Data Classification Research Articles

Performance of Minnesota Functionals on Vibrational Frequency

ABSTRACTMolecular geometry and harmonic frequency calculations are essential in thermochemical computations, with density functional theory (DFT) being widely employed for vibrational frequency predictions due to its efficiency and accuracy. In this study, we assessed the precision of 28 Minnesota based functionals with three different basis sets using the VIBFREQ1295 dataset. Scaling factors are necessary for predicting fundamental frequencies, global scaling factors were fitted by using F38/10 and VIBFREQ1295 datasets. The superior performing functionals were then fitted based on vibrational frequency ranges to obtain frequency‐range‐specific scaling factors. We observed consistent outlier across various model chemistries in vibrational frequency predictions, with alternative scaling factors showing minimal impact on reducing outlier occurrences. Besides, large basis sets are not indispensably required for fundamental frequency predictions. M06‐L, revM06‐L, SOGGA11‐X, PW6B95‐D3(BJ), CF22D, and M06‐2X consistently exhibit excellent performance across the three basis sets. When using frequency‐range‐specific scaling factors, the root mean squard errors (RMSEs) and median absolute errors (MedAEs) of almost all the selected functionals were reduced. PW6B95‐D3(BJ), CF22D, and MN12‐SX exhibited the lowest RMSEs. Comparisons were also done for different data classifications; the dataset was classified by the elements of the molecules, vibrational frequency intervals, and vibrational modes.

Classification of hand movements from EEG using a FusionNet based LSTM network

Abstract Objective.
Accurate classification of electroencephalogram (EEG) signals is crucial for advancing brain-computer interface (BCI) technology. However, current methods face significant challenges in classifying hand movement EEG signals, including effective spatial feature extraction, capturing temporal dependencies, and representing underlying signal dynamics.
Approach.
This paper introduces a novel multi-model fusion approach, FusionNet-LSTM, designed to address these issues. Specifically, it integrates Convolutional Neural Networks (CNN) for spatial feature extraction, Gated Recurrent Units (GRU) and Long Short-Term Memory (LSTM) networks for capturing temporal dependencies, and Autoregressive (AR) models for representing signal dynamics.
Main results.
Compared to single models and state-of-the-art methods, this fusion approach demonstrates substantial improvements in classification accuracy. Experimental results show that the proposed model achieves an accuracy of 87.1% in cross-subject data classification and 99.1% in within-subject data classification. Additionally, Gradient Boosting Trees were employed to evaluate the significance of various EEG features to the model.
Significance.
This study highlights the advantages of integrating multiple models and introduces a superior classification model, which is pivotal for the advancement of BCI systems.

Student experiences of cultural competence encounters during MPharm placements and foundation year training

Abstract Introduction Cultural competence is the ability of a healthcare professional to work effectively with clients from different backgrounds. With 18.3% of the UK population identifying with non-white1, pharmacists need to be culturally competent as they have a patient-facing role. Having a multicultural society would require culturally competent pharmacists to effectively deliver healthcare services to patients of different cultures. Exploring pharmacy students' experiences of CC encounters during their MPharm placements and foundation year training is crucial as it helps identify the challenges and barriers they may face when providing healthcare to diverse populations. Understanding these experiences can inform the development of effective training programs to enhance cultural competence among future pharmacists and highlight the impact of cultural factors on patient care and outcomes. Ultimately, this exploration contributes to the overall goal of improving healthcare delivery and promoting patient-centred, culturally sensitive pharmacy practice. Aim This study aimed to explore experiences of student regarding cultural competence encounters during placements and training. Methods A qualitative study was conducted between Oct – Dec 2023. All currently enrolled students in Parts 3, 4 and the foundation year were eligible to participate. Convenience sampling was used. Semi-structured interviews were conducted online using a pilot-tested script. Interviews were audio and video recorded and held online through a Microsoft Teams account, where an automatic electronic transcript was generated. Initial codes were generated from each transcript, to create themes and sub-themes. The researcher scrutinised the themes before defining and naming them. Ethical clearance was obtained. Results A total of 15 students (8 males and 7 females) participated in the study. Four participants were from year 3, five were from year 4, and six were from the foundation year. Six participants were from Asian backgrounds, four were Black, and three were White. All students had a placement in hospital, while 14 had a placement in community pharmacy in addition to hospital, and 8 had a placement in a GP surgery in addition to the hospital and community pharmacy. Key themes identified were 1) Impact of culture on patient health including language barriers and ethnic diversity, 2) Influence of personal culture on practice during placements and training such as using patient’s language to communicate, personal cultural awareness, and the influence of religious teachings, 3) Recommendations for improving cultural competence training in MPharm programme such as having more case studies. Conclusion This study provides a unique exploration into the experiences of pharmacy students and shows the importance of immersing in diverse cultural groups during placements and foundation training. There is a need to enhance pharmacy students’ training through curricular reforms that build on theoretical knowledge to instil confidence during placements and training. This approach will equip future pharmacists to navigate complex cultural dynamics, to meet the demands of an inclusive healthcare system. Ultimately this research extends beyond the current reforms to the MPharm curriculum, and advocates for an equitable and inclusive healthcare system to reduce health disparities. The predominance of participants from Asian backgrounds may limit the generalisability of the findings. Reference 1. Office for National Statistics. Measuring equality: A guide for the collection and classification of ethnic group, national identity and religion data in the UK. Office for National Statistics 2021 https://www.ons.gov.uk/methodology/classificationsandstandards/measuringequality/ethnicgroupnationalidentityandreligion. Accessed 20 Dec 2023.

Conv-attention ViT for classification of multi-label class imbalanced data of lung thoracic diseases

Conv-attention ViT for classification of multi-label class imbalanced data of lung thoracic diseases

Plastic Injection Molding Process Analysis: Data Integration and Modeling for Improved Production Efficiency

This paper presents a comprehensive analysis of the plastic injection molding process through the integration of data acquisition technologies and classification models. In collaboration with a company specializing in plastic injection, data were extracted directly from the machine during a specific period at the beginning of a shift change. These data were subjected to exploratory analysis to identify correlations between important variables, such as injection time, cycle time, and mold pressures. Additionally, classification models, including Random Forest and Logistic Regression, were constructed to predict and classify the process state based on these variables. The model results demonstrated high predictive performance, with 99.5% accuracy for Random Forest and 97% for Logistic Regression. These results provide a strong foundation for the early identification of potential problems and informed decision making to improve the efficiency of the plastic injection molding process. This study contributes to the advancement of the integration of intelligent technologies in industrial process optimization, aligned with the principles of Industry 4.0.

Investigating Remote Healthcare Accessibility with AI: Deep Learning and NLP-Based Knowledge Graph for Digitalized Diagnostics

Introduction: Recently, vast generational modern AI techniques have facilitated developments for accessing digital healthcare diagnosis with capabilities of detecting illnesses. Problem: There exists a lot of scepticism for e-health couple with high similarities on health symptoms which hinder text data analysis for remote diagnosis limiting remote services and affecting tech development. Objective: This research investigates and substantiates opportunities associated with computational leverage of text data analytics and cognitive extraction of knowledge insights to improve healthcare outcomes. Significance: The study presents an overview of public, an integrated deep learning (DL), and AI knowledge graph (KG) for healthcare accessibility of remote diagnostics with NLP assist. Method: This research applied both qualitative and quantitative analysis. Questionnaires were used to understand the computational analytics and cognitive extraction of AI knowledge graphs on healthcare data. Also, an AI model was built to detect, diagnose based on text data and streamline five (5) related disease symptoms for each given text input. Results: The result of the survey was tested with hypotheses of H1, H2, H3, H4, H5. Results show that deep learning models and knowledge graphs can effectively lead to a well-defined class of data classification. Our model also exhibits a tremendous level of acceptable prediction of health symptoms based on text data. The significant group was accepted as an identified health issue and the non-significant was identified as a non-health issue. Conclusion: The study concludes that a well-defined system based on a rigorous ethical healthcare standard can easily support determining a feasible remote diagnosis.

The application of template matching and novel unsupervised and supervised machine learning methodology to forensic hair analysis

ABSTRACT Hair pigmentation is a valuable feature in forensic hair analysis and hair comparisons. Microscopic pigmentation features from participants' hair were classified and documented. The discriminating power of template matching, unsupervised and supervised machine learning methods were compared to determine which method best distinguished between participants and accurately assigned hairto an individual, based on pigmentation features. Template matching analysis revealed a higher frequency of inter-person matches compared to intra-person matches, and the unsupervised model’s predicted labels did not align with true labels. These findings suggest the presence of an unknown dimensionality beyond the observable pigmentation features used in forensic hair classification, highlighting the crucial role of forensic expertise. In contrast, supervised machine learning demonstrated superior accuracy and greater interpretability due to its training on labelled data, making it more appropriate for forensic applications. This research underscores the continued importance of human expertise, particularly in the initial classification of training data for supervised machine learning. The potential applications of supervised machine learning in forensic science include training, competency testing and rapid intelligence as a novel and innovative tool while advancing the field towards more objective methodologies.

Generative adversarial network model to classify human induced pluripotent stem cell-cardiomyocytes based on maturation level

Our study develops a generative adversarial network (GAN)-based method that generates faithful synthetic image data of human cardiomyocytes at varying stages in their maturation process, as a tool to significantly enhance the classification accuracy of cells and ultimately assist the throughput of computational analysis of cellular structure and functions. Human induced pluripotent stem cell derived cardiomyocytes (hiPSC-CMs) were cultured on micropatterned collagen coated hydrogels of physiological stiffnesses to facilitate maturation and optical measurements were performed for their structural and functional analyses. Control groups were cultured on collagen coated glass well plates. These image recordings were used as the real data to train the GAN model. The results show the GAN approach is able to replicate true features from the real data, and inclusion of such synthetic data significantly improves the classification accuracy compared to usage of only real experimental data that is often limited in scale and diversity. The proposed model outperformed four conventional machine learning algorithms with respect to improved data generalization ability and data classification by incorporating synthetic data. This work demonstrates the importance of integrating synthetic data in situations where there are limited sample sizes and thus, effectively addresses the challenges imposed by data availability.

Analisis Potensi Kawasan Pengembangan Lahan Pertanian Tanaman Padi Sawah di Kabupaten Tanah Datar

This study aims to determine 1) the level of suitability of wet-rice land on food agricultural land in Tanah Datar Regency, 2) existing land cover in Tanah Datar Regency and 3) potential wet-rice land development areas in Tanah Datar Regency. The method used is a descriptive approach with quantitative research. Data was processed using fuzzy logic, supervised classification, and spatial data analysis. The results of this study show 1) Tanah Datar Regency has 3 levels of land suitability with an index value of 0-0.59 which is classified at the level of unsuitable to less suitable for rice paddy agricultural crops, with an area of 7,583.9 Ha with a percentage of 5.5%. The second category of land suitability with an index value of 0.6-0.79 is classified as moderately suitable to suitable, with an area of 98,955.7 Ha with a percentage of 71.8%. The third category of land suitability with an index value of 0.8-1.0 which is classified as moderately - highly suitable for wetland agricultural crops, with an area of 31,267.7 Ha with a percentage of 22.7% of the total area of the study site. 2) Analysis of existing land cover using Landsat 8 satellite images in 2023 in Tanah Datar District shows that the structure of land cover in 2023 is as follows: dense vegetation cover covering 93,385.5 Ha with a percentage of 67.9%, followed by agricultural land covering 35,630.6 Ha with a percentage of 25.8%, settlements covering 1,828.3 Ha with a percentage of 1.4%, open land covering 137.6 Ha with a percentage of 0.09%, and waters.

Earthquake Prediction and Alert System Using IoT Infrastructure and Cloud-Based Environmental Data Analysis

Earthquakes are one of the most life-threatening natural phenomena, and their prediction is of constant concern among scientists. The study proposes that abrupt weather parameter value fluctuations may influence the occurrence of shallow seismic events by focusing on developing an innovative concept that combines historical meteorological and seismic data collection to predict potential earthquakes. A machine learning (ML) model utilizing the ML.NET framework was designed and implemented. An analysis was undertaken to identify which modeling approach, value prediction, or data classification performs better in forecasting seismic events. The model was trained on a dataset of 8766 records corresponding to the period from 1 January 2001 to 5 October 2024. The achieved accuracy of the model was 95.65% for earthquake prediction based on weather conditions in the Vrancea region, Romania. The authors proposed a unique alerting algorithm and conducted a case study that evaluates multiple predictive models, varying parameters, and methods to identify the most effective model for seismic event prediction in specific meteorological conditions. The findings demonstrate the potential of combining Internet of Things (IoT)-based environmental monitoring with AI to improve earthquake prediction accuracy and preparedness. An IoT-based application was developed using C# with ASP.NET framework to enhance earthquake prediction and public warning capabilities, leveraging Azure cloud infrastructure. The authors also created a hardware prototype for real-time earthquake alerting, integrating the M5Stack platform with ESP32 and MPU-6050 sensors for validation. The testing phase and results describe the proposed methodology and various scenarios.

Rapid lithological mapping using multi-source remote sensing data fusion and automatic sample generation strategy

ABSTRACT The advancement of remote sensing technology aids geologists in obtaining lithological maps more quickly, comprehensively, and accurately. However, key challenges in lithological mapping include the limited spectral information from individual sensors and the difficulties in visually interpreting lithological samples. In this study, we integrated 241 scenes of optical data and 106 scenes of radar data on the Google Earth Engine (GEE) platform, proposing a rapid lithological identification framework that combines an automatic lithological sample data generation strategy with multi-source data. Using various machine learning algorithms, we evaluated the classification capabilities of heterogeneous predictive factors, feature optimization algorithms, and object-based algorithms. Results indicate that: (1) Combining optical and radar data improves prediction accuracy, with terrain data further enhancing mapping capabilities; (2) Terrain factors contribute most to classification, but SWIR and TIR bands of optical data are critical for lithological identification; (3) The feature optimization algorithm reduces feature redundancy and efficiency issues from multi-source data, achieving 96.51% accuracy with the optimal feature model, an improvement of 0.1%−2.02% over original features; (4) Object-based algorithms show significant potential in mapping areas with large rock outcrops. This study offers new insights for medium- to large-scale lithological maps and provides essential data support for geological work.

Strategic Transformation of E-Commerce Big Data Classification and Mining Algorithms Based on Artificial Intelligence Era

Strategic Transformation of E-Commerce Big Data Classification and Mining Algorithms Based on Artificial Intelligence Era

Remote Sensing Data Quality in the Era of AI

Abstract. The era of Artificial Intelligence ‘AI’ with all the benefits brought along, has raised new and additional challenges to the ongoing efforts of assessing, defining, formulating, and implementing the quality aspects of geospatial remote sensing data. Developed practices using artificial intelligence leveraged techniques such as image interpretation, classification, thematic mapping, and even image quality enhancement, necessitating by that the reassessment and redevelopment of some of the related emerging quality aspects. Moreover, technology also made the generation of false images and false data possible, this matter constrained and increased precaution and doubtfulness, altogether making some practices based on that data almost halt to further notice. This paper presents the collaborative research work to assess and clarify the quality aspects that arose with the advent and implementation of AI and associated technologies; the concerns and issues that can accompany the generation of false satellite and aerial images including the generated geospatial data out of which, how the new emerged quality aspects fit into the currently existing methods through the lifecycle of remote sensing data production and usage, and consequently how the quality dimensions are affected and should be further developed and improved to tackle the changes and innovations. Also, lame a bit on investigating how to accommodate the new challenges in standards, and practical procedures and raise the awareness to users, the level of dependency on improved and enhanced satellite images when it comes to data collection interpretation and classification, and finally define the research gaps, future expected challenges and thus enclose suggestions and recommendations in that respect.

Real-life boxing activity recognition with smartphones using attention assisted deep learning models

Mobile computing technologies play a pivotal role in narrowing the gap between athletes and sports monitoring systems, while also advancing towards intelligent and automatic supervision of individual sports activities. The widespread presence of smartphones equipped with multifunctional sensors has enabled the acquisition and analysis of data, facilitating Human Activity Recognition (HAR). Although recognising sports activities using a smart mobile phone’s accelerometer is widely used, traditional methods struggle with intricate and real time activities due to the high-dimensional sensor data. This study introduces a smartphone-based architecture for HAR utilising inertial accelerometers to record athlete’s game actions data sequences, extract relevant features and derive the player’s activity data through multiple three-axis accelerometers. In this paper an Attention assisted Deep Convolution Neural Network based Bi-LSTM (AT-DCNN-BL) model is proposed. The raw data undergoes sliding window pre-processing technique, the deep learning framework of deep convolution neural network layers helps in automatic feature extraction, the bi-LSTM structure process the boxing activity data and the attention is focussed over the boxing activity classification data. The attention mechanism redistributes the weights of the extracted features which aids in increasing the classification accuracy. Other classification models like Deep Convolutional Neural Network (DCNN), Bi-directional Long Short-Term Memory (bi-LSTM), Multi-Layer Perceptron Neural Network (MLPNN) and Random Forest (RF) are also applied to the dataset collected from a mobile sensor. The study explores training of deep learning methods and illustrates the superiority of the proposed approach over others using the collected mobile sensor dataset. The AT-DCNN-BL model achieved a higher classification accuracy compared to the other models. The AT-DCNN-BL model outperformed all the other models achieving a higher accuracy rate (92.71%).

3D dataset generation using virtual reality for forest biodiversity

ABSTRACT While forest biodiversity faces a concerning decline, modern technology presents promising avenues for mitigation. However, a critical gap persists in reconciling ecological knowledge with the technical expertise required to use state-of-the-art technologies in 3D data classification. Currently, one main issue is the scarcity of 3D datasets for biodiversity, particularly within the context of machine learning applications. Unlike the straightforward classification of human-made structures, forest environments are uniquely intricate and nuanced due to its inherently complex nature. This study addresses this challenge by introducing a fully automated pipeline for tree stem 3D point cloud segmentation, focussing on a biodiversity indicator: tree-related microhabitats (TreMs). Furthermore, our research advances the field by demonstrating that machine learning models trained with labels generated by our proposed virtual reality (VR) method, Labelling Flora, yield predictions statistically similar to the traditional desktop-based labelling methods. This implies that existing 3D datasets could be augmented using the more rapid approach of VR labelling. Additionally, the findings of this paper demonstrate the potential integration of VR and immersive technology into the 3D labelling workflow, facilitating a quicker and more intuitive labelling process. This could empower users, who are non-familiar with 3D modelling, to contribute their expertise to the segmentation process.

Practical approach for sand-shale mixtures classification based on rocks multi-physical properties

Sandstones are the most common reservoir rocks, providing reservoirs for oil and gas and serving as reservoirs for groundwater. The Gulf of Mexico is known for its sand-shale mixtures and potential for its oil and hydrate gas resources in sandstone units. Understanding these variations is essential for assessing hydrocarbon potential and unconventional prospectivity. In this study, we utilized the Elastic, Electrical, and Radioactive (EER) properties of rocks for lithological categorization of well logging data, leading to the development of a novel rock physics template. The electrical and radioactive properties of the rocks facilitated a broad lithological classification, while their elastic characteristics helped distinguish between porous and low-porosity zones. Electrical and radioactive properties are utilized for well data classification because in sandstone formations, there is a decrease in log gamma and an increase in log resistivity. As a result, these opposing shifts in the two geophysical logs enhance the spread of data points on the lithological resistivity-gamma ray scatter plot, thereby simplifying the process of lithological categorization. Ultimately, the well logging data was sorted into three distinct categories: low shale sands (shale volume < 30 %), sand-shale mixtures (shale volume = 30 to 80 %), and shale-dominated areas. Subsequently, the Thomas Stieber model was employed to identify the types of clay minerals present in both sandstones and sand-shale mixtures. The model's findings revealed that dispersed type clay minerals are predominantly found in sandstones, with laminar and structured types being relatively rare. However, in sand-shale mixtures, both dispersed and laminar clays observed.

A simple but tough-to-beat baseline for fMRI time-series classification

Current neuroimaging studies frequently use complex machine learning models to classify human fMRI data, distinguishing healthy and disordered brains, often to validate new methods or enhance prediction accuracy. Yet, where prediction accuracy is a concern, our results suggest that precision in prediction does not always require such sophistication. When a classifier as simple as logistic regression is applied to feature-engineered fMRI data, it can match or even outperform more sophisticated recent models. Classification of the raw time series fMRI data generally benefits from complex parameter-rich models. However, this complexity often pushes them into the class of black-box models. Yet, we found that a relatively simple model can consistently outperform much more complex classifiers in both accuracy and speed. This model applies the same multi-layer perceptron repeatedly across time and averages the results. Thus, the complexity and black-box nature of the parameter rich models, often perceived as a necessary trade-off for higher performance, do not invariably yield superior results on fMRI.Given the success of straightforward approaches, we challenge the merit of research that concentrates solely on complex model development driven by classification. Instead, we advocate for increased focus on designing models that prioritize the explainability of fMRI data or pursue applicable objectives beyond mere classification accuracy, unless they significantly outperform logistic regression or our proposed model. To validate our claim, we explore possible reasons for the superior performance of our straightforward model by examining the innate characteristics of fMRI time series data. Our findings suggest that the sequential information hidden in the temporal order may be far less important for the accurate fMRI classification than the stand-alone pieces of information scattered across the frames of the time series.

Excellent concordance of the molecular classification between preoperative biopsy and final hysterectomy in endometrial carcinoma

ObjectiveThe 2023 International Federation of Gynecology and Obstetrics classification with molecular classification shows superior discriminatory ability compared to staging systems lacking molecular data. However, the accuracy of endometrial biopsy data in molecular classification remains uncertain. This study aimed to assess the concordance of molecular classifications between preoperative biopsy and hysterectomy to predict prognosis before surgical staging. MethodsEndometrial biopsies and corresponding hysterectomy specimens were collected at the National Cancer Center Hospital between 2012 and 2023. Immunohistochemistry for p53 and mismatch repair (MMR) proteins and next-generation sequencing of all exons of polymerase epsilon (POLE) were performed. Given the limited number of POLE mut cases in prior studies, we prepared a POLE mut-enriched cohort. Cohen's kappa estimates were used to determine concordance for molecular and clinicopathological subgroup assignments. ResultsAmong 70 patients classified into four molecular subtype groups, 33 exhibited POLE mutations, 15 showed loss of MMR protein expression, 13 had p53-abnormality, and 9 had no specific molecular profile. Concordance between biopsy and hysterectomy specimens was 100% (κ = 1.000). In contrast, histological types and grades between biopsy and surgical specimens showed moderate and substantial agreement (κ = 0.420 and κ = 0.780, respectively). ConclusionsMolecular subtypes were completely consistent with those derived from surgical specimens, demonstrating high concordance between preoperative and postoperative molecular classifications. This suggests that endometrial biopsies could reliably predict prognosis. Future studies should investigate how biopsy-based molecular profiling influences treatment planning and patient outcomes.

Optimizing Data Classification in Support Vector Machines Using Metaheuristic Algorithms

Optimizing Data Classification in Support Vector Machines Using Metaheuristic Algorithms

Multilayer Evolving Fuzzy Neural Networks With Self-Adaptive Dimensionality Compression for High-Dimensional Data Classification

Multilayer Evolving Fuzzy Neural Networks With Self-Adaptive Dimensionality Compression for High-Dimensional Data Classification