Multinomial Logistic Research Articles

Text Analytics on YouTube Comments for Food Products

YouTube is a popular social media platform in the contemporary digital landscape. The primary focus of this study is to explore the underlying sentiment in user comments about food-related videos on YouTube, specifically within two pivotal food categories: plant-based and hedonic product. We labeled comments using sentiment lexicons such as TextBlob, VADER, and Google’s Sentiment Analysis (GSA) engine. Comment sentiment was classified using advanced Machine-Learning (ML) algorithms, namely Support Vector Machines (SVM), Multinomial Naive Bayes, Random Forest, Logistic Regression, and XGBoost. The evaluation of these models encompassed key macro average metrics, including accuracy, precision, recall, and F1 score. The results from GSA showed a high accuracy level, with SVM achieving 93% accuracy in the plant-based dataset and 96% in the hedonic dataset. In addition to sentiment analysis, we delved into user interactions within the two datasets, measuring crucial metrics, such as views, likes, comments, and engagement rate. The findings illuminate significantly higher levels of views, likes, and comments in the hedonic food dataset, but the plant-based dataset maintains a superior overall engagement rate.

Bayesian optimized multimodal deep hybrid learning approach for tomato leaf disease classification

Manual identification of tomato leaf diseases is a time-consuming and laborious process that may lead to inaccurate results without professional assistance. Therefore, an automated, early, and precise leaf disease recognition system is essential for farmers to ensure the quality and quantity of tomato production by providing timely interventions to mitigate disease spread. In this study, we have proposed seven robust Bayesian optimized deep hybrid learning models leveraging the synergy between deep learning and machine learning for the automated classification of ten types of tomato leaves (nine diseased and one healthy). We customized the popular Convolutional Neural Network (CNN) algorithm for automatic feature extraction due to its ability to capture spatial hierarchies of features directly from raw data and classical machine learning techniques [Random Forest (RF), XGBoost, GaussianNB (GNB), Support Vector Machines (SVM), Multinomial Logistic Regression (MLR), K-Nearest Neighbor (KNN)], and stacking for classifications. Additionally, the study incorported a Boruta feature filtering layer to capture the statistically significant features. The standard, research-oriented PlantVillage dataset was used for the performance testing, which facilitates benchmarking against prior research and enables meaningful comparisons of classification performance across different approaches. We utilized a variety of statistical classification metrics to demonstrate the robustness of our models. Using the CNN-Stacking model, this study achieved the highest classification performance among the seven hybrid models. On an unseen dataset, this model achieved average precision, recall, f1-score, mcc, and accuracy values of 98.527%, 98.533%, 98.527%, 98.525%, and 98.268%, respectively. Our study requires only 0.174 s of testing time to correctly identify noisy, blurry, and transformed images. This indicates our approach's time efficiency and generalizability in images captured under challenging lighting conditions and with complex backgrounds. Based on the comparative analysis, our approach is superior and computationally inexpensive compared to the existing studies. This work will aid in developing a smartphone app to offer farmers a real-time disease diagnosis tool and management strategies.

Emotion Classification System for ASD Group by Using Wireless EEG Monitoring Device

This paper delves into a study employing dry electroencephalograms (EEG) as input features to discern emotions in individuals with autism spectrum disorders (ASD). While EEG is a prevalent tool in emotion classification studies for typically developing individuals, less attention has been directed towards its application in the ASD population. In this study, ten participants diagnosed with ASD wore wireless dry EEG sensors to capture their EEG signals. These signals encompassed alpha, beta, delta, theta, and gamma waves, which were subsequently subjected to feature extraction techniques such as the t-test, principal component analysis (PCA), ReliefF, and Chi-Square. Classification of positive, neutral, and negative emotions was performed using various algorithms, including K-nearest neighbor (KNN), Multinomial Logistic Regression (MLR), Naive Bayes (NB), Random Tree (RT), Random Forest (RF), and Support Vector Machine (SVM). Ultimately, employing SVM with a t-test enhanced the accuracy of emotion classification for the ASD group from 66.4% to 74.1%.

Making the Case: Exploring the Role of Case Management in Relocation and Return Decisions in Choice Neighborhoods Initiative

Leveraging novel case management data, we present the first comprehensive investigation into the role of case management services in housing relocation and return decisions within the framework of the Choice Neighborhoods Initiative (CNI), the current place-based public housing revitalization program. Our study employs multinomial logistic (MNL) regression models to demonstrate that a higher level of involvement in case management services is correlated with an increased probability of moving to a higher-income neighborhood during the redevelopment process, as well as a greater likelihood of returning to the revitalized neighborhood afterward. By achieving these outcomes, case management services play a crucial role in enhancing the chances for original CNI residents to reap the benefits of neighborhood redevelopment—a matter of enduring concern among social scientists. These findings are contextualized with both sociodemographic and neighborhood characteristics associated with relocation and return decisions.

Phototrophs as the central components of the plastisphere microbiome in coastal environments

Upon entering the marine environment, plastics are colonized by a plethora of microorganisms to form a plastisphere, influencing the fate and transport of the plastic debris and the health of marine ecosystems. The assembly of marine plastisphere is generally believed to be dominated by stochastic processes. However, it remains elusive whether microbial interaction in the assembly of plastisphere microbial communities is conserved or not. We analyzed the plastisphere microbiomes of 137 plastic debris samples from intertidal zones at different geographical locations and habitats (seagrass, coral, mangrove, beach, and open ocean) and compared them with the surrounding sediment and seawater microbiomes. Microbial community structures of the plastisphere from different locations were more similar to each other but differed substantially from the surrounding sediment and water microbiomes, implying a common mechanism of plastisphere assembly. We used different machine learning algorithms (Multinomial Logistic Regression, Support Vector Machine, Decision Trees, Random Forest, and Artificial Neural Networks) to classify plastic debris samples with high sensitivity based on the microbiome composition. Eukaryotic and prokaryotic phototrophic organisms such as green algae, diatoms, and cyanobacteria, were found to be enriched on the plastic surfaces. Network analysis revealed the central role of the phototrophic organisms in the formation and sustenance of the plastispheres. We found that phototrophs served as core members interacting strongly with heterotrophic organisms in marine plastisphere, irrespective of the sampling location, habitats, and polymer types. This would explain the stochastic assembly of the plastisphere along with conserved properties driven by the phototrophs in the surrounding environment. Our results highlight the importance of phototrophic organisms in shaping the marine plastisphere microbial communities.

AGENT-BASED MODELING OF UP DILIMAN INTRACAMPUS PEDESTRIAN MOBILITY USING NETLOGO AND GIS

Abstract. In the Philippines, campus mobility studies remain underexplored. Since small-scale models help in policy making that may also be applied in a large spatiotemporal context, intracampus mobility modeling and simulation offer support for future mobility research. In this study, we designed a NetLogo model to apply ABM and GIS in understanding intracampus student pedestrian mobility. We created a deterministic model using discrete student schedule and a probabilistic model using the multinomial logistic (MNL) regression model derived from the student demographics data to analyze student movement. To provide a realistic representation of student pedestrians and campus environment, GIS spatiotemporal data was proven crucial to the pedestrian mobility models. The generated pedestrian count heatmaps show a significant increase in student count from online learning switching to face–to–face instruction. The overall campus building occupancy served as the key factor influencing the changes in agent behaviors such as walking speed and student tardiness. Moreover, the probabilistic model showed erratic movements of students. The model evaluation depends on the heavily imbalanced datasets and its multiclass nature with relatively higher model performance (F1 score > 0.8) is observed during morning, noon, and end schedule times, whereas suboptimal performance (F1 score < 0.6) where the dataset has a higher number of classes. The simulations demonstrate that ABM is a useful tool for examining pedestrian and transport patterns and can be enhanced further to allow multimodal and multiagent systems.

An Empirical Analysis of Language Detection in Dravidian Languages

Objectives: Language detection is the process of identifying a language associated with a text. The proposed system aims to detect the Dravidian language that is associated with the given text using different machine learning and deep learning algorithms. The paper presents an empirical analysis of the results obtained using the different models. It also aims to evaluate the performance of a language agnostic model for the purpose of language detection. Method: An empirical analysis of Dravidian language identification in social media text using machine learning and deep learning approaches with k-fold cross validation has been implemented. The identification of Dravidian languages, including Tamil, Malayalam, Tamil Code Mix, and Malayalam Code Mix, is performed using both machine learning (ML) and deep learning algorithms. The machine learning algorithms used for language detection are Naive Bayes (NB), Multinomial Logistic Regression (MLR), Support Vector Machine (SVM), and Random Forest (RF). The supervised Deep Learning (DL) models used include BERT, mBERT and language agnostic models. Findings: The language agnostic model outperform all other models considering the task of language detection in Dravidian languages. The results of both the ML and DL models are analyzed empirically with performance measures like accuracy, precision, recall, and f1-score. The accuracy associated with different machine learning algorithms varies from 85% to 89%. It is evident from the experimental result that the deep learning model outperformed with an accuracy of 98%. Novelty: The proposed system emphasizes on the use of the language agnostic model to implement the process of detecting Dravidian languages associated with the given text which provides a promising result of 98% accuracy which is higher than the existing methodologies. Keywords: Language, Machine learning, Deep learning, Transformer model, Encoder, Decoder

O114: Enhancing palliative oesophageal cancer treatment pathway prediction and prognostication through machine learning models

Abstract Introduction Non-curative treatment plans comprise the majority of Oesophageal Cancer (OC) decision-making by Multidisciplinary Teams (MDTs), operating under significant caseload pressures. Machine Learning (ML) can semi-automate, streamline, and standardise these decisions to predict treatments and prognosticate for new patients. We present ML models which predict treatment decisions and prognostication in palliative OC patients. Methods Using clinicopathological data from 437 palliative OC cases treated at a single tertiary centre over 12 years, we trained several ML algorithms (Multinomial Logistic Regression [MLR], Random Forests [RF], Extreme Gradient Boost [XGB], Decision Tree [DT], and Random Survival Forests [RSF]) to predict treatment pathways (best supportive care, chemotherapy, radiotherapy, palliative stent, or stent plus oncological adjunct) and survival prognoses. Model performance was evaluated using Area Under the Curve (AUC) for classifier models and C-index (1-concordance) along with calibration plots for the survival model. Additionally, the models were integrated into a web application for clinician-friendly usability. Results Mean AUCs for the classifier models were: MLR 0.801±0.090, RF 0.806±0.078, XGB 0.817±0.079 and DT 0.762±0.108. Mean C-Index for the RSF survival model was 0.330±0.018 while calibration curves showed good calibration within the first 6-12months (median survival for the cohort was 6.31 months (range 0.1-105.8 months)). Conclusion This study is the first use of ML to predict palliative treatment plans and offer prognostication for OC patients, seamlessly integrated into a user-friendly interface for real-time treatment pathway prediction. This offers significant potential to streamline MDT caseload and provide data-driven decision-support for clinicians counselling these patients.

Daily rhythm of urban space usage: insights from the nexus of urban functions and human mobility

As urban density increases, it becomes increasingly common for multiple functions to coexist within the same space, intensifying the complexity of human activity dynamics. However, traditional urban zoning, which relies on the spatial distribution of urban functions and human activities, focuses on the spatial heterogeneity of urban space and fails to capture the temporal dynamics of urban space usage. This paper aims to investigate the daily rhythm of urban space usage and illustrate how the distribution and combination of urban functions affect the daily usage rhythm. Taking Beijing in China as a case, we first identified the daily rhythm of urban space usage with the k-means algorithm and zoned urban space accordingly. Subsequently, multinomial logistic (MNL) models were employed to elucidate how the distribution and combination of urban functions influenced these daily usage patterns. Furthermore, a validation study in typical zones was conducted. The results revealed the existence of a distinct daily rhythm in urban space usage, resulting in the classification of urban space into seven distinct zones: high equilibrium, low equilibrium, diurnal, nocturnal, morning, evening, and noon-type zones. Also, we found that this daily usage rhythm is closely intertwined with the distribution and coexistence of urban functions. Our findings could provide valuable insights for the enhancement of various intricate aspects within urban decision-making processes, including urban planning, transportation management, and more, at a fine-grained scale.

Breast Cancer Detection using Image Processing and Machine Learning: A Comprehensive Review and Improved Segmentation Approach

Breast cancer stands as one of the most prevalent health concerns for women. Early detection of breast cancer can significantly improve the chances of survival. In developed countries, more than 19.9% of women will die per year due to breast cancer. Regular breast cancer screening is an important way to detect cancer early. Image processing techniques are highly used for different types of cancer detection applications with medical screening. Segmentation of the breast tumor region is a critical step in image processing related to this manner. Lots of research work can be found on developing ways for detecting breast cancers. However still, there is a need for a standard and robust cancer region segmentation method. Right cancer region segmentation is significant for better feature extraction and better classification. This study presents a comprehensive literature review about technologies used with image enhancement and tumor segmentation. Further, the study proposes a robust approach to image enhancement and cancer region segmentation for breast cancer detection using image processing techniques and machine learning. In this work, mammograms are enhanced using Contrast Limited Adaptive Histogram Equalization and denoised using the Median blurring filter. This study enables an effective image segmentation approach with two stages: removing the background using thresholding, tumor region segmentation using a combination of thresholding, and Canny edge detection. Segmented tumor region’s features are extracted using the Gabor filter. Here the accuracy of the approach is compared with three main machine learning classifiers: Decision Tree, Random Forest, Multinomial Logistic Regression and mammograms are classified into three classes (malignant, benign and normal). Finally, an ensemble approach is proposed using the hard voting mechanism to improve the accuracy. With the dataset of mini-MIAS this proposed approach achieved 78.89% accuracy. Results demonstrated that the proposed breast cancer detection approach improves the performance of segmentation breast tumor regions.

Enhancing the accuracy of digital soil mapping using the surface and subsurface soil characteristics as continuous diagnostic layers.

Digital soil mapping relies on relating soils to a particular set of covariates, which capture inherent soil spatial variation. In digital mapping of soil classes, the most commonly used covariates are topographic attributes, RS attributes, and maps, including geology, geomorphology, and land use; in contrast, the subsurface soil characteristics are usually ignored. Therefore, we investigate the possibility of using soil diagnostic characteristics as covariates in a mountainous landscape as the main aim of this study. Conventional covariates (CC) and a combination of soil subsurface covariates with conventional covariates (SCC) were used as covariates, and random forest (RF), Multinomial Logistic Regression (LR), and C5.0 Decision Trees (C5) were used as different machine learning algorithms in digital mapping of soil family classes. Based on the results, the RF model with the SCC dataset had the best performance (KC = 0.85, OA = 90). In all three models, adding soil covariates to the sets of covariates increased the model performance. Soil covariates, slope, and aspect were selected as the principal auxiliary variables in describing the distribution of soil family classes.

Race/ethnic disparities in mis‐identification of dementia in Medicare claims

AbstractBackgroundStudies have shown that mis‐identification of dementia in Medicare claims is quite common. We extend the literature by examining potential race/ethnic disparities in mis‐identification of dementia in Medicare claims in a diverse cohort of older adults who underwent careful clinical assessment.MethodParticipants were enrolled the Washington Heights‐Inwood Columbia Aging Project (WHICAP), a multiethnic, population‐based, prospective study of cognitive aging in which dementia status is assessed using a rigorous clinical protocol. The current study included 1,178 participants clinically diagnosed with dementia and 3,048 never diagnosed with dementia. ICD‐9‐CM diagnosis codes in all available Medicare claims (1999‐2019) were compared to clinical dementia diagnosis, and categorized into 3 mutually exclusive groups: (1) congruent identification, (2) over‐identification (no clinical dementia, claims‐identified dementia), and (3) under‐identification (clinical dementia, no claims‐identified dementia) during the study period. Race (White, African American/Black, Other) and ethnicity (Hispanic/Latinx, non‐Hispanic/Latinx) were self‐reported. Multinomial logistic regression model was used to examine the relationship between race/ethnicity and congruency of dementia identification after controlling for clinical (cognition, function, comorbidities) and demographic characteristics (age, sex, education), and inpatient and outpatient utilization. Estimated average marginal effects are reported.ResultThe study included 1,520 White, 1,333 African American/Black, and 1,373 participants of other races. 1,985 participants self‐identified as Hispanic, 2,241 non‐Hispanic. Among participants clinically diagnosed with dementia, the proportion who were accurately identified with dementia in Medicare claims were 83.2%, 77.8%, and 73.2% in White, African American/Black, and other races, respectively; 75.9% and 79.7% in Hispanics and non‐Hispanics, respectively. Among participants clinically diagnosed without dementia, the proportion of participants who were accurately identified without dementia in Medicare claims were: 86.1%, 87.3%, and 82.3% in White, African American/Black, and other races, respectively; 82.4% and 87.5% in Hispanics and non‐Hispanics, respectively. After controlling for participant characteristics, multinomial logistics regression results show the probability of over‐identification with dementia was 2.2% higher for African American/Black participants than White (p = 0.05) and 2.7% higher for Hispanic participants than non‐Hispanics (p = 0.03). Differences in under‐identification by race/ethnicity were no longer statistically significant.ConclusionAfrican American/Black and Hispanic participants were more likely to be over‐identified with dementia in Medicare claims.

An effective autism spectrum disorder screening method using machine learning classification techniques

SummaryNowadays, autism spectrum disorder (ASD) is one of the fastest‐growing developmental disorders globally. Screening test consumes more time and expensive to detect the autism signs. Due to advances in artificial intelligence and machine learning (ML), Autism can be predicted at the initial stage. Numerous researches have been conducted using different methods, but none of these researches presented any anticipated results about the capability to predict autism traits under different age groups. Therefore, this paper proposes an effectual prediction method based upon ML strategy to develop a mobile application for predicting ASD of any age people. The autism prediction model is developed by five ML classifiers, such as Gaussian Naive Bayes, Decision Tree Classifier, K‐Nearest Neighbors (KNN), Multinomial Logistic Regression (MLR), Support Vector Machine (SVM) and also a mobile application is developed using proposed prediction method. The proposed method is analyzed with IAPQ records gathered from certain areas in Erode district, Tamil Nadu, India. From the analysis, the SVM classifier achieves maximum sensitivity of 23.14%, 6.04%, 5.89%, 11.03% than other classifiers, like Gaussian Naive Bayes, Decision Tree Classifier, KNN, and MLR.

기업의 환경 경영 태도에 대한 유형화 및 결정요인 분석

Purpose - The main objective of this study is to cluster companies based on environmental management attitudes using various indicators, and analyze differences in activities among the clusters to gain insights into environmental management performance.
 Design/Methodology/Approach - The study encompasses panel data from 12 countries, 22 industry sectors, and 3,402 companies from 2013 to 2022. This study uses both machine learning methodology and conventional econometric methodology. The primary methodology involves using an unsupervised learning technique, K-means clustering, to categorize environmental management attitudes. Subsequently, Kernel Density estimation and Multinomial Logistic Regression were employed to conduct comparative analyses of environmental performance indicators within each cluster and identify the determinants shaping environmental management attitudes.
 Findings - The research revealed the existence of five distinct clusters of companies with varying environmental management attitudes. Through Multinomial Logistics Regression, it identified that variables such as greenhouse gas emissions, energy consumption, total assets, return on assets, and other significantly influence environmental management attitudes.
 Research Implications - By uncovering common characteristics and determinants within major countries and industries, this study offers valuable insights in promoting domestic environmental management in the context of rapidly changing international trade and investment environments. The findings provide policy implications and suggestions for fostering proactive environmental management practices among domestic companies.

Fuzzy based inference system with ensemble classification based intrusion detection system in MANET

Mobile ad hoc networks (MANET) have become one of the hottest research areas in computer science, including in military and civilian applications. Such applications have formed a variety of security threats, particularly in unattended environments. An Intrusion detection system (IDS) must be in place to ensure the security and reliability of MANET services. These IDS must be compatible with the characteristics of MANETs and competent in discovering the biggest number of potential security threats. In this work, a specialized dataset for MANET is implemented to identify and classify three types of Denial of Service (DoS) attacks: Blackhole, Grayhole and Flooding Attack. This work utilized a cluster-based routing algorithm (CBRA) in MANET.A simulation to gather data, then processed to create eight attributes for creating a specialized dataset using Java. Mamdani fuzzy-based inference system (MFIS) is used to create dataset labelling. Furthermore, an ensemble classification technique is trained on the dataset to discover and classify three types of attacks. The proposed ensemble classification has six base classifiers, namely, C4.5, Fuzzy Unordered Rule Induction Algorithm (FURIA), Multilayer Perceptron (MLP), Multinomial Logistic Regression (MLR), Naive Bayes (NB) and Support Vector Machine (SVM). The experimental results demonstrate that MFIS with the Ensemble classification technique enables an enhancing security in MANET’s by modeling the interactions among a malicious node with number of legitimate nodes. This is suitable for future works on multilayer security problem in MANET.

Analysis of human errors in maritime accidents: A Bayesian spatial multinomial logistic model

Considering the unobserved spatial heterogeneity, this study aims to build a Bayesian spatial multinomial logistic (BSMNL) model by utilizing the geographic information from historical maritime accidents. The proposed BSMNL model can be applied to investigate the determinants of human errors involved in maritime accidents. Compared to the traditional multinomial logistic (MNL) model, the proposed BSMNL model produces a more accurate estimate of the effects of environmental and accident factors on the occurrence likelihood of human errors in maritime accidents. Results show that accidents involving cargo and container ships; tankers carrying liquefied natural gas (LNG), liquefied petroleum gas (LPG), or oil; and fishing vessels are more likely to be associated with human errors. Further, one important finding is that the involvement of fishing vessels significantly increases the occurrence probability of both negligence errors and judgment or operational errors. In addition, the occurrence likelihood of human errors is generally higher in springtime, conditions of poor visibility, the absence of strong winds or waves, and the moored or docked status.

Satisfaction of Istanbul Citizens with Urban Public Transportation

Transportation is one of the most challenging urban subsystems to transform in an environmentally friendly and futuristic way. Many city dwellers use a variety of modes of transportation. An efficient and sustainable urban transportation system must include many modes of transportation for a single trip. Intermodal combinations are essential for urban transportation efficiency. Public transportation and commuting are essential elements of multimodal travel. In urban areas, a mix of bicycles, vehicles, and public transportation is prevalent, while in rural areas, car, and public transportation are more prevalent. By examining the characteristics that lead customers to prefer water transportation over Metrobus and Marmaray, we hope to gain a better understanding of how the Asian and European sides of Istanbul are traversed. The number of participants in the "Maritime Transportation Satisfaction Survey" was 2,343. During this period, a model was built using the survey item "frequency of use" (dependent variable). Numerous survey examines and evaluation methodologies were utilized to determine the effectiveness of this strategy. The study examines the intermodal travel motivations and the evaluation of transportation options by multimodal users. For a successful urban transportation system, urban planning must take into account multimodal travel behavior and user expectations. There are initiatives to improve water transportation in Istanbul. Conventional maritime transportation is inadequate from start to finish. An integrated route optimization method is needed to increase the efficiency of maritime transportation. We believe that by strengthening maritime transportation links will increase water consumption. Before the coronavirus pandemic, 2,343 maritime carriers were evaluated on March 8, 2020. (Different surveys were conducted among the passengers of City Lines, Private Motors, Metrobus, and Marmaray to compare their choices and reasons.) SPSS will be used for data analysis. Multivariate Statistical Analysis relies on Multinomial Logistic Regression and Discriminant Analysis models, both of which use the K-fold and Leave-one-out criteria to decide which attributes are valid in the regression model and which are valid in the discriminant approach. The Hosmer-Lemeshow test criteria yielded a p-value greater than 0.05 for MLR characteristics.

Improved accuracy and less fault prediction errors via modified sequential minimal optimization algorithm.

The benefits and opportunities offered by cloud computing are among the fastest-growing technologies in the computer industry. Additionally, it addresses the difficulties and issues that make more users more likely to accept and use the technology. The proposed research comprised of machine learning (ML) algorithms is Naïve Bayes (NB), Library Support Vector Machine (LibSVM), Multinomial Logistic Regression (MLR), Sequential Minimal Optimization (SMO), K Nearest Neighbor (KNN), and Random Forest (RF) to compare the classifier gives better results in accuracy and less fault prediction. In this research, the secondary data results (CPU-Mem Mono) give the highest percentage of accuracy and less fault prediction on the NB classifier in terms of 80/20 (77.01%), 70/30 (76.05%), and 5 folds cross-validation (74.88%), and (CPU-Mem Multi) in terms of 80/20 (89.72%), 70/30 (90.28%), and 5 folds cross-validation (92.83%). Furthermore, on (HDD Mono) the SMO classifier gives the highest percentage of accuracy and less fault prediction fault in terms of 80/20 (87.72%), 70/30 (89.41%), and 5 folds cross-validation (88.38%), and (HDD-Multi) in terms of 80/20 (93.64%), 70/30 (90.91%), and 5 folds cross-validation (88.20%). Whereas, primary data results found RF classifier gives the highest percentage of accuracy and less fault prediction in terms of 80/20 (97.14%), 70/30 (96.19%), and 5 folds cross-validation (95.85%) in the primary data results, but the algorithm complexity (0.17 seconds) is not good. In terms of 80/20 (95.71%), 70/30 (95.71%), and 5 folds cross-validation (95.71%), SMO has the second highest accuracy and less fault prediction, but the algorithm complexity is good (0.3 seconds). The difference in accuracy and less fault prediction between RF and SMO is only (.13%), and the difference in time complexity is (14 seconds). We have decided that we will modify SMO. Finally, the Modified Sequential Minimal Optimization (MSMO) Algorithm method has been proposed to get the highest accuracy & less fault prediction errors in terms of 80/20 (96.42%), 70/30 (96.42%), & 5 fold cross validation (96.50%).

Mapping the EQ-5D-5L from the Spanish national health survey functional disability scale through Bayesian networks.

Preference-based measures are valuable tools for evaluating therapeutic interventions and for cost-effectiveness studies. Mapping procedures are useful when it is not possible to collect these kind of measures. The objective of this study was to evaluate which mapping method is the most appropriate to estimate the EQ-5D-5L index from the Spanish National Health Survey functional disability scale. The sample, formed by 5708 older adults (aged 65years or older), was drawn from the Spanish National Health Survey ("Encuesta Nacional de Salud en España," ENSE in Spanish 2011-2012). The predictions of EQ-5D-5L index were performed with response mapping using Bayesian network (BN), ordered logit (Ologit), and multinomial logistic (ML). The following direct methods were used: ordinary least squares (OLS) and Tobit regression. The intraclass correlation coefficient (ICC), absolute error (MAE), mean squared error (MSE), and root-mean squared error (RMSE) were calculated to compare all models. The predictions of response models were obtained through the expected value method. BN model showed the highest ICC (0.756, 95% confidence interval, CI 0.733-0.777) and lowest MAE (0.110, 95% CI 0.104-0.115). OLS was the model with worse accuracy results with lowest ICC (0.621, 95% CI 0.553-0.681) and highest MAE (0.159, 95%CI: 0.145-0.173). Indirect mapping methods (BN, Ologit, and ML) had a better accuracy than the direct methods. The response mapping approach provides a robust method to estimate EQ-5D-5L scores from the functional disability scale.

Artificial Intelligence Based Approach for Classification of Human Activities Using MEMS Sensors Data.

The integration of Micro Electronic Mechanical Systems (MEMS) sensor technology in smartphones has greatly improved the capability for Human Activity Recognition (HAR). By utilizing Machine Learning (ML) techniques and data from these sensors, various human motion activities can be classified. This study performed experiments and compiled a large dataset of nine daily activities, including Laying Down, Stationary, Walking, Brisk Walking, Running, Stairs-Up, Stairs-Down, Squatting, and Cycling. Several ML models, such as Decision Tree Classifier, Random Forest Classifier, K Neighbors Classifier, Multinomial Logistic Regression, Gaussian Naive Bayes, and Support Vector Machine, were trained on sensor data collected from accelerometer, gyroscope, and magnetometer embedded in smartphones and wearable devices. The highest test accuracy of 95% was achieved using the random forest algorithm. Additionally, a custom-built Bidirectional Long-Short-Term Memory (Bi-LSTM) model, a type of Recurrent Neural Network (RNN), was proposed and yielded an improved test accuracy of 98.1%. This approach differs from traditional algorithmic-based human activity detection used in current wearable technologies, resulting in improved accuracy.