Search

The increasing frequency of vehicle accidents presents a significant challenge in our society. Unsafe behaviors, such as distracted driving (e.g., eating, texting, and talking on the phone), as well as fatigue, medication use, and driving under the influence, contribute to this rise. Drowsiness is a particularly concerning risk factor. This study proposes an automated driver drowsiness detection and warning system based on the Support Vector Machine (SVM) classifier. By analyzing EEG signals to measure the relative power ratio of alpha and beta waves, the system was validated using the renowned MIT-BIH polysomnographic database, which focuses on drowsiness research. Evaluation of the system demonstrates an average accuracy of 99 , 87 % , achieving real-time detection in 1072 , 590 ms, a recall of 99 , 77 % , and a false negative rate of 0 , 22 % . These results highlight the precision and reliability of the proposed system, with an overall F-score of 99 , 88 % . Compared to existing studies, this system stands out for its accuracy and robustness. It represents an effective tool for detecting drowsiness and reducing vehicle accidents. [ABSTRACT FROM AUTHOR]

Modern security faces challenges in detecting unauthorized and potentially harmful items in luggage, despite X-ray baggage scanning frameworks and research on efficiently screening highly disguised items. In response to this gap, a groundbreaking Modified Encoder-Decoder-based model has been introduced. This innovative model takes X-ray scan images as input and generates distinct feature representations for both suspicious and non-suspicious baggage materials. A key focus of the model is to address the denoising challenge inherent in X-ray images which reduces the models efficiency. This is achieved through the implementation of a Poisson Noise Reduction method during the preprocessing stage. Following preprocessing, the model effectively segments the non-threat image, identifying potential threats from the denoised input. The model showcases superior performance, as evidenced by high Peak Signal-to-Noise Ratio (PSNR) and low Mean Squared Error (MSE) values, outperforming existing filtering techniques. Rigorous testing on publicly available SIXray and GDXray datasets validates the effectiveness of the proposed methodology. Performance metrics for the SIXray dataset, including mAP, IoU, and DC values of 97.32%, 73.14%, and 85.12%, respectively, underscore the model's efficacy. Notably, the framework attains an impressive accuracy of 99.17% on the SIXray dataset, affirming its robustness in addressing contemporary security challenges. [ABSTRACT FROM AUTHOR]

The development of a rapid and accurate model for determining the genotoxicity and carcinogenicity of chemicals is crucial for effective cancer risk assessment. This study aims to develop a 1-day, single-dose model for identifying genotoxic hepatocarcinogens (GHCs) in rats. Microarray gene expression data from the livers of rats administered a single dose of 58 compounds, including 5 GHCs, was obtained from the Open TG-GATEs database and used for the identification of marker genes and the construction of a predictive classifier to identify GHCs in rats. We identified 10 gene markers commonly responsive to all 5 GHCs and used them to construct a support vector machine-based predictive classifier. In the silico validation using the expression data of the Open TG-GATEs database indicates that this classifier distinguishes GHCs from other compounds with high accuracy. To further assess the model's effectiveness and reliability, we conducted multi-institutional 1-day single oral administration studies on rats. These studies examined 64 compounds, including 23 GHCs, with gene expression data of the marker genes obtained via quantitative PCR 24 h after a single oral administration. Our results demonstrate that qPCR analysis is an effective alternative to microarray analysis. The GHC predictive model showed high accuracy and reliability, achieving a sensitivity of 91% (21/23) and a specificity of 93% (38/41) across multiple validation studies in three institutions. In conclusion, the present 1-day single oral administration model proves to be a reliable and highly sensitive tool for identifying GHCs and is anticipated to be a valuable tool in identifying and screening potential GHCs. [ABSTRACT FROM AUTHOR]

With the evolution of big data and information technology, sentiment analysis has become a research hotspot in the financial market. Researchers are increasingly focused on improving the efficiency of sentiment analysis using different machine learning and deep learning architectures. Feature extraction is a fundamental process in sentiment analysis that enhances text representation and classification. Though various feature extraction techniques are present in the field, limited attention has been given to hybrid feature extraction techniques. The primary objective of this study is to improve the sentiment analysis of financial news headlines using a hybrid Word2Vec-TFIDF feature extraction technique. The study evaluates the performance of Word2Vec, Doc2Vec, TFIDF, Word2Vec-TFIDF, and Doc2Vec-TFIDF with six machine learning classifiers. The results find that the hybrid feature extraction technique, Word2vec-TFIDF with SVM classifier, outperforms all other sentiment analysis models with an accuracy of 82 percent. [ABSTRACT FROM AUTHOR]

One of the most common causes of blindness, particularly in the elderly, is cataracts. Nearly half of India's elderly population has cataracts by the age of 80 or has had surgery to treat them. According to surveys conducted by the WHO and NPCB, there are over 12 million blind persons in India, and 80.1% of them are blind due to cataracts. Early detection of cataract cases is necessary to prevent total blindness. The World Health Organization (WHO) states that cataracts are the most frequent cause of blindness and visual loss. The risk of blindness among cataract patients can be decreased with prompt detection and treatment. On the other hand, clinical cataract identification requires the expertise of ophthalmologists. Therefore, the broad adoption of cataract detection to avert blindness may be hampered by the prospective expenses. Researchers are becoming more and more interested in artificial intelligence assisted diagnosis based on medical imagery. This study suggests an automated cataract detection procedure built on image processing and machine learning methods. A set of fundus retinal images serves as the input for the suggested model. The image dataset includes two kinds of images: healthy and images with cataracts to train the algorithm. This research consists of three primary phases: pre-processing, feature extraction and classification. The initial step of the method involves pre-processing the images to make them easier to process by extract the gray scale from the input image, then contrast-limited adaptive histogram equalization (CLAHE) is applied to improve the image and minimize noise, Finally ROI has been extracted. The second phase is feature extraction; by extract four kinds of texture features: (I) grey-level co-occurrence matrix (GLCM) to extract 11 features: 1) difference variance, 2) inverse difference moment, 3,4) information1\2, 5) entropy, 6) difference entropy, 7) correlation, 8) sum entropy, 9) maximal correlation coefficient, 10) contrast, and 11) angular second moment. (II) First Order Statistics (FOS) to extract 5 features: 1) entropy, 2) maximal gray level, 3) kurtosis, 4) skewness, and 5) energy. (III) Statistical Feature Matrix (SFM) to extract 4 features: 1) coarseness, 2) periodicity, 3) contrast, and 4) roughness. And finally (IV) Neighborhood Gray Tone Difference Matrix (NGTDM) to extract 4 features: 1) complexity, 2) coarseness, 3) strength, and 4) contrast. In the last phases, the extracted 24 features are put as input to the classifier, the classification was done by using Random Forest, support vector machines (SVM), Logistic Regression, K Neighbors (KNN), Decision Tree, and Naive Base Classifier. Classifies the retinal fundus images into two classes Cataracts or normal image. When compared to other current approaches, the experimental results of the suggested method show that its accuracy is 95%. [ABSTRACT FROM AUTHOR]

In recent days, stress is a major phenomenon that adversely affects both individuals and communities. The research in computing the stress factor has wider advantages as it improves personal learning, learning operations, and high productivity that benefits society. Several computational techniques come into concern to avoid and reduce the stress level using the electrocardiogram (ECG) signals. In this study, the stress level was classified using the feature extraction approach in combination with the classifier. The signal is processed using the variational mode decomposition denoising technique to reconstruct the original signal. The decomposed signal was further extracted using the time–frequency domain technique as characteristics of the ECG signal such as R-wave and T-wave constructed. Further, the support vector machine classifier was used to classify the stress level (low, medium, and high) of the extracted signal. Based on stress classification outcomes, the robot offers a range of personalized interventions to users. These interventions include relaxation exercises, deep breathing techniques, or guided mindfulness sessions. The average accuracy obtained using the proposed technique is 98.98% but without using the feature extraction technique, it is 97.71%. The other performance parameters also get improved and the results are finally compared with the existing techniques.

An algorithm for detecting partially occluded pedestrians based on multi-feature fusion and tree-structured semi-global stereo matching was proposed to address the issue of reduced detection accuracy in pedestrian detection caused by partial obstruction. The simple linear iterative clustering (SLIC) algorithm was employed for superpixel segmentation to enhance the contour information of pedestrians, and the tree-structured multi-feature fusion semi-global stereo matching algorithm was used to generate depth maps. Pedestrian, background, and obstacle information were separated using an adaptive segmentation algorithm to obtain the region of interest. The region of interest was positioned around the head and shoulders of the pedestrian, where features were distinct and stable, to impose constraints. Feature extraction was conducted using dimension-reduced histogram of gradient (HOG), and a sample set was generated for training an support vector machines(SVM) classifier, ultimately achieving the detection of partially occluded pedestrians. The experiment shows that compared with other pedestrian detection algorithms, the proposed algorithm has a higher accuracy in pedestrian detection in partially occluded scenes, proving the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Selecting wheat hybrids is vital for enhancing crop yield, adapting to changing climates, and ensuring food security. These hybrids align with market demands and sustainable farming practices, contributing to efficient crop management. Traditional methods for wheat hybrid selection, such as molecular techniques, are costly and time-consuming, and are prone to human error. However, advancements in artificial intelligence and machine learning offer non-destructive, objective, and more efficient solutions. This study is explored the classification of wheat varieties and hybrids using two deep learning models, MobileNetv2 and GoogleNet. These models are achieved impressive classification accuracy, with MobileNetv2 reaching 99.26% and GoogleNet achieving 97.41%. In the second scenario, the deep features obtained from these models are classified with Support Vector Machine (SVM). In the classification made with the MobileNetv2-SVM hybrid model, an accuracy of 99.91% is achieved. This study is provided rapid and accurate wheat variety and hybrid identification method, as well as contributing to breeding programs and crop management. [ABSTRACT FROM AUTHOR]

Being known as a nutrient-dense food, eggs are high in demand in the marketplace and high-quality eggs are much sought-after. Hence, egg grading is in place to sort eggs into different grades. Experienced graders are required for their knowledge to classify egg grades and as humans are involved, errors when performing manual grading are unavoidable. This study aims to develop a vision-based egg classification system that requires minimal human intervention. The proposed system houses a camera to acquire real-time images of the eggs and these images are served as the input to the algorithm. Based on the 6 geometrical features derived from the geometric parameters of the egg image, the eggs are classified using Support Vector Machine (SVM). The experiment results show the proposed egg grading system with a linear kernel SVM model can yield as high as 92.59% training accuracy. [ABSTRACT FROM AUTHOR]

Over the last two decades, functional Magnetic Resonance Imaging (fMRI) has provided immense data about the dynamics of the brain. Ongoing developments in machine learning suggest improvements in the performance of fMRI data analysis. Clustering is one of the critical techniques in machine learning. Unsupervised clustering techniques are utilized to partition the data objects into different groups. Supervised classification techniques applied to fMRI data facilitate the decoding of cognitive states while a subject is engaged in a cognitive task. Due to the high dimensional, sparse, and noisy nature of fMRI data, designing a classifier model for estimating cognitive states becomes challenging. Feature selection and feature extraction techniques are critical aspects of fMRI data analysis. In this work, we present one such synergy, a combination of Hierarchical Consensus Clustering (HCC) and the Statistics of Split Timeseries (SST) framework to estimate cognitive states. The proposed HCC-SST model's performance has been verified on StarPlus fMRI data. The obtained experimental results show that the proposed classifier model achieves 99% classification accuracy with a smaller number of voxels and lower computational cost. [ABSTRACT FROM AUTHOR]

Epilepsy is a neurological disorder, and its sudden seizures pose a serious threat to the quality of life of patients. Not only does this condition cause patients to potentially lose control and consciousness during seizures, leading to possible injuries or dangerous situations, but it also has a significant impact on their mental health, triggering issues such as anxiety and depression. An intelligent epilepsy diagnosis process based on electroencephalogram (EEG) signals offers notable advantages. First, it provides noninvasive brainwave signals that accurately monitor and record the patterns and characteristics of epileptic seizures, offering objective diagnostic criteria for doctors. Second, with the use of artificial intelligence and machine learning technologies, large amounts of EEG data can be efficiently analyzed, improving the speed and accuracy of diagnosis and providing timely and effective treatment plans for patients. Additionally, intelligent diagnostic systems can achieve real-time monitoring, promptly alert people to potential epileptic seizures, and provide a safer living environment for patients. In this context, this paper proposes an epilepsy diagnosis method based on a transferred AlexNet model and EEG signals. The main contributions of this paper are as follows. (1) A transfer learning mechanism is incorporated into the AlexNet model through the direct transfer of its neural network structure and the modification of some existing neural network structures, followed by collaborative training with the addition of a domain adaptation layer in the network. This introduced transfer mechanism can address small sample size issues. (2) The traditional AlexNet model suffers from redundant feature extraction, leading to slow training. This paper adds batch normalization (BN) layers after each convolutional layer in the AlexNet model to normalize the features extracted from the convolutional layers. This emphasizes the representation of the important features of EEG signals and enables the lower layers of the network to learn the features needed for EEG signal processing. (3) The transferred AlexNet model proposed in this paper is applied to extract the features of epilepsy EEG signals, and the extracted features are input into a support vector machine (SVM) classifier to obtain epilepsy diagnosis results. Comparative experiments show that the diagnostic method used in this paper yields superior results and shorter training times than those of the competing approaches. [ABSTRACT FROM AUTHOR]

An accurate method of diagnosis is needed as lung disease spreads around the globe. Since the virus spreads so quickly, diagnosing lung disease can be challenging for medical professionals. Accurate diagnosis and treatment are what set clinical diagnosis apart because they typically depend on a doctor's skill and knowledge. This is the most challenging aspect of diagnosing COVID-19 and pneumonia patients. Therefore, for the time being, this technology's major objective is to create a way to detect lung problems early and stop the virus from spreading quickly. This system offers a categorization framework for a challenging image analysis task in the medical field, where chest X-ray images are assessed. The pre-trained Alex Net is utilized to generate the feature map that was taken from the x-ray image. The LSTM model models the extracted feature map to extract a feature vector for a Support Vector Machine (SVM) classifier to categorize lung diseases. In the method of convolutional neural network (CNN) classification, a large number of layers, values, thresholds, and parameters are required to be defined for classification. Since the pre-trained Alex Net is used in our proposed framework, the parameter values for CNN don’t need to be defined, reducing processing time effectively. This paper proposes the modeling of feature maps using LSTM and the application of machine learning techniques gave the accuracy of 98.8% for the categorization of lung diseases in the form of 10-fold cross validation. Three diseases are distinguished in the proposed framework: normal, viral pneumonia, and COVID-19. In experiments, accuracy, true positive, false negative, positive predictive, and false discovery rates are used to evaluate classifier performance.

This study focuses on enhancing the accuracy and efficiency of semantic analysis systems for recognizing moving objects within video sequences. The primary aim is to improve object detection capabilities in dynamic environments using a hybrid model that integrates Convolutional Neural Networks (CNNs) with Support Vector Machines (SVMs). Our contribution involves developing and testing an advanced detection algorithm that utilizes the Faster Region-based Convolutional Neural Network (R-CNN) framework combined with SVM classifiers for refined object recognition and interaction assessment in complex video scenes. We implemented the system using Python 3.7 and tested it on approximately 350 video frames. The findings demonstrate that our model significantly outperforms existing methods such as Scale-Invariant Feature Transform (SIFT), Centrifugal Compressor Performance (CCP), and Local Binary Pattern (LBP) in terms of detection accuracy. The proposed model consistently outperformed traditional methods such as SIFT, CCP, and LBP across various noise levels, maintaining higher accuracy, particularly in high-noise environments. At 80% noise, the proposed model demonstrated a marked advantage in detection accuracy compared to the baseline methods. Overall, the model showcased robust performance with less degradation in accuracy even under significant processing errors, validating its effectiveness in noisy and dynamic settings.

The following ends have been established via an in-depth examination and assessment of numerous prior studies on olive fruit classifications: First, several of these researches rely on the use of an unrelated image library. Since every image features a single fruit with a background that contrasts sharply with the fruit’s hue, they are all ready for testing. As was previously stated, this issue is unrelated to reality. In practical application, one must deal with a frame that holds hundreds of fruits. To keep the fruits steady, they are put on a conveyor with multiple channels. It’s also notable that the majority of this study offered suggestions for useful technology that could yet be developed. Finally, it is important to emphasize that processing speed data is essential in this type of application and has not been collected in many of these experiments. The presented work deals with a new strategy based on two principles: first, a successful extraction of the fruits from the background; and second, the classification of olive fruits into eight categories based on colors and defects. The fruits were extracted from the backdrop using a modified version of the K-Means technique. The outcomes of the suggested fruit extraction were examined utilizing several assessment techniques. By contrasting the outcomes of pertinent procedures with the suggested proposal for fruit extraction, the efficacy and precision of the proposed method were verified. Depending on why the fruit needed to be separated, there were two stages to the process. Three colors were separated using the SVM algorithm, and five distinct defects were separated using the ANN algorithm Approximately 15,000 photos of olive fruits that were shot straight from the fruit conveyor were included in a robust database that was used in the proposed study to validate the effectiveness of the suggested technology. Efficiency was further validated by contrasting our outcomes with those of related technology. When the fruits were set on a white backdrop, the test accuracy results of the suggested approach showed that it was highly efficient in classifying the fruits in the shortest period; the suggested method had an effectiveness of 99.26% for fruit classification. The most important discovery was that it could classify fruits with an efficiency of 97.25% while they were being put on a fruit conveyor, which was in contrast to other approaches. The unique findings of the study that was presented hold promise for practical implementation.

Descriptors serve as algorithms responsible for the representation and processing of multimedia files. One of the main challenges in these algorithms involves establishing a tradeoff among conflicting performance requirements such runtime, on the one hand, and standard metrics such as accuracy, precision, recall and F-score, on the other hand. To address this challenge, a novel descriptor named Histogram of Enhanced Gradients (HEG) is introduced for noisy face recognition. The methodology behind HEG involves enhancing local gradients prior to feature extraction, corroborated by the Histogram of Oriented Gradients (HOG) descriptor and adaptive filtering. Initially, facial images are divided into blocks, and features are extracted from each block using magnitude and orientation maps to discriminate between edges, details, and flat regions. Then, these features undergo denoising with an adaptive anisotropic diffusion filter, individually customized for each of these three types. Subsequently, the enhanced histograms from the blocks are concatenated to create a comprehensive feature vector representing the original noisy face image. Finally, the HEG descriptor is integrated within a supervised machine learning scheme with a Support Vector Machine as the classifier. The proposed descriptor is evaluated not only in terms of runtime and the standard metrics cited above, but also on the basis of six other similarity metrics, across three online datasets. Experimental results, conducted under different noise levels, clearly demonstrate that the HEG descriptor outperforms nine stateof- the-art descriptors on all three datasets yielding significant enhancements in runtime efficiency, with speed improvements ranging from 1.64 to 29.56 times, and notable refinements in F-score, ranging from 1.03 to 2.39 times. These results highlight the effectiveness of the HEG descriptor in capturing facial features from multimedia noisy files. [ABSTRACT FROM AUTHOR]

Lung cancer is a prevalent malignancy, despite the great breakthroughs in detection and prevention, and it remains the important cause of death. In recent days, artificial intelligence has exploded in all fields of science. The use of deep learning in medical science has improved in accuracy and precision of predicting this infestation in the initial stages. In the work, a novel molecular imaging-based Res-U-Net is proposed for classifying two different types of lung cancer. The PET/CT (positron emission tomography/computed tomography) employing an injection 18F-FDG has developed as a useful tool in therapeutic oncologic imaging for both metabolic and anatomic analysis. The proposed model uses Res-U-Net to classify small cell lung cancer (SCLC) and non-small cell lung cancer (NSCLC) from normal by using 18F-FDG PET/CT images from the radiogenomics dataset. This dataset images are pre-processed by Gaussian smoothing to reduce the noise from the PET/CT images. Finally, the classification result is obtained through the support vector machine (SVM) classifier which proves the efficiency of the proposed technique. The outcome of the proposed technique yields the best and most accurate results, and it yields the classification accuracy rate of 96.45%for lung cancer into NSCLC and SCLC. [ABSTRACT FROM AUTHOR]

Hypertensive retinopathy (HR) results from the microvascular retinal changes triggered by hypertension, which is the most common leading cause of preventable blindness worldwide. Therefore, it is necessary to develop an automated system for HR detection and evaluation using retinal images. We aimed to propose an automated approach to identify and categorize the various degrees of HR severity. A new network called the spatial convolution module (SCM) combines cross-channel and spatial information, and the convolution operations extract helpful features. The present model is evaluated using publicly accessible datasets ODIR, INSPIREVR, and VICAVR. We applied the augmentation to artificially increase the dataset of 1200 fundus images. The different HR severity levels of normal, mild, moderate, severe, and malignant are finally classified with the reduced time when compared to the existing models because in the proposed model, convolutional layers run only once on the input fundus images, which leads to a speedup and reduces the processing time in detecting the abnormalities in the vascular structure. According to the findings, the improved SVM had the highest detection and classification accuracy rate in the vessel classification with an accuracy of 98.99% and completed the task in 160.4 s. The ten-fold classification achieved the highest accuracy of 98.99%, i.e., 0.27 higher than the five-fold classification accuracy and the improved KNN classifier achieved an accuracy of 98.72%. When computation efficiency is a priority, the proposed model's ability to quickly recognize different HR severity levels is significant. [ABSTRACT FROM AUTHOR]

In general, the prediction models are increasingly being used for reasoning and decision making in various applications. With the advancements in IT based devices such as Tablet-PC, touch-screen based smart phones, digital-pen/stylus based devices, and digitizers, the demand of real-time based applications is also increasing. The present study describes the Language Model (LM) based forecasting the occurrence of next possible Gurmukhi character/word in a word/sentence, which depends on the immediately preceding character(s)/word(s), written in the real-time environment. The online handwritten captured character/word information is first segmented into its individual strokes, which are recognized using Support Vector Machine (SVM) classifier. Once a character/word is recognized, this will be useful to assist the writers in order to provide the suggestions for next possible character/word. The n-gram language models (bigram and trigram) have been implemented at character- and word-level for this purpose. In this study, the corpus, "Punjabi Monolingual Text Corpus-AnglaMT" (available at https://tdil-dc.in), containing approximately 83,000 sentences has been used for training the model. Experimental results show that the proposed online handwritten character/word forecasting framework significantly outperforms and produce consistent forecasts for the most likely character/word on the basis of given handwritten character/word information and saving computational costs. This model can also be used for many other non-Indic and Indic scripting languages. [ABSTRACT FROM AUTHOR]

Predicting a protein's secondary structure is crucial for understanding the working of proteins. Despite advancements over the years, the top predictors have achieved only 80% Q8 accuracy when sequence profile information is the sole input. An ensemble approach is proposed using convolutional neural network (CNN) and a classifier known as support vector machine (SVM) on both the partial and the whole CullPDB datasets. The protein secondary structure (PSS) has a complex hierarchical structure, as well as the ability to take into account the reliance between neighbouring labels. A detailed experiment yielding high levels of Q8 accuracy with scores of 97.91%, 85.13%, and 78.02% using 20%, 80%, and 100% respectively of the protein residues on the new predicted dataset CullPDB6133 which is better than the accuracies predicted by similar models. The proposed methodology highlights the use of CNN as a general framework, for efficiently predicting eight-state (Q8) accuracy of secondary protein structures with a low time and space complexity. [ABSTRACT FROM AUTHOR]

Cashmere and wool are common raw materials in the textile industry. The clothes made of cashmere are popular because of the excellent comfort. A system that can quickly and automatically classify the two will improve the efficiency of fiber recognition in the textile industry. We propose a classification method of cashmere and wool fibers based on feature fusion using the maximum inter-class variance. First, the fiber target area is obtained by the preprocessing algorithm. Second, the features of sub-images are extracted through the algorithm of the Discrete Wavelet Transform. It is linearly fused by introducing the weight in the approximate and detailed features. The maximum separability of the feature data can be achieved by the maximum inter-class variance. Finally, different classifiers are used to evaluate the performance of the proposed method. The support vector machine classifier can achieve the highest recognition rate, with an accuracy of 95.20%. The experimental results show that the recognition rate of the fused feature vectors is improved by 6.73% compared to the original feature vectors describing the image. It verifies that the proposed method provides an effective solution for the automatic recognition of cashmere and wool. [ABSTRACT FROM AUTHOR]

In this paper, we applied the artificial intelligence technique (SVM Classifier) to compare the performance of two different technologies of PV modules (class to class and backsheet to glass) after five (05) months of operation in Algeria under the same weather conditions (moderate and humid climate) . We have a database for the outdoor monitoring of these two PV modules, consisting of data (Isc, Voc, Pmax, Imp, Vmp, Tm, Tamb, G, WD, WS, Date, Time) which are variables data, where the SVM creates the groups or class according to the conditions that we entered, after which it produces heatmaps that help us in reading the results and making the decision easily, unlike the classic methods which are very difficult. This method is applicable for comparison between several solar panels or several photovoltaic PV plants. It is enough just to give the database.

In recent years, satellite data have become available for free to the remote sensing community. Land use and land cover (LULC) changes are identified in remote sensing applications using Landsat satellite data. However, there is a lack of studies that utilize these data to assess the performance of satellite data on LULC classification and monitoring changes in complex landscapes. This study aims at evaluating LULC changes for the years 2013, 2018, and 2023 in the Sangha area using Landsat-8 OLI images. The Support Vector Machine (SVM) algorithm was implemented for detecting changes in the Sangha area. The results revealed that wetland forest and water bodies drastically declined, with a net change of −33.78 and-19.22%, respectively, while open forest, urban area, and bare soils with +77.91, +52.81, and +40.52% correspondingly substantially increased between 2013 and 2023. The overall accuracy and Kappa statistics achieved were above 91% and 0.85, respectively.

Agricultural operators can predict the yield of wheat at different stages of growth, development, and harvesting and take different measures to realize precise management. The purpose of this paper is to apply agricultural mechanical engineering automation to wheat yield prediction, and a UAV multimodal data wheat yield prediction model is developed using the RMGF algorithm. Different data sources, such as vertical distribution of terrain and spatial variability, canopy height and wheat plant height, canopy temperature difference, vegetation spectral characteristics, and vegetation index, were extracted using an agricultural UAV. Then GF decomposition algorithm based on MSD decomposes the multimodal image into an approximate image and detail image, and after optimization of the fused weight map using RSA, the fused image is obtained by IMST according to the optimized weight map. The model was used to carry out regression analysis of yield prediction for three types of wheat, heat-tolerant, medium heat-tolerant, and high-temperature-sensitive, and finally predicted the wheat yield from 2015 to 2024 in a production area. It was found that the R² of the RMGF multimodal model in this paper predicted the three kinds of wheat yields as 0.7936, 0.8609, and 0.9262 with excellent accuracy results. The predicted yields were basically in line with the actual yields in the high-yield portion, with large prediction errors above 9000 kg/ha. The prediction error for wheat was within 0-2.26%, and the predicted yield in a main wheat production area was 7050 kg/ha in 2024. This study provides a feasible method for large-scale yield estimation in the main production area, which contributes to high-throughput plant phenotyping and agricultural precision reform.

This paper builds a virtual simulation teaching system based on the Unity simulation platform, which contains a network connection module, resource loading module, and so on. Using the combination of natural interaction and virtual simulation teaching system, the design of Kinect depth information and SVM classifier for gesture recognition classification is integrated with the virtual simulation teaching scene to realize cross-platform collaborative interaction. The virtual simulation teaching process involves a large number of gesture interaction processes, using mf-score multi-feature selection of features that play a vital role in the classification of the data set, eliminating the raw noise of the customized gesture data and improving the contrast of the gesture image. The results of the practical application of the virtual simulation teaching system show that the discipline to which the virtual simulation course belongs (0.008) and the time of identification (0.047) have a significant effect on its application activity. The multisensory, immersive, and interactive nature of virtual simulation teaching (P < 0.001) all have a highly significant positive effect on learners’ foreign language useability. The foreign language assessment score at the end of the virtual simulation course is (92.74±3.32), which is significantly different from the traditional teaching method (P

Developing the “Gleaning” digital cultural collection platform can help promote rural culture and revitalization. In this paper, we propose the AdaBoost-SVM algorithm by using the AdaBoost algorithm to strengthen the SVM classifier by changing the input samples’ weights and increasing the misclassified samples’ weights to enhance the training of the misclassified samples. Then, by studying the characteristics of Qinghai coastal villages, we build a digital collection creative research and development platform based on big data technology and explore the digital features of the rural “Qingzhou” cultural creations with the help of the AdaBoost-SVM algorithm. After the access test of different platforms, the access efficiency of the digital collection platform seen in this paper is, on average, 2.80% higher than that of WhaleQuest, 2.14% higher than that of Phantom Core, 1.43% higher than that of one Digital Art, and 0.72% higher than that of Yuan Vision. In terms of the creativity rating of digital collections, the digital collections of this paper’s platform are rated 30.53%, 23.78%, 16.30%, and 6.15% higher than other platforms in order. The digital collection creative platform based on big data can skillfully integrate the special culture of villages into digital cultural and creative collections and help villages give play to their special cultural advantages.

The construction of a garden image classification model is done by combining spatial information technology and analyzing the process of hyperspectral classification of garden images is the main focus of this paper. The linear transformation of the image is performed by principal component analysis to achieve the effect of reducing image dimension. The SVM classifier is used to classify the garden images, and the hyperplane is found in the sample space to distinguish between positive and negative cases. Using a simple linear iterative algorithm, the image superpixels are segmented, and the information contained in them is fused with the features of the hyperspectral image. The positioning of the hyperpixel block impacts the calculation of the mean hyperspectral feature value for each hyperpixel region. The results show that a well-rounded designer needs to achieve 70% aesthetics and 80% rationality to present modern garden design.

Brain tumor segmentation from 2D Magnetic Resonance Images (MRI) is an important task for several applications in the field of medical analysis. Commonly, this task is performed manually by medical professionals, but it is not always obvious due to similarities between tumors and normal tissue and variations in tumor appearance. Therefore, the automation of medical image segmentation remains a real challenge that has attracted the attention of several researchers in recent years. Instead of choosing between region and contour approaches, in this article, we propose a region-edge cooperative method for brain tumor segmentation from MRI images. The region approach used is support vector machines (SVMs), one of the popular and highly motivated classification methods, the method distinguishes between normal and abnormal pixels based on some features: intensity and texture. To control and guide the segmentation region, we take advantage of the Ron Kimmel geodesic Active Contour Model (ACM) which produces a good delimitation of the boundaries of the object. The two methods have been cooperated sequentially in order to obtain a flexible and effective system for brain tumor segmentation. Experimental studies are performed on synthetic and real 2D MRI images of various modalities from the radiology unit of the university hospital center in Bab El Oued Algeria. The used MRI images represent various tumor shapes, locations, sizes, and intensities. The proposed cooperative framework outperformed SVM-based segmentation and ACM-based segmentation when executed independently. [ABSTRACT FROM AUTHOR]

Many current brain–computer interface (BCI) applications depend on the quick processing of brain signals. Most researchers strive to create new methods for future implementation and enhance existing models to discover an optimal feature set that can operate independently. This study focuses on four key concepts that will be used to complete future works. The first concept is related to potential future communication models, whereas the others aim to enhance previous models or methodologies. The four concepts are as follows. First, we suggest a new communication imagery model as a substitute for a speech imager that relies on a mental task approach. As speech imagery is intricate, one cannot imagine the sounds of every character in every language. Our study proposes a new mental task model for lip-sync imagery that can be employed in all languages. Any character in any language can be used with this mental task model. In this study, we utilized two lip-sync movements to indicate two sounds, characters, or letters. Second, we considered innovative hybrid signals. Choosing an unsuitable frequency range can lead to ineffective feature extractions. Therefore, the selection of an appropriate frequency range is crucial for processing. The ultimate goal of this method is to accurately discover distinct frequencies of brain imagery activities. The restricted frequency range combination presents an initial proposal for generating fragmented, continuous frequencies. The first model assesses two 4 Hz intervals as filter banks. The primary objective is to discover new combinations of signals at 8 Hz by selecting filter banks with a 4 Hz scale from the frequency range of 4 Hz to 40 Hz. This approach facilitates the acquisition of efficient and clearly defined features by reducing similar patterns and enhancing distinctive patterns of brain activity. Third, we introduce a new linear bond graph classifier as a supplement to a linear support vector machine (SVM) when handling noisy data. The performance of the linear support vector machine (SVM) significantly declines under high-noise conditions. To complement the linear support vector machine (SVM) in noisy-data situations, we introduce a new linear bond graph classifier. Fourth, this paper presents a deep-learning model for formula recognition that converts the first-layer data into a formula extraction model. The primary goal is to decrease the noise in the formula coefficients of the subsequent layers. The output of the final layer comprises coefficients chosen by different functions at various levels. The classifier then extracts the root interval for each formula, and a diagnosis is established based on these intervals. The final goal of the last idea is to explain the main brain imagery activity formula using a combination formula for similar and distinctive brain imagery activities. The results of implementing all of the proposed methods are reported. The results range between 55% and 98%. The lowest result is 55% for the deep detection formula, and the highest result is 98% for new combinations of signals. [ABSTRACT FROM AUTHOR]

Copyright of Computer Measurement & Control is the property of Magazine Agency of Computer Measurement & Control 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.)

One of the most difficult parts of stroke therapy is hand mobility recovery. Indeed, stroke is a serious medical disorder that can seriously impair hand and locomotor movement. To improve hand function in stroke patients, new medical technologies, such as various wearable devices and rehabilitation therapies, are being developed. In this study, a new design of electromyography (EMG)-controlled 3D-printed hand exoskeleton is presented. The exoskeleton was created to help stroke victims with their gripping abilities. Computer-aided design software was used to create the device's 3D architecture, which was then printed using a polylactic acid filament. For online classifications, the performance of two classifiers—the support vector machine (SVM) and the K-near neighbor (KNN)—was compared. The Robot Operating System (ROS) connects all the various system nodes and generates the decision for the hand exoskeleton. The selected classifiers had high accuracy, reaching up to 98% for online classification performed with healthy subjects. These findings imply that the new wearable exoskeleton, which could be controlled in accordance with the subjects' motion intentions, could aid in hand rehabilitation for a wider motion range and greater dexterity. [ABSTRACT FROM AUTHOR]

The human brain serves as the primary control centre for the humanoid system. Computer vision plays a vital part in the field of human health, which helps to reduce the amount of human judgement that is required to produce accurate findings. Scans using computed tomography, X-rays, and magnetic resonance imaging (MRI) are the most popular imaging technologies used in MRI, and they could also the greatest trustworthy and safe. The MRI can identify even the most minute of objects. In this paper, Alzheimer's disease detection in early stage, based on MRI by using the deep learning technique U-Net and EfficientNet which is a convolutional neural network, is implemented. Diagnosing Alzheimer's disease (AD) accurately is an vital aspect in treating AD patients, eventually during the early disease stages. This is particularly true in the early disease stages of the disease, when awareness of risk enables AD patients to take up protective measures well before the occurrence of brain damage that cannot be reversed. Despite of the fact that computers have been utilised in a significant number of recent research to diagnose AD, the majority of machine detection approaches are restricted by congenital findings. Early-stage Alzheimer's disease (AD) can be identified, but early-stage AD cannot be predicted because prediction of the disease is successful only before the (AD) disease reveals itself. Deep learning, often known as DL, has recently emerged as a popular method for the initial recognition of Alzheimer's disease (AD). In this article, we will give a quick overview of some of the key research that has been done on AD, and we will investigate how DL can assist researchers in the early phases of disease diagnosis. [ABSTRACT FROM AUTHOR]