Optimal Set Research Articles

Enhancing Network Intrusion Detection: A Genetic Programming Symbolic Classifier Approach

This investigation underscores the paramount imperative of discerning network intrusions as a pivotal measure to fortify digital systems and shield sensitive data from unauthorized access, manipulation, and potential compromise. The principal aim of this study is to leverage a publicly available dataset, employing a Genetic Programming Symbolic Classifier (GPSC) to derive symbolic expressions (SEs) endowed with the capacity for exceedingly precise network intrusion detection. In order to augment the classification precision of the SEs, a pioneering Random Hyperparameter Value Search (RHVS) methodology was conceptualized and implemented to discern the optimal combination of GPSC hyperparameter values. The GPSC underwent training via a robust five-fold cross-validation regimen, mitigating class imbalances within the initial dataset through the application of diverse oversampling techniques, thereby engendering balanced dataset iterations. Subsequent to the acquisition of SEs, the identification of the optimal set ensued, predicated upon metrics inclusive of accuracy, area under the receiver operating characteristics curve, precision, recall, and F1-score. The selected SEs were subsequently subjected to rigorous testing on the original imbalanced dataset. The empirical findings of this research underscore the efficacy of the proposed methodology, with the derived symbolic expressions attaining an impressive classification accuracy of 0.9945. If the accuracy achieved in this research is compared to the average state-of-the-art accuracy, the accuracy obtained in this research represents the improvement of approximately 3.78%. In summation, this investigation contributes salient insights into the efficacious deployment of GPSC and RHVS for the meticulous detection of network intrusions, thereby accentuating the potential for the establishment of resilient cybersecurity defenses.

Application of Machine Learning Methods for Process Optimization in Electronic Packaging Processes

Epoxy resins are commonly used as encapsulation materials in electronic packaging processes. Fluctuations in the materials lead to both changes in processability and to varying quality. Ideally, these variations should be identified, and measures taken as quickly as possible to reduce scrap parts and thus costs. A promising optimization approach for encapsulation processes are machine learning models, which have already shown good results in quality predictions, especially for injection molding. Subsequent quality measurements are avoided with good quality prediction models. With this type of models, not only predictions can be made, but also optimal parameter combinations can be found. In this paper, models for predicting quality criteria warpage and residual enthalpy of the epoxy molding compound were set up, trained and validated. Time series of in-situ sensors were used, from which relevant features were extracted and which, together with machine parameters, provide a dataset for prediction. The most promising prediction models are random forest regression and gradient boosting regression. T hey predict warpage with an accuracy of 90% to 91% and the residual enthalpy with an accuracy of 95%. Subsequently, optimization models of the machine parameters were set up. All relevant target variables were considered in a cost function, through the minimization of which an optimal parameter set was found. The gradient boosted tree and Bayesian optimization were determined to be the most promising models, as they lead to the lowest values of the respective cost function.

Analysis and Multi-Objective Optimization of the Rate of Penetration and Mechanical Specific Energy: A Case Study Applied to a Carbonate Hard Rock Reservoir Based on a Drill Rate Test Using Play-Back Methodology

Until early 2006, in Brazil, the focus used to be on oil and gas exploration/exploitation of post-salt carbonates. This changed when the industry announced the existence of large fields in pre-salt layers across the South Atlantic Ocean from nearshore zones up to almost 350 [km] from the shore. With the discovery of pre-salt hydrocarbons reservoirs, new challenges appeared. One of the main challenges is the necessity to optimize the drilling processes due to their high operational costs. Drilling costs are considerably high, which leads the oil and gas industry to search for innovative and entrepreneurial methods. The coupling of the mechanical specific energy (MSE) and the rate of penetration (ROP) is a method that allows for the identification of ideal conditions to efficiently enhance the drilling process. In addition, the performance of the drilling process can be estimated through pre-operational tests, which consist in continuously testing the applied drilling mechanic parameters, such as the weight-on-bit (WOB) and drill string rotary speed (RPM), looking for optimum sets that would ultimately provide the most desirable ROP. Thus, the goal of this research was to analyze field data from pre-salt layer operations, using a multi-objective optimization based on the play-back methodology for pre-operational drilling tests, through the ideal combination of the highest ROP and the lowest MSE. The results showed that the new concept of pre-operational tests based on the MSE proved to be effective in the drilling process optimization. The combination of the highest ROP and the lowest MSE allows for a high-performance drilling process. For WOB intervals of 5 and 7 [klb], a good fit of the parameters was obtained. Through the parameters obtained from pre-operational tests, the eventual cost-saving and time-saving values could be estimated, respectively, ranging from USD 1,056,180 to 1,151,898 and 19.50 to 21.27 [h], respectively. In addition, the results of this research can be applied to the exploration of other natural resources, such as natural hydrogen and geothermal sources.

Gold price prediction by a CNN-Bi-LSTM model along with automatic parameter tuning.

Banking and stock markets consider gold to be an important component of their economic and financial status. There are various factors that influence the gold price trend and its fluctuations. Accurate and reliable prediction of the gold price is an essential part of financial and portfolio management. Moreover, it could provide insights about potential buy and sell points in order to prevent financial damages and reduce the risk of investment. In this paper, different architectures of deep neural network (DNN) have been proposed based on long short-term memory (LSTM) and convolutional-based neural networks (CNN) as a hybrid model, along with automatic parameter tuning to increase the accuracy, coefficient of determination, of the forecasting results. An illustrative dataset from the closing gold prices for 44 years, from 1978 to 2021, is provided to demonstrate the effectiveness and feasibility of this method. The grid search technique finds the optimal set of DNNs' parameters. Furthermore, to assess the efficiency of DNN models, three statistical indices of RMSE, RMAE, and coefficient of determination (R2), were calculated for the test set. Results indicate that the proposed hybrid model (CNN-Bi-LSTM) outperforms other models in total bias, capturing extreme values and obtaining promising results. In this model, CNN is used to extract features of input dataset. Furthermore, Bi-LSTM uses CNN's outputs to predict the daily closing gold price.

Optimal system and conservation laws for the generalized Fisher equation in cylindrical coordinates

The reaction diffusion equation arises in physical situations in problems from population growth, genetics and physical sciences. In many practical situations, the physical domain of the problem is adequately described in cylindrical Coordinates. Therefore, we consider the Fisher equation in cylindrical coordinates. We consider the generalised Fisher equation in cylindrical coordinates from Lie theory stand point. An invariance method is performed and the optimal set of nonequivalent symmetries is obtained. Finally, the conservation laws are constructed using ’multiplier method’. We determine multipliers as functions of the dependent and independent variables only. The conservation laws are computed and presented in terms of conserved vector corresponding to each multiplier.

Prediction of Ship Painting Man-Hours Based on Selective Ensemble Learning

The precise prediction of painting man-hours is significant to ensure the efficient scheduling of shipyard production and maintain a stable production pace, which directly impacts shipbuilding cycles and costs. However, traditional forecasting methods suffer from issues such as low efficiency and poor accuracy. To solve this problem, this paper proposes a selective integrated learning model (ISA-SE) based on an improved simulated annealing algorithm to predict ship painting man-hours. Firstly, the improved particle swarm optimization (MPSO) algorithm and data grouping techniques are employed to achieve the optimal selection and hyperparameter optimization of base learners, constructing a candidate set of base learners. Subsequently, the simulated annealing algorithm is improved by adding random perturbations and using a parallel perturbation search mechanism to enhance the algorithm’s global search capability. Finally, an optimal set of base learners is composed of the candidate set utilizing the ISA-SE model, and a heterogeneous ensemble learning model is constructed with the optimal set of base learners to achieve the precise prediction of ship painting man-hours. The results indicate that the proposed ISA-SE model demonstrates improvements in accuracy, mean absolute error, and root mean square error compared to other models, validating the effectiveness and robustness of ISA-SE in predicting ship painting man-hours.

Study on flexible job shop scheduling problem considering energy saving

The Flexible Job Shop Scheduling Problem (FJSP) is an extension of the classical Job Shop Scheduling Problem (JSP). The research objective of the traditional FJSP mainly considers the completion time, but ignores the energy consumption of the manufacturing system. In this paper, a mathematical model of the energy-efficient flexible job shop scheduling problem is constructed. The optimization objectives are completion time, delay time, and total equipment energy consumption. To solve the model, an improved non-dominated sorting genetic algorithm (CT-NSGA-II) is proposed to obtain the optimal scheduling solution. First, the heuristic rules of GLR were used to generate the initial population with good quality and diversity. Second, different crossover and variation operators are designed for the process sequencing and equipment selection parts to enhance the diversity of the evolutionary population. The sparsity theory is introduced to find sparse solutions and three neighborhood structures are designed to perform local search on sparse solutions to improve the uniformity of the optimal solution set distribution. Finally, a competitive selection strategy based on the bidding mechanism is proposed for the Pareto optimal solution set to obtain a better scheduling scheme. The experimental results show that the proposed improved algorithm is feasible and effective in the FJSP problem considering energy consumption, and the algorithm has some application value in improving the efficiency of smart shop operation.

Three-level models of compromised multi-granularity rough sets using three-way decision

Multi-granularity rough sets facilitate knowledge-based granular computing, and their compromised models (called CMGRSs) outperform classical optimistic and pessimistic models with extremity. Three-level CMGRSs with statistic-optimization-location effectively process hierarchical granularities with attribute enlargements, and they are worth generalizing for general granularities with arbitrary feature subsets. Thus, three-level CMGRSs on knowledge, approximation, and accuracy are established for arbitrary granularities by using three-way decision (3WD). Corresponding 3WD-CMGRSs adopt statistic-optimization-3WD by adding optimistic and pessimistic bounds to the representative location, so they resort to optimal index sets to acquire the multi-granularity equilibrium and decision systematicness. As a result, multiple CMGRSs emerge within the three-level and three-way framework, they improve the classical MGRSs and enrich 3WD as well as three-level analysis, and exhibit the good simulation, extension, effectiveness, improvement, and generalization. Firstly at the knowledge level, cardinality statistic-optimization improves previous label statistic-optimization for equilibrium realization, so CMGRSs are improved for hierarchical granularities while 3WD-CMGRSs are proposed for arbitrary granularities. Then at the approximation and accuracy levels, measure statistic-optimization determines optimal index sets, so 3WD-CMGRSs are similarly proposed to complete the simulation and extension. Furthermore, mathematical properties and computational algorithms of relevant models are investigated. Finally, three-level 3WD-CMGRSs are illustrated by table examples and are validated by data experiments.

Intelligent decision support system for pulmonary tuberculosis detection using bipolar fuzzy utility matrix and bipolar Mamdani fuzzy inference system

Tuberculosis (TB) stands as the second leading global infectious cause of death, following closely behind the impact of COVID-19. The standard approach to diagnose TB involves skin tests, but these tests can yield inaccurate results due to limited access to healthcare and insufficient diagnostic resources. To enhance diagnostic accuracy, this study introduces a novel approach employing a Bipolar Fuzzy Utility Matrix Inference System (BFUMIS) and a Bipolar Mamdani Fuzzy Inference System (BMFIS) to assess TB disease levels. By considering factors associated with the causation of TB, the study devises suitable membership functions for bipolar fuzzy sets (BFS) using both triangular and trapezoidal fuzzy numbers. Using a point factor scale, the study clusters the rules systematically and assesses the level of uncertainty within these grouped rules by utilizing bipolar triangular fuzzy numbers (BTFN). To handle the BTFN, this study proposes converting bipolar triangular fuzzy into bipolar crisp score (CBTFBCS) algorithm as a defuzzification method. The optimal bipolar fuzzy utility sets (BFUS) are determined from the bipolar fuzzy utility matrix to identify patients’ TB disease levels. These sets play a pivotal role in characterizing the severity of TB disease levels in patients. Additionally, rigorous validation of the utility framework is accomplished through measures of bipolar fuzzy satisfactory factors and sensitivity analyses. Furthermore, the study introduces the BMFIS, which presents a novel perspective on the conventional fuzzy inference system. This innovative system integrates the Mamdani fuzzy inference system (MFIS) into a bipolar fuzzy context, enriching the diagnostic process with enhanced insights. To demonstrate the efficacy of the proposed methods, extensive validation is carried out using actual clinical data. The performance metrics used in this validation effectively demonstrate the superiority of the proposed approach.

Approximating rolling stock rotations with integrated predictive maintenance

We study the solution of the rolling stock rotation problem with predictive maintenance (RSRP-PdM) by an iterative refinement approach that is based on a state-expanded event-graph. In this graph, the states are parameters of a failure distribution, and paths correspond to vehicle rotations with associated health state approximations. An optimal set of paths including maintenance can be computed by solving an integer linear program. Afterwards, the graph is refined and the procedure repeated. An associated linear program gives rise to a lower bound that can be used to determine the solution quality. Computational results for six instances derived from real-world timetables of a German railway company are presented. The results show the effectiveness of the approach and the quality of the solutions.

Experimental Investigation of the Surface Roughness for Aluminum Alloy AA6061 in Milling Operation by Taguchi Method with the ANOVA Technique

The surface roughness of the machined parts is the most important parameter to predict the performance of mechanical components. Moreover, predicting the optimal machining parameters conditions is the preferable method for cost reduction and achieving the desired surface quality of the product. This study investigates three cutting parameters, such as depth of cut, spindle speed, and feed for the milling aluminium alloy AA6061, to predict the surface roughness quality. The experimental work utilized a manual milling machine with a coated carbide cutter. Furthermore, the experiments were arranged using the Taguchi L9 orthogonal array (OA) method. The average surface roughness (Ra) was measured and converted to signal-to-noise (S/N) ratio and then analyzed in the statistical method of analysis of variance (ANOVA). Finally, the optimal combination set speed, feed, and depth of cut was 2400 rpm, 30 mm/min, and 0.5 mm, respectively. Also, according to the ANOVA test, the most influential parameter was the spindle speed among the selected parameters, with the highest P value of (66.42%). In comparison, the lowest P value is a depth of cut (5.34%). Furthermore, spindle speed was the only significant factor statistically. By selecting a high spindle speed (2400 rpm), surface quality was enhanced, but the preferable level was low for depth of cut and feed.

Optimization of the gamma reaction history diagnostic for double-shell pusher areal density and reaction history measurements on the National Ignition Facility.

The double-shell inertial confinement fusion campaign, which consists of an aluminum ablator, a foam cushion, a high-Z pusher (tungsten or molybdenum), and liquid deuterium-tritium (DT) fuel, aims for its first DT filled implosions on the National Ignition Facility (NIF) in 2024. The high-Z, high density pusher does not allow x-rays to escape the double-shell capsule. Therefore, nuclear diagnostics such as the Gamma Reaction History (GRH) diagnostic on the NIF are crucial for understanding high-Z implosion performance. To optimize the GRH measurement of fusion reaction history and the pusher's areal density, the MCNP6.3-based forward model of the detector was built. When calculating the neutron-induced inelastic gamma ray production, the interaction of neutrons with the compressed fuel was additionally included. By folding the calculated gamma ray spectrum output and the previously calibrated GRH detector responses, the optimum set of GRH energy thresholds for measuring the pusher areal density is determined to be 2.9 and 6.3MeV for DT double-shell experiments. In addition, the effect of the down-scattering of neutrons on the gamma ray spectrum, the minimum required yield for measurements, and the attenuation of the gamma rays through the pusher are analyzed.

Friction and wear analysis of basalt micro-filler loaded various epoxies and esters based thermoset polymer composites

In this study, thermoset polymers (synthetic epoxy, bio-epoxy, polyester, and vinyl ester) and basalt-reinforced (30 wt%) polymer composites were examined for their hardness and tribological characteristics. Under two levels of basalt weight percentage (0% and 30%), and three levels of load (3, 6, and 9 N), speed (100, 150, and 200 rpm), and distance (100, 150, and 200 m) parameters, the coefficient of friction (COF) and specific wear rate (SWR) are examined. According to the L18 orthogonal array design, which was created using the statistical software MINITAB-19, the tests are carried out using Pin-on-Disk Tribometer as per ASTM G99 standard. The optimum parameters are determined for COF and SWR using Taguchi statistical method. The significance of each parameter and its contribution is analyzed using the ANOVA technique. For synthetic epoxy samples, the optimum set of parameters for the COF response is 30 wt% basalt (2nd rank), 9 N load (4th rank), 100 rpm speed (1st rank), and 150 m distance (3rd rank); for the SWR response, the parameters are 30 wt% basalt (1st rank), 3 N load (2nd rank), 100 rpm speed (4th rank), and 200 m distance (3rd rank). For bio-epoxy samples, the optimum set of parameters for the COF response is 30 wt% basalt (4th rank), 9 N load (1st rank), 150 rpm speed (3rd rank), and 100 m distance (2nd rank); for the SWR response, the parameters are 30 wt% basalt (4th rank), 6 N load (2nd rank), 200 rpm speed (3rd rank), and 200 m distance (1st rank). For polyester samples, the optimum set of parameters for the COF response are 30 wt% basalt (2nd rank), 6 N load (4th rank), 200 rpm speed (1st rank), and 200 m distance (3rd rank); for the SWR response, the parameters are 30 wt% basalt (1st rank), 3 N load (4th rank), 100 rpm speed (3rd rank), and 150 m distance (2nd rank). For vinyl ester samples, the optimum set of parameters for the COF response is 30 wt% basalt (1st rank), 9 N load (3rd rank), 100 rpm speed (4th rank), and 100 m distance (2nd rank); for the SWR response, the parameters are 30 wt% basalt (2nd rank), 6 N load (3rd rank), 100 rpm speed (1st rank), and 100 m distance (4th rank). The ANOVA method demonstrated that the addition of 30 wt% basalt considerably reduced both COF and SWR. The optimum parameters that are not included in the proposed array underwent confirmation tests, and the results showed that the optimum parameters had an error rate that was less than 10% and within the bounds of statistical acceptability. According to the SEM morphology, the basalt particles reduced the material's plastic flow under different processing conditions.

Seizure prediction based on improved vision transformer model for EEG channel optimization

Epileptic seizures are unpredictable events caused by abnormal discharges of a patient’s brain cells. Extensive research has been conducted to develop seizure prediction algorithms based on long-term continuous electroencephalogram (EEG) signals. This paper describes a patient-specific seizure prediction method that can serve as a basis for the design of lightweight, wearable and effective seizure-prediction devices. We aim to achieve two objectives using this method. The first aim is to extract robust feature representations from multichannel EEG signals, and the second aim is to reduce the number of channels used for prediction by selecting an optimal set of channels from multichannel EEG signals while ensuring good prediction performance. We design a seizure-prediction algorithm based on a vision transformer (ViT) model. The algorithm selects channels that play a key role in seizure prediction from 22 channels of EEG signals. First, we perform a time-frequency analysis of processed time-series signals to obtain EEG spectrograms. We then segment the spectrograms of multiple channels into many non-overlapping patches of the same size, which are input into the channel selection layer of the proposed model, named Sel-JPM-ViT, enabling it to select channels. Application of the Sel-JPM-ViT model to the Boston Children’s Hospital–Massachusetts Institute of Technology scalp EEG dataset yields results using only three to six channels of EEG signals that are slightly better that the results obtained using 22 channels of EEG signals. Overall, the Sel-JPM-ViT model exhibits an average classification accuracy of 93.65%, an average sensitivity of 94.70% and an average specificity of 92.78%.

Evaluation of Design Parameters for Daylighting Performance in Secondary School Classrooms Based on Field Measurements and Physical Simulations: A Case Study of Secondary School Classrooms in Guangzhou

The quality of natural lighting within secondary school classrooms can significantly affect the physical and mental well-being of both teachers and students. While numerous studies have explored various aspects of daylighting performance and its related factors, there is no universal standard for predicting and optimizing daylighting performance from a design perspective. In this study, a method was developed that combines measurements and simulations to enhance the design parameters associated with daylighting performance. This approach facilitates the determination of precise ranges for multiple design parameters and allows for the efficient attainment of optimal daylighting performance. Daylight glare probability (DGP), point-in-time illuminance (PIT), daylight factor (DF), and lighting energy consumption were simulated based on existing control parameters of operational classrooms. The simulation results were then validated using field measurements. Genetic algorithms (GAs) were employed to optimize the control parameters, yielding a set of optimal solutions for improving daylight performance. The differences between daylighting performance indicators corresponding to the optimal solution set and those of the basic model were compared to test the performance of the optimized parameters. The proposed method is a robust process for optimizing daylight design parameters based on GAs, which not only enhances daylighting performance but also offers scientifically grounded guidelines for the design phase. It is a valuable framework for creating healthier and more productive educational environments within secondary school classrooms.

Gradient pyramid mechanism and Nelder-Mead simplex enhanced Colony Predation Algorithm for optimal power flow problems

The escalating human energy demand, particularly in the realm of electricity consumption, imposes a substantial burden on power system planning, resulting in the emergence of the optimal power flow (OPF) problem. To address this challenge, researchers have implemented a Flexible AC Transmission System (FACTS) in modern power systems to optimize network congestion. This paper presents a new application of the Colony Predation Algorithm (CPA) in the domain of Optimal Power Flow (OPF) through the introduction of an enhanced Colony Predation Algorithm (PNMCPA). PNMCPA incorporates the gradient pyramid mechanism and the Nelder-Mead simplex (NMs), marking the first utilization of CPA in the OPF field. The proposed approach presents a novel hierarchical gradient pyramid mechanism that combines the approximate gradient descent method with the construction of a pyramid fall rate, thereby optimizing the population as a whole within a framework that enhances population diversity. Additionally, the NMs algorithm is employed to optimize the optimal set of solutions for the population, thereby accelerating the convergence efficiency of the algorithm. The primary objective of this study is to optimize multiple factors, including the generation cost and transmission loss of the power system when multiple FACT components are present. Utilizing the Weibull probability density function, the model captures the uncertain and unstable nature of wind energy resources, encompassing direct, penalty, and standby costs. The proposed algorithm is applied to the IEEE30 bus test system, and the experimental results demonstrate that PNMCPA achieves a final optimization cost of 806.0132 $/h, surpassing other optimization algorithms. Concerning the power loss matter within the bus system, the PNMCPA algorithm significantly effectively mitigates total power loss, reducing from 1.44 MW to 1.41 MW instead of the initial CPA and substantially enhancing convergence speed. Empirical simulation outcomes clearly endorse PNMCPA as a highly efficient approach to tackling optimal power flow problems in the presence of multiple FACTS devices. The significant advancements presented in this paper mark a significant contribution to the field, offering a novel and superior solution to optimize power systems in the face of escalating energy demands.

Determining the psycho-emotional state of the observed based on the analysis of video observations

This paper develops a system for determining the psycho-emotional state of the observed people based on the analysis of video surveillance with the application of artificial intelligence technology using hardware and software tools such as PoseNet, PyTorch, SQLite, FastAPI and Flask. In many areas of human endeavor, there is an urgent need for a surveillance system that can reliably function and detect suspicious activities. To solve this problem, this paper proposes a novel framework for a real-time surveillance system that automatically detects abnormal human activities. The system has been tested and validated in real environments. The results of testing artificial intelligence program models showed the best results (f1 score with values of 0.98–0.99). The weighted average value of the f1-score metric was 0.96, which is quite a high value. The use of PoseNet implemented with PyTorch allowed to accurately determine the pose of the person in the video and extract information about the position of different body parts. The peculiarity of this work lies in the development of artificial intelligence models for automatic detection of possible physical aggression in videos, in the methods of forming an optimal set of features for the development of AI models that identify the aggressor and the victim of bullying. The developed system has the potential to be a useful tool in various fields such as psychology, medicine, security and others where it is important to analyze the emotional state of people based on their physical manifestations. The obtained applied results can be used in educational institutions and in spheres where video analysis is necessary

TAILOR: InTer-feAture distinctIon fiLter fusiOn pRuning

Filter pruning is an effective method for reducing the size of convolutional neural networks without sacrificing performance. Most filter pruning methods prioritize filters with high information content, but fail to consider that filters with low information content might capture essential features. Moreover, we have discovered that the distinctions among feature maps generated by filters can identify crucial features. Based on this insight, we propose a novel pruning method called inTer-feAture distinctIon fiLter fusiOn pRuning (TAILOR), which fuses the feature distinctions between filters. TAILOR randomly selects multiple filter sets within a convolutional layer and calculates the output feature maps of the next convolutional layer of these sets. Subsequently, an intelligent distinction optimization scheme is proposed to obtain the optimal filter set for filter pruning, which supplants the original convolutional layer. Experimental results indicated that the inter-feature distinctions among filters significantly affect filter pruning. TAILOR outperforms state-of-the-art filter-pruning methods in terms of model prediction accuracy, floating-point operations, and parameter scale. For instance, with VGG-16, TAILOR achieves a 73.89% FLOPs reduction by removing 91.85% of the parameters, while improving accuracy by 0.36% on the CIFAR-10.

Correlation between serum markers and transjugular intrahepatic portosystemic shunt prognosis in patients with cirrhotic ascites.

Individuals with refractory ascites in the context of liver cirrhosis typically face an adverse prognosis. The transjugular intrahepatic portosystemic shunt (TIPS) is an efficacious intervention, but there is a lack of reliable tools for postoperative prognosis assessment. Previously utilized clinical biochemical markers, such as the serum albumin concentration (Alb), sodium (Na+) concentration, and serum creatinine (Scr), have limited predictive value. Therefore, the quest for novel, specific biomarkers to evaluate the post-TIPS prognosis in patients with liver cirrhosis and refractory ascites holds significant practical importance. To investigate the associations between the Child-Pugh score, model for end-stage liver disease (MELD) score, and serum cystatin C (Cys C) level and post-TIPS prognosis in patients with liver cirrhosis and refractory ascites. A retrospective analysis was conducted on 75 patients with liver cirrhosis and refractory ascites who underwent TIPS at our institution from August 2019 to August 2021. These patients were followed up regularly for two years, and the death toll was meticulously documented. The patients were allocated into a survival group (n = 45 patients) or a deceased group (n = 30 patients) based on their prognosis status. The clinical data of the two groups were collected, and Child-Pugh scores and MELD scores were calculated for analysis. Spearman correlation analysis was carried out to evaluate the correlation of prognosis with Child-Pugh grade, MELD score, and Cys C level. Additionally, a multiple-factor analysis utilizing the Cox proportional hazard model was used to identify independent risk factors affecting the post-TIPS prognosis of patients with liver cirrhosis and refractory ascites. The receiver operating characteristic curve (ROC) ascertained the predictive value of the Cys C concentration, Child-Pugh grade, and MELD score for the prognosis of liver cirrhosis with refractory ascites in post-TIPS patients. During a 2-year follow-up period, among 75 patients with liver cirrhosis and refractory ascites who underwent TIPS treatment, 30 patients (40.00%) passed away. The deceased cohort exhibited heightened aspartate aminotransferase, alanine aminotransferase, total bilirubin, Scr, prothrombin time, Cys C, international normalized ratio, Child-Pugh, and MELD scores compared to those of the survival cohort, while Alb and Na+ levels were attenuated in the deceased group (P < 0.05). Spearman analysis revealed moderate to high positive correlations between prognosis and Child-Pugh score, MELD score, and Cys C level (r = 0.709, 0.749, 0.671, P < 0.05). Multivariate analysis using the Cox proportional hazard model demonstrated that the independent risk factors for post-TIPS prognosis in patients with liver cirrhosis and refractory ascites were Cys C (HR = 3.802; 95%CI: 1.313-11.015), Child-Pugh (HR = 3.030; 95%CI: 1.858-4.943), and MELD (HR = 1.222; 95%CI: 1.073-1.393) scores. ROC analysis confirmed that, compared to those of the classic prognostic models for Child-Pugh and MELD scores, the predictive accuracy of Cys C for post-TIPS prognosis in patients with liver cirrhosis and refractory ascites was slightly lower. This analysis yielded sensitivity and specificity values of 83.33% and 82.22%, respectively. The area under the curve value at this juncture was 0.883, with an optimal cutoff value set at 1.95 mg/L. Monitoring the serum Cys C concentration is valuable for assessing the post-TIPS prognosis in patients with liver cirrhosis and refractory ascites. Predictive models based on serum Cys C levels, as opposed to Scr levels, are more beneficial for evaluating the condition and prognosis of patients with ascites due to cirrhosis.

Life Prediction of Rolling Bearing Based on Optimal Time-Frequency Spectrum and DenseNet-ALSTM.

To address the challenges faced in the prediction of rolling bearing life, where temporal signals are affected by noise, making fault feature extraction difficult and resulting in low prediction accuracy, a method based on optimal time-frequency spectra and the DenseNet-ALSTM network is proposed. Firstly, a signal reconstruction method is introduced to enhance vibration signals. This involves using the CEEMDAN deconvolution method combined with the Teager energy operator for signal reconstruction, aiming to denoise the signals and highlight fault impacts. Subsequently, a method based on the snake optimizer (SO) is proposed to optimize the generalized S-transform (GST) time-frequency spectra of the enhanced signals, obtaining the optimal time-frequency spectra. Finally, all sample data are transformed into the optimal time-frequency spectrum set and input into the DenseNet-ALSTM network for life prediction. The comparison experiment and ablation experiment show that the proposed method has high prediction accuracy and ideal prediction performance. The optimization terms used in different contexts in this paper are due to different optimization methods, specifically the CEEMDAN method.