد تحت سناریوهای ‏SSP‏ کاهش خواهد داشت. در آینده دور نیز میانگین بارش سالانه ‏ایستگاه الشتر بین 10 تا 20 درصد و ایستگاه خرم‌آباد بین 12 تا 24 درصد تحت سناریوهای ‏SSP‏ کاهش خواهد داشت.‏

The gastrointestinal system contains the upper and lower gastrointestinal tracts. The main tasks of the gastrointestinal system are to break down food and convert it into essential elements that the body can benefit from and expel waste in the form of feces. If any organ is affected, it does not work well, which affects the body. Many gastrointestinal diseases, such as infections, ulcers, and benign and malignant tumors, threaten human life. Endoscopy techniques are the gold standard for detecting infected parts within the organs of the gastrointestinal tract. Endoscopy techniques produce videos that are converted into thousands of frames that show the disease's characteristics in only some frames. Therefore, this represents a challenge for doctors because it is a tedious task that requires time, effort, and experience. Computer-assisted automated diagnostic techniques help achieve effective diagnosis to help doctors identify the disease and give the patient the appropriate treatment. In this study, many efficient methodologies for analyzing endoscopy images for diagnosing gastrointestinal diseases were developed for the Kvasir dataset. The Kvasir dataset was classified by three pre-trained models: GoogLeNet, MobileNet, and DenseNet121. The images were optimized, and the gradient vector flow (GVF) algorithm was applied to segment the regions of interest (ROIs), isolating them from healthy regions and saving the endoscopy images as Kvasir-ROI. The Kvasir-ROI dataset was classified by the three pre-trained GoogLeNet, MobileNet, and DenseNet121 models. Hybrid methodologies (CNN–FFNN and CNN–XGBoost) were developed based on the GVF algorithm and achieved promising results for diagnosing disease based on endoscopy images of gastroenterology. The last methodology is based on fused CNN models and their classification by FFNN and XGBoost networks. The hybrid methodology based on the fused CNN features, called GoogLeNet–MobileNet–DenseNet121–XGBoost, achieved an AUC of 97.54%, accuracy of 97.25%, sensitivity of 96.86%, precision of 97.25%, and specificity of 99.48%. [ABSTRACT FROM AUTHOR]

Alzheimer's disease (AD) is considered one of the challenges facing health care in the modern century; until now, there has been no effective treatment to cure it, but there are drugs to slow its progression. Therefore, early detection of Alzheimer's is vital to take needful measures before it develops into brain damage which cannot be treated. Magnetic resonance imaging (MRI) techniques have contributed to the diagnosis and prediction of its progression. MRI images require highly experienced doctors and radiologists, and the analysis of MRI images takes time to analyze each slice. Thus, deep learning techniques play a vital role in analyzing a huge amount of MRI images with high accuracy to detect Alzheimer's and predict its progression. Because of the similarities in the characteristics of the early stages of Alzheimer's, this study aimed to extract the features in several methods and integrate the features extracted from more than one method into the same features matrix. This study contributed to the development of three methodologies, each with two systems, with all systems aimed at achieving satisfactory accuracy for the detection of AD and predicting the stages of its progression. The first methodology is by Feed Forward Neural Network (FFNN) with the features of GoogLeNet and DenseNet-121 models separately. The second methodology is by FFNN network with combined features between GoogLeNet and Dense-121 models before and after high-dimensionality reduction of features using the Principal Component Analysis (PCA) algorithm. The third methodology is by FFNN network with combined features between GoogLeNet and Dense-121 models separately and features extracted by Discrete Wavelet Transform (DWT), Local Binary Pattern (LBP) and Gray Level Co-occurrence Matrix (GLCM) methods called handcrafted features. All systems yielded super results in detecting AD and predicting the stages of its progression. With the combined features of the DenseNet-121 and handcrafted, the FFNN achieved an accuracy of 99.7%, sensitivity of 99.64%, AUC of 99.56%, precision of 99.63%, and a specificity of 99.67%. [ABSTRACT FROM AUTHOR]

Knee osteoarthritis (KOA) is a chronic disease that impedes movement, especially in the elderly, affecting more than 5% of people worldwide. KOA goes through many stages, from the mild grade that can be treated to the severe grade in which the knee must be replaced. Therefore, early diagnosis of KOA is essential to avoid its development to the advanced stages. X-rays are one of the vital techniques for the early detection of knee infections, which requires highly experienced doctors and radiologists to distinguish Kellgren-Lawrence (KL) grading. Thus, artificial intelligence techniques solve the shortcomings of manual diagnosis. This study developed three methodologies for the X-ray analysis of both the Osteoporosis Initiative (OAI) and Rani Channamma University (RCU) datasets for diagnosing KOA and discrimination between KL grades. In all methodologies, the Principal Component Analysis (PCA) algorithm was applied after the CNN models to delete the unimportant and redundant features and keep the essential features. The first methodology for analyzing x-rays and diagnosing the degree of knee inflammation uses the VGG-19 -FFNN and ResNet-101 -FFNN systems. The second methodology of X-ray analysis and diagnosis of KOA grade by Feed Forward Neural Network (FFNN) is based on the combined features of VGG-19 and ResNet-101 before and after PCA. The third methodology for X-ray analysis and diagnosis of KOA grade by FFNN is based on the fusion features of VGG-19 and handcrafted features, and fusion features of ResNet-101 and handcrafted features. For an OAI dataset with fusion features of VGG-19 and handcrafted features, FFNN obtained an AUC of 99.25%, an accuracy of 99.1%, a sensitivity of 98.81%, a specificity of 100%, and a precision of 98.24%. For the RCU dataset with the fusion features of VGG-19 and the handcrafted features, FFNN obtained an AUC of 99.07%, an accuracy of 98.20%, a sensitivity of 98.16%, a specificity of 99.73%, and a precision of 98.08%. [ABSTRACT FROM AUTHOR]

Around 2.78% of the population in our nation cannot speak (dump). The fundamental way that two people engage is through communication. Since ancient times, people have used speech to interact with one another. Although science and technology have added comfort to human life, there are still some who are less fortunate who are battling to discover a solution that would make communication for them simpler. People who have trouble speaking utilise sign language that is based on hand movements. This programme enables the blind and deaf to interact with seeing people despite their communication challenges. This study suggested a novel method of FFNN (Feed Forward Neural Network) prototype that can automatically recognise sign language to assist normal individuals in more effective communication with those who are hearing, speech, or visually challenged. This system identified of the hand signal feature point extraction given with Feed Forward point extraction given with Feed Forward neural network. Hand Gesture Recognition with Voice Process system using HMM (Hidden Markov model) is used to provide the communication for dump people and the normal people. [ABSTRACT FROM AUTHOR]

In the manufacturing industry, computer numerical control (CNC) machine tools are of great importance since the processes in which they are used allow the creation of elements used in multiple sectors. Likewise, the condition of the cutting tools used is paramount due to the effect they have on the process and the quality of the supplies produced. For decades, methodologies have been developed that employ various signals and sensors for wear detection, prediction and monitoring; however, this field is constantly evolving, with new technologies and methods that have allowed the development of non-invasive, efficient and robust systems. This paper proposes the use of magnetic stray flux and motor current signals from a CNC lathe and the analysis of images of machined parts for wear detection using online and offline information under the variation in cutting speed and tool feed rate. The information obtained is processed through statistical and non-statistical indicators and dimensionally reduced by linear discriminant analysis (LDA) and a feed-forward neural network (FFNN) for wear classification. The results obtained show a good performance in wear detection using the individual signals, achieving efficiencies of 77.5%, 73% and 89.78% for the analysis of images, current and stray flux signals, respectively, under the variation in cutting speed, and 76.34%, 73% and 63.12% for the analysis of images, current and stray flux signals, respectively, under the variation of feed rate. Significant improvements were observed when the signals are fused, increasing the efficiency up to 95% for the cutting speed variations and 82.84% for the feed rate variations, achieving a system that allows detecting the wear present in the tools according to the needs of the process (online/offline) under different machining parameters. [ABSTRACT FROM AUTHOR]

Excessive feature dimensions impact the effectiveness of machine learning, computationally expensive and the analysis of feature correlations in the engineering area. This paper uses the colour descriptor to get the most optimal feature to improve time consumption and efficiency. This study investigated Ficus carica L. (figs) with three classification stages. The ripening classification of fig was examined using colour features descriptor with two different colour models, RGB and HSV. In addition, the machine learning classification model based on Artificial Neural Network (ANN) that utilised the Feed-Forward Neural Network (FFNN) model to classify the ripeness of fig is considered in this characterisation. Five different numbers of binning were characterised for RGB and HSV. Both colour feature descriptors were compared in terms of accuracy, sensitivity, precision, and time consumption to identify the dimension of the optimal feature. Based on the result, reducing the size of images will improve the time consumption with comparable accuracy. Moreover, the reduction of features dimension cannot be too small or too big due to inequitable enough to differentiate the ripeness stages and lead to a false error state. The optimal features dimension in binning for RGB was 8 (R/G/B) bins with 96.7% accuracy. Meanwhile, 96.7% accuracy for HSV at 15, 5, and 5 (H, S, V) bins as optimal colour features. [ABSTRACT FROM AUTHOR]

In this study, Covid-19 modeling in Indonesia is carried out using a time series model. The time series model used is the time series model for discrete data. These models consist of Feedforward Neural Network (FFNN), Error, Trend, and Seasonal (ETS), Singular Spectrum Analysis (SSA), Fuzzy Time Series (FTS), Generalized Autoregression Moving Average (GARMA), and Bayesian Time Series. Based on the results of forecast accuracy calculation using MAPE (Mean Absolute Percentage Error) as model evaluation for confirmed data, the most accurate case models is the bayesian model of 0.04%, while all recovered cases yield MAPE 0.05%, except for FTS = 0.06%. For data for death cases SSA and Bayesian Models, the best with MAPE is 0.07%.

Copyright of Revista CienciaUAT is the property of Universidad Autonoma de Tamaulipas and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Brain tumours are considered one of the deadliest tumours in humans and have a low survival rate due to their heterogeneous nature. Several types of benign and malignant brain tumours need to be diagnosed early to administer appropriate treatment. Magnetic resonance (MR) images provide details of the brain's internal structure, which allow radiologists and doctors to diagnose brain tumours. However, MR images contain complex details that require highly qualified experts and a long time to analyse. Artificial intelligence techniques solve these challenges. This paper presents four proposed systems, each with more than one technology. These techniques vary between machine, deep and hybrid learning. The first system comprises artificial neural network (ANN) and feedforward neural network (FFNN) algorithms based on the hybrid features between local binary pattern (LBP), grey-level co-occurrence matrix (GLCM) and discrete wavelet transform (DWT) algorithms. The second system comprises pre-trained GoogLeNet and ResNet-50 models for dataset classification. The two models achieved superior results in distinguishing between the types of brain tumours. The third system is a hybrid technique between convolutional neural network and support vector machine. This system also achieved superior results in distinguishing brain tumours. The fourth proposed system is a hybrid of the features of GoogLeNet and ResNet-50 with the LBP, GLCM and DWT algorithms (handcrafted features) to obtain representative features and classify them using the ANN and FFNN. This method achieved superior results in distinguishing between brain tumours and performed better than the other methods. With the hybrid features of GoogLeNet and hand-crafted features, FFNN achieved an accuracy of 99.9%, a precision of 99.84%, a sensitivity of 99.95%, a specificity of 99.85% and an AUC of 99.9%. [ABSTRACT FROM AUTHOR]

Tropical cyclones that originate from the Indian Ocean affect the Indian Sub-Continent. Heavy rainfall and flooding occur because of these cyclones. South Odisha was affected by Cyclonic Storm Daye in September 2018 and Cyclonic Storm Titli was occurred in August affecting Andhra Pradesh and Odisha as well. The Eastern portion of India was affected by the Cyclonic Storm Fani in April 2019. In May 2020, West Bengal was affected by the Amphan which is a Super Cyclonic Storm and in the same year Tamil Nadu was affected by the very severe Cyclonic Storm Nivar in November 2020. These are just a few of the notable cyclonic events in the Indian Sub-Continent. These cyclonic events cause a dramatic change in a very short time from dry soil to exceptional flooding. In this proposed work, we are attempting to create an observations-driven prediction model to quantify the soil moisture variations daily, predict county-based meteorology and evaluate the cause of cyclones and heavy rainfall in certain areas of India. In our work, we applied a deep learning-based methodology to predict soil moisture. For the prediction model, we fused Feed Forward Neural Networks with the Gated Recurrent Unit (GRU) model and present the prediction results. We have used climatic as well as environmental data published by the Indian Meteorological Department (IMD) Warning from 2011. The collected data is time-series data. Comparisons and the relationship that exists between soil moisture and meteorological data are made and analyzed. The soil moisture of the South Indian states Karnataka, Andhra Pradesh and Tamil Nadu are predicted from weather data using a hybrid deep learning model. The evaluations of the proposed work using Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE) and R-squared (R2) against Non-hybrid Neural Network models such as Artificial Neural Networks (ANN), Convolutional Neural Networks, and Gated Recurrent Unit (GRU) models is analyzes where our model has given better results. [ABSTRACT FROM AUTHOR]

The increasing number of mobile devices challenges the current radio frequency (RF) networks. A hybrid RF/VLC network (HLRN) is proposed to mitigate the spatial fluctuation of data rate, offering a system throughput greaterthan that of standalone visible light communications (VLC) or radio frequency (RF) networks. In hybrid networks, themain problem is load balancing, which reduces network performance. Therefore, to solve this problem, the load balancing(LB) schemes in HLRNs are studied and focus on the AP assignment for the users. In that, efficient spectrum sensing is found essential to prevent the wrong holes detection in the band using five technologies divided into three stages, namely: Received signal strength (RSS), particle swarm optimization (PSO) and deep learning methods: Feed forward neural network (FFNN), convolutional neural network (CNN) and cascade back propagation neural network (CBPNN). An event such as high energy noise availability or primary user fluctuation (mobility) impact on the throughput is studied, which was carried out in three stages depending on MATLAB. In the first stage, the received signal strength (RSS) algorithm is proposed, which is used the SNR to calculate throughputfor fixed and mobility user and user satisfaction. In stage two, the particle swarm optimization (PSO) algorithm is proposed to achieve a better performance than the RSS algorithm. At last, in stage three, the DL algorithms (FFNN, CNN,CBPNN) are used to enhance the performance's accuracy and compare them. The results in stage one show that throughput using RSS technique is decreasing when the number of users increases by achieving 390 Mbps approx. is detected with single user existence while 180 Mbps approx. is detected with 10 users' existence. And it can be noted that most of the users are connected to wireless fidelity (Wi-Fi) AP. Hence the Wi-Fi is overloaded. Further, only 34 % of the users in RSS based scheme will achieve the desired performance if a user satisfactionthreshold of 0.5 is considered for the system. The results in stage two shown that throughput using the PSO technique is outperformed over the others by achieving high average throughput of 960 Mbps approx. Also, it has offered acceptable load balancing for the access points with good user satisfaction reach to 80 % of the users will achieve the desired performance when the user satisfaction threshold is considered to be 0.9 for the system. In stage three, deep learning methods for system performance enhancement are used (as compared with the standard RSS method). throughput is improved, and this improvement is lesser than that in the case of the PSO algorithm. 800 Mbps approx. is achieved using the CNN method, and it is realized that 70 % of the users will achieve full user satisfaction when the user satisfaction threshold is considered 1.2 for the system. [ABSTRACT FROM AUTHOR]

Self-organizing networks (SONs) are considered as one of the key features for automation of network management in new generation of mobile communications. The upcoming fifth-generation mobile networks and beyond are likely to offer new advancements for SON solutions. In SON concept, self-healing is a prominent task which comes along with cell outage detection and cell outage compensation. Next-generation cellular networks are supposed to have ultra-dense deployments which make cell outage detection critical and harder for network maintenance. Therefore, by imitating the ultra-dense multi-tiered scenarios, this study scrutinizes femtocell outage detection with the help of long short-term memory and one-dimensional convolutional neural networks by using time sequences of key performance indicator parameters generated in user equipment. In both the proposed schemes, probable outage-related anomalies in femto access points (FAP) are detected and classified within predetermined time sequence intervals. Moreover, aggregation decision methods are also incorporated into the proposed framework for boosting cell outage detection procedure on FAP level. Our findings show that proposed deep learning approaches outperform existing feed-forward neural networks, and on the average, in more than 80% of the cases the outage states of the femtocells are correctly predicted among healthy and three anomalous states. [ABSTRACT FROM AUTHOR]

Malignant lymphoma is one of the types of malignant tumors that can lead to death. The diagnostic method for identifying malignant lymphoma is a histopathological analysis of lymphoma tissue images. Because of the similar morphological characteristics of the lymphoma types, it is difficult for doctors and specialists to manually distinguish the types of lymphomas. Therefore, deep and automated learning techniques aim to solve this problem and help clinicians reconsider their diagnostic decisions. Because of the similarity of the morphological characteristics between lymphoma types, this study aimed to extract features using various algorithms and deep learning models and combine them together into feature vectors. Two datasets have been applied, each with two different systems for the reliable diagnosis of malignant lymphoma. The first system was a hybrid system between DenseNet-121 and ResNet-50 to extract deep features and reduce their dimensions by the principal component analysis (PCA) method, using the support vector machine (SVM) algorithm for classifying low-dimensional deep features. The second system was based on extracting the features using DenseNet-121 and ResNet-50 and combining them with the hand-crafted features extracted by gray level co-occurrence matrix (GLCM), fuzzy color histogram (FCH), discrete wavelet transform (DWT), and local binary pattern (LBP) algorithms and classifying them using a feed-forward neural network (FFNN) classifier. All systems achieved superior results in diagnosing the two datasets of malignant lymphomas. An FFNN classifier with features of ResNet-50 and hand-crafted features reached an accuracy of 99.5%, specificity of 100%, sensitivity of 99.33%, and AUC of 99.86% for the first dataset. In contrast, the same technique reached 100% for all measures to diagnose the second dataset. [ABSTRACT FROM AUTHOR]

The energy sector which includes gas and oil is concerned to explore and develop refined oil and it’s a multitrillion business. As crude oil is a very important source of energy, and it has a very valuable impact on a country’s economic growth, national security, and social stability. Therefore, accurately predicting the crude oil price volatility is a very important topic of research and still, it is a challenge for researchers to accurately forecast crude oil prices. Therefore, this study is conducted to address the said problem significantly. This research presents a novel hybrid method for reconstructing EEMD IMFs that involves two steps. Visual analysis of Average Mutual Information (AMI) graphs were used to rebuild IMFs. EEMD IMFs were split into two components called stochastic and deterministic. In the proposed method, reconstruction of IMFs of EEMD was done at two stages to see if the stochastic components have more variation. Later, ARIMA and FFNN models were used to test the suggested method’s performance. For this purpose, Brent crude oil prices data was used, and the hybrid model EEMD-S2D1D2-ARIMA/FFNN outperformed the other existing hybrid model with minimum MAE = 0.2323, RMSE = 0.3058 and MAPE = 0.5273. A simulation study was also conducted to check the robustness of the proposed method for N = 50, 500, 1,000, 2000, 5,000, and 7,500. The simulation results also confirm that the unpredictability present in the reconstructed IMFs of the hybrid models EEMD-ARIMA/FFNN and EEMD-SD-ARIMA/FFNN has been reduced by the proposed hybrid models.

Diabetic retinopathy (DR) is a complication of diabetes that damages the delicate blood vessels of the retina and leads to blindness. Ophthalmologists rely on diagnosing the retina by imaging the fundus. The process takes a long time and needs skilled doctors to diagnose and determine the stage of DR. Therefore, automatic techniques using artificial intelligence play an important role in analyzing fundus images for the detection of the stages of DR development. However, diagnosis using artificial intelligence techniques is a difficult task and passes through many stages, and the extraction of representative features is important in reaching satisfactory results. Convolutional Neural Network (CNN) models play an important and distinct role in extracting features with high accuracy. In this study, fundus images were used for the detection of the developmental stages of DR by two proposed methods, each with two systems. The first proposed method uses GoogLeNet with SVM and ResNet-18 with SVM. The second method uses Feed-Forward Neural Networks (FFNN) based on the hybrid features extracted by first using GoogLeNet, Fuzzy color histogram (FCH), Gray Level Co-occurrence Matrix (GLCM), and Local Binary Pattern (LBP); followed by ResNet-18, FCH, GLCM and LBP. All the proposed methods obtained superior results. The FFNN network with hybrid features of ResNet-18, FCH, GLCM, and LBP obtained 99.7% accuracy, 99.6% precision, 99.6% sensitivity, 100% specificity, and 99.86% AUC.

White blood cells (WBCs) are one of the main components of blood produced by the bone marrow. WBCs are part of the immune system that protects the body from infectious diseases and an increase or decrease in the amount of any type that causes a particular disease. Thus, recognizing the WBC types is essential for diagnosing the patient’s health and identifying the disease. Analyzing blood samples to determine the amount and WBC types requires experienced doctors. Artificial intelligence techniques were applied to analyze blood samples and classify their types to help doctors distinguish between types of infectious diseases due to increased or decreased WBC amounts. This study developed strategies for analyzing blood slide images to classify WBC types. The first strategy is to classify WBC types by the SVM-CNN technique. The second strategy for classifying WBC types is by SVM based on hybrid CNN features, which are called VGG19-ResNet101-SVM, ResNet101-MobileNet-SVM, and VGG19-ResNet101-MobileNet-SVM techniques. The third strategy for classifying WBC types by FFNN is based on a hybrid model of CNN and handcrafted features. With MobileNet and handcrafted features, FFNN achieved an AUC of 99.43%, accuracy of 99.80%, precision of 99.75%, specificity of 99.75%, and sensitivity of 99.68%.

The gastrointestinal system contains the upper and lower gastrointestinal tracts. The main tasks of the gastrointestinal system are to break down food and convert it into essential elements that the body can benefit from and expel waste in the form of feces. If any organ is affected, it does not work well, which affects the body. Many gastrointestinal diseases, such as infections, ulcers, and benign and malignant tumors, threaten human life. Endoscopy techniques are the gold standard for detecting infected parts within the organs of the gastrointestinal tract. Endoscopy techniques produce videos that are converted into thousands of frames that show the disease’s characteristics in only some frames. Therefore, this represents a challenge for doctors because it is a tedious task that requires time, effort, and experience. Computer-assisted automated diagnostic techniques help achieve effective diagnosis to help doctors identify the disease and give the patient the appropriate treatment. In this study, many efficient methodologies for analyzing endoscopy images for diagnosing gastrointestinal diseases were developed for the Kvasir dataset. The Kvasir dataset was classified by three pre-trained models: GoogLeNet, MobileNet, and DenseNet121. The images were optimized, and the gradient vector flow (GVF) algorithm was applied to segment the regions of interest (ROIs), isolating them from healthy regions and saving the endoscopy images as Kvasir-ROI. The Kvasir-ROI dataset was classified by the three pre-trained GoogLeNet, MobileNet, and DenseNet121 models. Hybrid methodologies (CNN–FFNN and CNN–XGBoost) were developed based on the GVF algorithm and achieved promising results for diagnosing disease based on endoscopy images of gastroenterology. The last methodology is based on fused CNN models and their classification by FFNN and XGBoost networks. The hybrid methodology based on the fused CNN features, called GoogLeNet–MobileNet–DenseNet121–XGBoost, achieved an AUC of 97.54%, accuracy of 97.25%, sensitivity of 96.86%, precision of 97.25%, and specificity of 99.48%.

Knee osteoarthritis (KOA) is a chronic disease that impedes movement, especially in the elderly, affecting more than 5% of people worldwide. KOA goes through many stages, from the mild grade that can be treated to the severe grade in which the knee must be replaced. Therefore, early diagnosis of KOA is essential to avoid its development to the advanced stages. X-rays are one of the vital techniques for the early detection of knee infections, which requires highly experienced doctors and radiologists to distinguish Kellgren-Lawrence (KL) grading. Thus, artificial intelligence techniques solve the shortcomings of manual diagnosis. This study developed three methodologies for the X-ray analysis of both the Osteoporosis Initiative (OAI) and Rani Channamma University (RCU) datasets for diagnosing KOA and discrimination between KL grades. In all methodologies, the Principal Component Analysis (PCA) algorithm was applied after the CNN models to delete the unimportant and redundant features and keep the essential features. The first methodology for analyzing x-rays and diagnosing the degree of knee inflammation uses the VGG-19 -FFNN and ResNet-101 -FFNN systems. The second methodology of X-ray analysis and diagnosis of KOA grade by Feed Forward Neural Network (FFNN) is based on the combined features of VGG-19 and ResNet-101 before and after PCA. The third methodology for X-ray analysis and diagnosis of KOA grade by FFNN is based on the fusion features of VGG-19 and handcrafted features, and fusion features of ResNet-101 and handcrafted features. For an OAI dataset with fusion features of VGG-19 and handcrafted features, FFNN obtained an AUC of 99.25%, an accuracy of 99.1%, a sensitivity of 98.81%, a specificity of 100%, and a precision of 98.24%. For the RCU dataset with the fusion features of VGG-19 and the handcrafted features, FFNN obtained an AUC of 99.07%, an accuracy of 98.20%, a sensitivity of 98.16%, a specificity of 99.73%, and a precision of 98.08%.