Increased Accuracy Rate Research Articles

Wild Horse Optimizer and Support Vector Machine (SVM) Classifier Predicts The Heart Disease Converging Nature-Motivated Optimization and Machine Learning

Background: As one of the leading causes of morbidity and mortality worldwide, the diagnosis of acute cardiovascular disease (acute CVD) in emergency settings remains a significant challenge. Machine learning (ML) is artificial intelligence that allows computer programs to learn from and analyze large data sets without human intervention. As a diagnostic tool, ML presents numerous advantages, such as convenience, speed, and affordability. Methods: This research utilized a new model for predicting heart disease for feature selection(Wild Horse Optimizer, WHO) and another classification model (Support Vector Machine, SVM). In the WHO algorithm, like envisioning social behaviors of wild horses, we observe that wild horses display diverse behaviors like leading, grazing, moving, mating and chase. One odd behavior about wild horses is that young foals will break away from the herd to avoid the breed in its related herd before reaching maturity. It defines the decencies of the horses. Discussion: Multiple ML techniques were employed to train classifiers using the Cleveland heart disease dataset after conducting feature selection using WHO algorithm. The performance of these models was evaluated based on different parameters like Sensitivity, Accuracy, Specificity, and AUC. The SVM classifier model trained using the WHO approach proved better than the existing methods. In the research, we proposed a Wild Horse Optimization algorithm to optimize the features for Heart Disease prediction. After feature optimization, the optimized dataset is then given to Support Vector machine classification, which performs the classification of heart disease. After evaluating different experimental results, authors conclude that combining this feature selection algorithm and SVM as a classifier for forecasting heart disease is very effective. With the help of this approach, we can improve the early detection of heart disease and effectively manage severe heart disease. The experimental result graph shows an increased accuracy rate of the spectra feature subject.

Hearing Assistive Technology Facilitates Sentence-in-Noise Recognition in Chinese Children With Autism Spectrum Disorder.

Hearing assistive technology (HAT) has been shown to be a viable solution to the speech-in-noise perception (SPIN) issue in children with autism spectrum disorder (ASD); however, little is known about its efficacy in tonal language speakers. This study compared sentence-level SPIN performance between Chinese children with ASD and neurotypical (NT) children and evaluated HAT use in improving SPIN performance and easing SPIN difficulty. Children with ASD (n = 26) and NT children (n = 19) aged 6-12 years performed two adaptive tests in steady-state noise and three fixed-level tests in quiet and steady-state noise with and without using HAT. Speech recognition thresholds (SRTs) and accuracy rates were assessed using adaptive and fixed-level tests, respectively. Parents or teachers of the ASD group completed a questionnaire regarding children's listening difficulty under six circumstances before and after a 10-day trial period of HAT use. Although the two groups of children had comparable SRTs, the ASD group showed a significantly lower SPIN accuracy rate than the NT group. Also, a significant impact of noise was found in the ASD group's accuracy rate but not in that of the NT group. There was a general improvement in the ASD group's SPIN performance with HAT and a decrease in their listening difficulty ratings across all conditions after the device trial. The findings indicated inadequate SPIN in the ASD group using a relatively sensitive measure to gauge SPIN performance among children. The markedly increased accuracy rate in noise during HAT-on sessions for the ASD group confirmed the feasibility of HAT for improving SPIN performance in controlled laboratory settings, and the reduced post-use ratings of listening difficulty further confirmed the benefits of HAT use in daily scenarios.

Implementation of Hybrid Deep Reinforcement Learning Technique for Speech Signal Classification

Classification of speech signals is a vital part of speech signal processing systems. With the advent of speech coding and synthesis, the classification of the speech signal is made accurate and faster. Conventional methods are considered inaccurate due to the uncertainty and diversity of speech signals in the case of real speech signal classification. In this paper, we use efficient speech signal classification using a series of neural network classifiers with reinforcement learning operations. Prior classification of speech signals, the study extracts the essential features from the speech signal using Cepstral Analysis. The features are extracted by converting the speech waveform to a parametric representation to obtain a relatively minimized data rate. Hence to improve the precision of classification, Generative Adversarial Networks are used and it tends to classify the speech signal after the extraction of features from the speech signal using the cepstral coefficient. The classifiers are trained with these features initially and the best classifier is chosen to perform the task of classification on new datasets. The validation of testing sets is evaluated using RL that provides feedback to Classifiers. Finally, at the user interface, the signals are played by decoding the signal after being retrieved from the classifier back based on the input query. The results are evaluated in the form of accuracy, recall, precision, f-measure, and error rate, where generative adversarial network attains an increased accuracy rate than other methods: Multi-Layer Perceptron, Recurrent Neural Networks, Deep belief Networks, and Convolutional Neural Networks.

A Hybrid Branch Prediction Approach For High-Performance Processors

Background: In a parallel processor, the pipeline cannot fetch the conditional instructions with the next clock cycle, leading to a pipeline stall. Therefore, conditional instructions create a problem in the pipeline because the proper path can only be known after the branch execution. To accurately predict branches, a significant predictor is proposed for the prediction of the conditional branch instruction. Method: In this paper, a single branch prediction and a correlation branch prediction scheme are applied to the different trace files by using the concept of saturating counters. Further, a hybrid branch prediction scheme is proposed, which uses both global and local branch information, providing more accuracy than the single and correlation branch prediction schemes. Results: Firstly, a single branch prediction and correlation branch prediction technique are applied to the trace files using saturating counters. By comparison, it can be observed that a correlation branch prediction technique provides better results by enhancing the accuracy rate of 2.25% than the simple branch prediction. Further, a hybrid branch prediction scheme is proposed, which uses both global and local branch information, providing more accuracy than the single and correlation branch prediction schemes. The results suggest that the proposed hybrid branch prediction schemes provide an increased accuracy rate of 3.68% and 1.43% than single branch prediction and correlation branch prediction. Conclusion: The proposed hybrid branch prediction scheme gives a lower misprediction rate and higher accuracy rate than the simple branch prediction scheme and correlation branch prediction scheme.

Automated Detection of Pneumothorax Using Frontal Chest X-rays

Pneumothorax detection can assist doctors in treatment and diagnosis of diseases more accurately. In this paper automated method employed image segmentation techniques for the detection. The preprocessing methods are handled by image processing techniques using MATLAB 2020b software Support Vector machine is applied to classify normal and abnormal lung chest X-ray. Features are extracted from lung image with the texture based segmentation techniques. The rib boundaries are identified with sobel edge detection. The gray level incurrence matrices segmentation method increase accuracy rate with AUC 0.91.

Application of Artificial Intelligence Combined with Three-Dimensional Digital Technology in the Design of Complex Works of Art

Technological advancement is leaving its imprint on all domains and making works more accessible. They have also taken steps in the arts and crafts. Old arts and crafts can be given new life with digital technology. A combination of artificial intelligence and three-dimensional digital technology converts art images into three-dimensional image art by identifying the frequency of the image and storing the details in a database. This process is performed by transferring the image data through wireless sensor networks. The conversion of normal images into three-dimensional digital technology is achieved with the aid of sensors available in digital technology. This data will aid in the easy identification of the images. The Surface Wavefront Reconstruction on Fast Fourier Transform (SWRFFT) Method is implemented, evaluating the performance of a combination of AI and three-dimensional technology. This proposed method is compared with the existing system, and it is observed that the proposed SWRFFT method provides a 2.47% increased accuracy rate in the correlation of the image with the frequency generation.

Knowledge Graph and GNN-Based News Recommendation Algorithm With Edge Computing Support

The current news information from different media websites has posed a serious problem, i.e., it is very difficult to obtain the satisfactory news contents from the measured data information. There have been some researches on news recommendation to improve the experience of users. In spite of this, they always need the further improvement because the news information has showed the explosive increasing way. Therefore, this paper studies knowledge graph and graph neural network (GNN) based news recommendation algorithm with edge computing consideration. At first, the knowledge graph is used for the knowledge extraction. Then, GNN is used to train the extracted features to complete the news recommendation algorithm. Finally, the edge computing is used to offload the high volumes of traffic to the edge server for the news recommendation computation. Compared with two baselines, the proposed algorithm is more efficient, increasing accuracy rate by 2.73% and 9.94% respectively, and decreasing response time by 84.27% and 87.58 respectively.

Multi‐step wind speed and wind power forecasting using variational momentum factor and deep learning based intelligent neural network models

AbstractDeep learning based novel intelligent neural network models are developed in this research study and employed for performing multi‐step wind speed and wind power forecasting for the data pertaining to certain wind farms. It has always been tedious to predict wind speed and wind power accurately due the existence of non‐linearity in the wind farm data and as well previous traditional and heuristic techniques has their own merits and demerits in performing the prediction process. This research study intends to handle the prevailing non‐linearity of the wind farm data and as well perform prediction of the parameters in a better manner with increased accuracy rate. The prediction study facilitates the renewable energy community to install the wind mills in the locations with higher accuracy rate and thereby power production gets increased extravagantly. The intelligent neural network developed in this article includes the ELMAN and spiking neuronal models with incorporated deep learning procedure and varying momentum factor criterion to achieve minimal error and better accuracy rate. Multi‐step forecasting is carried for 10‐min ahead and the numerical simulation executed with the proposed intelligent non‐linear forecasting techniques. The attained results confirm the superiority of the developed models over other techniques from previous works.

Sensitivity to Regular and Irregular Past Tense Morphology in Native Speakers and Second Language Learners of English: Evidence From Intermediate-to-Advanced Persian Speakers of L2 English.

This study investigates whether L2 learners (L2ers) use the same mechanisms as those of native English speakers (NSs) for processing regular and irregular past tense forms. Intermediate-to-advanced Persian-English L2ers and NSs participated in two online experiments using Speeded Grammaticality Judgment tasks. Experiment 1 examined regular and irregular past tense forms and Experiment 2 the effect of frequency on regular past tense forms. The results of both the accuracy and reaction time data show a pattern of convergence between NSs and L2ers. Particularly, the accuracy data provide new evidence showing that L2ers converge on NSs in showing distinct processes for regular and irregular tense forms. Additionally, both groups similarly showed an anti-frequency effect for regular verbs, i.e., the frequency increased accuracy rates for low-frequency regular verbs in comparison to high-frequency ones. It is concluded that L2ers use mechanisms similar to those of NSs for processing regular and irregular past tense forms.

An efficient branch predictor for improved accuracy of instruction level parallelism

The need for modern processors is based on fast and precise branch predictors to improve the execution of instructions in the pipeline. In a parallel processor, the pipeline cannot execute the conditional instructions with the next clock cycle, leading to a pipeline stall. To address this issue, this paper suggests a variety of branch prediction techniques for improving the execution speed of conditional instructions. Firstly, a simple branch prediction and a dynamic branch prediction are applied to the trace files using saturating counters. Among these two, dynamic branch prediction provides better results by enhancing the accuracy rate of 2.01% than the static branch prediction. Further, the perceptron branch predictor predicts the implementation by using a table of perceptron and train function. This prediction scheme reduces the difficulties in dynamic branch predictor schemes such as reduces the complexity in history length table and improves the accuracy rate by 5.36%. For accuracy, a novel model based on global perceptron branch predictor is developed, which uses both global and per branch information. Trace-driven simulations have been performed by varying the range of hardware budget, traces file size, and the length of history register to increase the accuracy rate of each branch prediction technique. The obtained results suggest that the proposed global perceptron branch predictor provides an increased accuracy rate of 10.47% at 4 kb hardware budget and 8.06% at 4-bit history length than the perceptron branch predictor.

BAND REDUCTION FOR TARGET DETECTION IN HYPERSPECTRAL IMAGES

Due to the high spectral resolution, hyperspectral images need large data storage and processing time. Indeed, its high dimensional structure requires high computational complexity, especially for target detection. In order to overcome these problems, band reduction methods have been proposed. In this paper, we compare PCA and SNR-based band reduction methods to improve target detection performance in hyperspectral images. Experimental results show that band reduction methods not only reduce processing time, but also increase accuracy rate.

Age-Related Changes in the Neural Processes of Reward-Directed Action and Inhibition of Action.

Aging is associated with structural and functional brain changes which may impact the regulation of motivated behaviors, including both action and inhibition of action. As behavioral regulation is often exercised in response to reward, it remains unclear how aging may influence reward-directed action and inhibition of action differently. Here we addressed this issue with the functional magnetic resonance imaging data of 72 participants (aged 21–74) performing a reward go/no-go (GNG) task with approximately 2/3 go and 1/3 no-go trials. The go and no-go success trials were rewarded with a dollar or a nickel, and the incorrect responses were penalized. An additional block of the GNG task without reward/punishment served as the control to account for age-related slowing in processing speed. The results showed a prolonged response time (RT) in rewarded (vs. control) go trials with increasing age. Whole-brain multiple regressions of rewarded (vs. control) go trials against age and RT both revealed an age-related reduced activity of the anterior insula, middle frontal gyrus, and rostral anterior cingulate cortex. Furthermore, activity from these regions mediated the relationship between age and go performance. During rewarded (vs. control) no-go trials, age was associated with increased accuracy rate but decreased activation in the medial superior frontal and postcentral gyri. As these regions also exhibited age-related activity reduction during rewarded go, the finding suggests aging effects on common brain substrates that regulate both action and action inhibition. Taken together, age shows a broad negative modulation on neural activations but differential effects on performance during rewarded action and inhibition of action.

Bi-directional LSTM–CNN Combined method for Sentiment Analysis in Part of Speech Tagging (PoS)

In past few years, the popularity of social media has increased drastically, sentiment analysis on the reviews, comments and opinions from social media has become more active in research area. A high grade, sentiment analysis portrays the opinion about the real time objects, topics, products and tweet reviews. The social trends or customer opinion is better understood with sentiment analysis. The state-of-art methods in analyzing the sentiments are based on textual features and with different neural network models. In this paper, we demonstrate and generalize a model combining bi-directional long short term memory (LSTM) and convolutional neural network (CNN), as bi-directional LSTM used to hold the temporal data for part-of-speech (PoS) tagging and CNN to extract the potential features. The experiment results validate our combined model performance with individual models. Our combined model indicates performance accurately and efficiently, achieving a reduced execution time and increased accuracy rate 98.6% in sentiment analysis is achieved by using combined bi-directional LSTM-CNN technique as when compared with traditional techniques.

Manifold multi-view learning for cartoon alignment

Cartoon alignment is a key to retrieve cartoon characters and synthesise new cartoon clips. To successfully achieve the tasks, it is necessary to extract visual features that comprehensively denote cartoon characters and to align the feature points accurately between cartoon characters. In this paper, Speed Up Robust Feature (SURF) and Shape Context (SC) are introduced to characterise the cartoon character from multi-view. To increase accuracy rate of cartoon character alignment, semi-supervised alignment and Procrustes alignment require predetermining the correspondence. To overcome the flaw, we propose a Manifold Multi-View Learning (MML) to align cartoon characters. MML learns a projection that maps data instance (from cartoon characters with different dimensionality) to a lower-dimensional space, which simultaneously matches the local geometry and preserves the neighbourhood relationship within each cartoon character. The matching relationship can be obtained from local geometry structure. Experimental results show the good performance.

Manifold multi-view learning for cartoon alignment

Cartoon alignment is a key to retrieve cartoon characters and synthesise new cartoon clips. To successfully achieve the tasks, it is necessary to extract visual features that comprehensively denote cartoon characters and to align the feature points accurately between cartoon characters. In this paper, Speed Up Robust Feature (SURF) and Shape Context (SC) are introduced to characterise the cartoon character from multi-view. To increase accuracy rate of cartoon character alignment, semi-supervised alignment and Procrustes alignment require predetermining the correspondence. To overcome the flaw, we propose a Manifold Multi-View Learning (MML) to align cartoon characters. MML learns a projection that maps data instance (from cartoon characters with different dimensionality) to a lower-dimensional space, which simultaneously matches the local geometry and preserves the neighbourhood relationship within each cartoon character. The matching relationship can be obtained from local geometry structure. Experimental results show the good performance.

Enumeration and Alertness in Developmental Dyscalculia.

Enumeration, the ability to report an amount of elements, differs as a function of range. Subitizing (quantities 1–4) is an accurate and quick process with reaction times (RTs) minimally affected by the number of presented elements within its range. In the counting range (range of 5–9 elements), RTs increase linearly. Subitizing was considered to be a pre-attentive process for many years. However, recently we found that subitizing could be facilitated by improving engagement of attention. Specifically, brief alerting cues increase attentional engagement and reduced RTs in the subitizing range. Moreover, previous studies found that students with developmental dyscalculia (DD) have a smaller than normal subitizing range (3 vs. 4) and their alerting attentional system is impaired. In the current study, we explored whether an alerting cue would increase the subitizing range of adults suffering from DD from 3 to 4. For controls, alerting increased accuracy rates and facilitated enumeration of quantities only in the subitizing range. Participants with DD presented a larger alerting effect; an alerting cue enhanced their RTs in all ranges, but did not increase their smaller than normal subitizing range or accuracy. Our results suggest that both domain-general and domain-specific abilities contribute to the mechanism of enumeration and related to developmental dyscalculia.

Analysis and design of pressure sensors for micromechanical integrated pressure sensors

Accelerometers, pressure sensors and gyros have good prospects for the future among the wide range of micromechanical instruments that are developing most dynamically. The paper describes the modified version of the design of the pressure sensitive element created by the author with improved metrological characteristics and increased accuracy rates.

Motion artifact detection in colonoscopy images

Abstract Computer-aided detection is an integral part of medical image evaluation process because examination of each image takes a long time and generally experts’ do not have enough time for the elimination of images with motion artifact (blurred images). Computer-aided detection is required for both increasing accuracy rate and saving experts’ time. Large intestine does not have straight structure thus camera of the colonoscopy should be moved continuously to examine inside of the large intestine and this movement causes motion artifact on colonoscopy images. In this study, images were selected from open-source colonoscopy videos and obtained at Kayseri Training and Research Hospital. Totally 100 images were analyzed half of which were clear. Firstly, a modified version of histogram equalization was applied in the pre-processing step to all images in our dataset, and then, used Laplacian, wavelet transform (WT), and discrete cosine transform-based (DCT) approaches to extract features for the discrimination of images with no artifact (clear) and images with motion artifact. The Laplacian-based feature extraction method was used for the first time in the literature on colonoscopy images. The comparison between Laplacian-based features and previously used methods such as WT and DCT has been performed. In the classification phase of our study, support vector machines (SVM), linear discriminant analysis (LDA), and k nearest neighbors (k-NN) were used as the classifiers. The results showed that Laplacian-based features were more successful in the detection of images with motion artifact when compared to popular methods used in the literature. As a result, a combination of features extracted using already existing approaches (WT and DCT) and the Laplacian-based methods reached 85% accuracy levels with SVM classification approach

Research on Landing Risk Assessment for Carrier-Based Aircrafts by M-V Multiattribute Decision-Making

For increasing accuracy rate of landing risk assessment of carrier-based aircraft, this article is committed to research on landing risk assessment of carrier-based aircraft based on mean-variance dynamic multi-attribute decision making. Attribute values are provided in the form of triangle fuzzy number. Mean sort values is acquired by formula of possibility degree and order. For solving a problem of the same or similar orders, the improved method combines mean and variance, analyzing and judging, getting alternatives rank. Finally, the feasibility and availability of the improved method is proved by simulation results.

Species Identification and Delineation of Pathogenic Mucorales by Matrix-Assisted Laser Desorption Ionization-Time of Flight Mass Spectrometry.

This study aimed to validate the effectiveness of matrix-assisted laser desorption ionization-time of flight mass spectrometry (MALDI-TOF MS)-based identification of filamentous fungi of the order Mucorales. A total of 111 isolates covering six genera preserved at the Research Center for Medical Mycology of Peking University were selected for MALDI-TOF MS analysis. We emphasized the study of 23 strains of Mucor irregularis predominantly isolated from patients in China. We first used the Bruker Filamentous Fungi library (v1.0) to identify all 111 isolates. To increase the identification rate, we created a compensatory in-house database, the Beijing Medical University (BMU) database, using 13 reference strains covering 6 species, including M. irregularis, Mucor hiemalis, Mucor racemosus, Cunninghamella bertholletiae, Cunninghamella phaeospora, and Cunninghamella echinulata All 111 isolates were then identified by MALDI-TOF MS using a combination of the Bruker library and BMU database. MALDI-TOF MS identified 55 (49.5%) and 74 (66.7%) isolates at the species and genus levels, respectively, using the Bruker Filamentous Fungi library v1.0 alone. A combination of the Bruker library and BMU database allowed MALDI-TOF MS to identify 90 (81.1%) and 111 (100%) isolates at the species and genus levels, respectively, with a significantly increased accuracy rate. MALDI-TOF MS poorly identified Mucorales when the Bruker library was used alone due to its lack of some fungal species. In contrast, this technique perfectly identified M. irregularis after main spectrum profiles (MSPs) of relevant reference strains were added to the Bruker library. With an expanded Bruker library, MALDI-TOF MS is an effective tool for the identification of pathogenic Mucorales.