Unit Density Research Articles

Mung bean protein enhances the expansion of corn starch during twin-screw extrusion.

This study examined the effects of the inclusion of mung bean protein (MBP) on the direct expansion characteristics of corn starch during twin-screw extrusion. Six blends of corn starch and MBP isolate (0%, 5%, 10%, 15%, 20%, and 25% w/w) were hydrated to three different moisture contents (MCs) (16%, 19%, and 21%w.b.). The blends were extruded using a twin-screw extruder at three screw speeds (SSs) (300, 400, and 500rpm). The resulting extrudates were evaluated for their water solubility index, water absorption index, expansion ratio (ER), true density, unit density, and porosity. As the protein content increased, the porosity of the extrudates increased. The ER of all extrudates ranged from 2.90 to 5.46, with the largest ER observed at an SS of 400rpm, an MC of 19%, and 25% MBP inclusion. The porosity of the extrudates ranged from 1.79% to 11.42%. SS and protein content had a significant impact (p<0.05) on the porosity and ER of the extrudate. PRACTICAL APPLICATION: This work provides valuable information for the industry on utilizing mung bean protein in direct expanded corn starch-based extruded snacks. The information could be useful in the development of high-protein extruded snacks and breakfast cereals.

Geographic inequities in hemodialysis access: a call to reassess dialysis facility locations in Brazil.

Patients who travel more than 60 min to undergo hemodialysis may experience higher mortality and lower quality of life. The primary aim of this study was to calculate the travel distance between patient city areas and dialysis facility care locations in Brazil, to highlight barriers and need to optimize access to chronic dialysis. We conducted a retrospective cohort study using claims data from the Brazilian Public Health System's database, focusing on kidney replacement therapy (KRT) by hemodialysis. Our study population comprised all patients undergoing hemodialysis in Brazil between January 2023 and December 2023. For patients from different city areas, we calculated the Haversine distance between the patient city area and the dialysis facility. We evaluated 154,788 patients who received hemodialysis funded by the Brazilian Public Health System. Fifty-nine percent of the patients underwent dialysis in the same city area. Overall, patients traveled a median (IQR) distance of 35.9 [19.5 - 64.2] kilometers to the facilities, 48% traveled more than 40 km, with a maximum traveling distance of 353 km. Notably, the median distance traveled was shortest in the Southeast (27.6 km) and longest in the North (84.3 km). The number of patients that traveled more than 40 km was lower in the Southeast (32%) and higher in the North region (77%). The travel distance to the dialysis facility is an important inequity to KRT access in Brazil. In the South and Southeast, where there is a higher dialysis unit density, patients have greater regional availability of dialysis centers, and shorter traveling distances than in the North, Midwest, and Northeast regions.

High-Resolution Laminar Identification in Macaque Primary Visual Cortex Using Neuropixels Probes.

Laminar electrode arrays allow simultaneous recording of activity of many cortical neurons and assignment to layers using current source density (CSD) analyses. Electrode arrays with 100-micron contact spacing have been used to estimate borders between layer 4 versus superficial or deep layers, but in macaque primary visual cortex (V1) there are far more layers, such as 4A which is only 50-100 microns thick. Neuropixels electrode arrays have 20-micron spacing, and thus could potentially discern thinner layers and more precisely identify laminar borders. Here we show that laminar distributions of CSDs lack consistency and the spatial resolution required for thin layers and accurate layer boundaries. To take full advantage of high density Neuropixels arrays, we have developed approaches based on higher resolution electrical signals and analyses, including spike waveforms and spatial spread, unit density, high-frequency action potential (AP) power spectrum, temporal power change, and coherence spectrum, that afford far higher resolution of laminar distinctions, including the ability to precisely detect the borders of even the thinnest layers of V1.

Association between Built Environment and Bus Usage among Older Adults: Urban–Rural Differences in the Nonlinearities

Public transport improves mobility and well-being for the rapidly aging population. However, few planning interventions have addressed the urban–rural disparity in bus usage among older adults. Using data from Zhongshan, China, this study adopts the eXtreme Gradient Boosting (XGBoost) model to examine urban–rural differences in the nonlinear relationship between built environment and daily bus usage among elderly adults. The results indicate nonlinearities across all built environment variables and stronger effects of the built environment in rural areas. Distance to transit contributes the most in urban neighborhoods but least in rural ones. Furthermore, dwelling unit density and green space accessibility play the biggest roles in the rural context. Additionally, the most effective ranges of intersection density, land use mixture, and CBD accessibility are greater in rural areas. The findings facilitate fine-grained and diversified planning interventions to facilitate bus usage among older adults in both urban and rural areas.

Quantitative trichoscopic analysis of hair density in people attending tertiary care hospital - A cross-sectional study.

Hair is important to trace evidence commonly encountered in almost all criminal cases. Forensic anthropologists routinely compare the morphological characteristics of the hair samples to determine a transfer. Assessment of parameters such as hair density, hair diameter, follicular units, and empty hair follicle/yellow dots are useful for the diagnosis of various hair disorders, monitoring treatment outcomes, and research purposes. The study aimed to analyze the relationship between age and hair density. The present cross-sectional observational study was carried out at the Department of Dermatology at a tertiary care center. All the subjects attending the Dermatology Outpatient Department fulfilling inclusion criteria were studied. Data were collected after the approval from the Institutional Ethical Committee. The procedure was explained and a written consent was taken. Each patient's hair was parted in the middle and images from a point of roughly 5 inches from the patient's glabella were taken. The parameters such as hair thickness, hair density, hair count, follicular units, and empty hair follicles/yellow dots were noted. In the present study, the majority of the study subjects belonged to the age group 26-35 years (38%), followed by 18-25 years (34.7%), 36-45 years (20.7%), and least in the age group of 46-55 years (6.7%). In the present study, the mean unit density in males was 104.78 ± 14.33 and that of females was 108.36 ± 17.60. Mean hair density varies concerning age group in the study population.

Measurement of the distal bile duct density on computed tomography can differentiate choledocholithiasis from a control population.

Hounsfield unit density of biliary fluid on CT may be a useful clinical marker that has not been described in the literature. This method has been used to differentiate pyonephrosis from hydronephrosis in obstructed collecting systems of the kidney. We aimed to create a user-friendly technique to measure the density of the distal bile duct using CT. The bile duct density of cases with proven choledocholithiasis at ERCP were compared with those of a control group (no biliary pathology). A total of 106 patients with proven choledocholithiasis at ERCP and 50 control patients were analysed. The distal bile duct density was calculated using the 4-point and max ellipse methods. Two blinded, independent investigators calculated the bile duct density. The HU is significantly higher in the presence of choledocholithiasis (P < 0.0001). Using the Youden index a cut-off value of 28.6 HU for the 4-point technique is useful to predict the presence of choledocholithiasis (Sensitivity 58%, Specificity 86%). Calculation of the distal bile duct density can differentiate choledocholithiasis from a control population. It may be useful alone or as a component of a scoring system to select patients more effectively for intervention. The improved use of CT may also decrease use of MRCP and reduce time to ERCP, which have potential cost benefits.

Development and validation of a nomogram to predict impacted ureteral stones via machine learning.

To develop and evaluate a nomogram for predicting impacted ureteral stones using some simple and easily available clinical features. From June 2019 to July 2022, 480 patients who underwent ureteroscopic lithotripsy (URSL) for ureteral calculi were enrolled in the study. From the eligible study population between June 2019 and December 2020, a training and validation set was randomly generated in a 7:3 ratio. To further evaluate the generalization performance of the nomogram, we performed an additional validation using the data from January 2021 to July 2022. Lasso regression analysis was used to identify the most useful predictive features. Subsequently, a multivariate logistic regression algorithm was applied to select independent predictive features. The predictive performance of the nomogram was assessed using Receiver Operating Characteristic (ROC) curves, calibration curves and decision Curve Analysis (DCA). The Hosmer-Lemeshow Test was utilized to evaluate the overall goodness of fit of the nomogram. Multivariate logistic regression analysis showed that flank pain, hydronephrosis, stone length/width, HU below (Hounsfield unit density of the ureter center below the stone), HU above/below (HU above divided by HU below) and UWT (ureteral wall thickness) were ascertained as independent predictors of impacted ureteral stones. The nomogram showed outstanding performance within the training dataset, with the area under the curve (AUC) of 0.907. Moreover, the AUC was 0.874 in the validation dataset. The ROC curve, calibration curve, DCA curve and Hosmer-Lemeshow Test suggested that the nomogram maintains excellent clinical applicability and demonstrates commendable performance. Similar results were achieved in the test dataset as well. We established a nomogram that can be effectively used for preoperative diagnosis of impacted ureteral stones, which is of great significance for the treatment of this disease.

Can Hounsfield unit density value accurately predict prelaryngeal invasion in laryngeal carcinoma cases

ObjectiveThe Hounsfield unit density value (HUDV) is a relative quantitative measurement of radio density used by radiologists in the interpretation of computed tomography (CT) images. Our aim is to investigate the role of HUDV in evaluating pre-epiglottic space (PES) involvement of laryngeal carcinoma. MethodsSeventy-four patients treated for laryngeal carcinoma in our clinic between 2014 and 2019 were included in the study. The invasion status of PES was determined radiologically and pathologically. HUDV was measured with a circular selected region of interest, with a constant size of 10 mm2 for PES. The relationship between patological PES invasion, radiological PES invasion, and HUDV was evaluated. ResultsMeasuring HUDV to determine PES invasion (74.3 %) was significantly higher than​​ conventional CT evaluation (59.5 %) (p = 0.001). The agreement coefficient (kappa value) of the conventional CT evaluation and the HUDV regarding PES involvement was 0.673, which was interpreted as ‘good’. ConclusionHUDV could be used as an additional tool in diagnosing pre-epiglottic space invasion in laryngeal cancer.

Regional variation in access to and quality of acute stroke care: results of Germany’s Health System Performance Assessment pilot, 2014–2020

BackgroundHealth System Performance Assessments (HSPA) and analyses of unwarranted regional variation in health care both aim at identifying strengths and weaknesses of health systems to improve care. Applying HSPA’s conceptual approach of interrelated health system dimensions (e.g., access, quality) to regional levels might help to better understand variation in care to reduce inequity and improve performance.MethodsWe use four indicators identified and analysed in a pilot study for a German HSPA to assess variation in access to and quality of acute stroke care between Germany’s 16 federal states and urban vs. rural regions from 2014 to 2020. Stroke unit (SU) density, share of the population reaching a SU within 30 min by car, share of inpatient stroke cases treated in a hospital with a SU, and inpatient mortality were computed based on hospital quality reports and discharge data covering all acute care hospitals. Inpatient mortality was adjusted for age, sex, stroke type, and comorbidities.ResultsAbout 500 SU were identified, i.e., 2.0 per 1,000 inpatient stroke cases. Almost 95% of Germans could reach a SU hospital within 30 min (rural: 90%; urban: 99%; > 88% in all states but one). The share of inpatient stroke cases treated in a SU hospital increased to 93% with a decreasing span between rural (92%) and urban (95%) regions and between states (74–98%). Inpatient mortality stagnated around 8.5% and increased to 9.0% in 2020 (rural: 8.7%; urban: 9.2%; states: 7.0–9.7%, one outlier of 13.3%).ConclusionsThe results especially revealed varying performance patterns in access to and quality of acute stroke care between the federal states, indicating different areas for improvement which might be addressed by more targeted policy measures in the future.

On lattice hexagonal crystallization for non-monotone potentials

We prove that for α ≥ 1, among 2d unit density lattices, minL∑P∈L(|P|2−β)e−πα|P|2 is achieved at hexagonal lattice for β≤12πα and does not exist for β&amp;gt;12πα. Here the hexagonal lattice with unit density can be expressed by Λ1=132[Z(1,0)⊕Z(12,32)]. This leads to two applications as follows. (1) Assume that α ≥ 1. Then, among 2d unit density lattices, minL∑P∈L|P|2e−πα|P|2 is achieved at hexagonal lattice. (2) Assume that β &amp;gt; α ≥ 1. Then minz∈Hθ(α;z)−bθ(β;z) is achieved at z=eiπ3 (corresponding to hexagonal lattice) for b≤βα and does not exist for b&amp;gt;βα. Here θ(α; z) is the two-dimensional Theta function.

Hair transplantation versus scalp micropigmentation: A retrospective study of treatment selection in persons with female pattern hair loss.

Hair transplant (HT) is the standard treatment for female pattern hair loss (FPHL), but scalp micropigmentation (SMP) is an alternative. Currently, there are no criteria to help choose between HT and SMP. Forty female patients with FPHL who had successfully undergone HT and SMP, were reviewed to identify factors that might help decide between treatments. Hair density (HD) and hair caliber were measured at the part line and mid-occipital region by a Folliscope. The sensitivity and specificity of HT and SMP were determined by area under the curve (AUC) and receiver operating characteristic curve. Patients were divided into HT (n = 23) and SMP (n = 17) groups. The follicular unit density (FUD) (HT: 62.06 ± 4.8551/cm2; SMP: 66.59 ± 3.4971/cm2) and HD (HT: 96.16 ± 16.6954/cm2; SMP: 116.08 ± 17.0520/cm2) were significantly different (p < 0.01) between groups. The AUC for FUD was 77.6% with a cutoff value of 66.83 and 87.0% (1-0.412) sensitivity. The AUC for HD was 82.4% with a cutoff value of 96.17 and 69.6% (1-0.118) sensitivity. HD was the most important factor when deciding between HT surgery and SMP. SMP is recommended when the HD is ≥104.6 hairs/cm2 and HT surgery is strongly recommended when the HD is ≤96.17 hairs/cm2.

Asymptotic analysis of fundamental solution of multi-dimensional distributed-order time-fractional diffusion equation with unit density function

In this paper, we consider the multi-dimensional distributed-order time-fractional diffusion equation with the unit density function. We introduce the new Volterra–Bessel function and give the integral representations of fundamental solutions of equations in terms of this function in the whole- and half-space. The fractional moments of fundamental solutions are also provided in the higher dimensions using the Mellin transforms. We further apply steepest descent method to find the asymptotic behaviors of solutions using the Schläfli integral of the Volterra–Bessel function. In this respect, we study the asymptotic analysis of the Volterra–Bessel function with the large parameters, and subsequently obtain the asymptotic behaviors of fundamental solutions with a discussion on the large space variable, large time variable, higher dimensions and small diffusivity constant.

Using a new artificial intelligence-aided method to assess body composition CT segmentation in colorectal cancer patients.

This study aimed to evaluate the accuracy of our own artificial intelligence (AI)-generated model to assess automated segmentation and quantification of body composition-derived computed tomography (CT) slices from the lumber (L3) region in colorectal cancer (CRC) patients. A total of 541 axial CT slices at the L3 vertebra were retrospectively collected from 319 patients with CRC diagnosed during 2012-2019 at a single Australian tertiary institution, Western Health in Melbourne. A two-dimensional U-Net convolutional network was trained on 338 slices to segment muscle, visceral adipose tissue (VAT) and subcutaneous adipose tissue (SAT). Manual reading of these same slices of muscle, VAT and SAT was created to serve as ground truth data. The Dice similarity coefficient was used to assess the U-Net-based segmentation performance on both a validation dataset (68 slices) and a test dataset (203 slices). The measurement of cross-sectional area and Hounsfield unit (HU) density of muscle, VAT and SAT were compared between two methods. The segmentation for muscle, VAT and SAT demonstrated excellent performance for both the validation (Dice similarity coefficients >0.98, respectively) and test (Dice similarity coefficients >0.97, respectively) datasets. There was a strong positive correlation between manual and AI segmentation measurements of body composition for both datasets (Spearman's correlation coefficients: 0.944-0.999, P < 0.001). Compared to the gold standard, this fully automated segmentation system exhibited a high accuracy for assessing segmentation and quantification of abdominal muscle and adipose tissues of CT slices at the L3 in CRC patients.

A novel oxidative microwave torrefaction approach for producing empty fruit bunch-starch binder briquettes as a potential biomass-based energy

This study introduced a novel microwave torrefaction (MWT) strategy combining optimal briquetting conditions and oxidative MWT (OMWT) to create briquettes using empty fruit bunch (EFB)-starch binder for enhanced physical and fuel properties. An analysis was conducted to evaluate the impacts of compaction pressure (20–80 MPa), EFB-to-starch binder mixing ratios (90:10, 80:20, and 70:30 by wt%), and drying duration (50–150 min) on the final moisture content, unit density, and physical properties of the EFB-starch binder briquettes. This study also investigated the influences of heating duration (5–15 min), microwave (MW) power levels (200–400 W), and oxygen (O2) concentration (0–6 vol%) on the physical and fuel properties of oxidative MW-torrefied EFB-starch binder briquettes. The optimal briquetting parameters were determined using a compaction pressure of 80 MPa, mixing ratio of 80:20 (wt%), and drying duration of 120 min. Meanwhile, the optimal conditions for the OMWT process to produce satisfactory physical appearance and competitive compressive strength with higher heating value were a heating duration of 10 min, MW power level of 300 W, and O2 concentration of 6 vol%. Consequently, this process demonstrated an enhanced MWT method using minimal charcoal-activated carbon (C-AC) in an oxidative environment.

Amoxicillin/clavulanate in combination with rifampicin/clarithromycin is bactericidal against Mycobacterium ulcerans.

Buruli ulcer (BU) is a skin neglected tropical disease (NTD) caused by Mycobacterium ulcerans. WHO-recommended treatment requires 8-weeks of daily rifampicin (RIF) and clarithromycin (CLA) with wound care. Treatment compliance may be challenging due to socioeconomic determinants. Previous minimum Inhibitory Concentration and checkerboard assays showed that amoxicillin/clavulanate (AMX/CLV) combined with RIF+CLA were synergistic against M. ulcerans. However, in vitro time kill assays (TKA) are a better approach to understand the antimicrobial activity of a drug over time. Colony forming units (CFU) enumeration is the in vitro reference method to measure bacterial load, although this is a time-consuming method due to the slow growth of M. ulcerans. The aim of this study was to assess the in vitro activity of RIF, CLA and AMX/CLV combinations against M. ulcerans clinical isolates by TKA, while comparing four methodologies: CFU enumeration, luminescence by relative light unit (RLU) and optical density (at 600 nm) measurements, and 16S rRNA/IS2404 genes quantification. TKA of RIF, CLA and AMX/CLV alone and in combination were performed against different M. ulcerans clinical isolates. Bacterial loads were quantified with different methodologies after 1, 3, 7, 10, 14, 21 and 28 days of treatment. RIF+AMX/CLV and the triple RIF+CLA+AMX/CLV combinations were bactericidal and more effective in vitro than the currently used RIF+CLA combination to treat BU. All methodologies except IS2404 quantitative PCR provided similar results with a good correlation with CFU enumeration. Measuring luminescence (RLU) was the most cost-effective methodology to quantify M. ulcerans bacterial loads in in vitro TKA. Our study suggests that alternative and faster TKA methodologies can be used in BU research instead of the cumbersome CFU quantification method. These results provide an in vitro microbiological support to of the BLMs4BU clinical trial (NCT05169554, PACTR202209521256638) to shorten BU treatment.

Adhesion of Candida Albicans to digital versus conventional acrylic resins: a systematic review and meta-analysis

BackgroundThe present systematic review and meta-analysis investigated the available evidence about the adherence of Candida Albicans to the digitally-fabricated acrylic resins (both milled and 3D-printed) compared to the conventional heat-polymerized acrylic resins.MethodsThis study followed the guidelines of the Preferred Reporting Items for Systematic Review and Meta-analyses (PRISMA). A comprehensive search of online databases/search tools (Web of Science, Scopus, PubMed, Ovid, and Google Scholar) was conducted for all relevant studies published up until May 29, 2023. Only in-vitro studies comparing the adherence of Candida albicans to the digital and conventional acrylic resins were included. The quantitative analyses were performed using RevMan v5.3 software.ResultsFourteen studies were included, 11 of which were meta-analyzed based on Colony Forming Unit (CFU) and Optical Density (OD) outcome measures. The pooled data revealed significantly lower candida colonization on the milled digitally-fabricated compared to the heat-polymerized conventionally-fabricated acrylic resin materials (MD = − 0.36; 95%CI = − 0.69, − 0.03; P = 0.03 and MD = − 0.04; 95%CI = − 0.06, − 0.01; P = 0.0008; as measured by CFU and OD respectively). However, no differences were found in the adhesion of Candida albicans between the 3D-printed digitally-fabricated compared to the heat-polymerized conventionally-fabricated acrylic resin materials (CFU: P = 0.11, and OD: P = 0.20).ConclusionThe available evidence suggests that candida is less likely to adhere to the milled digitally-fabricated acrylic resins compared to the conventional ones.

Neighborhood built and food environment in relation to glycemic control in people with type 2 diabetes in the moving to health study

ObjectiveTo examine whether built environment and food metrics are associated with glycemic control in people with type 2 diabetes.Research Design and Methods: We included 14,985 patients with type 2 diabetes using electronic health records from Kaiser Permanente Washington. Patient addresses were geocoded with ArcGIS using King County and Esri reference data. Built environment exposures estimated from geocoded locations included residential unit density, transit threshold residential unit density, park access, and having supermarkets and fast food restaurants within 1600-m Euclidean buffers. Linear mixed effects models compared mean changes of HbA1c from baseline at 1, 3 (primary) and 5 years by each built environment variable. ResultsPatients (mean age = 59.4 SD = 13.2, 49.5% female, 16.6% Asian, 9.8% Black, 5.5% Latino/Hispanic, 57.1% White, 20% insulin dependent, mean BMI = 32.7±7.7) had an average of 6 HbA1c measures available. Participants in the 1st tertile of residential density (lowest) had a greater decline in HbA1c (−0.42, −0.43, and −0.44 in years 1, 3, and 5 respectively) than those in the 3rd tertile (HbA1c = −0.37 at 1- and 3-years and −0.36 at 5-years; all p-values <0.05). Having any supermarkets within 1600 m of home was associated with a greater decrease in HbA1c at 1-year and 3-years compared to having none (all p-values <0.05). ConclusionsLower residential density and better proximity to supermarkets may benefit HbA1c control in people with people with type 2 diabetes. However, effects were small and indicate limited clinical significance.

Talc and calcium carbonate inclusions in direct expanded pea starch extrudates exhibit different behavior under increasing screw speeds.

The ability to modulate direct expanded product structures improves the versatility and range of product applications. The effect of nucleating agents, namely, talc and calcium carbonate (CC), on the expansion characteristics of pea starch extrudates as impacted by screw speed was explored. Pea starch blends with increasing levels of nucleating agents (0.25%, 1%, and 2%) at 18% moisture (w.b.) were extruded across a range of screw speeds (150, 250, 350, and 450rpm). The water absorption index, water solubility index (WSI), expansion ratio (ER), unit density, and cell count were determined to evaluate the performance of nucleating agents. The nucleating efficiency of CC, as assessed by cell count, improved with increasing screw speeds. In contrast, the nucleating efficiency of talc was influenced by inclusion levels irrespective of screw speed. ER values ranged from 2.10 to 2.88, where higher nucleating agent inclusions and screw speeds corresponded with lower ER values. Increased nucleating agents and screw speeds corresponded to higher WSI values suggesting the nucleating agents promoted starch degradation. The nucleating agents appeared to promote flow instabilities indicated upon assessment of the extrudate surface. PRACTICAL APPLICATION: This study provides helpful information on the expanded extrudate structure of pea starch as influenced by screw speed and nucleating agents. These findings may help the food industry select processing parameters and appropriate nucleating agent inclusion levels when producing new expanded products with unique textures.

Big Data Anomaly Prediction Algorithm of Smart City Power Internet of Things Based on Parallel Random Forest

Abstract Conventional power data prediction algorithms easily lead to the loss of key power data in a complex wireless network environment. Therefore, a power big data anomaly prediction algorithm based on parallel random forest is proposed. According to the power big data anomaly prediction algorithm based on parallel random forest, a network power big data anomaly prediction algorithm platform is established, and based on the platform, key data features such as user address and power transmission packet structure are extracted according to the category of power users. According to the relationship between power shunt function value and power data unit density, the parameter value of the system and finally the reasonable anomaly prediction of power big data in wireless network are determined. Finally, filter the classified data through attribute reduction and gene expression programming algorithm to obtain the data to be encrypted and complete the research on the anomaly prediction algorithm of power big data. Experimental results show that the proposed algorithm has better prediction performance and can ensure better data prediction effect.

Interval prediction of sinter screening index based on gate recurrent unit and kernel density estimation algorithm

Since there are many uncertain factors in the actual production process, reliable information cannot be obtained from point prediction results. Therefore, this paper proposes an interval prediction method to evaluate the screening index. Firstly, feature engineering algorithms are used to select the most suitable data and variables for modeling. Secondly, based on the sequential characteristics of the sintering process, the gated cycle unit (GRU) model is used to make point predictions on the indicators. then the kernel density estimation (KDE) algorithm is used to quantify the error of the index to obtain the interval prediction results, and the RandomizedSearchCV algorithm is used to optimize the parameters of the model. Finally, comparison shows that the GRU model has higher point prediction accuracy, and the KDE algorithm can better quantify the prediction error, and then obtain reliable interval prediction results. This method has guiding significance for the high-quality production of sinter.