Analytical Model Research Articles

Car Price Prediction Using Machine Learning

Abstract: The objective of the "Car Price Prediction Using Machine Learning" project is to anticipate car prices based on pertinent variables by utilizing predictive modelling and advanced data analytics. The rising need for precise and active pricing systems in the automobile sector is addressed by this initiative. The system will evaluate past vehicle data, including brand, model, manufacturing year, the mileage, type of fuel, and other details, by utilizing machine learning techniques. In order to produce specific predictions, the suggested model will be trained on an extensive dataset, noticing patterns and parallels within the data. In order to create a reliable prediction model, the research focuses on using regression techniques, such as ensemble approaches or linear regression. System of measurement like as absolute mean error and R-squared coefficient will be used to evaluate the predicted accuracy of the system in order to regulate its usefulness. If this resourcefulness is employed successfully, it will have a big impact on the automobile business for clients and venders alike by giving them a tool to evaluate fair market prices and helping them make decisions. This study enhances to the body of knowledge in price analysis using machine learning and lays the footing for future improvements in the prognostication of dynamic market trends in the automobile sector.

A covalent organic framework nanosheet-nanochannel composite with signal amplification strategy for electrochemical enantioselective recognition

Recognition and separation of chiral isomers are of great importance in both industrial and biological applications. However, owing to identical molecular formulas and chemical properties of enantiomers, signal transduction and amplification are still two major challenges in chiral sensing. In this study, we developed an enantioselective device by integrating chiral covalent organic framework nanosheets (CONs) with nanochannels for sensitive identification and quantification of enantiomers. Using 3,4-dihydroxyphenylalanine (DOPA) as the model analyte, the as-prepared chiral nanofluidic device exhibits a remarkable chiral recognition ability to l-DOPA than d-DOPA. More importantly, due to the chelation of DOPA with Fe3+ ions, it can efficiently block the ion transport through channel and shield the channel surface charge, which will amplify the difference in the electrochemical response of l-DOPA and d-DOPA. Therefore, a sensitive chiral recognition can be achieved using the present nanofluidic device coupled using electrochemical amplification strategy. Notably, using this method, an ultra-low concentration of l-DOPA (as low as 0.21 pM) can be facilely and successfully detected with a linear range of 1 pM–10 μM. This study provides a reliable and sensitive approach for achieving highly selective detection of chiral molecules.

MCR-Tree: An Efficient Index for Multi-dimensional Core Search

Core models are well-known cohesive subgraph models for graph analytics that have been extensively studied. These models, including (α, β)-core, (k, l)-core, and k -core, have multiple parameters, which are referred to as multi-dimensional cores. The goal of core search is to retrieve subgraphs from a graph that satisfy the semantics of a given core model. In the literature, various indexes have been proposed to accelerate core search for different core models. However, existing indexes suffer from several limitations, such as significant redundancy, lack of scalability with respect to the number of parameters, limited generality, and inadequate consideration of index maintenance. To address these limitations, in this paper, we thoroughly investigate the problem of multi-dimensional core search. In particular, we propose a novel index called MCR-Tree, which can be applied to different core models. The MCR-Tree projects all vertices into a multi-dimensional space by leveraging the skyline corenesses, which are indexed by an R-tree. Furthermore, the MCR-Tree integrates the connectivity information of subgraphs into the nodes of the R-tree to facilitate multi-dimensional core search. Subsequently, an efficient branch-and-bound algorithm is designed to perform multi-dimensional core search by traversing the MCR-Tree. Additionally, we discuss how to maintain the MCR-Tree for graph updates. Extensive experiments demonstrate that the MCR-Tree is up to two orders of magnitude smaller than existing indexes and the MCR-Tree-based core search method is up to an order of magnitude faster than existing algorithms.

Single-step batch fabrication of microfluidic paper-based analytical devices with a 3D printer and their applications in nanoenzyme-enhanced visual detection of dopamine.

Wax printing is the most widely used method for fabricating microfluidic paper-based analytical devices (μPADs), but it still suffers from disadvantages like discontinuation of wax printers and need for additional equipment for heating treatment. To address these issues, this work initially describes a new class of wax printing approach for high-precision, batch fabrication of μPADs using a household 3D printer. It only involves a one patterning step of printing polyethylene wax into rice paper body. Under optimized parameters, a fabrication resolution, namely the minimum hydrophilic channel width, down to ~189 ± 30 μm could be achieved. In addition, the analytical applicability of such polyethylene wax-patterned μPADs was demonstrated well with enhanced colorimetric detection of dopamine as a model analyte by combining metal-organic framework (MOF) based nanoenzymes (ZIF-67) with a smartphone (for portable quantitative readout). The developed nanosensor could linearly detect dopamine over a concentration range from 10 to 1000 μM, with a detection limit of ca. 2.75 μM (3σ). The recovery results for analyzing several real samples (i.e., pig feed, chicken feed, pork and human serum) were between 91.82 and 102.79%, further validating its good detection accuracy for potential practical applications in food safety and medical diagnosis.

Personalized risk reduction of hiv plans with artificial intelligence: a narrative review

This narrative review explores the current landscape and future potential of utilizing Artificial Intelligence (AI) in the development and implementation of personalized risk reduction plans for individuals at risk of HIV infection. Traditional HIV prevention strategies often adopt a generic approach, overlooking the diverse and dynamic factors contributing to an individual's risk profile. In contrast, this review synthesizes existing literature to highlight recent advancements in AI applications, focusing on their role in tailoring HIV risk reduction interventions to the unique characteristics and circumstances of each individual. The review encompasses studies employing machine learning algorithms, predictive modeling, and data analytics to analyze and interpret large datasets related to HIV epidemiology, behavioral patterns, and socio-economic determinants. By providing an overview of these AI-driven methodologies, the review aims to showcase the potential for personalized risk assessment and intervention planning. Furthermore, it examines the integration of AI into mobile health applications, wearable devices, and telehealth platforms, facilitating real-time monitoring, feedback, and support for individuals seeking personalized risk reduction strategies.

Predictive Analysis for Personalized Machine: Leveraging Patient Data for Enhanced Healthcare

This research explores predictive analysis for personalized machine: leveraging patient data for enhanced healthcare. By leveraging the power of information and analytics, the healthcare industry can be driven towards a more patient-centric, proactive model that enhances outcomes and improve the overall quality of care. The objectives of the study are to: determine the significance and challenges of predictive analytics in healthcare, ascertain the data analytics techniques used in healthcare to enhance patient care, find out how predictive analytics can be applied for enhanced healthcare, and determine the ethical considerations associated with healthcare predictive analytics. This study employs the case study approach and experimental design. The study analyzes case studies of real-time deployment of predictive analytics models in healthcare centers, examines how these models enhance the healthcare delivery in those centers. Experiments were also conducted to understand how predictive analytics works. The C4.5 learning algorithm was employed to predict the presence of chronic kidney disease (CKD) in patients and differentiate between those not affected by the condition. The C4.5 classifier shows reasonable strength, evident in the large number of rightly classified occurrences (396) and a low misclassification of only 4 occurrences. This is further demonstrated by a low error rate of 0.37, as shown in table 5. The prevalence of this algorithm is emphasized by the large value of KS (0.97), indicating the classifier’s ground-breaking accuracy and performance. The performance of C4.5, featured by its minimal execution time and accuracy, puts it as a decent classifier. This characteristic makes it specifically well-suited for application in the healthcare sector, particularly for tasks involving prediction and classification. The application of data analytics methods for predictive analysis holds significant benefits in the health sector, as it gives us the power to predict and address potential threats to human health, covering different age groups, from the young ones to the elderly. This proactive method enables early disease detection, helping in timely interventions and contributing to better decision-making.

Accelerated and precise identification of antioxidants and pesticides using a smartphone-based colorimetric sensor array

The integration of smartphones with conventional analytical approaches plays a crucial role in enhancing on-site detection platforms for point-of-care testing. Here, we developed a simple, rapid, and efficient three-channel colorimetric sensor array, leveraging the peroxidase (POD)-like activity of polydopamine-decorated FeNi foam (PDFeNi foam), to identify antioxidants using both microplate readers and smartphones for signal readouts. The exceptional catalytic capacity of PDFeNi foam enabled the quick catalytic oxidation of three typical peroxidase substrates (TMB, OPD and 4-AT) within 3 min. Consequently, we constructed a colorimetric sensor array with cross-reactive responses, which was successfully applied to differentiate five antioxidants (i.e., glycine (GLY), glutathione (GSH), citric acid (CA), ascorbic acid (AA), and tannic acid (TAN)) within the concentration range of 0.1–10 μM, quantitatively analyze individual antioxidants (with AA and CA as model analytes), and assess binary mixtures of AA and GSH. The practical application was further validated by discriminating antioxidants in serum samples with a smartphone for signal readout. In addition, since pesticides could be absorbed on the surface of PDFeNi foam through π-π stacking and hydrogen bonding, the active sites were differentially masked, leading to featured modulation on POD-like activity of PDFeNi foam, thereby forming the basis for pesticides discrimination on the sensor array. The nanozyme-based sensor array provides a simple, rapid, visual and high-throughput strategy for precise identification of various analytes with a versatile platform, highlighting its potential application in point-care-of diagnostic, food safety and environmental surveillance.

Electronic Effect Driven Specific and Sensitive Recognition toward GHB.

Precise detection of a trace substance that intrinsically possesses weak chemical activity and less-distinctive spatial structure is of great significance, but full of challenges, as it could not be effectively recognized via either an active covalent reaction process or multiple noncovalent interactions toward its simple structure. Here, the electronic-effect-driven recognition strategy was proposed to visually sense an illicit drug, γ-hydroxybutyric acid (GHB), which was treated as an analyte model due to its inherent simple structure. In particular, a sensing system composed of two probes substituted by the nitro (-NO2) and the hydrogen (-H), was constructed with the characteristic yellow coloring and blue fluorescence, as well as high sensitivity (0.586 ng/mL), fast response (0.2 s), and specific recognition, even in the presence of 22 interferents. In addition, a portable eyeshadow box-like sensing chip was fabricated and proven to be reliable and feasible in sensing GHB disguised in liquors for self-protection in a covert manner. Hence, this work developed an electronic-effect-driven modulation strategy of the recognition interaction between the probe and the analyte and, thus, would open up a new thought for detecting the analyte with weak activity and a simple structure, as well as propel the relevant application in real scenarios.

Analytic Modeling for Grant-Free Transmission in Cell-Free Massive MIMO: A Stochastic Geometry Approach

Analytic Modeling for Grant-Free Transmission in Cell-Free Massive MIMO: A Stochastic Geometry Approach

Automated analyses of dried blood spots collected by volumetric microsampling devices

BackgroundDried blood spot (DBS) sampling on cellulose cards suffers from varying blood haematocrit levels and from chromatographic effects, which have a direct impact on quantitative DBS analyses. Commercial volumetric microsampling devices were, therefore, introduced to mitigate these effects, however, these devices are not compatible with automated DBS processing systems and must be processed manually. ResultsCapillary electrophoresis (CE) instruments use fused-silica (FS) capillaries for precise and accurate liquid handling as well as for injection, separation, and quantitative analyses of liquid samples. These inherent features of an Agilent 7100 CE instrument were employed for the automated processing (elution and homogenization) of DBSs collected by hemaPEN® volumetric devices (2.74 μL of capillary blood per spot). The hemaPEN® samples were processed directly in CE vials by consecutive transfers of 56 μL of methanol and 14 μL of deionized water through the FS capillary in a sequence of 39 DBSs with repeatability of the liquid transfers better than 1.4 %. The resulting DBS eluates were homogenized by a quick air flush through the capillary and analyzed by the same capillary and CE instrument. Creatinine was selected as a clinically relevant model analyte and its endogenous concentrations in DBSs were determined by CE with capacitively coupled contactless conductivity detection (CE-C4D) in a background electrolyte solution consisting of 50 mM acetic acid and 0.1 % (v/v) Tween 20 (pH 3.0). The overall repeatability of the automated DBS processing and CE-C4D analyses of 39 DBSs was ≤7.1 % (peak areas) and ≤0.6 % (migration times), the calibration curve was linear in the 25–500 μM range (R2 = 0.9993) and covered all endogenous blood creatinine levels, the limit of detection was 5.0 μM, and sample throughput was >12 DBSs per hour. DBS ageing for 60 days and varying blood haematocrit levels (20–70 %) did not affect creatinine quantitative results (≤6.9 % for peak areas). Inter-capillary and inter-instrument repeatability was ≤7.7 % (peak areas) and ≤3.4 % (migration times) and demonstrated an excellent transferability of the proposed analytical concept among laboratories. Significance and noveltyThis contribution is the first-ever report on the use of a single off-the-shelf analytical instrument for fully automated analyses of DBSs collected by commercial volumetric microsampling devices and holds great promise for future unmanned quantitative DBS analyses.

Morphological effect on Core@shell AuAg nanoparticles for detecting p‐aminothiophenol dimerization by surface‐enhanced Raman spectroscopy

AbstractA series of non‐spherical metallic Au and bimetallic core@shell AuAg nanoparticles (NPs) have been synthesized for SERS improvements. The bimetallic core@shell AuAg NPs were obtained through a controlled overgrowth of an Ag shell onto the surface of two types of non‐spherical Au NPs, used as seeds, Au nanooctaheda (Au NOc) and Au nanotriangles (Au NTs). This Ag overgrowth was able to produce bimetallic core@shell structures such as nanocubes and nanopyramids, respectively. Transmission electron microscopy (TEM) was used to determine the particle size and particle morphology for metallic and bimetallic NPs, and energy‐dispersive X‐ray (EDX) elemental mapping analysis confirmed the core@shell structure of the bimetallic NPs. The plasmonic absorption bands exhibited for each nanosystem were observed by UV–vis spectroscopy. The concentration of Au and Ag in the bimetallic systems was determined by inductively coupled plasma mass spectrometry (ICP‐MS). After synthesis and characterization, p‐aminothiophenol (PATP) was used as a model analyte to investigate the surface‐enhanced Raman spectroscopy (SERS) capabilities of the synthesized metallic and bimetallic nanosystems. In PATP, a dimerization reaction to 4,4′‐dimercaptoazobenzene (DMAB) is produced when it is adsorbed onto the surface of certain noble metals. This SERS analysis was performed at 10−4 M of PATP and by using two different laser wavelengths (532 and 785 nm) in all cases. In this context, we were able to detect the dimerization reaction of PATP to DMAB only for the bimetallic structures and under the 532 nm laser line. Moreover, we have found that the dimerization capacity also depends on the nanoparticle morphology.

Optimization of resolution as a simultaneous function of solvent composition, pH and temperature in reversed-phase liquid chromatography

BackgroundThe latest chromatographic retention models are capable of accurately describe the dependencies of retention over a wide range of experimental conditions. By using a suitable conversion, these models can be transformed into equations expressing the optimization criteria as function of multiples variables. Even though that theoretical models significantly reduce the experimental requirements for optimizations, these models have been barely used. Instead, most optimizations rely on empirical exploration of the relationships between criterions and variables.There is a need for a strategy to reduce the required number of experiments in multivariated optimization of separations, and Fundamental Models offer a clear opportunity for addressing it. ResultsA Fundamental Model is used to give the simultaneous dependence of chromatographic retention of seven ionizable pesticides on the three variables: solvent composition, temperature and pH (w, T, pH). Based on few experiments, the 10 parameters required to predict the chromatographic retention of those compounds, taken as model analytes, can be obtained. Two mathematical treatments to convert retentions into resolutions between pairs are used: one considering extracolumn dispersions and other neglecting these contributions. Using the Overlapped Resolutions Maps, extended to four dimensions, two optimal conditions can be found for the two different mathematical conversions. Chromatographic conditions were empirically evaluated obtaining the best results for the optimization considering extracolumn dispersions, proving that this condition is a true optimal. It was demonstrated that any small shift in any of the variables from this true optimal leads to a loss in resolution. SignificanceFundamental Models describing chromatographic retention as a simultaneous function of multiple variables are nowadays very accurate. In this work is demonstrated that these models are useful not only to predict retentions, but also to optimize separations, even in the more challenging mode: isocratic, isothermal and iso-pH. However, the success in the optimization procedure depends also on the proper definition of the mathematical conversion of the Fundamental Models into optimization criteria.

Smart Urban Food Re-Distribution using Web Application

Smart Urban Food Re-Distribution using Web Application

Development and Impact Analysis of a Multi-Pandemic Real-Time Data Dashboard: A Comparative Analytical Approach

This research presents the development and implementation of a Multi Pandemic Real-Time Data Dashboard, designed to facilitate enhanced comparative analysis across various global pandemics. Utilizing a combination of real-time data acquisition, statistical modeling, and predictive analytics, the dashboard provides a dynamic platform for analyzing pandemic trends and outcomes. Our methodology involved integrating diverse data sources, employing mathematical models such as the SIR (Susceptible, Infected, Recovered) model and machine learning algorithms for data processing and trend prediction. Key findings indicate that the dashboard effectively identifies patterns in pandemic spread and impact, offering valuable insights for public health decision-making. The research underscores the significance of advanced data analytics in managing public health crises, highlighting the dashboard’s potential in aiding proactive pandemic response and policy formulation.

Quartz Crystal Microbalance as a Holistic Detector for Quantifying Complex Organic Matrices during Liquid Chromatography: 2. Compound-Specific Isotope Analysis.

In carbon-compound-specific isotope analysis (carbon CSIA) of environmental micropollutants, purification of samples is often required to guarantee accurate measurements of a target compound. A companion paper has brought forward an innovative approach to couple a quartz crystal microbalance (QCM) with high-performance liquid chromatography (HPLC) for the online quantification of matrices during a gradient HPLC purification. This work investigates the benefit for isotope analysis of polar micropollutants typically present in environmental samples. Here, we studied the impact of the natural organic matter (NOM) on the isotopic integrity of model analytes and the suitability of the NOM-to-analyte ratio as a proxy for the sample purity. We further investigated limitations and enhancement of HPLC purification using QCM on C18 and C8 phases for single and multiple targets. Strong isotopic shifts of up to 3.3% toward the isotopic signature of NOM were observed for samples with an NOM-to-analyte ratio ≥10. Thanks to QCM, optimization of matrix removal of up to 99.8% of NOM was possible for late-eluting compounds. The efficiency of HPLC purification deteriorated when aiming for simultaneous purification of two or three compounds, leading to up to 2.5% less NOM removal. Our results suggest that one optimized HPLC purification can be achieved through systematic screening of 3 to 5 different gradients, thereby leading to a shift of the boundaries of accurate carbon CSIA by up to 2 orders of magnitude toward lower micropollutant concentrations.

ADDRESSING PRIVACY AND ETHICAL CONSIDERATIONS IN HEALTH INFORMATION MANAGEMENT SYSTEMS (IMS)

This paper explores the crucial role of privacy and ethics in Health Information Management Systems (HIMS), addressing the inherent challenges and presenting innovative solutions through detailed case studies. We examine the significant privacy concerns, such as data breaches and unauthorized data sharing, alongside ethical issues like informed consent and equitable access to technology. Effective solutions including the Privacy-Preserving Distributed Analytics (PPDA) model and proactive bioethics committees, as demonstrated by institutions like Vanderbilt University Medical Center, illustrate successful strategies for managing these concerns. The paper emphasizes the importance of prioritizing privacy and ethics not merely as compliance requirements but as foundational elements essential to the trustworthiness and effectiveness of HIMS. It advocates for a continuous, proactive approach to address these issues as technology evolves and regulations change. Furthermore, we call for a collaborative effort among policymakers, healthcare providers, technologists, and patients to develop and refine HIMS that uphold the highest standards of privacy, ethics, and accessibility, thus enhancing the quality of care and health outcomes for all stakeholders.

Analytical Release Voltage Model of Monolithic 3-D Integrated Nanoelectromechanical Memory Switches

Analytical Release Voltage Model of Monolithic 3-D Integrated Nanoelectromechanical Memory Switches

Analytical Dynamic Energy-Carbon Flow Model and Application in Cost Allocation for Integrated Energy Systems

Analytical Dynamic Energy-Carbon Flow Model and Application in Cost Allocation for Integrated Energy Systems

A method of determining the bremsstrahlung flux-weighted average photonuclear cross section

Based on a developed analytical model, a method is proposed for measuring the photonuclear cross section averaged over bremsstrahlung flux without application of additional target-monitor of photon flux. The method involves the use of a thin isotopic target, that completely overlaps the photon beam (a photonuclear converter), as well as an algorithm for processing the data on the yield of a reaction under study in such a target. The novel technique was validated on the reactions 100Mo(γ,n)99Mo and 58Ni(γ,n)57Ni in the range of photon end-point energy of 40.7–93.9 MeV. The photon flux-weighted average cross sections of the reactions measured experimentally are in good agreement with Monte Carlo simulations and TALYS predictions on their excitation functions.

A New Approach to Computationally- Successful Linear and Polynomial Regression Analytics of Large Data in Medicine

In the realm of healthcare, predictive modeling stands as a pivotal tool for deciphering patient outcomes and refining medical decision-making processes. However, the accuracy of machine learning algorithms, which underpin these predictive models, often falls short, leading to erroneous predictions. This study offers a new approach to optimize linear and polynomial regression models for healthcare analytics, which aims to tackle this challenge. In contrast to earlier efforts, this method focuses on using a scaled-down data transformation to improve linear regression model performance. The main goal of this study is to reduce the sum of squared errors (SSE) and improve the predictive power of linear regression models by using a data transformation function to reduce the size of all variables. In a series of experiments, we used non-Bayesian statistics in SPSS and Matlab to generate 40 trials of linear regression models, with 1,000 observations in each trial. In addition, we used SPSS for regression analysis, Excel for data manipulation, Wilcoxon signed-rank tests, and Cronbach’s alpha statistics for optimization model performance evaluation.Our findings show that the suggested scale-down transformation method is effective, since the sum of squared errors is significantly reduced (absolute Z-score=5.511, effect size=0.779, p-value<0.001, Wilcoxon signed-rank test). Furthermore, the optimized model's robust internal consistency was confirmed by inter-item reliability testing (Cronbach's alpha=0.993)