Time Requirements Research Articles

From Bench to Babies - Drug Development for Male Subfertility.

Infertility is estimated to affect more than 50 million couples around the world, with male factor accounting for half of these cases, yet there is a notable absence of effective treatment options for men, other than in-vitro fertilisation (IVF) or intracytoplasmic sperm injection (ICSI). This review considers unlicensed and empirical treatments used for male subfertility, including hormonal therapy, phosphodiesterase inhibitors, and antioxidants. Compounds generally demonstrate variable improvements in sperm function but benefits for fertility are less clear. There is a pressing need for effective treatment options for subfertile men, however, our knowledge of sperm function is limited, restricting the identification of precise treatment targets. The traditional drug discovery pathway is also notorious for its extensive resource and time requirements, often extending over decades and demanding significant financial investment. Unfortunately, a substantial number of potential therapies fail before reaching the marketplace. Furthermore, reliance on mammalian models is not possible in the drug development process for male subfertility, due to significant variability between animals and man. We review recent breakthroughs and highlight novel methods aimed at improving the effectiveness and efficiency of drug discovery for male subfertility. High-throughput screening, combinatorial chemistry, and the repurposing of established medications have great potential. These strategies offer the promise of accelerating the pace of drug development, curbing the extensive demand for resources, and, in the case of drug repurposing, diminish the demand for comprehensive pharmacokinetic and pharmacodynamic studies. As these innovative approaches are adopted, the feasibility of addressing male subfertility through scientific advancements appears to be increasingly attainable.

Network-calculus service curves of the interleaved regulator

The interleaved regulator (implemented by IEEE TSN Asynchronous Traffic Shaping) is used in time-sensitive networks for reshaping the flows with per-flow contracts. When applied to an aggregate of flows that come from a FIFO system, an interleaved regulator that reshapes the flows with their initial contracts does not increase the worst-case delay of the aggregate. This shaping-for-free property supports the computation of end-to-end latency bounds and the validation of the network’s timing requirements. A common method to establish the properties of a network element is to obtain a network-calculus service-curve model. The existence of such a model for the interleaved regulator remains an open question. If a service-curve model were found for the interleaved regulator, then the analysis of this mechanism would no longer be limited to the situations where the shaping-for-free holds, which would widen its use in time-sensitive networks. In this paper, we investigate if network-calculus service curves can capture the behavior of the interleaved regulator. For an interleaved regulator that is placed outside of the shaping-for-free requirements (after a non-FIFO system), we develop Spring, an adversarial traffic generation that yields unbounded latencies. Consequently, we prove that no network-calculus service curve exists to explain the interleaved regulator’s behavior. It is still possible to find non-trivial service curves for the interleaved regulator. However, their long-term rate cannot be large enough to provide any guarantee. Specifically, we prove that for the regulators that process at least four flows with the same contract, the long-term rate of any service curve is upper bounded by three times the rate of the per-flow contract.

COMBINED SUPERCHARGING SYSTEM OF DOMESTIC HIGH-PRESSURE TWO-STROKE SPECIAL PURPOSE DIESEL

Modern trends in engine construction are inextricably linked to the improvement of power units by modernizing existing models. The introduction of a forced to 1100 kW diesel engine of the DN type allows to increase the efficiency and bring the equipment in line with modern requirements in a short time and with lower costs. The key method of improvement is the modernization of the supercharging system, which increases power without increasing the dimensions and weight of the engine, as well as improves technical and economic characteristics. A combined supercharging system with a low-pressure turbocharger (LPT) and a high-pressure drive compressor (HPT) is proposed, which work together or separately depending on the operating mode. The use of a mathematical model of the workflow made it possible to carry out a computational and experimental study of the proposed system in the modes of maximum power and maximum torque, confirming its high efficiency. The use of modern technologies and materials, as well as the introduction of innovative design and modeling methods, allows to create more reliable and durable power units. Modernization of the supercharging system is one of the most important directions in the development of modern engine construction, which allows to achieve an increase in the level of specific power, improvement of fuel economy and environmental characteristics of engines by ensuring optimal conditions for their operation in various operating conditions and in a wide range of operating modes. The paper presents the research results of the proposed two-stage supercharging scheme of the DN type diesel engine, which makes it possible to achieve a power of 1100 kW. It is shown that this scheme has advantages over the traditional one, as it makes it possible to provide a higher boost pressure in a wider range of crankshaft RPM, as well as to reduce power consumption from the crankshaft to drive the compressor at modes close to the nominal ones. These factors collectively lead to a significant improvement in the characteristics of the diesel due to the introduction of the two-stage supercharging system.

Modified FDM with cartesian expansions for electromagnetic scattering from PEC targets

AbstractIn this article, a modified scheme of the fast dipole method (FDM) is proposed based on the Cartesian tensor. To achieve separation between the field and the source, the Taylor series used in the FDM is an incomplete second‐order expansion, which limits computational accuracy and flexibility. To address this issue, a Cartesian tensor is employed to expand the interactions between the far‐group pairs. This approach allows for a complete expansion of any order and offers flexibility in precision control, enabling a balance between computational efficiency and accuracy requirements across different application scenarios. Moreover, the computational accuracy of the proposed method can be improved without a substantial increase in time and memory requirements compared to the FDM. The validity and accuracy of the proposed method are demonstrated with numerical examples.

Treatment of table olive processing wastewater with US/UV processes

Agroindustry factory's such as the table olive industry etc. that gain importance in the economies of Mediterranean countries. Conventional treatment methods are not effective for treating table olive processing wastewater due to its unique composition. Ultrasound/Ultraviolet light (US/UV) oxidation was used to treat wastewater of table olive industry to improve hydroxyl radicals and enhance organic compound removals. A statistical experimental design was used on table olive processing wastewater to examine the effects of the UV/US oxidation process. The highest removal efficiency for chemical oxygen demand, total organic carbon, color, suspended solids and phenol were obtained as 64 %, 52 % 60 %, 87.5 % and 22.3 %, respectively. These results were obtained under optimal conditions of 20 min reaction time for ultrasound process, intensity of 50 W/cm2, and 20 min reaction time for ultraviolet process in the US/UV process. The study also showed that the ultrasound/ultraviolet oxidation process resulted in small reaction time and low chemical requirements. Sludge production and operational cost decreased at best experimental conditions due to small reaction time and low chemical requirement.

GGTyper: genotyping complex structural variants using short-read sequencing data.

Complex structural variants (SVs) are genomic rearrangements that involve multiple segments of DNA. They contribute to human diversity and have been shown to cause Mendelian disease. Nevertheless, our abilities to analyse complex SVs are very limited. As opposed to deletions and other canonical types of SVs, there are no established tools that have explicitly been designed for analysing complex SVs. Here, we describe a new computational approach that we specifically designed for genotyping complex SVs in short-read sequenced genomes. Given a variant description, our approach computes genotype-specific probability distributions for observing aligned read pairs with a wide range of properties. Subsequently, these distributions can be used to efficiently determine the most likely genotype for any set of aligned read pairs observed in a sequenced genome. In addition, we use these distributions to compute a genotyping difficulty for a given variant, which predicts the amount of data needed to achieve a reliable call. Careful evaluation confirms that our approach outperforms other genotypers by making reliable genotype predictions across both simulated and real data. On up to 7829 human genomes, we achieve high concordance with population-genetic assumptions and expected inheritance patterns. On simulated data, we show that precision correlates well with our prediction of genotyping difficulty. This together with low memory and time requirements makes our approach well-suited for application in biomedical studies involving small to very large numbers of short-read sequenced genomes. Source code is available at https://github.com/kehrlab/Complex-SV-Genotyping.

A Comparative Study Between Two Cybersecurity Attacks: Brute Force and Dictionary Attacks

In today's world, information drives not only business but nearly every aspect of human life. Therefore, safeguarding valuable information from malicious activities like attacks has become essential. Brute force search and dictionary attacks are prevalent cybersecurity threats, in which an attacker systematically attempts all possible passwords and passphrases to gain access to a user's account. These types of attacks are common due to the widespread reuse of simple password variations. The goal of this study is to discover as many passwords as possible and demonstrate their predictability and susceptibility. Our focus was on comparing two cracking methods, such as brute force search attacks and dictionary attacks, assessing their effectiveness and time requirements.

Warehouse layout optimization for fishbone robotic mobile fulfillment systems

The rapid development of electronic commerce has increased demands for order fulfillment efficiency, making this a crucial challenge for warehouse systems. The study proposes a novel fishbone robotic mobile fulfillment system (FRMFS) to optimize warehouse layout and enhance the picking efficiency of automated warehouse systems, such as robotic mobile fulfillment systems (RMFS). Through the construction and analysis of mathematical models, the research demonstrates that FRMFS can significantly reduce the travel distance of robots when compared to traditional RMFS. This leads to an improvement in the overall picking efficiency of the warehouse system. The study also examines the impact of warehouse parameters, cross-aisle angles, and the number of picking stations on system operational efficiency. Simulation experiments confirm that FRMFS can reduce picking distances by 18%–28% compared to traditional RMFS. This makes it particularly suitable for complex warehouse systems with high requirements for operational response time and system throughput. Furthermore, the study introduces a point-based layout design method for picking stations in FRMFS, demonstrating its efficiency as a heuristic approach. This research presents a scientific analysis framework and model support for the operational design and optimization of FRMFS, offering valuable insights for management practices.

The Loran-C Pseudorange Positioning and Timing Algorithm Based on the Vincenty Formula

To improve the positioning accuracy of the Loran system and meet the requirements of Loran/BDS integrated positioning and timing, it is necessary to enhance the traditional Loran hyperbolic positioning method, making its pseudorange calculation consistent with the BDS positioning and timing solution. The existing pseudorange algorithm based on the Andoyer-Lambert formula has issues such as strict initial value selection range and susceptibility to singularities during calculations. This study proposes a new Loran pseudorange calculation method based on the Vincenty distance formula and conducts a simulation analysis of it. The results show that, in the absence of noise interference, the positioning and timing errors of this pseudorange algorithm are close to zero, demonstrating high accuracy. When subjected to random noise with a standard deviation of less than 100 ns, the latitude and longitude errors are both less than 10 m, and the timing error is less than 10−4 ns, meeting the requirements of Loran positioning and timing. Compared to the pseudorange algorithm based on the Andoyer-Lambert formula, the one based on the Vincenty formula has comparable positioning longitude accuracy but superior timing accuracy. Moreover, the latter offers a wider range of initial value selection and can avoid more singularity issues during calculations.

ТЕАТР ӨНӨРҮНДӨГҮ КӨРКӨМ ОКУУНУ ОКУТУУНУН АЙРЫМ МАСЕЛЕЛЕРИ

The article discusses some issues of teaching art education in the theatrical arts. I must say that there is very little research on the great values of the Kyrgyz people, including theatrical art. Generally speaking, we all know that our culture ‒ these are literature, theater, cinema, fine arts, folk art, etc.B. It should be recognized that there are very few works published in the form of special books, except for articles published on the pages of periodicals devoted specifically to this theatrical art. Today, art reading education is in demand not only in the theatrical sphere, but also in various spheres of society, in the field of culture and television. Thus, it is safe to say that by improving the teaching of art education in higher and secondary educational institutions, we will contribute to the moral education of the younger generation, improving aesthetic taste. Creating conditions for solving such research tasks, making efforts, and carrying out scientific activities is a requirement of time.

Online chatter detection via lightweight deep learning framework with efficient signal pre-processing

Deep learning methods have attracted considerable attention in the field of chatter detection due to their exceptional feature extraction and identification capabilities. However, it is challenging to adapt these methods to diverse machining conditions with limited sensor resources. In addition, the computational efficiency of these methods is compromised by their complexity, resulting in a reduced real-time performance for online chatter detection. To address them, this paper proposes a novel deep learning-based framework that combines an efficient signal pre-processing method with a novel lightweight parallel convolutional neural network (LPNN). A fast continuous wavelet transform algorithm is applied to the raw signal, effectively generating time–frequency maps that represent chatter characteristics. The LPNN incorporates the condensed block as a feature extraction unit, which is constructed using depthwise separable convolution. The introduction of the condensed block and the parallel structure increases the depth and width of the designed model while maintaining fewer parameters and higher computational efficiency. A transfer learning strategy is adopted to train the model, reducing the training time and data requirements for online chatter detection. Experimental results using large open-source turning datasets demonstrate the effectiveness of the proposed method in identifying chatter under various machining conditions. The proposed method outperforms other methods with a classification accuracy of 96.5% on the test set. Furthermore, the performance of the proposed method for online chatter detection is validated in our milling experiments, exhibiting enhanced real-time performance compared to other methods.

A Linear Regression Approach for Best Scanline Determination in the Object to Image Space Transformation Using Pushbroom Images.

The use of linear array pushbroom images presents a new challenge in photogrammetric applications when it comes to transforming object coordinates to image coordinates. To address this issue, the Best Scanline Search/Determination (BSS/BSD) field focuses on obtaining the Exterior Orientation Parameters (EOPs) of each individual scanline. Current solutions are often impractical for real-time tasks due to their high time requirements and complexities. This is because they are based on the Collinearity Equation (CE) in an iterative procedure for each ground point. This study aims to develop a novel BSD framework that does not need repetitive usage of the CE with a lower computational complexity. The Linear Regression Model (LRM) forms the basis of the proposed BSD approach and uses Simulated Control Points (SCOPs) and Simulated Check Points (SCPs). The proposed method is comprised of two main steps: the training phase and the test phase. The SCOPs are used to calculate the unknown parameters of the LR model during the training phase. Then, the SCPs are used to evaluate the accuracy and execution time of the method through the test phase. The evaluation of the proposed method was conducted using ten various pushbroom images, 5 million SCPs, and a limited number of SCOPs. The Root Mean Square Error (RMSE) was found to be in the order of ten to the power of negative nine (pixel), indicating very high accuracy. Furthermore, the proposed approach is more robust than the previous well-known BSS/BSD methods when handling various pushbroom images, making it suitable for practical and real-time applications due to its high speed, which only requires 2-3 s of time.

Pathology diagnosis of intraoperative frozen thyroid lesions assisted by deep learning

BackgroundThyroid cancer is a common thyroid malignancy. The majority of thyroid lesion needs intraoperative frozen pathology diagnosis, which provides important information for precision operation. As digital whole slide images (WSIs) develop, deep learning methods for histopathological classification of the thyroid gland (paraffin sections) have achieved outstanding results. Our current study is to clarify whether deep learning assists pathology diagnosis for intraoperative frozen thyroid lesions or not.MethodsWe propose an artificial intelligence-assisted diagnostic system for frozen thyroid lesions that applies prior knowledge in tandem with a dichotomous judgment of whether the lesion is cancerous or not and a quadratic judgment of the type of cancerous lesion to categorize the frozen thyroid lesions into five categories: papillary thyroid carcinoma, medullary thyroid carcinoma, anaplastic thyroid carcinoma, follicular thyroid tumor, and non-cancerous lesion. We obtained 4409 frozen digital pathology sections (WSI) of thyroid from the First Affiliated Hospital of Sun Yat-sen University (SYSUFH) to train and test the model, and the performance was validated by a six-fold cross validation, 101 papillary microcarcinoma sections of thyroid were used to validate the system’s sensitivity, and 1388 WSIs of thyroid were used for the evaluation of the external dataset. The deep learning models were compared in terms of several metrics such as accuracy, F1 score, recall, precision and AUC (Area Under Curve).ResultsWe developed the first deep learning-based frozen thyroid diagnostic classifier for histopathological WSI classification of papillary carcinoma, medullary carcinoma, follicular tumor, anaplastic carcinoma, and non-carcinoma lesion. On test slides, the system had an accuracy of 0.9459, a precision of 0.9475, and an AUC of 0.9955. In the papillary carcinoma test slides, the system was able to accurately predict even lesions as small as 2 mm in diameter. Tested with the acceleration component, the cut processing can be performed in 346.12 s and the visual inference prediction results can be obtained in 98.61 s, thus meeting the time requirements for intraoperative diagnosis. Our study employs a deep learning approach for high-precision classification of intraoperative frozen thyroid lesion distribution in the clinical setting, which has potential clinical implications for assisting pathologists and precision surgery of thyroid lesions.

Coping mechanisms and strategies adopted to improve the quality and timeliness of immunization data among lower-level private-for-profit service providers in Kampala Capital City, Uganda.

Lower-level urban private-for-profit health service providers are actively engaged in the delivery of immunization services. However, not much is known about their everyday endeavours to improve data quality and ensure the submitted data meets the quality and timeliness requirements as per established guidelines. The objective of this paper was to examine the coping mechanisms and strategies adopted to improve the quality and timeliness of immunization data among lower-level private-for-profit service providers in Kampala Capital City, Uganda. A qualitative study design was adopted with in-depth interviews (n = 17) and key informant interviews (n = 8) completed among frontline health workers, district health managers and immunization implementing partners. Analysis followed a thematic approach with coding conducted using Atlas. ti, a qualitative data management software. Overall, coping mechanisms and strategies adopted to improve the data quality among lower-level urban private-for-profit immunization service providers included; Experiential attachment for practical skills acquisition in data management, data quality peer-to-peer learning among private-for-profit immunization service providers, registration using cohort system for easy tracking of records during subsequent visits, separation of visiting service user records from regular attendants, service delivery modifications such as reward for better performance, engagement of Village Health Teams (VHTs) in outreaches and data completion, and data quality checks through review of monitoring charts to identify gaps in data quality. Within the urban context, the delivery of immunization services by lower-level private-for-profit services faces data quality challenges some of which stem from the implementation context. Different coping strategies focusing on frontline health worker skills, enhanced experience sharing through peer-to-peer learning, modifications to registration and routine review of monitoring charts. However, these efforts were often faced with chronic barriers such as the high staff turnover calling for dedicated efforts to optimize the available implementation opportunities like guidelines mandating the public health facilities to supervise the lower-level private immunization service providers within their catchment areas to respond to the identified gaps.

Movie trailer genre classification using multimodal pretrained features

We introduce a novel method for movie genre classification, capitalizing on a diverse set of readily accessible pretrained models. These models extract high-level features related to visual scenery, objects, characters, text, speech, music, and audio effects. To intelligently fuse these pretrained features, we train small classifier models with low time and memory requirements. Employing the transformer model, our approach utilizes all video and audio frames of movie trailers without performing any temporal pooling, efficiently exploiting the correspondence between all elements, as opposed to the fixed and low number of frames typically used by traditional methods. Our approach fuses features originating from different tasks and modalities, with different dimensionalities, different temporal lengths, and complex dependencies as opposed to current approaches. Our method outperforms state-of-the-art movie genre classification models in terms of precision, recall, and mean average precision (mAP). To foster future research, we make the pretrained features for the entire MovieNet dataset, along with our genre classification code and the trained models, publicly available.

Representing Clinical Study Schedule of Activities as FHIR Resources: Required Characteristic Attributes

Introduction: The HL7 FHIR interoperability standard is nowimplemented widely to expose healthcare records, and the FHIR definitionalresources are being investigated and developed to enable research studyprotocol requirements to directly support research data collection from the clinicinto sponsors databases. Objective.  Methods:  A minimal setof attributes to model SoA scheduling requirements was identified, tested anddeveloped using graph methods. The model was tested using various standard, complex,and publicly available SoA examples. The ability of these examples to be generatedas FHIR resources compliant with the recently published HL7 Vulcan SoA ProjectImplementation Guide was tested.  Results: A minimum viable set of SoA characteristics hasbeen identified that can generate SoA FHIR Implementation Guide (IG) compliant resourcesconsistent with the scheduling and timing requirements of a study. Conclusion:  A minimumviable set of SoA characteristics able to describe common study timingrequirements for defining, creating, and confirming study specific FHIRresources was developed.  Although this workwas focused on creating SoAs in FHIR format, the same attributes should be presentand identifiable in SoA models in other formats. The findings here thereforemay have a broader applicability for confirming machine-readable SoArequirements.

Drying strategies for maximizing polyhydroxybutyrate recovery from microalgae cultivated in a raceway pond: A comparative study

Polyhydroxybutyrate (PHB) derived from microalgae are considered a promising alternative bioplastic material to replace synthetic plastics. This study evaluated the effects of various drying techniques (sun, freeze, oven and air drying) on PHB recovery from microalgae. Freeze drying recovered the maximum PHBs (6.2%) followed by sun drying (5.2%), air drying (2.3%), oven drying (2%), and the lowest in wet biomass (1.2%). The most energy-intensive drying method was freeze drying (26.83 kW) followed by oven drying (3 kW) while the other methods did not require energy. The minimum time requirement for drying was oven drying (6 h), followed by freeze drying (24 h), sun drying (48–72 h), and air drying (96–120 h) while wet biomass did not require time. In terms of PHB yield per unit time, oven (0.33%/h) is a more effective drying technique than freeze drying (0.25%/h) which produces 24.24% higher PHB yield per unit time. Fourier transform infrared spectroscopy (FTIR), thermogravimetric analysis (TGA) and differential scanning calorimetry (DSC) confirmed PHB structure and thermal stability up to 300 °C from dried biomasses compared to wet biomass at 200 °C. This study indicated that drying techniques significantly influence the PHB recovery from microalgae biomass. Findings also revealed that the oven dried technique can be efficiently scaled up for PHB recovery.

Augmented reality for enhanced documentation and anchor inspection reporting in conventional tunnelling

This study explores the feasibility of Augmented Reality (AR) technology for efficient quality inspection documentation on tunnel construction sites. Conventional tunnel construction relies heavily on paper-based documentation processes, leading to potential errors and increased documentation and site inspection time requirements. Introducing AR as a digital tool offers a promising solution to address these challenges. The paper identifies potential use of AR for tunnel inspection reports. The methodology involves Design Science Research, including prototype development and a case study in a tunnel environment. The findings of the case study show that the developed AR prototype facilitates quality management and speeds up documentation processes compared to the current paper-based solutions. Despite some input detection issues and current hardware limitations, the approach presents a promising and robust solution suitable for real-world environments.

How does pesticide reduction affect labour time and profitability? A crop production case study

CONTEXTNational and international agendas are focusing on reducing pesticides due to their detrimental effects on flora, fauna, and human health, which has led to the introduction of agri-environmental programmes aimed at reducing the risk of pesticides. Pesticide reduction in agriculture can have an impact on labour time requirements and profitability. OBJECTIVEWe used winter wheat, sugar beet, and potatoes as examples to analyse the changes in profitability and working time requirements, including management tasks. METHODSFor the calculations, we used five different production schemes for each crop: reference; (A) reduction of herbicides; (B) reduction of growth regulators, fungicides, and insecticides; combination of schemes (A) and (B); and organic production. The working time requirements for fieldwork and farm management work were modelled for each scheme and crop. The respective partial costs and benefits of the schemes were calculated for each crop. RESULTS AND CONCLUSIONSBased on the model assumptions, scheme (B) appears favourable in terms of working time requirements, and profitability of winter wheat and sugar beet. Scheme (A) offers synergies between the same parameters for potato production. Economic analysis shows that crop production with reduced pesticide use may even experience an increase in financial viability if the yield is not severely jeopardised, and farmers can be compensated through premiums and direct payments. SIGNIFICANCEOur results can support policy-making, since the labour time requirement and profitability of pesticide-reduced crop production can affect the success of voluntary agri-environmental programmes for the reduction of the risks from pesticide use in agriculture.

Exploring the pre-disaster evacuation network design problem under five traffic equilibrium models

This paper explores modeling approaches for the pre-disaster Evacuation Network Design Problem (ENDP) considering different flow equilibrium conditions. We combine this problem with the modeling idea of Continuous Network Design Problem (CNDP), which we call Continuous Evacuation Network Design Problem (CENDP) in this paper. We develop five CENDP models, which are under the consideration of User Equilibrium (UE), Stochastic User Equilibrium (SUE), Boundedly Rational User Equilibrium (BRUE), and Non-equilibrium (NONE), among which we develop two types of models based on BRUE. The modeling is mainly to consider the single objective of optimizing the total evacuation time, and then to provide reasonable road expansion solutions under certain budget constraints and different equilibrium conditions. Our main motivation for developing models is to introduce various types of equilibrium conditions into models and design algorithms to solve these problems while mining for key insights. We design the corresponding five heuristic algorithms to solve models and verify the applicability of the models and algorithms by two test networks (Nguyen-Dupuis network and Sioux-Falls network). We demonstrate whether evacuation flow equilibrium need or not need to be considered in the CENDP, the applicability of different equilibrium conditions, and the correlation between the total evacuation time, the network investment cost, and the network congestion degree. Additionally, we conduct model and algorithm tests on 40 instance networks, dividing them into medium-sized networks (20 instances) and large-sized networks (20 instances). Not only do we further validate the insights obtained from the test networks, but we also expand upon them. Specifically, the main findings of this study are as follows: (1) We demonstrate that considering evacuation flow equilibrium in CENDP is essential to reduce total evacuation time, construction costs, and mitigate congestion. (2) While increased investment in road construction can meet evacuation time requirements, it is crucial to make informed decisions, as investment alone does not directly reduce total evacuation time and congestion. (3) Optimizing road evacuation time is more effective than merely increasing road capacity for reducing total evacuation time and mitigating congestion. (4) From the perspectives of total evacuation time, investment cost, and network congestion degree, the CENDP model considering user equilibrium performs better in medium-sized networks, while the CENDP model considering stochastic user equilibrium performs better in large-sized networks. Conversely, the CENDP model that does not consider flow equilibrium performs the worst across all above three metrics. Based on this, we also provide recommendations on which model to choose for different metrics. In summary, this study not only reveals the importance of different flow equilibrium conditions in evacuation network design but also provides valuable strategic recommendations for practical applications to optimize evacuation effectiveness and resource allocation.