Evaluation Criteria Research Articles

Machine Learning Based Decision Support System for the Diagnosis of Breast Cancer

Breast cancer is among the most prevalent diseases encountered among women worldwide. Early diagnosis of breast cancer is crucial for the treatment of the disease. Detecting the disease at an early stage prevents deaths resulting from the condition. Recently, computer-aided systems have been developed to ensure early-stage diagnosis and accuracy of breast cancer. Computer-aided systems developed with machine learning approaches significantly contribute to the process of diagnosing breast cancer. The aim of this study is to propose a new classification system based on machine learning algorithms developed for the diagnosis of breast cancer. In this study, sub-data sets were created by reducing features, and data cleaning processes were applied. After these procedures, stages such as feature selection and feature extraction were applied. In this study, classification processes such as Ensemble, k- Nearest Neighbors (kNN), Support Vector Machines (SVMs), and Hybrid Artificial Intelligence were used in line with machine learning. With the obtained results, a Breast Cancer diagnosis algorithm was created. Performance evaluation criteria such as accuracy rate, specificity, sensitivity, kappa number and F-Measure were applied to the created algorithms. In the results obtained in this study, the highest accuracy rate was found to be 99.3% with the Ensemble method, the highest specificity rate was 98.7% with the Ensemble method, and the highest sensitivity rate was found to be 100% with many methods. In light of these results, it was observed that the machine learning algorithms used in this study, implemented in the Matlab environment, were effective. Consequently, it was proven that higher accuracy, specificity, and sensitivity rates can be found with different machine learning techniques. This also demonstrates that the study in our article is a reliable one in detecting diseased and healthy individuals in the diagnosis of breast cancer, showing that it is a more applicable and feasible study in the healthcare field.

Business Analytics in Customer Lifetime Value: An Overview Analysis

ABSTRACTIn customer‐oriented systems, customer lifetime value (CLV) has been of significant importance for academia and marketing practitioners, especially within the scope of analytical modeling. CLV is a critical approach to managing and organizing a company's profitability. With the vast availability of consumer data, business analytics (BA) tools and approaches, alongside CLV models, have been applied to gain deeper insights into customer behaviors and decision‐making processes. Despite the recognized importance of CLV, there is a noticeable gap in comprehensive analyses and reviews of BA techniques applied to CLV. This study aims to fill this gap by conducting a thorough survey of the state‐of‐the‐art investigations on CLV models integrated with BA approaches, thereby contributing to a research agenda in this field. The review methodology consists of three main steps: identification of relevant studies, creating a coding plan, and ensuring coding reliability. First, relevant studies were identified using predefined keywords. Next, a coding plan—one of the study's significant contributions—was developed to evaluate these studies comprehensively. Finally, the coding plan's reliability was tested by three experts before being applied to the selected studies. Additionally, specific evaluation criteria in the coding plan were implemented to introduce new insights. This study presents exciting and valuable results from various perspectives, providing a crucial reference for academic researchers and marketing practitioners interested in the intersection of BA and CLV.

A perceived community typology in older Korean Americans: implications for mental health.

The aims of this study were to identify a community typology in older Korean Americans and to examine how the typology is associated with feelings of loneliness and mental distress. We hypothesized that distinct community groups would be identified and that they would be differentially associated with mental health and background characteristics. Data were drawn from a survey with older Korean Americans aged 60 and older, collected during 2017-2018 in diverse locations (n = 2138). To identify a community typology, a series of latent profile analyses (LPA) were conducted using 15 community-related variables in three domains (neighbourhood characteristics, social cohesion, ethnic attachment). Based on model evaluation criteria, an LPA model with five community groups was identified as the best fit. The five groups were identified as "safe/integrated" (10%), "safe/distant" (10%), "moderate integration" (38%), "marginal" (31%), and "vulnerable" (11%). After examining descriptive characteristics of the identified groups, regression models of loneliness and mental distress were estimated. Using the safe/integrated group as reference, the marginal and vulnerable groups were consistently associated with elevated feelings of loneliness and mental distress. The results suggest the need to understand community profiles and their relationships with health/well-being among older immigrants.

Predicting Team Advancement in Major League Baseball Postseason Using Borda Count

The prediction of sports competition outcomes has long been a topic of interest in academia and among sports enthusiasts. This study focuses on Major League Baseball (MLB) as its research subject, encompassing the years 2020, 2021, and 2022. By employing a set of established evaluation criteria, comprising five pitching and five hitting indicators from previous literature, the regular-season performance of the 30 MLB teams across both leagues (National League and American League) over the three-year period was compiled. Subsequently, a data normalization technique combined with the Borda count concept was proposed to develop a model for forecasting team advancement in the postseason. The predictive accuracy of the model presented in this study for determining MLB postseason qualifiers from 2020 to 2022 fell within the range of 55.6% to 66.7%, akin to models utilizing extensive datasets. Notably, the proposed model is more comprehensible and user-friendly, offering ease of understanding and application for sports enthusiasts and facilitating its potential utilization and dissemination in the sporting community.

Efficacy, safety, and biomarker analysis of TACE combined with lenvatinib plus sintilimab in unresectable hepatocellular carcinoma: a real-world study

BackgroundThe integration of transarterial chemoembolization (TACE) with systemic therapy has demonstrated improved survival outcomes in patients with unresectable hepatocellular carcinoma (HCC). However, there is limited evidence evaluating the combination of TACE with the systemic regimen of anti-PD-1/L1 inhibitor plus lenvatinib. This study aims to assess the efficacy and safety of TACE combined with lenvatinib and sintilimab in unresectable HCC patients.MethodsUnresectable HCC patients who received TACE in combination with sintilimab plus Lenvatinib as first-line treatment from 1 January 2020 to 31 March 2023 were included for the analysis. Overall survival (OS), progression-free survival (PFS), objective response rate (ORR) and disease control rate (DCR) were evaluated by modified Response Evaluation Criteria in Solid Tumors criteria. Exploratory biomarker analysis was conducted.ResultsThe study included 70 patients with unresectable HCC, predominantly male and infected with Hepatitis B. The median follow-up duration for the whole cohort was 13.8 months (95% CI 11.08–16.7). The ORR was 61.4% (95% CI, 49.0%–72.8%) and the DCR was 68.6% (95%CI, 56.4%–79.2%). The median PFS was 13.2 months (95% CI 11.0-NA), with a corresponding 1-year PFS rate of 50.3% (95% CI 39.7%-65.5%). The median OS was not reached, and the 1-year OS rate was 89.3% (95% CI 81.4%–97.9%). The most common treatment-related adverse events (TRAEs) were fatigue 38.6% (27/70), hypertension 32.9% (23/70), and hand-foot syndrome 31.4% (22/70). Most TRAEs were mild-to-moderate and manageable. In addition, significant predictive value was found in alpha-fetoprotein levels (AFP), with patients showing a level of decrease post-treatment having better PFS.ConclusionThe combination regimen demonstrated promising efficacy in treating unresectable HCC, accompanied by manageable safety profiles. Furthermore, the results of this investigation suggest that AFP holds promise as predictive biomarkers for this treatment strategy.

Soluplus-Stabilized Nimodipine-Entrapped Spanlastic Formulations Prepared with Edge Activator (Tween20): Comparative Physicochemical Evaluation.

Nimodipine (ND) is a vasodilator drug that is used for acute subarachnoid hemorrhage. It has a predominant hydrophobic property, causing low solubility and low bioavailability. Spanlastics are elastic nanovesicular systems based on non-ionic surfactants and edge activators as major components. The goal of this work is to formulate ND as spanlastic nanovesicles to improve the drug's bioavailability. Spanlastic formulations containing ND were prepared by using the ethanol injection method. The composition of the ND formulation includes Span60 as a nonionic surfactant and Tween 20 as edge activators in different ratios. Stabilizers like Soluplus are used in some formulations and then compared with other formulations without that stabilizer. The evaluation study involved Vesicle Size (VS), PolyDispersity Index (PDI), and Entrapment Efficiency (%EE). Then, the optimized formula was subjected to an in vitro release study and zeta potential, additionally comparing the optimized formula with the formula without soluplus in the same concentration in Scanning Electron Microscopy (SEM), solubility study, Deformability Index (DI), and stability study. The results indicated a significant shift in some evaluation criteria and a non-significant change in other characterizations, including the difference in polymer ratio, sonication time, and the existence of a stabilizer. The best formula, F27, was found to have VS, PDI, %EE, and zeta potential of 125.7±0.29 nm, 0.4744±0.002, and 85.43±0.17% and -20.01 ± 0.89 mV, respectively. The photomicrographs of the prepared spanlastic revealed a more uniform and spherical spanlastic, indicating a greater capacity for continuous release. With the addition of Soluplus, the formula became more stable in one month and had a higher deformability index. A significant shift was observed in both VS and PDI. As the stabilizer concentration increases, VS and PDI will decrease. The non-significant shift was noted in the %EE with the presence of a stabilizer. Soluplus has the ability to spontaneously self-assemble into spherical particles. Additionally, PEG 6000, as a component of Soluplus's structure, has a tendency to form strong or tightly bound bilayers and prevent aggregation and formulation of large vesicles. This study explains the accessibility of the formulation of ND as spanlastic nanovesicles by using the ethanol injection method. This spanlastic formulation contains non-ionic surfactants and edge activators (Span 40 and Tween 20) in varying ratios. To get a stable formula, Soluplus is added to prevent the development of crystals and agglomeration.

A Study on Functional Requirements and Inspection Items for AI System Change Management and Model Improvement on the Web Platform

The rapid adoption of artificial intelligence (AI) on the web platform across multiple sectors has highlighted not only its inherent technical hurdles, such as unpredictability and lack of transparency, but also significant societal concerns. These include the misuse of AI technology, invasions of privacy, discrimination fueled by biased data, and infringements of copyright. Such challenges jeopardize the sustainable growth of AI and risk the erosion of societal trust, industry adoption and financial investment. This analysis explores the AI system’s lifecycle, emphasizing the essential continuous monitoring and the need for creating trustworthy AI technologies. It advocates for an ethically oriented development process to mitigate adverse effects and support sustainable progress. The dynamic and unpredictable nature of AI, compounded by variable data inputs and evolving distributions, requires consistent model updates and retraining to preserve the integrity of services. Addressing the ethical aspects, this paper outlines specific guidelines and evaluation criteria for AI development, proposing an adaptable feedback loop for model improvement. This method aims to detect and rectify performance declines through prompt retraining, thereby cultivating robust, ethically sound AI systems. Such systems are expected to maintain performance while ensuring user trust and adhering to data science and web technology standards. Ultimately, the study seeks to balance AI’s technological advancements with societal ethics and values, ensuring its role as a positive, reliable force across different industries. This balance is crucial for harmonizing innovation with the ethical use of data and science, thereby facilitating a future where AI contributes significantly and responsibly to societal well-being.

Artificial Intelligence as Research Methods in Urban Design

This paper delves into the role of artificial intelligence (AI) in urban design, focusing on its capability to manage complex urban systems via paradigm classification and comparative analysis. It methodically explores how AI improves design generation, optimizes morphology, and simulates real-world scenarios, thereby enhancing design quality and efficiency throughout the urban design process. Furthermore, the study contributes to the development of comprehensive AI evaluation criteria, integrating both theoretical and practical perspectives to critically understand the advantages and limitations of AI in urban design applications.

Construction of Sensory Evaluation System of Purple Sweet Potato Rice Steamed Sponge Cake Based on Fuzzy Mathematics.

This paper presents the establishment of a sensory evaluation system for purple sweet potato rice steamed sponge cake (PSPRSSC) utilizing fuzzy mathematics. Initially, eight key sensory evaluation indices were identified through expert consultations. These indices were subsequently prioritized using fuzzy binary comparison, resulting in the following order: aroma, taste, crust color, elasticity, viscosity, chewiness, hardness, and brightness. The corresponding weight values assigned to each index were 23%, 18%, 16%, 13%, 12%, 8%, 6%, and 4%, respectively. Notably, aroma was found to have a more significant impact than visual attributes in the sensory evaluation of PSPRSSC. Based on this prioritization, comprehensive sensory evaluation criteria for PSPRSSC were formulated. Verification tests confirmed the efficacy of the proposed evaluation system. This study provides critical data and theoretical support for the sensory quality assessment of PSPRSSC, thereby facilitating its industrialization and enhancing its market viability.

Generative AI in education: ChatGPT-4 in evaluating students’ written responses

ABSTRACT The study highlights ChatGPT-4’s potential in educational settings for the evaluation of university students’ open-ended written examination responses. ChatGPT-4 evaluated 54 written responses, ranging from 24 to 256 words in English. It assessed each response using five criteria and assigned a grade on a six-point scale from fail to excellent, resulting in 3,240 evaluations. Verification-based chain-of-thought prompting with the RAG framework ensured ChatGPT-4’s accurate recall of responses and secure alignment in the university’s evaluation criteria. ChatGPT-4’s grading showed good consistency with the teacher’s grading. Mistakes in recalls and discrepancies between ChatGPT-4 and teacher assessments could be reduced. The results suggest a promising potential for using LLMs like ChatGPT-4 in academic written response evaluations.

Research on the prognosis and efficacy criteria of sudden sensorineural hearing loss

Sudden sensorineural hearing loss is a common and frequently-occurring disease. Looking at the efficacy evaluation of the diagnosis and treatment of sudden sensorineural hearing loss at home and abroad, each country has its own characteristics in the indicators and criteria of the treatment efficacy evaluation, and the common indicators of efficacy evaluation include: average pure-tone hearing threshold, the absolute value of hearing improvement of impaired frequency, the percentage of average pure-tone hearing threshold increase, speech discrimination score, speech recognition threshold, etc. The evaluation criteria mostly take the efficacy grade or the improvement level of average hearing threshold as the criterion of effective treatment, and the lack of unified standards is not conducive to the homogenization of global research related to sudden sensorineural hearing loss. In order to provide reference for the clinical evaluation of sudden sensorineural hearing loss in China, this study systematically reviewed the clinical practice guidelines and the evaluation indexes and criteria of clinical efficacy in high quality clinical multicenter studies of the disease in many countries.

Health Technology Assessment of Nailfold Capillaroscopy and Digital Retina Imaging in Diabetes Screening

AimThis study aims to identify the criteria for the evaluation of medical technologies in diabetes screening and then perform health technology assessment (HTA) for two technologies: digital retina imaging (DRI) and Nailfold Capillaroscopy (NFC). MethodsA multicriteria decision-making tool measuring attractiveness using a categorical-based evaluation technique (MACBETH) was used to calculate and compare alternatives. A focus group of ten decision-makers with more than ten years of experience in health technology was used for the decision-making. The Delphi Method was used to get a consensus about comparing criteria and alternatives to these criteria. The sampling method used in the study was the nonprobability purposive sampling method. ResultsThe study concluded that clinical efficacy (0.42) is the most important criterion for evaluating medical technologies, followed by cost-effectiveness (0.27). At the same time, ethical considerations were found to be less important (0.03). The sensitivity analysis concluded that the decision is sensitive to clinical efficacy and cost-effectiveness changes. The study found that none of the alternatives dominates others as an option for early detection of diabetes through vascular changes. LimitationsThis study primarily uses systemic literature review methods to identify criteria for evaluating alternatives. There may be additional criteria for evaluation. ConclusionThis study provides an approach for a multicriteria comparison of medical devices. The study findings are useful for public health professionals and health policymakers. Plain Language SummaryThis study assesses nailfold capillaroscopy (NFC) as a substitute for digital retina imaging (DRI) in diabetes screening using the MACBETH multicriteria decision-making tool. The research identifies five key evaluation criteria: clinical efficacy, cost-effectiveness, patient needs, user safety, and ethical considerations. A focus group of experienced health technology decision-makers was used to compare NFC and DRI. Results indicate that clinical efficacy and cost-effectiveness are the most critical factors, with NFC showing potential but not significantly outperforming DRI. Sensitivity analyses highlight the need for further research to validate NFC as an effective diabetes screening tool.

Influence of micromorphology and water content on the rheological properties and performance evaluation model of loess mudflow

Evaluation of the rheological characteristics of loess mudflow is of great significance to ecological environment protection (by loess, we mean a wind-blown Quaternary silt deposit), and geological disaster assessment in the Loess Plateau of China. Rheological characteristics of rheology for loess mudflow are highly variable due to heterogeneity in particle micromorphology and water content, and current rheological models struggle to reconcile the structural dynamics with the equilibrium behavior of soil at different concentrations and microstructures. A rheological study of loess mudflow for five regions on the Loess Plateau was carried out in this investigation, and the results showed that loess transformed from a solid-like stage to a liquid-like stage under steady loads and exhibited significant shear thinning characteristics and shear rate dependence, in which the shear rate less than 2 s−1 was the main region of loess strength attenuation and the maximum yield stress is about 1411 Pa. A smaller water content and more complex particle micromorphology led to a higher yield stress, but there was no significant correlation between flow index and particle shape and water content. Additional structural dynamics and particle fractal theory were then introduced, providing an improved model that could reconcile the structural dynamics and particle micromorphology of loess with its equilibrium behavior at different water contents and shear stresses. All the test data were distributed around a dimensionless master curve. Considering the difficulty of obtaining rheological parameters, an evaluation criterion containing three levels (clay-rich, silt-rich, and sand-rich) for the evaluation of the rheological properties of loess mudflow was proposed, which can reconcile the test results and models under different working conditions. Such an evaluation criterion can also be applied to soils of other textures, providing a straightforward manner to determine the relevant rheological parameters. The research results provide a theoretical basis for ecological environmental protection and geological disaster assessment in the Loess Plateau region based on rheological characteristics.

Effects of Surface Roughness Obtained by Milling on Interface Bonding Quality for 316H during Metal Additive Forging

The metallurgical bonding quality of bonded joints is affected by the substrate surface condition in metal additive forging process, and the surface roughness serves as a critical indicator for the surface condition. Nevertheless, the effect of surface roughness obtained by milling on interface bonding quality(IBQ) remains unclear, resulting in the lack of effective evaluation criteria for surface roughness in the milling process. This study prepared samples with various surface roughness through milling, and introduced three parameters, Ra, Rc, and Rsm, to quantify surface roughness. The interfacial morphology, elemental distribution, and mechanical properties were used to characterize the IBQ, and the influence of surface roughness on the IBQ was finally revealed. The results show that a reduction in surface roughness obtained by milling leads to an improvement in interfacial bonding, more uniform elemental distribution, and enhanced mechanical properties, all of which were related to the size of the initial voids and the dynamic recrystallization mechanism of the bonding interface. And the interface bonding process with various surface roughness involves grain boundary bulging and continuous dynamic recrystallization mechanisms. Finally, the Ra 1.2 μm was recommended as the evaluation criteria in milling process, and a high-feed face milling cutter equipped with wiper edge was suggested for machining to achieve high-quality and high-efficiency cutting of the substrate. This study provide a theoretical basis and practical guidance for the efficient acquisition of substrate surfaces suitable for interface bonding in metal additive forging process.

A novel leaf bionic flow field with structured multi-level channel based on Murray's law in proton exchange membrane fuel cell for enhanced mass transfer

The design of flow field has a significant impact on the performance of proton exchange membrane fuel cells (PEMFCs). In this study, a novel leaf bionic flow field is designed and optimized based on Murray's law. The power consumption ratio is first used in the bionic PEMFC. Additionally, an evaluation criterion, the mass transfer efficiency evaluation criterion (MTEEC), is proposed to characterize mass transfer efficiency, and field synergy theory is used to analyze performance differences in mass transfer among various flow fields. The results demonstrate that adding multi-level channel and obstacles in the flow field significantly enhances cell output performance and reduces voltage losses in mass transfer regions. Applying Murray's law to distribute multi-level channel improves the uniformity of oxygen concentration distribution in the flow field and alleviates under-rib water accumulation. Compared to the secondary stream flow field (SSFF), the structure mesh of leaf bionic flow field (SMLBFF) demonstrates a nearly 19% increase in current density output at 0.45 V. SMLBFF exhibits an 81.51% increase in convective mass transfer rate compared to SSFF at 0.4 V. Moreover, the MTEEC of SMLBFF shows improvements of 179.68% at 0.5 A/cm2 and 135.43% at 1.0 A/cm2, compared to SSFF.

Image restoration through few-mode fiber using a new comprehensive attention model

Few-mode fibers (FMF) has unique advantages in single fiber imaging (SFI) in special applications. However, the limited number of transmission modes restricts the information carriers, hence the high-quality image restoration is a major challenge. A deep learning network with new comprehensive attention, called few-mode fiber Swin Transformer (FFST), is developed based on Swin Transformer V2 to realize successful image restoration with a FMF on handwriting letters and numbers. This network is proved outperforming nine widely used convolutional neural networks or Transformer-based models with four evaluation criteria. In addition, single-fiber-multi-location (SFML) experiment is conducted to investigate the effect of different view on imaging feasibility, the result of which shows that SFML can improve the restoration quality despite one object corresponds to multiple different speckle images, indicating that multi-mapping relationships has constructive effect in single FMF imaging. This paper provides a method for imaging in very narrow cavities.

Employing Convolutional Neural Networks And Explainable Artificial intelligence for the Detection of Seizures from Electroencephalogram Signal

A seizure is a rapid, uncontrolled burst of electrical activity in the brain. Epilepsy is a neurological disorder caused by repeated seizures. Effective management requires early detection. This research aims to create a convolutional neural network (CNN) and explainable artificial intelligence (XAI) integrated system for epileptic seizure detection, using techniques such as Shapley additive explanation (SHAP) for better interpretability. The relevant data is acquired from a variety of electroencephalogram (EEG) dataset to facilitate the development of the model. To identify the EEG data, the proposed system combines deep learning models with feature extraction technique. Model visualization and XAI approaches like feature importance analysis from SHAP values offer clear insights into the model's decision-making process. Evaluation criteria like specificity and accuracy are used to assess the models' performance. This framework's objective is to create simple seizure detection systems that assist early epilepsy patient identification and individualized treatment plans. This research aims in opening the door to improved patient care and treatment by developing the field of epilepsy seizure detection.

A three-stage framework for optimal site selection of hybrid offshore wind-photovoltaic-wave-hydrogen energy system: A case study of China

The integration of offshore wind-photovoltaic-wave-hydrogen production is a sustainable energy development concept that could smooth the intermittency of renewable energy generation, reduce energy abandonment, and improve energy efficiency. However, the successful deployment of a hybrid offshore wind-photovoltaic-wave-hydrogen energy system is premised on the selection of an appropriate location, which necessitates a robust framework to support this decision. This study proposes a three-stage decision framework based on Geographic Information System and multi-criteria decision-making to determine the optimal location from macro and micro perspectives. To ensure the effectiveness of site selection, it develops a comprehensive criteria system, including exclusion criteria and evaluation criteria, encompassing geographical, resource, economy, risk, and sustainable potential aspects. Then, the spatial simulation of alternative sites is conducted according to exclusion criteria to rule out infeasible alternative sites. The multi-criteria decision-making in the third stage is performed in a rough-fuzzy environment to eliminate the uncertainty in decision-making. Finally, a case study is conducted on Hainan Island, China. The results show that the western sea area of Dongfang City is the optimal location to deploy the hybrid offshore wind-photovoltaic-wave-hydrogen energy system. The proposed framework offers a reference for practical offshore renewable energy project implementation.

Choreographing multi-degree of freedom behaviors in large-scale crowd simulations

This study introduces a novel framework for choreographing multi-degree of freedom (MDoF) behaviors in large-scale crowd simulations. The framework integrates multi-objective optimization with spatio-temporal ordering to effectively generate and control diverse MDoF crowd behavior states. We propose a set of evaluation criteria for assessing the aesthetic quality of crowd states and employ multi-objective optimization to produce crowd states that meet these criteria. Additionally, we introduce time offset functions and interpolation progress functions to perform complex and diversified behavior state interpolations. Furthermore, we designed a user-centric interaction module that allows for intuitive and flexible adjustments of crowd behavior states through sketching, spline curves, and other interactive means. Qualitative tests and quantitative experiments on the evaluation criteria demonstrate the effectiveness of this method in generating and controlling MDoF behaviors in crowds. Finally, case studies, including real-world applications in the Opening Ceremony of the 2022 Beijing Winter Olympics, validate the practicality and adaptability of this approach.

Research on Driver Emotion Monitoring and Regulation System in Intelligent Assisted Driving

Abstract. With the rapid development of smart connected vehicles, the influence, recognition and regulation of driver's emotions are crucial for intelligent cockpits with "emotional interaction". This review aims to provide a comprehensive analysis of driver emotion monitoring systems in intelligent assisted driving. By summarizing and analyzing related literature, the structure and application of emotion monitoring systems are introduced, their principles and evaluation criteria are discussed in depth, and the advantages and limitations of the three sub-systems, namely, detection, decision-making and regulation, are analyzed in detail. The results show that although emotion monitoring and modulation technologies perform well in enhancing driving safety and comfort, their practical applications still face challenges in terms of technology maturity, cost control, and privacy protection. In addition, the reliability and accuracy of current emotion monitoring systems in complex driving environments have yet to be improved. Future research should focus on interdisciplinary cooperation to integrate the latest achievements in psychology, computer science and engineering. At the same time, it is necessary to develop unified technical standards and evaluation guidelines to promote compatibility and interoperability between different systems and enhance research on privacy protection measures to ensure the security and confidentiality of user data. Through these efforts, the field of intelligent driving is expected to achieve comprehensive development and wide application, further enhancing driver safety and user experience.