Centroid Values Research Articles

Fe7S8 coupled with VS4 heterogeneous interface engineering driven by FeV bimetallic MOFs: An efficient all-pH and durable hydrogen evolution

Rational design and preparation of a multiphase electrocatalyst for hydrogen evolution reaction (HER) has become a hot research topic, while applicable and pH versatility of vanadium tetrasulfide (VS4) and heptairon octasulfide (Fe7S8) composites have rarely been reported. Here, the facile topological sulfide self-template sacrifice method using FeV bimetallic MOFs is designed to obtain Fe7S8 coupled with VS4 heterostructures, enhancing the electron precipitation in the catalysts and attracts electrons to migrate. According to DFT simulations, the electronic coupling at the atomic orbital level and the modulation of interfacial electrons among various interfaces play a crucial role in enhancing the intermediate state process of the hydrogen evolution reaction (HER) across the entire pH range, promoting the optimal d-band centroid value (εd). Reassuringly, the prepared 3D Fe7S8/VS4 electrodes possessed excellent performances of η10 = 53 mV, η10 = 135 mV and η10 = 38 mV in a conventional three-electrode configuration in a 1 M KOH, 1 M Na2SO4, and 0.5 M H2SO4, and the stabilized currents can all be maintained for 48 h. This innovative design of in situ heterostructured materials constructed from dual transition metal sulfides provides inspiring ideas for the preparation of all-pH catalysts.

Decoding characteristics of key physical properties in silver nanoparticles by attaining centroids for cytotoxicity prediction through data cleansing

This research underscores the profound impact of data cleansing, ensuring dataset integrity and providing a structured foundation for unraveling convoluted connections between diverse physical properties and cytotoxicity. As the scientific community delves deeper into this interplay, it becomes clear that precise data purification is a fundamental aspect of investigating parameters within datasets. The study presents the need for data filtration in the background of machine learning (ML) that has widened its horizon into the field of biological application through the amalgamation of predictive systems and algorithms that delve into the intricate characteristics of cytotoxicity of nanoparticles. The reliability and accuracy of models in the ML landscape hinge on the quality of input data, making data cleansing a critical component of the pre-processing pipeline. The main encounter faced here is the lengthy, broad and complex datasets that have to be toned down for further studies. Through a thorough data cleansing process, this study addresses the complexities arising from diverse sources, resulting in a refined dataset. The filtration process employs K-means clustering to derive centroids, revealing the correlation between the physical properties of nanoparticles, viz, concentration, zeta potential, hydrodynamic diameter, morphology, and absorbance wavelength, and cytotoxicity outcomes measured in terms of cell viability. The cell lines considered for determining the centroid values that predicts the cytotoxicity of silver nanoparticles are human and animal cell lines which were categorized as normal and carcinoma type. The objective of the study is to simplify the high-dimensional data for accurate analysis of the parameters that affect the cytotoxicity of silver NPs through centroids.

Re-examination of effects of pairing gaps on charge-changing transitions

We re-examine the effects of pairing gaps on charge-changing transitions and the associated β-decay half-lives. Calculations are performed using the proton-neutron quasiparticle random phase approximation (pn-QRPA) model for 250 nuclei possessing astrophysical significance. Pairing gaps between like nucleons are key model parameters in the pn-QRPA approach. Three different values of empirically computed pairing gaps were used as input parameters in our nuclear model. Changing the pairing gap values significantly altered the Gamow-Teller distributions including the total strength and centroid values. The β-decay half-lives also changed substantially. The half-lives computed via the three-term pairing formula, based on separation energies of nucleons, were in best agreement with the measured data.

Nuclear structure properties and weak interaction rates of even–even Fe isotopes

Nuclear structure properties and weak interaction rates of neutron-rich even–even iron (Fe) isotopes (A = 50 – 70) are investigated using the Interacting Boson Model-1 (IBM-1) and the proton–neutron Quasiparticle Random Phase Approximation (pn-QRPA) model. The IBM-1 is used for the calculation of energy levels and the B(E2) values of neutron-rich Fe isotopes. Later their geometry was predicted within the potential energy formalism of the IBM-1 model. Weak interaction rates on neutron-rich nuclei are needed for the modeling and simulation of presupernova evolution of massive stars. In the current study, we investigate the possible effect of nuclear deformation on stellar rates of even–even Fe isotopes. The pn-QRPA model is applied to calculate the weak interaction rates of selected Fe isotopes using three different values of deformation parameter. It is noted that, in general, bigger deformation values led to smaller total strength and larger centroid values of the resulting Gamow–Teller distributions. This later translated to smaller computed weak interaction rates. The current finding warrants further investigation before it may be generalized. The reported stellar rates are up to 4 orders of magnitude smaller than previous calculations and may bear astrophysical significance.

Prediction of Graduation Accuracy Using the K-Means Clustering Algorithm and Classification Decision Tree

Becoming a scholar at the right time for students is a very meaningful award for them if it is supported by seriousness and perseverance in their studies. Here, sample data was taken from 131 randomly taken in testing. Where there are still students who are not detected by the study program in completing their lectures, so research is carried out on clustering and classification with decision trees in determining the level of accuracy of lectures by clustering data, determining the initial centroid value and the centroid point. The results found were that there were 78 people grouped in cluster 0 and 53 people grouped in cluster 1, where those with potential for punctuality for their studies were in cluster 0 so they were students who could finish within the specified time. Meanwhile, students grouped in cluster 1 illustrate that these students need coaching and guidance both in the study program and with their supervisors. In the classification taken from the results of data clustering, two classes were obtained, namely class a and class b, with 73 and 58 data respectively, so that the results between clustering and classification did not differ too much in the data to predict the accuracy of a student's graduation.

Neurological activation during verbal fluency task and resting-state functional connectivity abnormalities in obsessive-compulsive disorder: a functional near-infrared spectroscopy study.

This study aims to investigate the activation of frontotemporal functional brain areas in patients with Obsessive-Compulsive Disorder (OCD) during a Verbal Fluency Task (VFT), and to compare their brain functional connectivity in a resting state with that of healthy controls. The goal is to deepen our understanding of the neuropathological mechanisms underlying OCD. 32 patients with OCD and 32 controls matched for age, gender, handedness, and years of education participated in this study, they were divided into OCD group and healthy comtrol group. We conducted VFT task tests and 10-minute resting state tests on both groups by using functional Near-Infrared Spectroscopy (fNIRS). The VFT was utilized to assess the activation (beta values) and the integral and centroid values of the frontal and bilateral temporal lobes, including brain areas BA9 and 46 (dorsolateral prefrontal cortex), BA10 (frontal pole), BA45 (inferior frontal gyrus), BA21 (middle temporal gyrus), and BA22 (superior temporal gyrus). We evaluated the functional connectivity levels of these areas during the resting state. Differences in these measures between OCD patients and healthy controls were analyzed using two-sample independent t-tests and non-parametric Mann-Whitney U tests. During VFT, OCD had smaller integral values(z=5.371, p<0.001; t=4.720, p<0.001), and larger centroid values(t=-2.281, p=0.026; z=-2.182, p=0.029) compared to healthy controls, along with a reduced number of activated channels detected by fNIRS. Additionally, activation values (β) in various functional brain areas, including BA9, BA46, BA10, BA45, BA21, and BA22, were significantly lower in the OCD group (all p< 0.01). In the resting state, notable disparities in functional connectivity were observed between the inferior frontal gyrus (IFG) and dorsolateral prefrontal cortex (DLPFC) in the OCD group, in comparison to the control group. Specifically, there was a significant increase in connectivity between the left IFG and right DLPFC, suggesting the presence of altered connectivity patterns in these areas. The study highlights significant disparities in neural activation and functional connectivity between OCD patients and healthy controls during VFT. Specifically, reduced activation was noted in the frontal and bilateral temporal lobes of OCD patients, alongside alterations in resting-state functional connectivity between the IFG and DLPFC. These findings contribute to our understanding of the neurobiological underpinnings of OCD and may guide future therapeutic strategies.

K-Means Algorithm Method for Clustering Best-Selling Product Data at XYZ Grocery Stores

This study aims to utilize the K-means clustering algorithm in data mining to categorize sales data at XYZ Grocery store. The research is essential for understanding sales patterns and enhancing inventory management strategies. The research methodology involves implementing the K-means clustering algorithm to generate centroid values for each cluster, thereby creating groups of products based on their sales performance. The findings of this study are expected to provide insights into sales trends at the store. While the abstract provides a general overview, specific results and contributions of this research are not detailed. Further studies could offer a more in-depth understanding of the practical applications of these findings in improving store management and inventory control.

Optimal planning target margin for prostate radiotherapy based on interfractional and intrafractional variability assessment during 1.5T MRI-guided radiotherapy.

We analyzed daily pre-treatment- (PRE) and real-time motion monitoring- (MM) MRI scans of patients receiving definitive prostate radiotherapy (RT) with 1.5 T MRI guidance to assess interfractional and intrafractional variability of the prostate and suggest optimal planning target volume (PTV) margin. Rigid registration between PRE-MRI and planning CT images based on the pelvic bone and prostate anatomy were performed. Interfractional setup margin (SM) and interobserver variability (IO) were assessed by comparing the centroid values of prostate contours delineated on PRE-MRIs. MM-MRIs were used for internal margin (IM) assessment, and PTV margin was calculated using the van Herk formula. We delineated 400 prostate contours on PRE-MRI images. SM was 0.57 ± 0.42, 2.45 ± 1.98, and 2.28 ± 2.08 mm in the left-right (LR), anterior-posterior (AP), and superior-inferior (SI) directions, respectively, after bone localization and 0.76 ± 0.57, 1.89 ± 1.60, and 2.02 ± 1.79 mm in the LR, AP, and SI directions, respectively, after prostate localization. IO was 1.06 ± 0.58, 2.32 ± 1.08, and 3.30 ± 1.85 mm in the LR, AP, and SI directions, respectively, after bone localization and 1.11 ± 0.55, 2.13 ± 1.07, and 3.53 ± 1.65 mm in the LR, AP, and SI directions, respectively, after prostate localization. Average IM was 2.12 ± 0.86, 2.24 ± 1.07, and 2.84 ± 0.88 mm in the LR, AP, and SI directions, respectively. Calculated PTV margin was 2.21, 5.16, and 5.40 mm in the LR, AP, and SI directions, respectively. Movements in the SI direction were the largest source of variability in definitive prostate RT, and interobserver variability was a non-negligible source of margin. The optimal PTV margin should also consider the internal margin.

Optimasi Pelayanan Kapal Penumpang melalui Clustering Penumpang dengan Metode Silhouette Coefficient

Improving the efficiency of passenger ship services is a big challenge for the shipping industry. This research aims to optimize ship passenger services at Muara angke port by segmenting passengers using the Silhouette Coefficient method. This research uses the k-means algorithm and the Silhouette Coefficient method in order to get passenger clusters based on boarding passengers and disembarking passengers. The Silhouette Coefficient method in this research is used to find the number of clusters. The dataset used is passenger data from January 1 - December 31, 2021. The results showed that 2 clusters were obtained, namely the highest cluster (C1) and the lowest cluster (C2) from the k-means algorithm with the results of the centroid value obtained for cluster 1 passengers up, namely 53,414 and passengers down, namely 54,585, the centroid value obtained for cluster 2 passengers up, namely 596,396 and passengers down, namely 532,455. The value with the Silhouette Coefficient method is obtained 0.704 in cluster 1 for the highest cluster there are 2091 data with a percentage value of 57.27% and 0.548 in cluster 2 for the lowest cluster there are 1560 data with a presentation value of 42.73%. The Silhouette Coefficient value is close to the value of 1, which means that the Muara angke port is good enough in optimizing passenger services.

Wind turbine blade damage detection and classification based on sound feature signal using machine learning

Wind turbine blades experience variable environmental conditions and are prone to failure due to fatigue and weather-induced damage. In this study, the aerodynamic sound signal of wind turbine blades is collected while in operation. Short-Time Fourier Transform method identified and used to analyze the periodic signal of the rotation of the wind turbine blades. The spectral centroid of the pulse signal and the variation of the corresponding three blades spectral centroid are extracted as the input features for supervised machine learning. Gaussian mixture model algorithm classified features and used with blades damage trend for structural health monitoring. Through the Gaussian mixture model established by using the mean value and standard deviation of the peak value of the spectral centroid, the results after the model test show the accuracy of the damaged blade judgment can reach 98 %. In addition, from the visual classification chart, it can be known that the blade will enter the damage state, and maintenance should be carried out in advance to avoid damage to the blade and maintain the stable operation of the wind turbine.

Prefrontal cortex functional connectivity changes during verbal fluency test in adults with short-term insomnia disorder: a functional near-infrared spectroscopy study.

Individuals suffering from short-term insomnia disorder (SID) experience difficulties in falling or staying asleep, often leading to daytime fatigue and impaired concentration. However, the underlying mechanisms of SID remain unclear. This study aims to investigate the alterations in brain activation patterns and functional connectivity in patients with SID. The study enrolled a total of 31 adults diagnosed with SID and 31 healthy controls (HC). Functional near-infrared spectroscopy (fNIRS) was utilized to assess the concentrations of oxyhemoglobin (Oxy-Hb) and functional connectivity in the prefrontal cortex of each participant while performing the verbal fluency test (VFT) task. In the VFT task, no significant difference was found between the SID group and the HC group in terms of integral values, centroid values, and mean Oxy-Hb variations. These findings suggest that both groups exhibit similar hemodynamic responses. However, the functional connectivity analysis revealed significant differences in inter-channel connectivity strength between the two groups. The SID group showed significantly lower average inter-channel connectivity strength compared to the HC group. Moreover, six channel pairs (right frontopolar cortex - left frontopolar cortex, left orbitofrontal cortex - left temporopolar cortex, left temporopolar cortex - left frontopolar cortex, left frontopolar cortex-Ch38, left frontopolar cortex - right pre-motor and supplementary motor cortex, and left frontopolar cortex - right dorsolateral prefrontal cortex) exhibited significantly higher connectivity strength in the HC group compared to the SID group (FDR corrected, p < 0.05). Specifically, channel 27 exhibited the highest frequency of significant connectivity across different channel pairs, occurring five times in total. The channel pair Ch27-Ch39, representing left frontopolar cortex and right dorsolateral prefrontal cortex, exhibited a negative correlation with PSQI scores (r = -0.422, p = 0.018). Our findings suggest that patients with SID may exhibit altered brain connectivity during the VFT task, as measured by fNIRS. These results provide valuable insights into the functional brain differences associated with SID. Further research is needed to validate and expand upon these findings.

An Adaptive Fuzzy C-Means segmentation and deep learning model for efficient mammogram classification using VGG-Net

Breast cancer mortality can be prevented by only early, accurate mammography screening and diagnosis. Although CNN-based computer-aided diagnosis (CAD) systems for breast cancer have made tremendous progress recently, accurate identification of mammography lesions is still difficult because of poor signal-to-noise ratio (SNR) and physiological features. In this manuscript, an Adaptive Fuzzy C-Means Segmentation and Deep Learning Model for Efficient Mammogram Classification Using VGG-Net (AFCM-DCNN) is proposed. The input image is given to Grey Code Approximation Pre-processing (GCAP) algorithm to enhance the quality of image by adjusting the pixel contrast. The preprocessed image is given to Adaptive Fuzzy C-Means (AFCM) algorithm and is applied in segmenting dominant regions in an input image. But in conventional AFCM technique, the centroid values get generated randomly, which consumes more computational time. Hence to enhance the performance of traditional AFCM, centroid value is optimally chosen by means of optimization algorithm. A technique for classifying images called DCNN analyses the input image and categorizes it as either benign, malignant and normal. The method extracts the features of the image and train with VGG-16 Net classifier. The neurons at the output layer have been designed to compute Class Centric Disease Support (CCDS) towards various classes. Accordingly, the mammogram class is identified towards detecting the brain tumor. The performance of the proposed method AFCM-DCNN exhibits higher accuracy of 29.3%, 25.6% and 24.6%, higher sensitivity of 15.4%, 16.6% compared with the existing methods. Therefore, in future work, hope to enhance the performance depending on transfer learning with similar data.

Fracture mechanical properties and identification of principal stress direction from the rock frequency domain

The characterization of rock instability precursors and the identification of principal stress direction are essential for the safety construction of underground engineering. This study explores the characterization of rock instability precursors from the frequency domain and identification of principal stress direction by the anisotropy of frequency variation. The results show that the dense distribution of peak frequency and frequency centroid in the high frequency domain, along with an increase in peak frequency bandwidth and a decrease in mean frequency centroid value, can be used as frequency domain criteria for rockburst prediction and early warning. Both peak frequency and frequency centroid are effective monitoring parameters for rock instability. The anisotropic frequency centroid variation can be used to identify the principal stress direction, and a process is proposed. This paper not only offers a valuable complement to existing methods for rock instability precursor and principal stress direction identification, but also provides a new analytical method for stability monitoring in rock engineering.

The cephalometric evaluation of the position of maxillary 1st permanent molar in class II division I malocclusion.

Objective: To conclude the sagittal position of the maxillary 1st permanent molar in class II division I malocclusion patients from lateral cephalogram. Study Design: “Descriptive” (“Cross-sectional study”). Setting: Dental OPD “Department of Orthodontics, University College of Medicine and Dentistry, The University of Lahore”. Study Period: 1st December 2021, till 30th May 2022. Material &amp; Methods: A total of 160 patients ensuring the confidentiality of their diagnostic data, lateral cephalometric was exposed and cephalometric tracing was done by placing mate acetate paper for evaluation of sagittal and vertical dysplasia. For the selected sample, the distance between the distal cusps of the “Maxillary” 1st permanent molar to the PTV line (Pterygoid Vertical) was assessed (PTV-U6). Distance between the PTV lines (Pterygoid Vertical) to the Maxillary Centroid was also calculated. To compare the mean of the variables i.e. PTV-U6 and PTV-Maxillary molar Centroid a student t-test was applied with a P-value ≤ 0.05 as significant. Results: The mean age of patients was 23.69 ± 3.72 years with minimum and maximum ages of 18 and 30 years. There were 73(45.62%) male and 87(54.38%) female cases with a higher female-to-male ratio. The mean PTV-U6 was 20.83 mm ± 2.14 mm with minimum and maximum values as 17 mm and 24.50 mm. The mean PTV-molar centroid value was 28.70 mm ± 0.88 mm with smallest and extreme values of 27.10 mm and 30.10 mm. Conclusion: It was concluded that the sagittal station of maxillary 1st perpetual molar in class II division I malocclusion patients from lateral cephalogram was found, hence by keeping these values of the local population the strategies can be designed as it may be helpful for the patients that many unwanted extractions can be avoided and treatment will be planned as no extraction.

Optimal Planning Target Margin for Prostate Radiotherapy Based on Interfractional and Intrafractional Variability Assessment during 1.5T MR-Guided Radiotherapy.

MR-guided radiotherapy (MRgRT) provides superior soft-tissue contrast over CT-based image guidance. We collected and analyzed daily pre-treatment (PRE) and real-time motion-monitoring (MM) MR images of patients receiving prostate radiotherapy to assess interfractional and intrafractional variability of prostate using two localization methods: pelvic bony anatomy (bone) and prostate during online adaptive radiotherapy (ART). PRE and MM MRIs for the first five fractions of twenty prostate cancer patients who received definitive MRgRT with 1.5T MRI were collected. Using MIM software, rigid registration between PRE MRI and planning CT images based on pelvic bony anatomy and prostate reproduced bone localization and online ART, respectively. To determine interfractional setup margin (SM), prostate was delineated on all PRE MRIs registered after bone and prostate localizations by a radiation oncologist, and centroid values of prostate contours between planning CT and PRE MRIs were compared. To determine interobserver variability, another radiation oncologist, a medical physicist, and a radiotherapist contoured prostate for both localization methods. For internal margin (IM) assessment, we used MM MRIs of the five patients who had all three sets of coronal, sagittal, and axial cine images and determined the maximum contour displacement using in-house MATLAB-based software converting binary image files to 2D cine images with a superimposed grid of 1 mm spacing. A total of 100 PRE and 25 MM MRIs were analyzed. Four hundred prostate contours were delineated on MR images registered with planning CT based on both bony anatomy and prostate. After bone localization, SM was 0.57±0.42 mm in left-right (LR), 2.45±1.98 mm in anterior-posterior (AP), and 2.28±2.08 mm in superior-inferior (SI) directions, and IO was 1.06±0.58 mm in LR, 2.32±1.08 mm in AP, and 3.30±1.85 mm in SI directions. After prostate localization, SM was 0.76±0.57 mm in LR, 1.89±1.60 mm in AP, and 2.2±1.79 mm in SI directions, and IO was 1.11±0.55 mm in LR, 2.13±1.07 mm in AP, and 3.53±1.65 mm in SI directions. Average IM was 2.12±0.86 mm, 2.24±1.07 mm, and 2.84±0.88 mm in LR, AP, and SI directions, respectively. Using daily MRIs from MRgRT, we showed that movements in the SI direction were the largest source of variability in prostate definitive RT. In addition, interobserver variability was a non-negligible source of margin. Optimal PTV margin should also consider internal margin, especially in the SI direction.

APPLICATION OF THE K-MEANS CLUSTERING METHOD FOR PERFORMANCE ASSESSMENT BASED ON EDUCATOR COMPETENCE

Performance appraisal is one thing to respect someone while working in an institution, one of which is a private higher education institution. To respect the performance of resources, there needs to be a value assigned to someone. Assessments carried out for one semester need to be reviewed again because during filling in the student assessments do not fill in according to their understanding so that a review needs to be carried out again. The assessment was carried out using the K-Means method by applying the concept of the centroid value. There are 4 (four) variables used, namely pedagogic competence, personal competence, social and professional competence with a value of K = 3. The maximum number of observations for cluster 3 is 368 while the value of Distances Between Cluster Centroids shows 2 suitable clusters, namely cluster 1 and cluster 2, which is 1.7020. The author gives suggestions to remove outlier data before entering the data to be trained into the algorithm to improve visualization if the dataset is large. Key Word: Performance Appraisal, Data Mining, K-Means

NIRS-aided differential diagnosis among patients with major depressive disorder, bipolar disorder, and schizophrenia

BackgroundTo establish a clinically applicable neuroimaging-guided diagnostic support system that uses near-infrared spectroscopy (NIRS) for differential diagnosis at the individual level among major depressive disorder (MDD), bipolar disorder (BPD), and schizophrenia (SZ). MethodsA total of 192 participants were recruited, including 40 patients with MDD, 38 patients with BPD, 65 patients with SZ, and 49 healthy individuals. We analyzed the spatiotemporal characteristics of hemodynamic responses in the frontotemporal cortex during a verbal fluency test (VFT) measured by NIRS to assess the accuracy of single-subject classification for differential diagnosis among the three psychiatric disorders. The optimal threshold of the frontal centroid value (54 seconds) was utilized on the basis of the findings of the Japanese study. ResultsThe application of the optimal threshold of the frontal centroid value (54 seconds) allowed for the accurate differentiation of patients with unipolar MDD (72.5%) from BPD (78.9%) or SZ (84.6%). ConclusionThese results suggest that the NIRS-aided differential diagnosis of major psychiatric disorders can be a promising biomarker in Taiwan. Future multi-site studies are needed to validate our findings.

Outcomes of peripheral corneal relaxing incisions for residual astigmatism in patients after cataract surgery.

To evaluate the outcomes of peripheral corneal relaxing incisions (PCRIs) for correcting residual astigmatism in eyes after cataract surgery. Cullen Eye Institute, Baylor College of Medicine, Houston, Texas. Retrospective case series. Retrospectively, we reviewed all consecutive cases that had previous cataract surgery and subsequent PCRIs by 1 surgeon. The PCRI length was determined according to a nomogram based on age and manifest refractive astigmatism. Visual acuity and manifest refractive astigmatism before and after the PCRIs were compared. Vector analysis was performed, and net refractive changes along the incision meridian were calculated. Criteria were met by 111 eyes. After the PCRIs, mean uncorrected visual acuity was significantly improved, and the percentage of eyes with uncorrected distance visual acuity of ≥20/20 increased significantly by 36%; the mean refractive astigmatism magnitude decreased significantly, and the percentages of eyes with refractive cylinder of ≤0.25 diopters (D) and ≤0.50 D increased significantly by 63% and 75%, respectively (all P < .05). The vector magnitude difference between pre- and post-operative refractive astigmatism was 0.88 ± 0.38 D. The postoperative refractive astigmatism had significantly smaller centroid and variance values than the preoperative refractive astigmatism ( P < .05). PCRIs are an effective approach for correcting low amounts of residual astigmatism in patients after cataract surgery.

Research on Road Sign Detection and Visual Depth Perception Technology for Mobile Robots

To accomplish the task of detecting and avoiding road signs by mobile robots for autonomous running, in this paper, we propose a method of road sign detection and visual depth perception based on improved Yolov5 and improved centroid depth value filtering. First, the Yolov5 model has a large number of parameters, a large computational volume, and a large model size, which is difficult to deploy to the CPU side (industrial control computer) of the robot mobile platform. To solve this problem, the study proposes a lightweight Yolov5-SC3FB model. Compared with the original Yolov5n model, the Yolov5-SC3FB model only loses lower detection accuracy, the parameter volume is reduced to 0.19 M, the computational volume is reduced to 0.5 GFLOPS, and the model size is only 0.72 MB, making it easy to deploy on mobile robot platforms. Secondly, the obtained depth value of the center point of the bounding box is 0 due to the influence of noise. To solve this problem, we proposed an improved filtering method for the depth value of the center point in the study, and the relative error of its depth measurement is only 2%. Finally, the improved Yolov5-SC3FB model is fused with the improved filtering method for acquiring centroid depth values and the fused algorithm is deployed to the mobile robot platform. We verified the effectiveness of this fusion algorithm for the detection and avoidance of road signs of the robot. Thus, it can enable the mobile robot to correctly perceive the environment and achieve autonomous running.

APPLICATION OF THE K-MEANS METHOD FOR CLUSTERING BEST SELLING PRODUCTS IN ICE CREAM SALES

From youngsters to adults, ice cream is a culinary item that is highly sought after by a variety of demographics. The ice cream combination, which includes a variety of culinary items including dairy products, sugars, stabilizers, flavor enhancers, and eggs, is frozen to create this dish. Aice Ice Cream has a wide variety of goods, which makes it popular with customers. According to various data that the author has observed from Agent Aice Harun, including the fact that there are still challenges in the stock of goods available to meet consumer demand, it is necessary to forecast sales of Ice Cream Aice products that are most in demand by consumers in order to facilitate stock provision. Due to these problems, the researchers conducted. The K-Means Clustering Algorithm approach will be applied manually during the clustering process, and Python data mining tools will be used for the implementation. The final calculation results are the same, showing that 48 things are the most desirable, 6 items are pretty attractive, and 6 items are less desirable, according to the results of determining centroid values arbitrarily using the Euclidian Distance formula manually using Python Tools. Agent Aice Harun is able to supply goods that are in line with consumer preferences as a result. Python computations and manual calculations get the same conclusion. Therefore, it is evident from these data that the accuracy value attained is 100%.