Support Vector Machine Algorithm Research Articles

Monitoring of Chlorophyll Content of Potato in Northern Shaanxi Based on Different Spectral Parameters

Leaf chlorophyll content (LCC) is an important physiological index to evaluate the photosynthetic capacity and growth health of crops. In this investigation, the focus was placed on the chlorophyll content per unit of leaf area (LCCA) and the chlorophyll content per unit of fresh weight (LCCW) during the tuber formation phase of potatoes in Northern Shaanxi. Ground-based hyperspectral data were acquired for this purpose to formulate the vegetation index. The correlation coefficient method was used to obtain the “trilateral” parameters with the best correlation between potato LCCA and LCCW, empirical vegetation index, any two-band vegetation index constructed after 0–2 fractional differential transformation (step size 0.5), and the parameters with the highest correlation among the three spectral parameters, which were divided into four combinations as model inputs. The prediction models of potato LCCA and LCCW were constructed using the support vector machine (SVM), random forest (RF) and back propagation neural network (BPNN) algorithms. The results showed that, compared with the “trilateral” parameter and the empirical vegetation index, the spectral index constructed by the hyperspectral reflectance after differential transformation had a stronger correlation with potato LCCA and LCCW. Compared with no treatment, the correlation between spectral index and potato LCC and the prediction accuracy of the model showed a trend of decreasing after initial growth with the increase in differential order. The highest correlation index after 0–2 order differential treatment is DI, and the maximum correlation coefficients are 0.787, 0.798, 0.792, 0.788 and 0.756, respectively. The maximum value of the spectral index correlation coefficient after each order differential treatment corresponds to the red edge or near-infrared band. A comprehensive comparison shows that in the LCCA and LCCW estimation models, the RF model has the highest accuracy when combination 3 is used as the input variable. Therefore, it is more recommended to use the LCCA to estimate the chlorophyll content of crop leaves in the agricultural practices of the potato industry. The results of this study can enhance the scientific understanding and accurate simulation of potato canopy spectral information, provide a theoretical basis for the remote sensing inversion of crop growth, and promote the development of modern precision agriculture.

Optimization of parallel SVM algorithm for big data

Parallel Support Vector Machine (SVM) based on big data has achieved some results in data mining, but due to the complexity of the data itself and a large amount of noisy data, its execution efficiency and classification accuracy in the big data environment are very low. In order to eliminate noise, a noise reduction method based on Noise Cleaning (NC) strategy was proposed, and redundant training samples in big data environments were deleted; Introduce an improved Artificial Fish Swarm Algorithm (IAFSA) to obtain the final Parallel SVM algorithm using mutual information and artificial fish swarm algorithm based on MapReduce (MIAFSA-PSVM) classification model. The results indicate that when compared to CMI-PSVM, the execution time of MIAFSA-PSVM algorithm is higher on the NDC dataset with the largest data size, The SVM parameter optimization algorithm based on MapReduce and cuckoo search (CSSVM-MR) and the particle swarm optimization based parallel support vector machine ensemble algorithm (PSO-PSVM) decreased by 40.1%, 79.3%, and 51.7%, respectively. This indicates that GIESVM-MR and MIAFSA-PSVM have strong adaptability to big data environments and high classification accuracy.

Quantum Support Vector Machine for Multi Classification

Abstract Classical machine learning algorithms seem to be totally incapable of processing tremendous data, while quantum machine learning algorithms could deal with big data unhurriedly and provide exponential acceleration over classical counterpart. In this paper, we propose two quantum support vector machine algorithms for multi classification. One is the quantum version of directed acyclic graph support vector machine. The other one is to use the Grover search algorithm before measurement, which amplifies the amplitude of the phase stored in the classification result. For $k$ classification, the former provides quadratic reduction in computational complexity when classifying. The latter accelerates the training speed significantly and more importantly, the classification result can be read out with a probability of at least 50\% using only one measurement. We conduct numerical simulations on two algorithms, and their classification success rates are 96\% and 88.7\%, respectively.

A Hybrid Optimization Model for Efficient Detection and Classification of Malware in the Internet of Things

The proliferation of Internet of Things (IoT) devices and their integration into critical infrastructure and business operations has rendered them susceptible to malware and cyber-attacks. Such malware presents a threat to the availability and reliability of IoT devices, and a failure to address it can have far-reaching impacts. Due to the limited resources of IoT devices, traditional rule-based detection systems are often ineffective against sophisticated attackers. This paper addressed these issues by designing a new framework that uses a machine learning (ML) algorithm for the detection of malware. Additionally, it also employed sequential detection architecture and evaluated eight malware datasets. The design framework is lightweight and effective in data processing and feature selection algorithms. Moreover, this work proposed a classification model that utilizes one support vector machine (SVM) algorithm and is individually tuned with three different optimization algorithms. The employed optimization algorithms are Nuclear Reactor Optimization (NRO), Artificial Rabbits Optimization (ARO), and Particle Swarm Optimization (PSO). These algorithms are used to explore a diverse search space and ensure robustness in optimizing the SVM for malware detection. After extensive simulations, our proposed framework achieved the desired accuracy among eleven existing ML algorithms and three proposed ensemblers (i.e., NRO_SVM, ARO_SVM, and PSO_SVM). Among all algorithms, NRO_SVM outperforms the others with an accuracy rate of 97.8%, an F1 score of 97%, and a recall of 99%, and has fewer false positives and false negatives. In addition, our model successfully identified and prevented malware-induced attacks with a high probability of recognizing new evolving threats.

Simultaneous measurement of NH3 and NO by mid-infrared tunable diode laser absorption spectroscopy based on machine-learning algorithms

Accurate measurements of NH3 and NO are essential for controlling NOx emissions from coal-fired power plants, reducing ammonia slip, and improving the efficiency of selective catalytic reduction (SCR) operation. We propose a method for measuring NH3 and NO concentrations based on machine learning algorithms to address the challenges posed by overlapping interference of CO2 and H2O spectral lines in flue gas. Our approach introduces a novel method for acquiring mixture spectra for the model. Initially, we measure the spectra of individual components under different concentrations and temperatures. Subsequently, mixed spectral samples are generated by combining the measured spectra of the individual components. This approach simplifies the spectral measurement process while preserving accuracy. The particle swarm optimization support vector machine (PSO-SVM) algorithm is leveraged, providing a reliable foundation for the continuous and synchronous measurement of NH3 and NO. Upon testing, the PSO-SVM demonstrates average relative errors of 4.0 % and 0.8 % for NH3 and NO concentrations, respectively. The corresponding measurement precision is 0.05 ppm for NH3 and 0.42 ppm for NO, better than the conventional integral absorbance method. The minimum detection limit (MDL) for NH3 is 16.1 ppb at an average time of 50 s, while for NO, it is 38.4 ppb at an average time of 71 s. The methodology of this paper is expected to play an important role in reducing the influence of interfering components and improving the accuracy of field measurements.

Enhancing Coronary Artery Disease Detection with a Hybrid Machine Learning Approach: Integrating K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) Algorithms

Recent studies have identified coronary artery disease (CAD) as a leading cause of death globally. Early detection of CAD is crucial for reducing mortality rates. However, accurately predicting CAD poses challenges, particularly in treating patients effectively before a heart attack occurs due to the complexity of data and relationships in traditional methodologies. This research has successfully developed a machine learning model for CAD prediction by combining K-Nearest Neighbors (KNN) and Support Vector Machine (SVM) Classifier techniques. The model, trained and tested on a dataset of 918 samples (508 with cardiac issues and 410 healthy cases), achieved an accuracy of 82% for KNN, 84.3% for SVM, and 88.7% for the hybrid model after rigorous training and testing.

A study of oil–water two-phase flow pattern recognition based on thermal sensors

To understand the flow characteristics and kinetic modelling of oil–water two-phase flow(OWTPF), this paper employs thermal array sensors to identify the flow pattern (FP) in OWTPF horizontal pipelines. Firstly, the thermal array sensor installation was constructed. Secondly, the time-varying characteristics of multi-feature signals were qualitatively analyzed using the adaptive optimal kernel time–frequency representation (AOK-TFR) method and unthresholded recurrence plot (URP) method. Finally, the sparrow search algorithm-support vector machine (SSA-SVM) machine learning algorithm is used for quantitative prediction of multi-feature classification, which leads to high prediction accuracy. The experiment proves that the correct rate of the thermal method in recognizing six types of OWTPF is above 91%, the correct rate of five types of flow is above 97.33%. This paper adopts the thermal method to identify the multiphase FP, which is a major innovation in this paper and also lays the foundation for recognizing the flow characteristics of multiphase flow.

Abstract PO5-14-04: FTIR Spectroscopy Analysis of Lipid Region: Distinguishing Breast Cancer from Benign Breast Diseases Using PCA-SVM

Abstract Background: Breast cancer (BC) is the most diagnosed type worldwide, with 2.26 million new cases in 2020. Mammography is the preferred screening method, but it has limitations such as radiation exposure and low sensitivity in dense breasts. Therefore, there is a need for accurate diagnostic methods to detect breast cancer and distinguish benign conditions. Objective: This study aimed to develop an automated tool for the comparison of lipid spectral region in benign breast disease (BBD) and breast cancer (BC) to determine their potential diagnostic value using Fourier Transform Infrared Spectroscopy (ATR-FTIR). Methods: This study was conducted at a Clinical Hospital in Uberlandia, MG, Brazil, after approval by the Human Research Ethics Committee of the Federal University of Uberlandia, and all subjects provided written informed consent. Women who went to the Clinical Hospital for breast surgery were invited to participate in the study as volunteers. After surgery and histopathological analysis, the tumors and lesions found were classified according to histological type, staging, and the status of ER, PR, and HER2 receptors. A total of 60 women participated in the study, of whom 27 had BBD, and 33 had BC. Spectra were measured in the wavenumber range of 4000 cm-1 to 650 cm-1 using an Agilent Cary 600 Series FTIR spectrometer coupled to an MCT detector. The air spectrum was used as a background before each sample analysis. The sample spectra were obtained in triplicate, with a spectral resolution of 4 cm-1, and 128 scans were performed for each measurement. The infrared spectra were analyzed after undergoing preprocessing, which involved positive baseline rubberband normalization, normalization by minimum and maximum, and application of the second derivative. Results: The region of 3050-2800 cm-1 was able to differentiate BC from BBD using principal component analysis (PCA) followed by the support vector machine algorithm (PCA-SVM) with an accuracy of 80%, sensitivity of 88%, and specificity of 70%. This range corresponds to the vibration of lipids, and it is known that changes in the contents of biomolecules in the serum, an increase or decrease, can be related to the presence or absence of BC. The implementation of this approach in clinical practice may automate the diagnosis of BC, monitoring whether changes in therapy or interventions are necessary throughout the treatment. FTIR can potentially assist in clinical decision-making regarding follow-up or biopsy recommendations, avoiding unnecessary biopsies that are more invasive and expensive than blood collection, and which often cause significant anxiety to the patient even if the lesion is not highly suspicious. Conclusion: This study shows that it is possible to detect BC with good accuracy through a minimally invasive, fast, and cost-effective method analyzing the lipid spectral region using principal component analysis (PCA) followed by the support vector machine algorithm (PCA-SVM). Citation Format: Juliana Pereira, Alinne Faria, Izabella Ferreira, Letícia Santos, Donizeti Santos, Marcelo Maia, Ohanna Costa, Raul Freitas, Carlos Paiva, Yara Maia. FTIR Spectroscopy Analysis of Lipid Region: Distinguishing Breast Cancer from Benign Breast Diseases Using PCA-SVM [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO5-14-04.

Research on DCT shift strategy for various driving style based on “driver-vehicle-cloud” machine learning

In order to solve the problem that the DCT static shift strategy cannot adapt to the difference in driving style, the driving style identification model based on multi-dimensional data mining and intelligent algorithm heavily depends on vehicle terminal data storage and calculation, an intelligent shift strategy based on “driver-vehicle-cloud” cooperative control is proposed. Firstly, the dynamic model of the DCT vehicle is analyzed, the primary shift schedule is calculated, and a method to adaptively modify the shifting schedule of DCT according to driving style is proposed. Then, many vehicle driving data are collected, cleaned, and reconstructed by wavelet denoising and other methods, and a driving style database with 80-dimensional features is constructed. Five essential features are selected by the ReliefF method, and the driving style recognition model is constructed by combining random forest, support vector machine, naive Bayesian, and other algorithms. Finally, the support vector machine model with the highest precision is selected, and the “driver-vehicle-cloud” collaborative control system is deployed using cloud computing and vehicle-cloud collaborative technology. The experiment car test shows that the system can identify the driver’s driving style in real time and realize the differential shift schedule and driving experience of DCT.

Disruption detection for a cognitive digital supply chain twin using hybrid deep learning

Recent disruptive events, such as COVID-19 and Russia–Ukraine conflict, had a significant impact of global supply chains. Digital supply chain twins have been proposed in order to provide decision makers with an effective and efficient tool to mitigate disruption impact. This paper introduces a hybrid deep learning approach for disruption detection within a cognitive digital supply chain twin framework to enhance supply chain resilience. The proposed disruption detection module utilises a deep autoencoder neural network combined with a one-class support vector machine algorithm. In addition, long-short term memory neural network models are developed to identify the disrupted echelon and predict time-to-recovery from the disruption effect. The obtained information from the proposed approach will help decision-makers and supply chain practitioners make appropriate decisions aiming at minimizing negative impact of disruptive events based on real-time disruption detection data. The results demonstrate the trade-off between disruption detection model sensitivity, encountered delay in disruption detection, and false alarms. This approach has seldom been used in recent literature addressing this issue.

Fusion of Diverse Data Sources for Flood Extent Mapping and Risk Assessment in Sindh: A Comparative Study of Inundation Mapping Approaches

Accurate and timely mapping of flood extent is crucial for effective disaster response and management. However, existing methods often face challenges in integrating diverse data sources and leveraging advanced techniques for precise inundation mapping. This research aimed to address this gap by proposing and evaluating four different methods for improving flood extent mapping in Sindh, Pakistan, through the integration of various data sources, including precipitation, Synthetic Aperture Radar (SAR), buildings, population, and optical data. The first strategy involves categorizing post-flood SAR data immediately using non-parametric (Support Vector Machine (SVM) and Random Forest (RF)), parametric (Maximum Likelihood Estimation (MLE)), and cluster (ISO) algorithms for Vertical transmit and Vertical received (VV) and Vertical transmit and Horizontal received (VH) polarisations. The second method relies on Otsu’s method for automatic thresholding on post-flood event VH and VV data. The third approach utilizes both pre- and post-flood event data by creating a stack of Pre-event VH, Pre-event VV, Post-event VH, and Post-event VV data, which is then classified using the SVM, RF, MLE and ISO algorithms. Lastly, the fourth method employs the stack of Principal Component Analysis (PCA) bands, consisting of PCA components 1, 2, and 3, to categorize data for flooding using the SVM, RF, MLE and ISO algorithms. The rationale behind evaluating these diverse methods was to identify the most effective approach for accurately mapping flood extent by exploiting the strengths of different algorithms and data processing techniques. The accuracy and precision of these approaches were rigorously evaluated using Landsat-9 Normalized Difference Water Index (NDWI) as a reference dataset, along with error matrix and compound value (Cv) metrics. The findings show that a PCA-based technique with SVM is marginal superior (based on the overall accuracy and Kappa coefficient with value of 92.20 % and kappa coefficient 0.821) than the other approaches tested in the study. By reducing the dimensionality of the dataset while preserving relevant information, PCA offers a computationally efficient approach to flood extent mapping. Among all the approaches, the collective performance of the algorithms was computed using the Cv metric. The SVM algorithm with a Cv of 1.25 demonstrated the best performance, followed by the RF algorithm with Cv of 1.5, and the MLE algorithm with Cv of 2.5. The worst performing algorithm among all is found to be ISO with Cv of 4. It comes into view that first and second approach underperformed in VH polarisation compared to the VV polarisation and provide a more accurate representation of flooded area in VV polarisation. The flood extent with highest accuracy, together with the world’s gridded population, latest Microsoft’s Global ML Building Footprints, and OpenStreetMap building data are used in conjunction to estimate the number of people and buildings at risk within the study area.

Development and validation of a pathological model predicting the efficacy of neoadjuvant therapy for breast cancer based on RCB scoring

IntroductionBreast cancer has become the most prevalent malignant tumor among women globally, posing a serious threat to women's life and health. Neoadjuvant therapy (NAT) has emerged as one of the standard treatment approaches for breast cancer patients. However, due to varying responses to NAT among different patients, significant differences in treatment effectiveness occur, impacting the timely alteration of treatment strategies for patients.Material and methodsBased on clinical and pathological characteristics along with the RCB scoring, we utilized a support vector machine (SVM) algorithm to construct a Breast Cancer Pathological Characteristics(PBCS) prediction model. We thoroughly validated the PBCS and compared it to a Pathomics Signatures (PS) prediction model.Resultswe developed a pathological prediction label, named PS. Subsequently, through univariate and multivariate analysis, we discovered a significant correlation between HER2 and the patients' RCB scores. Integrating HER2 into PS, we constructed a breast cancer pathological prediction model, named PBCS.PBCS exhibits good performance in predicting the effectiveness of postoperative therapy（RCB 0~Ⅰ） in both the training sets(AUC0.86[95%CI0.7988-0.9173])and validation sets（AUC0.83[95%CI0.7219-0.9382 ]). In the validation set, PBCS significantly outperforms the PS（AUC0.65[95%CI0.5121-0.7886 ]）.Calibration curves and clinical decision curves also strongly support PBCS's ability to effectively predict the efficacy of therapy（RCB 0~Ⅰ）. ConclusionsConclusionsPBCS can assist clinical and pathological physicians in accurately predicting patients' post-treatment RCB grading before initiating NAT. This offers a new approach to forecast breast cancer patients' responsiveness to NAT, aiding in devising personalized treatment strategies for patients.

Machine Learning Based Classification for Spam Detection

Electronic Electronic messages, i.e. e-mails, are a communication tool frequently used by individuals or organizations. While e-mail is extremely practical to use, it is necessary to consider its vulnerabilities. Spam e-mails are unsolicited messages created to promote a product or service, often sent frequently. It is very important to classify incoming e-mails in order to protect against malware that can be transmitted via e-mail and to reduce possible unwanted consequences. Spam email classification is the process of identifying and distinguishing spam emails from legitimate emails. This classification can be done through various methods such as keyword filtering, machine learning algorithms and image recognition. The goal of spam email classification is to prevent unwanted and potentially harmful emails from reaching the user's inbox. In this study, Random Forest (RF), Logistic Regression (LR), Naive Bayes (NB), Support Vector Machine (SVM) and Artificial Neural Network (ANN) algorithms are used to classify spam emails and the results are compared. Algorithms with different approaches were used to determine the best solution for the problem. 5558 spam and non-spam e-mails were analyzed and the performance of the algorithms was reported in terms of accuracy, precision, sensitivity and F1-Score metrics. The most successful result was obtained with the RF algorithm with an accuracy of 98.83%. In this study, high success was achieved by classifying spam emails with machine learning algorithms. In addition, it has been proved by experimental studies that better results are obtained than similar studies in the literature.

Machine learning technique for detecting diabetes disease

Diabetes is considered a critical disease and it has been a growing concern owing to its increased morbidity. Moreover, the average age of people who are affected by diabetes illness has currently declined to the mid-20s. Given the high prevalence, it is necessary to address this problem effectively. Due to the significant prevalence of diabetes illness, it is essential to handle and address this issue appropriately. Currently, machine learning methods are considered a vital area for detecting and diagnosing disease. These methods can learn from data and classify data based on the coordinate subjects. This paper presents a model for detecting diabetes illness based on a machine learning technique. The Support Vector Machine (SVM) algorithm is used for classifying the people who are categorized as patients with diabetes disease from the people who are categorized as non-diabetic. Further, the database is compiled from the Pima Indian Diabetes Dataset (PIDD). The results show that the proposed model achieves 81.8% accuracy. Moreover, the proposed model achieves 84.34% sensitivity and 74.35% specificity.

High-performance grating-like SERS substrate based on machine learning for ultrasensitive detection of Zexie-Baizhu decoction

Rapid, universal and accurate identification of chemical composition changes in multi-component traditional Chinese medicine (TCM) decoction is a necessary condition for elucidating the effectiveness and mechanism of pharmacodynamic substances in TCM. In this paper, SERS technology, combined with grating-like SERS substrate and machine learning method, was used to establish an efficient and sensitive method for the detection of TCM decoction. Firstly, the grating-like substrate prepared by magnetron sputtering technology was served as a reliable SERS sensor for the identification of TCM decoction. The enhancement factor (EF) of 4-ATP probe molecules was as high as 1.90 × 107 and the limit of detection (LOD) was as low as 1 × 10−10 M. Then, SERS technology combined with support vector machine (SVM), decision tree (DT), Naive Bayes (NB) and other machine learning algorithms were used to classify and identify the three TCM decoctions, and the classification accuracy rate was as high as 97.78 %. In summary, it is expected that the proposed method combining SERS and machine learning method will have a high development in the practical application of multi-component analytes in TCM.

Predicting response of hepatoblastoma primary lesions to neoadjuvant chemotherapy through contrast-enhanced computed tomography radiomics

ObjectiveTo investigate the clinical value of contrast-enhanced computed tomography (CECT) radiomics for predicting the response of primary lesions to neoadjuvant chemotherapy in hepatoblastoma.MethodsClinical and CECT imaging data were retrospectively collected from 116 children with hepatoblastoma who received neoadjuvant chemotherapy. Tumor response was assessed according to the Response Evaluation Criteria in Solid Tumors (RECIST). Subsequently, they were randomly stratified into a training cohort and a test cohort in a 7:3 ratio. The clinical model was constructed using univariate and multivariate logistic regression, while the radiomics model was developed based on selected radiomics features employing the support vector machine algorithm. The combined clinical–radiomics model incorporated both clinical and radiomics features.ResultsThe area under the curve (AUC) for the clinical, radiomics, and combined models was 0.704 (95% CI: 0.563–0.845), 0.830 (95% CI: 0.704–0.959), and 0.874 (95% CI: 0.768–0.981) in the training cohort, respectively. In the validation cohort, the combined model achieved the highest mean AUC of 0.830 (95% CI 0.616–0.999), with a sensitivity, specificity, accuracy, precision, and f1 score of 72.0%, 81.1%, 78.5%, 57.2%, and 63.5%, respectively.ConclusionCECT radiomics has the potential to predict primary lesion response to neoadjuvant chemotherapy in hepatoblastoma.

Sentiment Analysis Siap Kerja Training Services with Naive Models Bayes and SVM

Training service Siap Kerja has an important function in improving the quality of human resources and developing a competent workforce in various industrial sectors. To ensure trainee success and satisfaction, sentiment analysis in trainee reviews is essential to evaluate the strengths and weaknesses of the service offered. This research intends to compare the performance of algorithms Support Vector Machine (SVM) and Naive Bayes in sentiment analysis of trainee reviews on pages service training Siap Kerja. Review data was collected using web scraping on the Siap Kerja training service page by collecting ratings and reviews of training participants after completing the training they attended on the page training service Siap Kerja. Methods of data pre-processing, data sharing, feature extraction, model training, model evaluation, and results analysis were used in this research. The research results show that the SVM model has higher accuracy (0.93) compared to the Naive model Bayes (0.80). Additionally, positive sentiment was found at 99%, negative at 0.3%, and neutral at 0.7%. ased on the results of this research, it is recommended that the SVM model be used in sentiment analysis in the context of Siap Kerja training services and that the model be optimized to improve performance in classifying reviews with negative or neutral feelings.  

Volcanic clouds detection applying machine learning techniques to GNSS radio occultations

AbstractVolcanic clouds detection is a challenge especially when meteorological clouds are present in the same area. Several algorithms have been developed to detect and monitor volcanic clouds by using satellite instruments based on different remote sensing techniques. This work aims at classifying volcanic clouds based on atmospheric profiles retrieved by the GNSS (Global Navigation Satellite Systems) radio occultation technique. We collocated the radio occultations with the volcanic cloud detection from AIRS (Atmospheric InfraRed Sounder) and IASI (Infrared Atmospheric Sounding Interferometer) for 11 big eruptions happening in the period 2008–2015 resulting in about 15000 profiles. We created an archive with the collocations and a corresponding number of profiles in “non-volcanic” environment in the same area and on the same period of the year. A support vector machine algorithm was applied to the archive in order to classify the clouds and to distinguish the volcanic clouds from the other types. The model performances are promising: the GNSS radio occultations are able to distinguish the volcanic clouds with an accuracy higher than 80% when the eruption occurs at high latitudes. The performances of the model are affected by the number of collocations used for the training. Nowadays, the number of radio occultations is higher than in the period considered in this research, making this work a pioneering study for a future operational product.

Electric power prediction of a two-body hinge-barge wave energy converter using machine learning techniques

Investigating the electric power generated by wave energy converters (WECs) has attracted increasing attention along with the developments of wave energy converting technologies in recent years. Electric power estimation currently depends on wave-to-wire model-based numerical analysis and experimental studies of scale-down prototypes. However, traditional numerical simulations are time-consuming and expensive for power orediction of a full-scale WECs operated in real sea. More importantly, they cannot accurately predict WECs’ power performance in real time, thereby cannot be used for prediction-based real-time control. To address those problems, four machine learning techniques are employed as an alternative to traditional, complex physical modelling processes to evaluate and predict the generated electric power, based on historical experimental data of a two-body hinge-barge WEC. Comparative results of a Backpropagation (BP) Neural Network algorithm, a Long Short-Term Memory (LSTM) algorithm, a Support Vector Machine (SVM) algorithm and a Radial Basis Neural Network (RBFF) algorithm indicate that machine-learning-based approaches can accurately predict the electric performance of this complex multi-degree-of-freedom WEC, where the coefficient of determination (R2) of the BP Neural Network on the test dataset is up to 0.9987.

Early automated detection system for skin cancer diagnosis using artificial intelligent techniques

Recently, skin cancer is one of the spread and dangerous cancers around the world. Early detection of skin cancer can reduce mortality. Traditional methods for skin cancer detection are painful, time-consuming, expensive, and may cause the disease to spread out. Dermoscopy is used for noninvasive diagnosis of skin cancer. Artificial Intelligence (AI) plays a vital role in diseases’ diagnosis especially in biomedical engineering field. The automated detection systems based on AI reduce the complications in the traditional methods and can improve skin cancer’s diagnosis rate. In this paper, automated early detection system for skin cancer dermoscopic images using artificial intelligent is presented. Adaptive snake (AS) and region growing (RG) algorithms are used for automated segmentation and compared with each other. The results show that AS is accurate and efficient (accuracy = 96%) more than RG algorithm (accuracy = 90%). Artificial Neural networks (ANN) and support vector machine (SVM) algorithms are used for automated classification compared with each other. The proposed system with ANN algorithm shows high accuracy (94%), precision (96%), specificity (95.83%), sensitivity (recall) (92.30%), and F1-score (0.94). The proposed system is easy to use, time consuming, enables patients to make early detection for skin cancer and has high efficiency.