Data Normalization Techniques Research Articles

Whole slide image-based weakly supervised deep learning for predicting major pathological response in non-small cell lung cancer following neoadjuvant chemoimmunotherapy: a multicenter, retrospective, cohort study.

Develop a predictive model utilizing weakly supervised deep learning techniques to accurately forecast major pathological response (MPR) in patients with resectable non-small cell lung cancer (NSCLC) undergoing neoadjuvant chemoimmunotherapy (NICT), by leveraging whole slide images (WSIs). This retrospective study examined pre-treatment WSIs from 186 patients with non-small cell lung cancer (NSCLC), using a weakly supervised learning framework. We employed advanced deep learning architectures, including DenseNet121, ResNet50, and Inception V3, to analyze WSIs on both micro (patch) and macro (slide) levels. The training process incorporated innovative data augmentation and normalization techniques to bolster the robustness of the models. We evaluated the performance of these models against traditional clinical predictors and integrated them with a novel pathomics signature, which was developed using multi-instance learning algorithms that facilitate feature aggregation from patch-level probability distributions. Univariate and multivariable analyses confirmed histology as a statistically significant prognostic factor for MPR (P-value< 0.05). In patch model evaluations, DenseNet121 led in the validation set with an area under the curve (AUC) of 0.656, surpassing ResNet50 (AUC = 0.626) and Inception V3 (AUC = 0.654), and showed strong generalization in external testing (AUC = 0.611). Further evaluation through visual inspection of patch-level data integration into WSIs revealed XGBoost's superior class differentiation and generalization, achieving the highest AUCs of 0.998 in training and robust scores of 0.818 in validation and 0.805 in testing. Integrating pathomics features with clinical data into a nomogram yielded AUC of 0.819 in validation and 0.820 in testing, enhancing discriminative accuracy. Gradient-weighted Class Activation Mapping (Grad-CAM) and feature aggregation methods notably boosted the model's interpretability and feature modeling. The application of weakly supervised deep learning to WSIs offers a powerful tool for predicting MPR in NSCLC patients treated with NICT.

Impact Load Localization Based on Multi-Scale Feature Fusion Convolutional Neural Network.

In order to achieve impact load localization of complex structures such as ships, this paper proposes a multi-scale feature fusion convolutional neural network (MSFF-CNN) method for impact load localization. An end-to-end machine learning model is used, where the raw vibration signals of impact loads are directly fed into the network model to avoid the process of feature extraction. Automatic feature learning and feature concatenation of the signal are achieved through four independent convolutional layers, each using a different size of convolutional kernel. Data normalization and L2 regularization techniques are introduced to enhance the data and prevent overfitting. Classification and localization of impact loads are accomplished using a softmax classification layer. Validation experiments are carried out using a ship's stern compartment model. Our results show that the classification and localization accuracy of the impact load sample group of MSFF-CNN reaches 94.29% compared with a traditional CNN. The method further improves the ability of the network to extract state features, takes local perception and global vision into account, effectively improves the classification ability of the model, and has good prospects for engineering applications.

Investigating the Impact of Data Normalization Methods on Predicting Electricity Consumption in a Building Using different Artificial Neural Network Models.

The study investigates the impact of data normalization on the prediction of electricity consumption in buildings using four multilayer Artificial Neural Networks (ANN) algorithms: Long Short-Term Memory Networks (LSTM), Levenberg-Marquardt Back-propagation (LMBP), Recurrent Neural Networks (RNN), and General Regression Neural Network (GRNN). Four data normalization approaches, Min-Max Scaling, Mean, Z-score, and Gaussian function were assessed on experimental datasets. The LSTM algorithm, when combined with Min-Max normalization, showed the most favorable predictive capabilities, with a low Coefficient of Variation of the Root Mean Square Error (CVRMSE) of 10.3 and Normalized Mean Bias Error (NMBE) of 0.6. The remaining three normalization approaches showed satisfactory concordance with empirical data, but with slight disparities in precision. The LMBP model, when using Z-score normalization, had favorable performance in forecasting electricity consumption, but the discrepancies across the models were not significant. The Recurrent Neural Network (RNN) model, when used with Gaussian normalization, exhibited the most favorable performance, with the lowest Coefficient of Variation of Root Mean Square Error (CVRMSE) at 11.8 and Normalized Mean Biased Error (NMBE) at 0.6. The Generalized Regression Neural Network (GRNN) model, trained on unprocessed data, exhibited superior performance, with the lowest Coefficient of Variation of Root Mean Square Error (CVRMSE) at 19.2 and NMBE at 1.0. In conclusion, the study highlights the significant influence of data normalization on the predictive capabilities of various ANN models, suggesting that careful use of data normalization techniques can significantly improve the accuracy of electricity consumption forecasting in buildings.

A Study on the Man-Hour Prediction in Structural Steel Fabrication

Longitudinal cutting is the most common process in steel structure manufacturing, and the man-hours of the process provide an important basis for enterprises to generate production schedules. However, currently, the man-hours in factories are mainly estimated by experts, and the accuracy of this method is relatively low. In this study, we propose a system that predicts man-hours with history data in the manufacturing process and that can be applied in practical structural steel fabrication. The system addresses the data inconsistency problem by one-hot encoding and data normalization techniques, Pearson correlation coefficient for feature selection, and the Random Forest Regression (RFR) for prediction. Compared with the other three Machine-Learning (ML) algorithms, the Random Forest algorithm has the best performance. The results demonstrate that the proposed system outperforms the conventional approach and has better forecast accuracy so it is suitable for man-hours prediction.

Security Information Event Management data acquisition and analysis methods with machine learning principles

In the face of increasing global disruptions, the cybersecurity field is confronting rising threats posed by offensive groups and individual hackers. Traditional security measures often fall short in detecting and mitigating these sophisticated attacks, necessitating advanced intrusion detection methods. The goal of our study is to develop robust network intrusion detection methods using machine learning techniques. In addition, we evaluate the effectiveness of various machine learning models in detecting network intrusions. Model performances are optimized through hyperparameter tuning and feature selection. A range of classification and clustering models have been employed. Data from SIEM systems capturing real-time statistics from cloud-hosted Windows virtual machines has been gathered and augmented with web attack logs from CICIDS2017, each comprising approximately fifteen thousand rows. Hyperparameter tuning, data normalization, standardization and feature selection techniques for model optimization have been used in our study. The research showcases the potential of machine learning in enhancing network intrusion detection capabilities. The findings underscore the effectiveness of the Random Forest Classifier (0.97) and highlight the importance of utilizing diverse datasets and advanced optimization techniques. This study offers valuable insights and sets a foundation for future advancements in cybersecurity strategies and intrusion detection systems.

Innovative Framework for Thyroid Disease Detection by Leveraging Hybrid AGTEO Feature Selection and GRU Classification Model

Thyroid disease remains a significant health concern, necessitating advanced diagnostic tools for swift and accurate identification. The initial step involves preprocessing datasets, employing an Outlier Detection Method with Isolated Forest in conjunction with data normalization techniques to eliminate noise and standardize the data, laying a robust groundwork for subsequent analysis. Subsequently, feature extraction is conducted utilizing an Enhanced AlexNet architecture augmented by a more intricate Chameleon Swarm Algorithm (CSA) model to discern finer patterns within the data, enhancing the discriminative nature of the extracted features. Following this, a feature selection strategy employing hybrid optimization is deployed, amalgamating the strengths of Equilibrium Optimizer and Artificial Gorilla Troops Optimizer (AGTO) into a hybrid model named HAGTEO, aiming to identify the most informative features, thus reducing dimensionality and enhancing classifier efficiency. Ultimately, the Gated Recurrent Unit (GRU) classifier is employed for thyroid disease classification based on the extracted and selected features. Renowned for its capability to capture temporal dependencies, the GRU model further enhances classification accuracy. The proposed framework is subjected to testing on two distinct datasets, demonstrating its efficacy in thyroid disease detection. Experimental outcomes reveal superior performance compared to conventional methods, achieving accuracies of 98.07% and 98.00% for dataset 1 and dataset 2, respectively. As an advanced diagnostic solution for thyroid disease, it holds promising potential.

Deep learning in spatially resolved transcriptfomics: a comprehensive technical view

Spatially resolved transcriptomics (SRT) is a pioneering method for simultaneously studying morphological contexts and gene expression at single-cell precision. Data emerging from SRT are multifaceted, presenting researchers with intricate gene expression matrices, precise spatial details and comprehensive histology visuals. Such rich and intricate datasets, unfortunately, render many conventional methods like traditional machine learning and statistical models ineffective. The unique challenges posed by the specialized nature of SRT data have led the scientific community to explore more sophisticated analytical avenues. Recent trends indicate an increasing reliance on deep learning algorithms, especially in areas such as spatial clustering, identification of spatially variable genes and data alignment tasks. In this manuscript, we provide a rigorous critique of these advanced deep learning methodologies, probing into their merits, limitations and avenues for further refinement. Our in-depth analysis underscores that while the recent innovations in deep learning tailored for SRT have been promising, there remains a substantial potential for enhancement. A crucial area that demands attention is the development of models that can incorporate intricate biological nuances, such as phylogeny-aware processing or in-depth analysis of minuscule histology image segments. Furthermore, addressing challenges like the elimination of batch effects, perfecting data normalization techniques and countering the overdispersion and zero inflation patterns seen in gene expression is pivotal. To support the broader scientific community in their SRT endeavors, we have meticulously assembled a comprehensive directory of readily accessible SRT databases, hoping to serve as a foundation for future research initiatives.

Historical Projection of the Rainfall Distribution in the North Region of Brazil

From a set of primary and secondary monthly data from 1991 to 2022, the annual and seasonal climatological pattern of the North region of Brazil, where most of the Amazon Biome is located, was analyzed. An incomplete Gamma distribution model was applied to the climatological precipitation data (mm); atmospheric pressure (mb); incidence of solar radiation (kJ/m²); air temperature and dew (ºC); relative humidity (%); wind intensity (m/s) with direction and maximum gust. Data normalization techniques and spatial similarity identified different patterns and trends of precipitation in the region, with significant seasonality, especially in terms of rainfall. The highest precipitation rates occurred in the N-NW axis, inside the northern Amazonian area, while the lowest values were observed in the southern equatorial zone, on the limits of the Pará State with the Cerrado Biome. Four zones and one climate range were established: southern, central, northern west and northern east zones and extreme north area, all with significant similarity in precipitation and humidity. A trend was observed in the number of days with precipitation between 25 and 50% in the southern and central zones, and an increase in precipitation of 50 to 75% for the northern zone. The wind distribution model showed a tendency towards the presence of isotropic climate phenomena, presenting the same properties or characteristics. The results obtained are relevant to support research aimed at understanding global warming and its consequences, in addition to contributing to forest management programs, and establishing more effective protocols for cultivation in agricultural areas in the Amazon.

A Comparative Study of Z-Score and Min-Max Normalization for Rainfall Classification in Pekanbaru

Data preprocessing plays a crucial role in enhancing the performance of machine learning algorithms for classification tasks. Among the essential preprocessing stages is data normalization, which aims to standardize data into a comparable range of values. This study focuses on normalizing rainfall data in Pekanbaru from 2019 to 2023. The objective is to compare various data normalization techniques, including Min-Max Normalization and Z-Score Normalization. The comparison of these particular strategies is justified becausethey are widely applied and have different approaches. Min-max normalizationis an easy-to-implement technique that makes the data sensitive to outliers by scaling it to a specific range, often from 0 to 1. However, Z-Score Normalization, sometimes referred to as Standardization, standardizes the data by dividing by the standard deviation and subtracting the mean, maintaining the shape of the distribution and making it resistant to outliers.The findings demonstrate that applying normalization techniques effectively enhances classification performance compared to using unnormalized data. Specifically, the optimal classification performance is achieved through Z-Score Normalization, yielding accuracy, sensitivity, and specificity rates of 74.59%, 82.48%, and 63.92%, respectively

Enhancing Fault Detection and Diagnosis in Grid-Connected PV Systems under Irradiance Variations: A Novel Approach Using New Data Normalization Techniques on RBFNN Algorithm

With the global shift towards renewable energy, the reliability and efficiency of photovoltaic (PV) systems have become paramount. A crucial aspect of this is the timely detection and accurate classification of faults within the system. In fact, accurate fault detection and classification in the diagnostic systems can prevent severe damages, enhance operational efficiency, and prolong the lifespan of the installations. This paper introduces a novel data normalization technique tailored for enhancing the performance of meta-heuristic algorithms (namely RBFNN) applied to single-phase inverter current signals for fault detection in PV systems. While conventional normalization technics have shown their limitations in capturing the nuances of PV system faults, our proposed strategy demonstrates a more effective approach in preserving fault-specific features in the data. The proposed method is evaluated using multiple datasets encompassing a variety of fault scenarios. Empirical results show a significant improvement in both fault detection rates and classification accuracy. This study not only presents a breakthrough in PV system fault diagnosis but also sheds light on the broader potential of specialized normalization techniques in all signal-processing field, such as biomedical signal processing, industrial process control, or financial time series analysis, and other domains. The supremacy of the proposed diagnostic in reducing false alarms and providing more clear-cut classifications is highlighted by several simulations under Matlab-Simulink.

Characterization of controlled low-strength materials from waste expansive soils

Expansive soil from civil excavation projects is often considered waste material due to its propensity to swell. This study pioneers a novel approach to sustainable infrastructure by exploring the viability of repurposing expansive soils in the production of controlled low-strength materials (CLSM), incorporating sand and cement into the mix. Laboratory tests were conducted on CLSMs with varying mix proportions to assess their fresh (flowability, bleeding rate, and setting time) and hardened (swelling, unconfined compressive strength, and dry-wet durability) properties. The investigation focuses on three critical parameters: sand-to-soil ratio (S), cement-to-aggregate ratio (C), and water-to-solid ratio (W). Experimental results indicate the problematic swelling behavior of CLSM is mitigated when C surpasses 18%, at an S value of 10%. Adjusting either W or S enhances flowability but also elevates the bleeding rate. An increase in C has a marginal effect on flowability and bleeding rate, but markedly accelerates the setting time. Flowability follows a negative exponential relationship with time. Furthermore, increasing C or decreasing W markedly enhances both residual strength after dry-wet cycles and compressive strength. When S is below 10%, both compressive and residual strengths show a positive correlation with S. Conversely, when S exceeds 10%, a negative correlation is observed with compressive strength. A predictive model for the compressive strength and flowability of CLSM made from expansive soil has been developed, utilizing data normalization techniques. This model assists in determining the optimal mix proportions appropriate for applications in narrow backfills.

Deep learning based Glaucoma Network Classification (GNC) using retinal images

AbstractThe proposed deep learning framework for glaucoma classification addresses critical challenges of limited data and computational costs. Employing data augmentation and normalization techniques, the three‐stage model, utilizing InceptionV3 and ResNet50, achieves high training (99.3% ‐ 99.8%) and testing accuracy (91.6% ‐ 92.12%) on a dataset comprising 16,328 images from fused public datasets. This outperforms existing automated models. The approach leverages transfer learning and convolutional neural networks, showcasing its potential for accurate and timely glaucoma diagnosis. However, ongoing validation on diverse datasets and ethical considerations regarding fairness and transparency in medical applications remain essential. The model's reliability suggests its promising role in aiding early glaucoma detection, potentially averting irreversible vision impairment.

Variability in donor leukocyte counts confound the use of common RNA sequencing data normalization strategies in transcriptomic biomarker studies performed with whole blood

Gene expression data generated from whole blood via next generation sequencing is frequently used in studies aimed at identifying mRNA-based biomarker panels with utility for diagnosis or monitoring of human disease. These investigations often employ data normalization techniques more typically used for analysis of data originating from solid tissues, which largely operate under the general assumption that specimens have similar transcriptome composition. However, this assumption may be violated when working with data generated from whole blood, which is more cellularly dynamic, leading to potential confounds. In this study, we used next generation sequencing in combination with flow cytometry to assess the influence of donor leukocyte counts on the transcriptional composition of whole blood specimens sampled from a cohort of 138 human subjects, and then subsequently examined the effect of four frequently used data normalization approaches on our ability to detect inter-specimen biological variance, using the flow cytometry data to benchmark each specimens true cellular and molecular identity. Whole blood samples originating from donors with differing leukocyte counts exhibited dramatic differences in both genome-wide distributions of transcript abundance and gene-level expression patterns. Consequently, three of the normalization strategies we tested, including median ratio (MRN), trimmed mean of m-values (TMM), and quantile normalization, noticeably masked the true biological structure of the data and impaired our ability to detect true interspecimen differences in mRNA levels. The only strategy that improved our ability to detect true biological variance was simple scaling of read counts by sequencing depth, which unlike the aforementioned approaches, makes no assumptions regarding transcriptome composition.

Analisis Tingkat Akurasi Variasi Algoritma Min-Max Backpropagation sebagai Pre-Processing Data Time Series

Forecasting data does not have to be static, there are also data with high fluctuations with up and down trends. Therefore, data normalization techniques are very important before training and testing data. This paper aims to test eight types of Min-Max backpropagation algorithms with several types of data, namely static data, seational data, monotonically fluctuating data up and down. A backpropagation network architecture with three hidden layers is used to test these data. The test results show that the 6th Min-Max algorithm has a high level of accuracy. Furthermore, the results of the 6th Min-Max modification found that changes in the multiplier variable can reduce the MSE value in the training process to a maximum value of 35.25% and in the testing process to 27.39%. The results of this study can be used as a reference in the future in performing the data nornalization process before the forecasting process is carried out.

Expanding the Data Normalization Strategy to the MACONT Method for Multi-Criteria Decision Making

The Mixed Aggregation by Comprehensive Normalization Technique (MACONT) is a well-known Multi-Criteria Decision-Making (MCDM) method with significant benefits compared to traditional approaches. The key difference that distinguishes this method from most others is the use of data normalization techniques and aggregation approaches. MACONT uses three different data normalization techniques simultaneously along with two aggregation approaches throughout its evaluation process. This reduces the derivation of evaluation values and enhances the reliability of the final decision results, making the process more precise and convergent. However, the original MACONT emphasizes the integration of multiple normalization techniques of the same type of criteria that might perform badly in some circumstances. This paper proposes combination strategies of six normalization techniques to be coupled with the MACONT to help the normalized data synthetically reflect the original information and solve different types of data, criteria, and alternatives. The proposed approach was applied in four case studies. In all studies, the ranking results were compared with the other MCDM methods, producing the same best alternatives and overcoming the cases when the original MACONT did not work properly.

Enhancing deep learning techniques for the diagnosis of the novel coronavirus (COVID-19) using X-ray images

Deep learning techniques combined with radiological imaging provide precision in the diagnosis of diseases that can be utilised for the classification and diagnosis of several diseases in the medical sector. Several research studies have focused on binary classification of COVID-19, and there is limited research focusing on multiclass classification of COVID-19. The purpose of this study is to develop a model that can enhance the multiclass classification of COVID-19 using raw chest X-ray images. The study involved using convolutional neural networks as the classifier. Five pre-trained deep learning models including VGG16, MobileNet, EfficientNetB0, NasNetMobile and ResNet50V2 are used to distinguish between COVID-19 infection and other lung diseases. Data Augmentation and Normalization techniques have been used to improve the models’ performance and avoid training problems. The study findings revealed that it is possible to distinguish between COVID-19 infection and other lung diseases using pre-trained deep learning models. The proposed technique successfully classifies five classes (normal, COVID-19, lung opacity, viral pneumonia, and bacterial pneumonia). It is found that NasNetMobile model outperformed the rest of the models and achieved the highest results. It achieved an overall accuracy, sensitivity, specificity and precision of 91%, 91%, 97.7% and 91%, respectively. The VGG16 model produced better results in detecting COVID-19 infection, resulting in an accuracy of 95.8%. The suggested technique is more accurate in comparison to the other newly developed techniques presented in the literature. This provides healthcare staff with a powerful tool for the diagnosis of COVID-19 based on deep learning.

A New Dual Normalization for Enhancing the Bitcoin Pricing Capability of an Optimized Low Complexity Neural Net with TOPSIS Evaluation

Bitcoin, the largest cryptocurrency, is extremely volatile and hence needs a better model for its pricing. In the literature, many researchers have studied the effect of data normalization on regression analysis for stock price prediction. How has data normalization affected Bitcoin price prediction? To answer this question, this study analyzed the prediction accuracy of a Legendre polynomial-based neural network optimized by the mutated climb monkey algorithm using nine existing data normalization techniques. A new dual normalization technique was proposed to improve the efficiency of this model. The 10 normalization techniques were evaluated using 15 error metrics using a multi-criteria decision-making (MCDM) approach called technique for order performance by similarity to ideal solution (TOPSIS). The effect of the top three normalization techniques along with the min–max normalization was further studied for Chebyshev, Laguerre, and trigonometric polynomial-based neural networks in three different datasets. The prediction accuracy of the 16 models (each of the four polynomial-based neural networks with four different normalization techniques) was calculated using 15 error metrics. A 16 × 15 TOPSIS analysis was conducted to rank the models. The convergence plot and the ranking of the models indicated that data normalization plays a significant role in the prediction capability of a Bitcoin price predictor. This paper can significantly contribute to the research with a new normalization technique for utilization in varied fields of research. It can also contribute to international finance as a decision-making tool for different investors as well as stakeholders for Bitcoin pricing.

A Framework for Comparison and Assessment of Synthetic RNA-Seq Data.

The ever-growing number of methods for the generation of synthetic bulk and single cell RNA-seq data have multiple and diverse applications. They are often aimed at benchmarking bioinformatics algorithms for purposes such as sample classification, differential expression analysis, correlation and network studies and the optimization of data integration and normalization techniques. Here, we propose a general framework to compare synthetically generated RNA-seq data and select a data-generating tool that is suitable for a set of specific study goals. As there are multiple methods for synthetic RNA-seq data generation, researchers can use the proposed framework to make an informed choice of an RNA-seq data simulation algorithm and software that are best suited for their specific scientific questions of interest.

Investigations on Impact of Feature Normalization Techniques for Prediction of Hydro-Climatology Data Using Neural Network Backpropagation with Three Layer Hidden

Data normalization techniques are a very important initial stage to be carried out in order to obtain a good predictive data approach. Many researchers get different prediction and error results in each use of these data normalization techniques. Thereby, in this article discusses the accuracy rate of the seven normalization techniques at the preprocessing stage in the Neural Network Backpropagation (NNBP) architecture including decimal scaling, Z-score, min-max (there are 6 types), sigmoid, tanh estimators, mean-MAD, and median-MAD. We used two data patterns: seasonal data (rainfall) and stationary data (air humidity) that taken over the past 10 years (at 10-day intervals). We use accuracy rate parameters including number of epochs, MAE, and MSE when conducting training, testing, and predictions. The results showed that the Z-score technique was very good for the normalization of rainfall data with epochs of 10, MAE of 0.051, and MSE of 0.004. In the case of air humidity data, mean-MAD and Z-score techniques can be recommended with the number of mean-MAD technique epochs of 8, MAE of 0.013, MSE of 0.0004, while the number of epochs of Z-score techniques of 7, MAE of 0.018, and MSE of 0.0006. Thus, we conclude that when other researchers predict seasonal data or stationary data can use the Z-score technique for data normalization.

Categorization of emotions in dog behavior based on the deep neural network

AbstractThe aim of this article is to present a neural system based on stock architecture for recognizing emotional behavior in dogs. Our considerations are inspired by the original work of Franzoni et al. on recognizing dog emotions. An appropriate set of photographic data has been compiled taking into account five classes of emotional behavior in dogs of one breed, including joy, anger, licking, yawning, and sleeping. Focusing on a particular breed makes it easier to experiment and recognize the emotional behavior of dogs. To broaden our conclusions, in our research study we compare our system with other systems of different architectures. In addition, we also use modern transfer learning with augmentation and data normalization techniques. The results show that VGG16 and VGG19 are the most suitable backbone networks. Therefore, a certain deep neural network, named mVGG16, based on the suboptimal VGG16 has been created, trained and fine‐tuned with transfer (without augmentation and normalization). The developed system is then tested against an internal test dataset. In addition, to show the robustness of the system, a set of external data outside the breed is also taken into account. Being able to detect unsafe dog behavior and rely on a generalization for other breeds is worth popularizing. Equally important are the possible applications of the system to monitor the behavior of pets in the absence of their owners.