Cancer detection and classification using a simplified binary state vector machine.

Wind speed forecasting is critical for a variety of engineering tasks, such as wind energy harvesting, scheduling of a wind power system, and dynamic control of structures (e.g., wind turbine, bridge, and building). Wind speed, which has characteristics of random, nonlinear and uncertainty, is difficult to forecast. Nowadays, machine learning approaches (generalized regression neural network (GRNN), back propagation neural network (BPNN), and extreme learning machine (ELM)) are widely used for wind speed forecasting. In this study, two schemes are proposed to improve the forecasting performance of machine learning approaches. One is that optimization algorithms, i.e., cross validation (CV), genetic algorithm (GA), and particle swarm optimization (PSO), are used to automatically find the optimal model parameters. The other is that the combination of different machine learning methods is proposed by finite mixture (FM) method. Specifically, CV-GRNN, GA-BPNN, PSO-ELM belong to optimization algorithm-assisted machine learning approaches, and FM is a hybrid machine learning approach consisting of GRNN, BPNN, and ELM. The effectiveness of these machine learning methods in wind speed forecasting are fully investigated by one-year field monitoring data, and their performance is comprehensively compared.

ABSTRACTDeveloping an accurate model that can effectively simulate groundwater levels is of immense significance for water resource management and aquifer protection. To achieve this, it is crucial to identify key factors in remote sensing, topography, and meteorology, and to improve hydrological models to enhance prediction accuracy. This study proposes a multistep modelling framework, the RF‐PSO‐GRNN algorithm model, to improve the accuracy of groundwater level simulations in data‐scarce hilly regions. The framework combines the random forest (RF) model with the particle swarm optimization (PSO) algorithm and the generalised regression neural network (GRNN). First, the study area was divided into hilly and plain regions, decreasing mean absolute error (MAE) by 0.2 m in plain areas and 0.1 m in hilly areas. The RF‐Gini index combination was then used to calculate the contributing factors for each region, facilitating the determination of an optimal balancing strategy, which reduced RMSE by 4.35 m in hilly areas and 3.82 m in plain areas. Subsequently, the PSO algorithm was employed to compute the optimal smoothing factor for GRNN, further reducing RMSE by approximately 10 m. Additionally, MAE decreased by 11 m in hilly areas and 7.5 m in plain areas. Finally, the RF‐PSO‐GRNN model was applied to simulate the spatiotemporal evolution of groundwater levels in three counties within the Fu River Basin of Jiangxi Province, China. The findings confirm the effectiveness of GRNN in simulating groundwater levels with limited data samples. This study provides a practical solution for hydrological modelling and groundwater management under data‐scarce conditions, contributing to the understanding and predicting groundwater dynamics.

This paper presented three disease diagnosis systems using pattern recognition based on genetic algorithm (GA) and neural networks. All systems dealt with feature selection and classification. GA chose subsets of features for the input of the classifier (neural network) and the accuracy of the classifier determined the percentage of effectiveness of each subset of features. The classifiers using in this paper were general regression neural network (GRNN), radial basis function (RBF) and radial basis network exact fit (RBEF). It uses breast cancer and hepatitis disease datasets taken from UCI machine learning database as medical dataset. The system performances were estimated by classification accuracy and they were compared with similar methods without feature selection. Key words: Pattern recognition, genetic algorithm, neural networks, classification.

In India, the oral cancers are usually presented in advanced stage of malignancy. It is critical to ascertain the diagnosis in order to initiate most advantageous treatment of the suspicious lesions. The main hurdle in appropriate treatment and control of oral cancer is identification and risk assessment of early disease in the community in a cost-effective fashion. The objective of this research is to design a data mining model using probabilistic neural network and general regression neural network (PNN/GRNN) for early detection and prevention of oral malignancy. The model is built using the oral cancer database which has 35 attributes and 1025 records. All the attributes pertaining to clinical symptoms and history are considered to classify malignant and non-malignant cases. Subsequently, the model attempts to predict particular type of cancer, its stage and extent with the help of attributes pertaining to symptoms, gross examination and investigations. Also, the model envisages anticipating the survivability of a patient on the basis of treatment and follow-up details. Finally, the performance of the PNN/GRNN model is compared with that of other classification models. The classification accuracy of PNN/GRNN model is 80% and hence is better for early detection and prevention of the oral cancer.

Mammography is the modality of choice for the early detection of breast cancer, primarily because of its sensitivity to the detection of breast cancer. However, because of its high rate of false positive predictions, a large number of biopsies of benign lesions result. The paper explores the use and evaluates the performance of two neural network hybrids as an aid to radiologists in avoiding biopsies of these benign lesions. These hybrids provide the potential to improve both the sensitivity and specificity of breast cancer diagnosis. The first hybrid, the Generalized Regression Neural Network (GRNN) Oracle, focuses on improving the performance output of a set of learning algorithms that operate and are accurate over the entire (defined) learning space. The second hybrid, an evolutionary programming (EP)/adaptive boosting (AB) based hybrid, intelligently combines the outputs from an iteratively called learning algorithm (one which performs at least slightly better than random guessing), in order to boost the performance of the weak learner. The second part of the paper discusses modifications to improve the EP/AB hybrid's performance, and further evaluates how the use of the EP/AB hybrid may obviate biopsies of benign lesions (as compared to an EP only classification system), given the requirement of missing few if any cancers.

To assess the correlation between the clinical and molecular assays in identify early and robust prostate cancer detection. Early detection, management of cancer and decision about the disease are important for beneficial treatment of prostate cancer. We used a computerized search of the Medline/ PubMed databases with the key words prostate cancer, biomarker, and early detection. Clinical management of cancer is facilitated by a conventional test such as prostate-specific antigen and digital rectal exam for application in clinical practice. Although these tests have significantly reduced the mortality with prostate cancer, but have some drawbacks and false positive rate. Fortunately, there are strong correlations between the clinical and molecular assays in identifying early and robust cancer detection, because molecular assays are less invasive and reliable. The use of genetic markers has the potential to providing useful prognostic or predictive information into clinically useful diagnostic tests to improve clinical decision-making and enhance therapeutic success. Different clinical and molecular assays are for detecting prostate cancer and use the biomarkers as potential tumor markers could be a useful predictor in the screening and monitoring to avoid over treatment prostate cancer.

The problem of conditional simulation of non-Gaussian stochastic processes and fields has gained a significant interest recently because of its applications in many fields, such as wind engineering, ocean engineering, and soil engineering. In this paper, the support vector machines (SVM) approach is developed for the conditional simulation of non-Gaussian stochastic processes and fields. To show the advantages of the presented method, the conditional simulation of non-Gaussian fluctuating wind pressures is carried out by using SVM and artificial neural networks (ANN). SVM considers three kinds of kernel function, such as linear function, Gaussian radial basis function, and exponential radial basis function, whereas ANN employs back-propagation and generalized regression. In machine learning of these artificial intelligences, two ways (interpolation and extrapolation) are employed to train finite non-Gaussian samples. The feasibility and validity of these algorithms are evaluated through the correlation coefficients, root mean square errors, skewness errors, and kurtosis errors between simulated samples and target samples and probability density functions (PDF), power spectral density (PSD) functions, and autocorrelation functions (ACF) of the simulated non-Gaussian fluctuating wind pressures versus their corresponding targets. The results show that the accuracy and effectiveness of SVM with an appropriate kernel function are superior to the back-propagation neural network (BPNN) and generalized regression neural network (GRNN). Furthermore, the advantage of the presented SVM approach is very obvious when the trained non-Gaussian samples are few.

BackgroundPhysical activity (PA) level is associated with multiple health benefits during early childhood. However, inconsistency in the methods for quantification of PA levels among preschoolers remains a problem.ObjectiveThis study aimed to develop PA intensity cut points for wrist-worn accelerometers by using machine learning (ML) approaches to assess PA in preschoolers.MethodsWrist- and hip-derived acceleration data were collected simultaneously from 34 preschoolers on 3 consecutive preschool days. Two supervised ML models, receiver operating characteristic curve (ROC) and ordinal logistic regression (OLR), and one unsupervised ML model, k-means cluster analysis, were applied to establish wrist-worn accelerometer vector magnitude (VM) cut points to classify accelerometer counts into sedentary behavior, light PA (LPA), moderate PA (MPA), and vigorous PA (VPA). Physical activity intensity levels identified by hip-worn accelerometer VM cut points were used as reference to train the supervised ML models. Vector magnitude counts were classified by intensity based on three newly established wrist methods and the hip reference to examine classification accuracy. Daily estimates of PA were compared to the hip-reference criterion.ResultsIn total, 3600 epochs with matched hip- and wrist-worn accelerometer VM counts were analyzed. All ML approaches performed differently on developing PA intensity cut points for wrist-worn accelerometers. Among the three ML models, k-means cluster analysis derived the following cut points: ≤2556 counts per minute (cpm) for sedentary behavior, 2557-7064 cpm for LPA, 7065-14532 cpm for MPA, and ≥14533 cpm for VPA; in addition, k-means cluster analysis had the highest classification accuracy, with more than 70% of the total epochs being classified into the correct PA categories, as examined by the hip reference. Additionally, k-means cut points exhibited the most accurate estimates on sedentary behavior, LPA, and VPA as the hip reference. None of the three wrist methods were able to accurately assess MPA.ConclusionsThis study demonstrates the potential of ML approaches in establishing cut points for wrist-worn accelerometers to assess PA in preschoolers. However, the findings from this study warrant additional validation studies.

Non-Line-of-Sight (NLoS) propagation condition is a crucial factor affecting the precision of the localization in the Ultra-Wideband (UWB) Indoor Positioning System (IPS). Numerous supervised Machine Learning (ML) approaches have been applied for NLoS identification to improve the accuracy of the IPS. However, it is difficult for existing ML approaches to maintain a high classification accuracy when the database contains a small number of NLoS signals and a large number of Line-of-Sight (LoS) signals. The inaccurate localization of the target node caused by this small number of NLoS signals can still be problematic. To solve this issue, we propose feature-based Gaussian Distribution (GD) and Generalized Gaussian Distribution (GGD) NLoS detection algorithms. By employing our detection algorithm for the imbalanced dataset, a classification accuracy of $96.7\%$ and $98.0\%$ can be achieved. We also compared the proposed algorithm with the existing cutting-edge such as Support-Vector-Machine (SVM), Decision Tree (DT), Naive Bayes (NB), and Neural Network (NN), which can achieve an accuracy of $92.6\%$, $92.8\%$, $93.2\%$, and $95.5\%$, respectively. The results demonstrate that the GGD algorithm can achieve high classification accuracy with the imbalanced dataset. Finally, the proposed algorithm can also achieve a higher classification accuracy for different ratios of LoS and NLoS signals which proves the robustness and effectiveness of the proposed method.

Micropropagation techniques offer opportunity to proliferate, maintain, and study dynamic plant responses in highly controlled environments without confounding external influences, forming the basis for many biotechnological applications. With medicinal and recreational interests for Cannabis sativa L. growing, research related to the optimization of in vitro practices is needed to improve current methods while boosting our understanding of the underlying physiological processes. Unfortunately, due to the exorbitantly large array of factors influencing tissue culture, existing approaches to optimize in vitro methods are tedious and time-consuming. Therefore, there is great potential to use new computational methodologies for analyzing data to develop improved protocols more efficiently. Here, we first tested the effects of light qualities using assorted combinations of Red, Blue, Far Red, and White spanning 0–100 μmol/m2/s in combination with sucrose concentrations ranging from 1 to 6% (w/v), totaling 66 treatments, on in vitro shoot growth, root development, number of nodes, shoot emergence, and canopy surface area. Collected data were then assessed using multilayer perceptron (MLP), generalized regression neural network (GRNN), and adaptive neuro-fuzzy inference system (ANFIS) to model and predict in vitro Cannabis growth and development. Based on the results, GRNN had better performance than MLP or ANFIS and was consequently selected to link different optimization algorithms [genetic algorithm (GA), biogeography-based optimization (BBO), interior search algorithm (ISA), and symbiotic organisms search (SOS)] for prediction of optimal light levels (quality/intensity) and sucrose concentration for various applications. Predictions of in vitro conditions to refine growth responses were subsequently tested in a validation experiment and data showed no significant differences between predicted optimized values and observed data. Thus, this study demonstrates the potential of machine learning and optimization algorithms to predict the most favorable light combinations and sucrose levels to elicit specific developmental responses. Based on these, recommendations of light and carbohydrate levels to promote specific developmental outcomes for in vitro Cannabis are suggested. Ultimately, this work showcases the importance of light quality and carbohydrate supply in directing plant development as well as the power of machine learning approaches to investigate complex interactions in plant tissue culture.

<p dir="ltr">Early cancer detection is critical for improving survival rates, yet it requires a careful balance between minimising missed diagnoses and avoiding over- investigation. Primary care plays a central role in this process. This thesis aims to enhance understanding of the complexities involved in early cancer detection by analysing symptoms and signs, with the goal of contributing to the development of risk assessment and prediction tools to identify cancer at an early stage within primary care.</p><p dir="ltr">This thesis is based on five quantitative studies conducted within the Swedish healthcare system. Study I examined symptoms reported by referred patients via questionnaires at the Department of Pulmonary Medicine at Karolinska University Hospital. It investigated whether machine learning could predict which patients subsequently received a lung cancer diagnosis, stratified by smoking status. Studies II and III focused on comprehensive diagnostic data and coded symptoms from primary care to facilitate early detection of non-metastatic colorectal cancer, with Study II conducted in Region Stockholm and Study III in Region Västra Götaland. Studies IV and V used comprehensive clinical and laboratory data from the entire adult population of Stockholm County. Study IV presents a cohort description, while Study V examines the association and discriminatory capacity of newly developed anaemia as an indicator for cancer.</p><p dir="ltr">In Study I, the findings demonstrate that predictive models, using machine learning, exhibit good discriminatory ability for patients who either never smoked or were current smokers. In Study II, an existing Swedish risk assessment tool was validated by replicating it in a different region, with consistent results across regions. In Study III, a new predictive model was developed using machine learning to analyse all diagnostic data for identifying non-metastatic colorectal cancer. Study IV introduces the extensive STEADY-CAN (Stockholm early detection of cancer study) cohort, providing opportunities to analyse early cancer detection patterns. Study V investigates the association between newly developed anaemia and cancer risk within the STEADY-CAN cohort, revealing a significant impact on risk assessment.</p><p dir="ltr">These findings collectively address the value of improved risk stratification in primary care by leveraging existing data to better identify patients at elevated risk of having cancer. The results highlight key themes in early detection- predictive accuracy, risk stratification, clinical utility, and applicability across populations-and identify areas where current evidence has been limited or inconclusive. Future research should prioritise the validation of novel diagnostic approaches and the development of systems that support clinical decision- making, while upholding the principles of accessible, patient-centred care. Keywords: Early cancer detection, Primary care, Machine learning, Colorectal cancer, Lung cancer, Risk assessment tools, Anaemia, STEADY-CAN.</p><h3>List of scientific papers</h3><p dir="ltr">I. <b>Nemlander E</b>, Rosenblad A, Abedi E, Ekman S, Hasselström J, Eriksson LE, Carlsson AC. Lung cancer prediction using machine learning on data from a symptom e-questionnaire for never smokers, formers smokers and current smokers. PLoS One. 2022 Oct 21;17(10):e0276703. PMID: 36269746; PMCID: PMC9586380.</p><p dir="ltr">Erratum for: PLoS One. 2022 Oct 21;17(10):e0276703. PMID: 38060550; PMCID: PMC10703334. <a href="https://doi.org/10.1371/journal.pone.0276703">https://doi.org/10.1371/journal.pone.0276703</a></p><p dir="ltr">II. <b>Nemlander E</b>, Rosenblad A, Abedi E, Hasselström J, Sjövall A, Carlsson AC, Ewing M. Validation of a diagnostic prediction tool for colorectal cancer: a case-control replication study. Fam Pract. 2023 Jan 5:cmac147. PMID: 36611019. <a href="https://doi.org/10.1093/fampra/cmac147">https://doi.org/10.1093/fampra/cmac147</a><br><br>III. <b>Nemlander E</b>, Ewing M, Abedi E, Hasselström J, Sjövall A, Carlsson AC, Rosenblad A. A machine learning tool for identifying non- metastatic colorectal cancer in primary care. European Journal of Cancer. 2023 Jan 11. <a href="https://doi.org/10.1016/j.ejca.2023.01.011">https://doi.org/10.1016/j.ejca.2023.01.011</a><br><br>IV. <b>Nemlander E</b>, Abedi E, Ljungman P, Hasselström J, Carlsson AC, Rosenblad A. The Stockholm Early Detection of Cancer Study (STEADY-CAN): rationale, design, data collection, and baseline characteristics for 2.7 million participants. <a href="https://doi.org/10.1007/s10654-024-01192-8" rel="noreferrer" target="_blank">https://doi.org/10.1007/s10654-024-01192-8</a></p><p dir="ltr"><br>V. <b>Nemlander E</b>, Rosenblad A, Abedi E, Hasselström J, Ljungman P, Carlsson AC. Newly developed anaemia predicts incident cancer and death within 18 months: Findings from 1.1 million patients in the Stockholm Early Detection of Cancer Study (STEADY-CAN) cohort. [Manuscript]</p>

A reliable model to predict mercury solubility in natural gas components: A robust machine learning framework and data assessment.

The present study was conducted to assess the awareness and practice regarding early detection and prevention of breast and cervical cancers among women of kudumbashree units. A quantitative approach and non experimental descriptive design was used for the study. The study was theoretically supported by Nola J Pender's revised health promotion model. A total of 504 women of kudumbashree units were selected using multistage sampling technique. The data was collected using socio personal data sheet, structured questionnaire to measure the awareness and a rating scale to rate the practice regarding early detection and prevention of breast and cervical cancers, all developed by the researcher. The data was analysed using descriptive and inferential statistics. The findings of the study revealed that 81.9% of women of kudumbashree units had average awareness and 59.5% of women of kudumbashree units had good practice. There was no significant correlation between awareness and practice among women of kudumbashree units regarding early detection and prevention of breast and cervical cancers. The selected variables namely education of women of kudumbashree units, occupation of women of kudumbashree units and previous exposure to information regarding breast or cervical cancers had association with awareness regarding early detection and prevention of breast and cervical cancers. Also, there is no association between practice regarding early detection and prevention of breast and cervical cancers and any of the selected variables. An information booklet was prepared on early detection and prevention of breast and cervical cancers and distributed to all study participants.

Microarray data often contains multiple missing genetic expression values that degrade the performance of statistical and machine learning algorithms. This paper presents a K ranked diagonal covariance-based missing value estimation algorithm (KRCOV) that has demonstrated significantly superior performance compared to the more commonly used K-nearest neighbour (KNN) imputation algorithm when it is applied to estimate missing values of BRCA1, BRCA2 and Sporadic genetic mutation samples present in ovarian cancer. Experimental results confirm KRCOV outperformed both KNN and zero imputation techniques in terms of their classification accuracies when used toimpute randomly missing values from 1% to 5%.The classifier used for this purpose was the Generalized Regression Neural Network.The paper also provides a hypothesis for why KRCOV performs better than KNN not only for bioinformatics data but also for other data types having strong correlated values.

In this paper, Statistical Neural Networks have been proven to be an effective classifier method for large sample and high dimensional letter recognition problem. For this purpose, Probabilistic Neural Network (PNN) and General Regression Neural Networks (GRNN) have been applied to classify the 26 capital letters in the English alphabet. Principal Component Analysis (PCA) has been established as a feature extraction and a data compression method to achieve less computational complexity. The low computational complexity obtained by PCA provides a solution for high dimensional letter recognition problem for online operations. Simulation results illustrate that GRNN and PNN are suitable and effective methods for solving classification problems with higher classification accuracy and better generalization performances than their counterparts.