Global Accuracy Research Articles

Dimensional Accuracy of Novel Vinyl Polysiloxane Compared with Polyether Impression Materials: An In Vitro Study.

Transferring the intraoral situation accurately to the dental laboratory is crucial for fabricating precise restorations. This study aimed to compare the dimensional accuracy of a new hydrophilic quadrofunctional vinyl polysiloxane (VPS) and polyether (PE), in combination with different impression techniques (mono-phase single step or dual-phase single step). The reference model simulated a partially edentulous mandible. Stainless-steel precision balls were welded to specific teeth and were used to detect dimensional deviations. Fifteen impressions were made for each of the following four test groups: (1) VPS mono-phase, (2) PE mono-phase, (3) VPS dual-phase, and (4) PE dual-phase. Global accuracy was measured by deviations from the reference model, while local accuracy focused on the trueness and precision of abutment tooth surfaces. Statistical analysis was conducted using ANOVA (α = 0.05). All distances were underestimated, with the highest global inaccuracies for the cross-arch distance, ranging from -82 µm to -109 µm. The abutment tooth surfaces showed excellent local accuracy for all the materials and techniques, with crown surface trueness < 10 µm and precision < 12 µm. Inlay surfaces had higher inaccuracies (trueness < 15 µm, precision < 26 µm). Within the limitations of this study, all impression materials and techniques can be used to produce models with clinically acceptable accuracy.

CGJO: a novel complex-valued encoding golden jackal optimization

Golden jackal optimization (GJO) is inspired by mundane characteristics and collaborative hunting behaviour, which mimics foraging, trespassing and encompassing, and capturing prey to refresh a jackal’s position. However, the GJO has several limitations, such as a slow convergence rate, low computational accuracy, premature convergence, poor solution efficiency, and weak exploration and exploitation. To enhance the global detection ability and solution accuracy, this paper proposes a novel complex-valued encoding golden jackal optimization (CGJO) to achieve function optimization and engineering design. The complex-valued encoding strategy deploys a dual-diploid organization to encode the real and imaginary portions of the golden jackal and converts the dual-dimensional encoding region to the single-dimensional manifestation region, which increases population diversity, restricts search stagnation, expands the exploration area, promotes information exchange, fosters collaboration efficiency and improves convergence accuracy. CGJO not only exhibits strong adaptability and robustness to achieve supplementary advantages and enhance optimization efficiency but also balances global exploration and local exploitation to promote computational precision and determine the best solution. The CEC 2022 test suite and six real-world engineering designs are utilized to evaluate the effectiveness and feasibility of CGJO. CGJO is compared with three categories of existing optimization algorithms: (1) WO, HO, NRBO and BKA are recently published algorithms; (2) SCSO, GJO, RGJO and SGJO are highly cited algorithms; and (3) L-SHADE, LSHADE-EpsSin and CMA-ES are highly performing algorithms. The experimental results reveal that the effectiveness and feasibility of CGJO are superior to those of other algorithms. The CGJO has strong superiority and reliability to achieve a quicker convergence rate, greater computation precision, and greater stability and robustness.

Photovoltaic modules fault detection, power output, and parameter estimation: A deep learning approach based on electroluminescence images

Accurately detecting faults in photovoltaic modules/cells and estimating their effective power output and parameters of the equivalent circuit representation of photovoltaic modules is becoming increasingly critical for both the reliability of associated systems and the efficiency of electricity production from renewable energy sources. Existing studies often work with datasets containing photovoltaic cells that exhibit one fault at a time, leading to the classification of photovoltaic cells with multiple faults as “mixed” faults. Moreover, factors such as cell alignment and specific fault types, collectively called “cell level features”, are not considered in current studies estimating the power output of a photovoltaic module. Therefore, this paper focuses on a comprehensive deep-learning pipeline to separately detect three types of faults in photovoltaic modules/cells using electroluminescence images. Furthermore, it addresses the estimation of the output power of photovoltaic modules and the series resistance of their equivalent circuit, considering the cell-level characteristics extracted from the electroluminescence images. The proposed model demonstrates its ability to detect “black core”, “crack”, and “edge” faults with global accuracies of 0.93, 0.868, and 0.95, respectively. Furthermore, the proposed model estimates the power output of photovoltaic modules with a normalized mean absolute error of 0.03547 and a normalized root mean squared error of 0.04892. This outperforms the base model that relies solely on non-pre-processed detected faults and significantly larger models adept at extracting features from the electroluminescence images. Moreover, the VGG16-based model estimates the series resistance in the equivalent circuit representation of photovoltaic modules with a normalized mean absolute error of 0.04472 and a normalized root mean squared error of 0.0622.

Deep Learning and Minimally Invasive Endoscopy: Panendoscopic Detection of Pleomorphic Lesions

Introduction: Capsule endoscopy (CE) is a minimally invasive exam suitable of panendoscopic evaluation of the gastrointestinal (GI) tract. Nevertheless, CE is time-consuming with suboptimal diagnostic yield in the upper GI tract. Convolutional neural networks (CNN) are human brain architecture-based models suitable for image analysis. However, there is no study about their role in capsule panendoscopy. Methods: Our group developed an artificial intelligence (AI) model for panendoscopic automatic detection of pleomorphic lesions (namely vascular lesions, protuberant lesions, hematic residues, ulcers, and erosions). 355,110 images (6,977 esophageal, 12,918 gastric, 258,443 small bowel, 76,772 colonic) from eight different CE and colon CE (CCE) devices were divided into a training and validation dataset in a patient split design. The model classification was compared to three CE experts’ classification. The model’s performance was evaluated by its sensitivity, specificity, accuracy, positive predictive value, negative predictive value, and area under the precision-recall curve. Results: The binary esophagus CNN had a diagnostic accuracy for pleomorphic lesions of 83.6%. The binary gastric CNN identified pleomorphic lesions with a 96.6% accuracy. The undenary small bowel CNN distinguished pleomorphic lesions with different hemorrhagic potentials with 97.6% accuracy. The trinary colonic CNN (detection and differentiation of normal mucosa, pleomorphic lesions, and hematic residues) had 94.9% global accuracy. Discussion/Conclusion: We developed the first AI model for panendoscopic automatic detection of pleomorphic lesions in both CE and CCE from multiple brands, solving a critical interoperability technological challenge. Deep learning-based tools may change the landscape of minimally invasive capsule panendoscopy.

Indoor Infrared Sensor Layout Optimization for Elderly Monitoring Based on Fused Genetic Gray Wolf Optimization (FGGWO) Algorithm.

With the increasing aging of the global population, the efficiency and accuracy of the elderly monitoring system become crucial. In this paper, a sensor layout optimization method, the Fusion Genetic Gray Wolf Optimization (FGGWO) algorithm, is proposed which utilizes the global search capability of Genetic Algorithm (GA) and the local search capability of Gray Wolf Optimization algorithm (GWO) to improve the efficiency and accuracy of the sensor layout in elderly monitoring systems. It does so by optimizing the indoor infrared sensor layout in the elderly monitoring system to improve the efficiency and coverage of the sensor layout in the elderly monitoring system. Test results show that the FGGWO algorithm is superior to the single optimization algorithm in monitoring coverage, accuracy, and system efficiency. In addition, the algorithm is able to effectively avoid the local optimum problem commonly found in traditional methods and to reduce the number of sensors used, while maintaining high monitoring accuracy. The flexibility and adaptability of the algorithm bode well for its potential application in a wide range of intelligent surveillance scenarios. Future research will explore how deep learning techniques can be integrated into the FGGWO algorithm to further enhance the system's adaptive and real-time response capabilities.

Neuro-XAI: Explainable deep learning framework based on deeplabV3+ and bayesian optimization for segmentation and classification of brain tumor in MRI scans

The prevalence of brain tumor disorders is currently a global issue. In general, radiography, which includes a large number of images, is an efficient method for diagnosing these life-threatening disorders. The biggest issue in this area is that it takes a radiologist a long time and is physically strenuous to look at all the images. As a result, research into developing systems based on machine learning to assist radiologists in diagnosis continues to rise daily. Convolutional neural networks (CNNs), one type of deep learning approach, have been pivotal in achieving state-of-the-art results in several medical imaging applications, including the identification of brain tumors. CNN hyperparameters are typically set manually for segmentation and classification, which might take a while and increase the chance of using suboptimal hyperparameters for both tasks. Bayesian optimization is a useful method for updating the deep CNN's optimal hyperparameters. The CNN network, however, can be considered a "black box" model because of how difficult it is to comprehend the information it stores because of its complexity. Therefore, this problem can be solved by using Explainable Artificial Intelligence (XAI) tools, which provide doctors with a realistic explanation of CNN's assessments. Implementation of deep learning-based systems in real-time diagnosis is still rare. One of the causes could be that these methods don't quantify the Uncertainty in the predictions, which could undermine trust in the AI-based diagnosis of diseases. To be used in real-time medical diagnosis, CNN-based models must be realistic and appealing, and uncertainty needs to be evaluated. So, a novel three-phase strategy is proposed for segmenting and classifying brain tumors. Segmentation of brain tumors using the DeeplabV3+ model is first performed with tuning of hyperparameters using Bayesian optimization. For classification, features from state-of-the-art deep learning models Darknet53 and mobilenetv2 are extracted and fed to SVM for classification, and hyperparameters of SVM are also optimized using a Bayesian approach. The second step is to understand whatever portion of the images CNN uses for feature extraction using XAI algorithms. Using confusion entropy, the Uncertainty of the Bayesian optimized classifier is finally quantified. Based on a Bayesian-optimized deep learning framework, the experimental findings demonstrate that the proposed method outperforms earlier techniques, achieving a 97 % classification accuracy and a 0.98 global accuracy.

Use of whistles for acoustic classification of delphinids (odontoceti: Delphinidae) in the Western South Atlantic Ocean.

This study focuses on the acoustic classification of delphinid species at the southern continental slope of Brazil. Recordings were collected between 2013 and 2015 using towed arrays and were processed using a classifier to identify the species in the recordings. Using Raven Pro 1.6 software (Cornell Laboratory of Ornithology, Ithaca, NY), we analyzed whistles for species identification. The random forest algorithm in R facilitates classification analysis based on acoustic parameters, including low, high, delta, center, beginning, and ending frequencies, and duration. Evaluation metrics, such as correct and incorrect classification percentages, global accuracy, balanced accuracy, and p-values, were employed. Receiver operating characteristic curves and area-under-the-curve (AUC) values demonstrated well-fitting models (AUC ≥ 0.7) for species definition. Duration and delta frequency emerged as crucial parameters for classification, as indicated by the decrease in mean accuracy. Multivariate dispersion plots visualized the proximity between acoustic and visual match data and exclusively acoustic encounter (EAE) data. The EAE results classified as Delphinus delphis (n = 6), Stenella frontalis (n = 3), and Stenella longirostris (n = 2) provide valuable insights into the presence of these species between approximately 23° and 34° S in Brazil. This study demonstrates the effectiveness of acousting classification in discriminating delphinids through whistle parameters.

Prediction of Drug-Induced Liver Injury: From Molecular Physicochemical Properties and Scaffold Architectures to Machine Learning Approaches.

The process of developing new drugs is widely acknowledged as being time-intensive and requiring substantial financial investment. Despite ongoing efforts to reduce time and expenses in drug development, ensuring medication safety remains an urgent problem. One of the major problems involved in drug development is hepatotoxicity, specifically known as drug-induced liver injury (DILI). The popularity of new drugs often poses a significant barrier during development and frequently leads to their recall after launch. In silico methods have many advantages compared with traditional invivo and invitro assays. To establish a more precise and reliable prediction model, it is necessary to utilize an extensive and high-quality database consisting of information on drug molecule properties and structural patterns. In addition, we should also carefully select appropriate molecular descriptors that can be used to accurately depict compound characteristics. The aim of this study was to conduct a comprehensive investigation into the prediction of DILI. First, we conducted a comparative analysis of the physicochemical properties of extensively well-prepared DILI-positive and DILI-negative compounds. Then, we used classic substructure dissection methods to identify structural pattern differences between these two different types of chemical molecules. These findings indicate that it is not feasible to establish property or substructure-based rules for distinguishing between DILI-positive and DILI-negative compounds. Finally, we developed quantitative classification models for predicting DILI using the naïve Bayes classifier (NBC) and recursive partitioning (RP) machine learning techniques. The optimal DILI prediction model was obtained using NBC, which combines 21 physicochemical properties, the VolSurf descriptors and the LCFP_10 fingerprint set. This model achieved a global accuracy (GA) of 0.855 and an area under the curve (AUC) of 0.704 for the training set, while the corresponding values were 0.619 and 0.674 for the test set, respectively. Moreover, indicative substructural fragments favorable or unfavorable for DILI were identified from the best naïve Bayesian classification model. These findings may help prioritize lead compounds in the early stage of drug development pipelines.

Balanced Quality Score: Measuring Popularity Debiasing in Recommendation

Popularity bias is the tendency of recommender systems to further suggest popular items while disregarding niche ones, hence giving no chance for items with low popularity to emerge. Although the literature is rich in debiasing techniques, it still lacks quality measures that effectively enable their analyses and comparisons. In this article, we first introduce a formal, data-driven, and parameter-free strategy for classifying items into low, medium, and high popularity categories. Then we introduce Balanced Quality Score (BQS) , a quality measure that rewards the debiasing techniques that successfully push a recommender system to suggest niche items, without losing points in its predictive capability in terms of global accuracy. We conduct tests of BQS on three distinct baseline collaborative filtering frameworks: one based on history-embedding and two on user/item-embedding modeling. These evaluations are performed on multiple benchmark datasets and against various state-of-the-art competitors, demonstrating the effectiveness of BQS.

Dynamic formulation and inertia fast estimation of a 5-DOF hybrid robot

As the main driving mechanism of a hybrid robot, the parallel mechanism is a nonlinear time-varying system. The load inertia of its actuated joints changes with the configuration of the robot. Analyzing and fitting the inertia variation is of great significance to the design and control of hybrid robots. By taking a hybrid robot named TriMule as an example, the variation of load inertia of each actuated joint in the whole workspace is first revealed based on the dynamic analyses of the robot. Then two methods based on the circular and elliptical membership are proposed to calculate fitted inertia over the whole workspace using inertia information at a few configurations. Finally, the fitting methods of the two membership functions are compared and discussed. The results show that the maximum value and global mean value of the fitting error of the elliptical membership method are 39.18% (51.23%) and 65.79% (81.25%) for actuated joint-1 (joint-2 and joint-3) lower than those of circular membership method, which promise a better global fitting accuracy. The proposed method can be used to estimate the joint load inertia or other control variables affected by inertia in a quick manner, allowing the algorithm to be easily integrated into the robot control system.

Use of Deep Neural Networks to Predict Obesity With Short Audio Recordings: Development and Usability Study.

The escalating global prevalence of obesity has necessitated the exploration of novel diagnostic approaches. Recent scientific inquiries have indicated potential alterations in voice characteristics associated with obesity, suggesting the feasibility of using voice as a noninvasive biomarker for obesity detection. This study aims to use deep neural networks to predict obesity status through the analysis of short audio recordings, investigating the relationship between vocal characteristics and obesity. A pilot study was conducted with 696 participants, using self-reported BMI to classify individuals into obesity and nonobesity groups. Audio recordings of participants reading a short script were transformed into spectrograms and analyzed using an adapted YOLOv8 model (Ultralytics). The model performance was evaluated using accuracy, recall, precision, and F1-scores. The adapted YOLOv8 model demonstrated a global accuracy of 0.70 and a macro F1-score of 0.65. It was more effective in identifying nonobesity (F1-score of 0.77) than obesity (F1-score of 0.53). This moderate level of accuracy highlights the potential and challenges in using vocal biomarkers for obesity detection. While the study shows promise in the field of voice-based medical diagnostics for obesity, it faces limitations such as reliance on self-reported BMI data and a small, homogenous sample size. These factors, coupled with variability in recording quality, necessitate further research with more robust methodologies and diverse samples to enhance the validity of this novel approach. The findings lay a foundational step for future investigations in using voice as a noninvasive biomarker for obesity detection.

LociPARSE: a locality-aware invariant point attention model for scoring RNA 3D structures.

A scoring function that can reliably assess the accuracy of a 3D RNA structural model in the absence of experimental structure is not only important for model evaluation and selection but also useful for scoring-guided conformational sampling. However, high-fidelity RNA scoring has proven to be difficult using conventional knowledge-based statistical potentials and currently-available machine learning-based approaches. Here we present lociPARSE, a locality-aware invariant point attention architecture for scoring RNA 3D structures. Unlike existing machine learning methods that estimate superposition-based root mean square deviation (RMSD), lociPARSE estimates Local Distance Difference Test (lDDT) scores capturing the accuracy of each nucleotide and its surrounding local atomic environment in a superposition-free manner, before aggregating information to predict global structural accuracy. Tested on multiple datasets including CASP15, lociPARSE significantly outperforms existing statistical potentials (rsRNASP, cgRNASP, DFIRE-RNA, and RASP) and machine learning methods (ARES and RNA3DCNN) across complementary assessment metrics. lociPARSE is freely available at https://github.com/Bhattacharya-Lab/lociPARSE.

Multi-objective hull form optimization utilizing sequential sampling optimization method

With advancements in computer technology, Computational fluid dynamics (CFD) theory provides a numerical tool for evaluating the comprehensive hydrodynamic performance of ships. On this basis, the Simulation-based design (SBD) technology based on the static sampling method (SSM) which is termed as SBD-SSM in this paper is recognized as a hull form optimization method with significant advantages. However, in the SBD-SSM method, the excessive pursuit of the global accuracy of the surrogate model leads to the need for more CFD evaluations. Consequently, this demands the substantiality of computing resources and diminishes optimization efficiency. We apply a novel hull form optimization method based on the Sequential Sampling-based Optimization (SBO) method to address this challenge. Furthermore, to strike an appropriate balance between prediction value and uncertainty while finding optimal solutions, we employ the adaptive sampling method known as Pseudo Expected Improvement Matrix (PEIM). By integrating SBO with PEIM, we introduce the SBO-PEIM optimization method, initially applied through mathematical optimization functions to verify its feasibility in optimization. Subsequently, we apply this method to optimize the total resistance and wake performance of the KCS ship. Our findings demonstrate that the SBO-PEIM method achieves higher prediction accuracy in near-optimal solutions than the SBD-SSM method, enhancing optimization efficiency by at least 17.5%. It validates the efficacy of the SBO-PEIM approach in addressing real-world engineering optimization challenges.

A comparative study of breast tumour detection using a semantic segmentation network coupled with different pretrained CNNs

ABSTRACT Breast cancer is one of the most prevalent malignancies and the primary origin of cancer-related deaths among females worldwide. Ultrasound image segmentation plays a crucial role in identifying breast tumours by precisely delineating the boundaries of the tumour within the images. Deep learning segmentation networks such as DeepLabV3+ have been used in the literature for this purpose. The coupling of DeepLabV3+ with base convolutional neural networks (CNN) can play a key role in its accuracy in tumour detection. The present study investigates the segmentation performance of four combinations of DeepLabV3+ segmentation network by coupling with the four base decoder CNN networks: DarkNet53, SqueezeNet, EfficientNet-b0 and DarkNet19. The accuracy of segmentation is confirmed using standard segmentation error metrics such as global and mean accuracy, mean and weighted Intersection over union (IoU), Boundary F1 (BF) Score and Dice Score. DeepLabV3+ coupled with DarkNet53 and EfficientNet-b0 as the decoder CNNs performed better than the other two combinations with a global accuracy of 96.50% and 96.18%. Precise tumour delineation can assist in tumour growth monitoring and treatment planning by providing detailed information on tumour size, shape, and location; thereby aiding in patient management and follow-up care.

Real-Time Monitoring of Cable Sag and Overhead Power Line Parameters Based on a Distributed Sensor Network and Implementation in a Web Server and IoT.

Based on the need for real-time sag monitoring of Overhead Power Lines (OPL) for electricity transmission, this article presents the implementation of a hardware and software system for online monitoring of OPL cables. The mathematical model based on differential equations and the methods of algorithmic calculation of OPL cable sag are presented. Considering that, based on the mathematical model presented, the calculation of cable sag can be done in different ways depending on the sensors used, and the presented application uses a variety of sensors. Therefore, a direct calculation is made using one of the different methods. Subsequently, the verification relations are highlighted directly, and in return, the calculation by the alternative method, which uses another group of sensors, generates both a verification of the calculation and the functionality of the sensors, thus obtaining a defect observer of the sensors. The hardware architecture of the OPL cable online monitoring application is presented, together with the main characteristics of the sensors and communication equipment used. The configurations required to transmit data using the ModBUS and ZigBee protocols are also presented. The main software modules of the OPL cable condition monitoring application are described, which ensure the monitoring of the main parameters of the power line and the visualisation of the results both on the electricity provider's intranet using a web server and MySQL database, and on the Internet using an Internet of Things (IoT) server. This categorisation of the data visualisation mode is done in such a way as to ensure a high level of cyber security. Also, the global accuracy of the entire OPL cable sag calculus system is estimated at 0.1%. Starting from the mathematical model of the OPL cable sag calculation, it goes through the stages of creating such a monitoring system, from the numerical simulations carried out using Matlab to the real-time implementation of this monitoring application using Laboratory Virtual Instrument Engineering Workbench (LabVIEW).

A Multi-Strategy Collaborative Grey Wolf Optimization Algorithm for UAV Path Planning

The Grey Wolf Optimization Algorithm (GWO) is a member of the swarm intelligence algorithm family, which possesses the highlights of easy realization, simple parameter settings and wide applicability. However, in some large-scale application problems, the grey wolf optimization algorithm easily gets trapped in local optima, exhibits poor global exploration ability and suffers from premature convergence. Since grey wolf’s update is guided only by the best three wolves, it leads to low population multiplicity and poor global exploration capacity. In response to the above issues, we design a multi-strategy collaborative grey wolf optimization algorithm (NOGWO). Firstly, we use a random walk strategy to extend the exploration scope and enhance the algorithm’s global exploration capacity. Secondly, we add an opposition-based learning model influenced by refraction principle to generate an opposite solution for each population, thereby improving population multiplicity and preventing the algorithm from being attracted to local optima. Finally, to balance local exploration and global exploration and elevate the convergence effect, we introduce a novel convergent factor. We conduct experimental testing on NOGWO by using 30 CEC2017 test functions. The experimental outcomes indicate that compared with GWO and some swarm intelligence algorithms, NOGWO has better global exploration capacity and convergence accuracy. In addition, we also apply NOGWO to three engineering problems and an unmanned aerial vehicle path planning problem. The outcomes of the experiment suggest that NOGWO performs well in solving these practical problems.

Diagnostic performance of plasma pTau217, pTau181, Aβ1-42 and Aβ1-40 in the LUMIPULSE automated platform for the detection of Alzheimer disease

BackgroundRecently developed blood markers for Alzheimer's disease (AD) detection have high accuracy but usually require ultra-sensitive analytic tools not commonly available in clinical laboratories, and their performance in clinical practice is unknown.MethodsWe analyzed plasma samples from 290 consecutive participants that underwent lumbar puncture in routine clinical practice in a specialized memory clinic (66 cognitively unimpaired, 130 participants with mild cognitive impairment, and 94 with dementia). Participants were classified as amyloid positive (A +) or negative (A-) according to CSF Aβ1–42/Aβ1–40 ratio. Plasma pTau217, pTau181, Aβ1–42 and Aβ1–40 were measured in the fully-automated LUMIPULSE platform. We used linear regression to compare plasma biomarkers concentrations between A + and A- groups, evaluated Spearman’s correlation between plasma and CSF and performed ROC analyses to assess their diagnostic accuracy to detect brain amyloidosis as determined by CSF Aβ1–42/Aβ1–40 ratio. We analyzed the concordance of pTau217 with CSF amyloidosis.ResultsPlasma pTau217 and pTau181 concentration were higher in A + than A- while the plasma Aβ1–42/Aβ1–40 ratio was lower in A + compared to A-. pTau181 and the Aβ1–42/Aβ1–40 ratio showed moderate correlation between plasma and CSF (Rho = 0.66 and 0.69, respectively). The areas under the ROC curve to discriminate A + from A- participants were 0.94 (95% CI 0.92–0.97) for pTau217, and 0.88 (95% CI 0.84–0.92) for both pTau181 and Aβ1–42/Aβ1–40. Chronic kidney disease (CKD) was related to increased plasma biomarker concentrations, but ratios were less affected. Plasma pTau217 had the highest fold change (× 3.2) and showed high predictive capability in discriminating A + from A-, having 4–7% misclassification rate. The global accuracy of plasma pTau217 using a two-threshold approach was robust in symptomatic groups, exceeding 90%.ConclusionThe evaluation of blood biomarkers on an automated platform exhibited high diagnostic accuracy for AD pathophysiology, and pTau217 showed excellent diagnostic accuracy to identify participants with AD in a consecutive sample representing the routine clinical practice in a specialized memory unit.

Private Blockchain-Based Efficient Secure Cloud Data Storage Using Federated Learning Framework

Background: Some of the new challenges that consumers are confronted with include safeguarding data and privacy. Data retrieved from the cloud's external sources and the calculations that follow aren't always accurate. Addressing the risk of adversaries utilizing various exploitation techniques to compromise transactional data privacy is a basic concern when establishing big private networks. The profession of criminal investigation is quickly embracing new technologies, and one of these is blockchain. Every sector, from banking and supply chain management to smart apps and the Internet of Things (IoT), has been increasingly vulnerable to security threats in recent years. Methods: An effective solution to the "data island" problem, federated-learning (FL) has recently been a hot and broad concern topic. But as FL technology finds more practical uses, training management gets more complicated, and the trade-off of multi-tasking gets more difficult, due to the increasing quantity of FL tasks. A privacy-preserving FL framework with multi-tasks using a partitioned blockchain is proposed in this study to address this shortcoming. The framework may execute several FL tasks by separate requesters. To start, an FL task force is established to help with the visualization, organization, and administration of security aggregation. Result: In order to safeguard users' privacy and guarantee the accuracy of the global model, the suggested framework incorporates both Paillier-homomorphic-encryption(PHE) and Pearson-correlation-coefficient(PCC). Lastly, a novel incentive system based on the blockchain is introduced to encourage individuals to provide their valuable data. Conclusion: Our suggested framework achieves a global model accuracy of 99.2% according to the experimental data. Specifically, in the realm of industrial applications, the suggested framework is clearly more suited to real-world settings.

EEG BASED SEQUENTIAL EPILEPTIC SEIZURE DETECTION USING CNN

The objective of the research work is to propose an electroencephalography based sequential approach for epileptic seizure detection method in a real time environment using chronological 2D convolutional neural network (CNN). Even though in link with CNN an electroencephalography (EEG) shows a substantial characters in observing the brain commotion of patients detecting epilepsy, it is pretended to investigate number of EEG illustration and its histories to perceive apprehensive epileptic activity. The proposed Model flows towards a BiLSTM (Bi-directional LSTM) to find multi-channel EEG signals and deliberates longitudinal temporal association, a feature in epileptic seizure discovery based on 2D convolutional layers. This research also been motivated to invoke and frame of CNN based raw electroencephalography indicators to advance the accuracy of finding epileptic seizure, as an alternative of regular feature abstraction to differentiate ictal, preictal, and interictal variations to find epileptic seizure detection. It was compared the routines of time and regularity domain signals in the detection of epileptic signals which is constructed and based on the health organization and its collaburation worldwide with scalp record which is transportable and potential in these parameters. Sorting the sequential approach and its consequences show that CNN has an approaching ability in the classification of EEG signals with a sequential verification and validation to recognition an accurate epileptic seizures by reaching 99.18% of global classification accuracy. Key words: Convolutional neural network (CNN), Bi-LSTM, Electroencephalography (EEG), Epileptic seizure.

High-resolution mapping of tree species and associated uncertainty by combining aerial remote sensing data and convolutional neural networks ensemble

Mapping tree species diversity is essential for monitoring and managing forest ecosystems. Automating ecoforestry mapping using remote sensing images remains an important challenge due to the tremendous variability in forest covers and the conditions under which images used for classification are acquired. Deep learning algorithms have been increasingly used over the last few years to analyse remote sensing data for mapping tree species. However, most of these studies focus only on a small number of species or a limited area and avoid providing a spatially explicit representation of the uncertainty related to the predictions, rendering them unsuitable for operational use.In this study, we used an ensemble of convolutional neural networks to map forest species and land cover types across a 10,000 km2 area in Quebec, Canada, spanning mixed and boreal forests. We built a georeferenced label database to train and test nine models, which resulted from the combination of three training datasets and three-commonly used convolutional neural network architectures (VGG16, ResNet50v2, Densenet121). These models were trained on multiband aerial photographs and a canopy height model derived from airborne lidar point clouds and used to map the diversity and distribution of tree species and land cover types. The level of agreement among models was used to generate uncertainty maps. The performance of the super-ensemble using 1311 independent forest inventory plots and assessed the extent to which uncertainty maps could serve as a spatially explicit indicator of model performance.The super-ensemble achieved 90% global accuracy. Our results indicated that the performance of the super-ensemble surpassed that of all individual architectures while also showing a positive effect of the canopy height model on performance. The comparison of the super-ensemble map with the proportion of basal area measured in forest inventory plots confirmed the reliability of the model over the study area. Our results also indicated that mapping the inter-model agreement provides a reliable spatially explicit estimate of model performance. The robustness and reliability of the proposed approach support its use in an operational context while also providing a conceptual framework to evaluate the reliability of uncertainty maps.