Predicting Human Discretion to Adjust Algorithmic Prescription: A Large-Scale Field Experiment in Warehouse Operations

2021 ◽  
Author(s):  
Jiankun Sun ◽  
Dennis J. Zhang ◽  
Haoyuan Hu ◽  
Jan A. Van Mieghem
Keyword(s):  
Field Experiment ◽  
Operations Management ◽  
Large Scale ◽  
Bin Packing ◽  
Optimization Algorithms ◽  
Machine Learning Techniques ◽  
Control Group ◽  
Original Algorithm ◽  
Conventional Optimization ◽  
Packing Time

Conventional optimization algorithms that prescribe order packing instructions (which items to pack in which sequence in which box) focus on box volume utilization yet tend to overlook human behavioral deviations. We observe that packing workers at the warehouses of the Alibaba Group deviate from algorithmic prescriptions for 5.8% of packages, and these deviations increase packing time and reduce operational efficiency. We posit two mechanisms and demonstrate that they result in two types of deviations: (1) information deviations stem from workers having more information and in turn better solutions than the algorithm; and (2) complexity deviations result from workers’ aversion, inability, or discretion to precisely implement algorithmic prescriptions. We propose a new “human-centric bin packing algorithm” that anticipates and incorporates human deviations to reduce deviations and improve performance. It predicts when workers are more likely to switch to larger boxes using machine learning techniques and then proactively adjusts the algorithmic prescriptions of those “targeted packages.” We conducted a large-scale randomized field experiment with the Alibaba Group. Orders were randomly assigned to either the new algorithm (treatment group) or Alibaba’s original algorithm (control group). Our field experiment results show that our new algorithm lowers the rate of switching to larger boxes from 29.5% to 23.8% for targeted packages and reduces the average packing time of targeted packages by 4.5%. This idea of incorporating human deviations to improve optimization algorithms could also be generalized to other processes in logistics and operations. This paper was accepted by Charles Corbett, operations management.

Biodata response elaboration: A large-scale field experiment

2010 ◽  
Author(s):  
Julia Levashina ◽  
Frederick P. Morgeson ◽  
Michael A. Campion
Keyword(s):  
Field Experiment ◽  
Large Scale ◽  
Scale Field ◽  
Large Scale Field

Evaluation of Ovaries in Patients with Polycystic Ovary Syndrome using Shear Wave Elastography

2020 ◽  
Vol 16 (5) ◽  
pp. 578-583
Author(s):  
Aysegul Altunkeser ◽  
Zeynep Ozturk Inal ◽  
Nahide Baran
Keyword(s):  
Shear Wave ◽  
Large Scale ◽  
Polycystic Ovary ◽  
Shear Wave Elastography ◽  
Left Ovary ◽  
Control Group ◽  
Tissue Elasticity ◽  
Group I ◽  
Pcos Group ◽  
The Right

Background: Shear wave electrography (SWE) is a novel non-invasive imaging technique which demonstrate tissue elasticity. Recent research evaluating the elasticity properties of normal and pathological tissues emphasize the diagnostic importance of this technique. Aims: Polycystic ovarian syndrome (PCOS), which is characterized by menstrual irregularity, hyperandrogenism, and polycystic overgrowth, may cause infertility. The aim of this study was to evaluate the elasticity of ovaries in patients with PCOS using SWE. Methods: 66 patients diagnosed with PCOS according to the Rotterdam criteria (PCOS = group I) and 72 patients with non-PCOS (Control = group II), were included in the study. Demographic and clinical characteristics of the participants were recorded. Ovarian elasticity was assessed in all patients with SWE, and speed values were obtained from the ovaries. The elasticity of the ovaries was compared between the two groups. Results: While there were statistically significant differences between the groups in body mass index (BMI), right and left ovarian volumes, luteinizing hormone and testosterone levels (p<0.05), no significant differences were found between groups I and II in the velocity (for the right ovary 3.89±1.81 vs. 2.93±0.72, p=0.301; for the left ovary 2.88±0.65 vs. 2.95±0.80, p=0.577) and elastography (for the right ovary 36.62±17.78 vs. 36.79±14.32, p=0.3952; for the left ovary 36.56±14.15 vs. 36.26±15.10, p=0.903) values, respectively. Conclusion: We could not obtain different velocity and elastography values from the ovaries of the patients with PCOS using SWE. Therefore, further large-scale studies are needed to elucidate this issue.

scholarly journals Optimizing Manufacturing and Osseointegration of Ti6Al4V Implants through Precision Casting and Calcium and Phosphorus Ion Implantation? In Vivo Results of a Large-Scale Animal Trial

Materials ◽  
2020 ◽  
Vol 13 (7) ◽  
pp. 1670 ◽  
Author(s):  
Wölfle-Roos JV ◽  
Katmer Amet B ◽  
Fiedler J ◽  
Michels H ◽  
Kappelt G ◽  
...  
Keyword(s):  
Ion Implantation ◽  
Large Scale ◽  
In Vivo Studies ◽  
Control Group ◽  
Implant Surface ◽  
Precision Casting ◽  
Pull Out ◽  
Significant Difference ◽  
Calcium And Phosphorus

Background: Uncemented implants are still associated with several major challenges, especially with regard to their manufacturing and their osseointegration. In this study, a novel manufacturing technique—an optimized form of precision casting—and a novel surface modification to promote osseointegration—calcium and phosphorus ion implantation into the implant surface—were tested in vivo. Methods: Cylindrical Ti6Al4V implants were inserted bilaterally into the tibia of 110 rats. We compared two generations of cast Ti6Al4V implants (CAST 1st GEN, n = 22, and CAST 2nd GEN, n = 22) as well as cast 2nd GEN Ti6Al4V implants with calcium (CAST + CA, n = 22) and phosphorus (CAST + P, n = 22) ion implantation to standard machined Ti6Al4V implants (control, n = 22). After 4 and 12 weeks, maximal pull-out force and bone-to-implant contact rate (BIC) were measured and compared between all five groups. Results: There was no significant difference between all five groups after 4 weeks or 12 weeks with regard to pull-out force (p > 0.05, Kruskal Wallis test). Histomorphometric analysis showed no significant difference of BIC after 4 weeks (p > 0.05, Kruskal–Wallis test), whereas there was a trend towards a higher BIC in the CAST + P group (54.8% ± 15.2%), especially compared to the control group (38.6% ± 12.8%) after 12 weeks (p = 0.053, Kruskal–Wallis test). Conclusion: In this study, we found no indication of inferiority of Ti6Al4V implants cast with the optimized centrifugal precision casting technique of the second generation compared to standard Ti6Al4V implants. As the employed manufacturing process holds considerable economic potential, mainly due to a significantly decreased material demand per implant by casting near net-shape instead of milling away most of the starting ingot, its application in manufacturing uncemented implants seems promising. However, no significant advantages of calcium or phosphorus ion implantation could be observed in this study. Due to the promising results of ion implantation in previous in vitro and in vivo studies, further in vivo studies with different ion implantation conditions should be considered.

An Internet-based health gateway device for interactive communication and automatic data uploading: Clinical efficacy for type 2 diabetes in a multi-centre trial

2016 ◽  
Vol 23 (6) ◽  
pp. 595-604 ◽  
Author(s):  
Jae Hyoung Cho ◽  
Hun-Sung Kim ◽  
Seung Hyun Yoo ◽  
Chang Hee Jung ◽  
Woo Je Lee ◽  
...  
Keyword(s):  
Adverse Events ◽  
Healthcare System ◽  
Glucose Control ◽  
Large Scale ◽  
Diabetes Management ◽  
Intervention Group ◽  
Diabetes Control ◽  
Control Group ◽  
Anthropometric Parameters ◽  
Automatic Data

Introduction The aim of this study was to improve the quality of diabetes control and evaluate the efficacy of an Internet-based integrated healthcare system for diabetes management and safety. Methods We conducted a large-scale, multi-centre, randomized clinical trial involving 484 patients. Patients in the intervention group ( n = 244) were treated with the Internet-based system for six months, while the control group ( n = 240) received the usual outpatient management over the same period. HbA1c, blood chemistries, anthropometric parameters, and adverse events were assessed at the beginning of the study, after three months, and the end of the study. Results There were no initial significant differences between the groups with respect to demographics and clinical parameters. Upon six-month follow-up, HbA1c levels were significantly decreased from 7.86 ± 0.69% to 7.55 ± 0.86% within the intervention group ( p < 0.001) compared to 7.81 ± 0.66% to 7.70 ± 0.88% within the control group. Postprandial glucose reduction was predominant. A subgroup with baseline HbA1c higher than 8% and good compliance achieved a reduction of HbA1c by 0.8 ± 1.05%. Glucose control and waist circumference reduction were more effective in females and subjects older than 40 years of age. There were no adverse events associated with the intervention. Discussion This e-healthcare system was effective for glucose control and body composition improvement without associated adverse events in a multi-centre trial. This system may be effective in improving diabetes control in the general population.

The effect of preloading statins prior to primary reperfusion on in-hospital mortality risk in a contemporary large-scale cohort of patients with ST-elevation myocardial infarction

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
R Fu ◽  
C.X Song ◽  
X.D Li ◽  
Y.J Yang
Keyword(s):  
Myocardial Infarction ◽  
Acute Myocardial Infarction ◽  
Hospital Mortality ◽  
Mortality Risk ◽  
Large Scale ◽  
Reperfusion Therapy ◽  
St Elevation Myocardial Infarction ◽  
Control Group ◽  
Funding Source ◽  
St Elevation

Abstract Background The benefit of statins in secondary prevention of patients stabilized after acute coronary syndrome (ACS) has been well established. However, the benefit of preloading statins, i.e. high-intensity statins prior to reperfusion therapy remains unclear. Most previous studies included all types of ACS patients, and subgroup analysis indicated the benefit of preloading statins was only seen in ST-elevation myocardial infarction (STEMI) patients who underwent percutaneous coronary intervention (PCI). However, the sample size of subgroup population was relatively small and such benefit requires further validation. Objective To investigate the effect of loading dose of statins before primary reperfusion on 30-mortality in patients with STEMI. Methods We enrolled patients in China Acute Myocardial Infarction (CAMI) registry from January 2013 to September 2014. CAMI registry was a prospective multicenter registry of patients with acute acute myocardial infarction in China. Patients were divided into two groups according to statins usage: preloading group and control group. Patients in preloading group received loading does of statins before primary reperfusion and during hospitalization. Patients in control group did not receive statins during hospitalization or at discharge. Primary outcome was in-hospital mortality. Baseline characteristics, angiographic characteristics and outcome were compared between groups. Propensity score (PS) matching was used to mitigate baseline differences between groups and examine the association between preloading statins on in-hospital mortality risk. The following variables were used to establish PS matching score: age, sex, classification of hospitals, clinical presentation (heart failure at presentation, cardiac shock, cardiac arrest, Killip classification), hypertension, diabetes, prior angina, prior myocardial infarction history, prior stroke, initial treatment. Results A total of 1169 patients were enrolled in control group and 6795 in preloading group. A total of 833 patients (334 in control group and 499 in preloading group) died during hospitalization. Compared with control group, preloading group were younger, more likely to be male and present with Killip I classification. The proportion of hypertension and diabetes were higher in preloading group. After PS matching, all the variables used to generate PS score were well balanced. In the PS-matched cohort, 30-day mortality risk was 26.3% (292/1112) in the control group and 11.9% (132/1112) in the preloading group (p&lt;0.0001). Conclusions The current study found preloading statins treatment prior to reperfusion therapy reduced in-hospital mortality risk in a large-scale contemporary cohort of patients with STEMI. Funding Acknowledgement Type of funding source: Public Institution(s). Main funding source(s): Chinese Academy of Medical Sciences

scholarly journals Comparison of the curative effect and prognosis of stereotactic drainage and conservative treatment for moderate and small basal ganglia haemorrhage

BMC Neurology ◽  
2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Xin Huang ◽  
Lai Jiang ◽  
Shaojun Chen ◽  
Gang Li ◽  
Wanxi Pan ◽  
...  
Keyword(s):  
Basal Ganglia ◽  
Large Scale ◽  
Neurological Function ◽  
Lower Limbs ◽  
Control Group ◽  
Roc Curve Analysis ◽  
Curative Effect ◽  
Nihss Score ◽  
Haematoma Volume ◽  
Experimental Group

Abstract Background Minimally invasive surgery has achieved good results in the treatment of cerebral haemorrhage.However, no large-scale clinical study has demonstrated that surgical treatment of cerebral haemorrhages less than 30 ml can improve the curative effect. Our study explored the efficacy and complication of stereotactic drainage based on the amount of cerebral hemorrhage (15-30 ml) in hypertensive basal ganglia. Method Sixty patients with hypertensive basal ganglia haemorrhages were divided into a control group and an experimental group with 30 patients in each group. Patients in the control group were treated conservatively. In contrast, those in the experimental group received stereotactic drainage, and urokinase was injected into the haematoma cavity after the operation. The haematoma volume at admission and 1, 3, 7 and 30 days after treatment and National Institute of Health stroke scale(NIHSS) score data were recorded. Complications after treatment in the two groups of data were compared and analysed. Result No significant differences in age, sex, time of treatment after onset, admission blood pressure, admission haematoma volume or admission NIHSS score were noted between these two groups (P > 0.05). After treatment, significant differences in haematoma volume were noted between the two groups on the 1st, 3rd, 7th and 30th days after treatment (P < 0.05). The amount of hematoma of patients in the experimental group was significantly reduced compared with that in the control group, and the NIHSS scores were significantly different on the 3rd, 7th and 30th days after treatment. The neurological deficit scores of patients in the experimental group were significantly reduced compared with those in the control group, and the incidence of pulmonary infection and venous thrombosis in the lower limbs of patients in the experimental group were significantly reduced (P < 0.05). ROC curve analysis showed that stereotactic drainage affected the early neurological function of patients with small and medium basal ganglia haemorrhages. Conclusion For patients with small and medium basal ganglia haemorrhages, stereotactic drainage can be used due to the faster drainage speed of haematomas after operation, which is beneficial to the recovery of neurological function and reduce complications.

scholarly journals EEG Data Quality: Determinants and Impact in a Multicenter Study of Children, Adolescents, and Adults with Attention-Deficit/Hyperactivity Disorder (ADHD)

2021 ◽  
Vol 11 (2) ◽  
pp. 214
Author(s):  
Anna Kaiser ◽  
Pascal-M. Aggensteiner ◽  
Martin Holtmann ◽  
Andreas Fallgatter ◽  
Marcel Romanos ◽  
...  
Keyword(s):  
Data Quality ◽  
Large Scale ◽  
Linear Models ◽  
Spectral Power ◽  
Control Group ◽  
Continuous Performance Task ◽  
Related Data ◽  
Eyes Closed ◽  
Eeg Data ◽  
Eyes Open

Electroencephalography (EEG) represents a widely established method for assessing altered and typically developing brain function. However, systematic studies on EEG data quality, its correlates, and consequences are scarce. To address this research gap, the current study focused on the percentage of artifact-free segments after standard EEG pre-processing as a data quality index. We analyzed participant-related and methodological influences, and validity by replicating landmark EEG effects. Further, effects of data quality on spectral power analyses beyond participant-related characteristics were explored. EEG data from a multicenter ADHD-cohort (age range 6 to 45 years), and a non-ADHD school-age control group were analyzed (ntotal = 305). Resting-state data during eyes open, and eyes closed conditions, and task-related data during a cued Continuous Performance Task (CPT) were collected. After pre-processing, general linear models, and stepwise regression models were fitted to the data. We found that EEG data quality was strongly related to demographic characteristics, but not to methodological factors. We were able to replicate maturational, task, and ADHD effects reported in the EEG literature, establishing a link with EEG-landmark effects. Furthermore, we showed that poor data quality significantly increases spectral power beyond effects of maturation and symptom severity. Taken together, the current results indicate that with a careful design and systematic quality control, informative large-scale multicenter trials characterizing neurophysiological mechanisms in neurodevelopmental disorders across the lifespan are feasible. Nevertheless, results are restricted to the limitations reported. Future work will clarify predictive value.

scholarly journals Analysis of Risk Factors in Dementia Through Machine Learning

2020 ◽  
pp. 1-17
Author(s):  
Francisco Javier Balea-Fernandez ◽  
Beatriz Martinez-Vega ◽  
Samuel Ortega ◽  
Himar Fabelo ◽  
Raquel Leon ◽  
...  
Keyword(s):  
Machine Learning ◽  
Optimization Algorithms ◽  
Progressive Increase ◽  
Control Group ◽  
Data Sets ◽  
Modifiable Factors ◽  
Validation Set ◽  
The One ◽  
And Control ◽  
Potential Tool

Background: Sociodemographic data indicate the progressive increase in life expectancy and the prevalence of Alzheimer’s disease (AD). AD is raised as one of the greatest public health problems. Its etiology is twofold: on the one hand, non-modifiable factors and on the other, modifiable. Objective: This study aims to develop a processing framework based on machine learning (ML) and optimization algorithms to study sociodemographic, clinical, and analytical variables, selecting the best combination among them for an accurate discrimination between controls and subjects with major neurocognitive disorder (MNCD). Methods: This research is based on an observational-analytical design. Two research groups were established: MNCD group (n = 46) and control group (n = 38). ML and optimization algorithms were employed to automatically diagnose MNCD. Results: Twelve out of 37 variables were identified in the validation set as the most relevant for MNCD diagnosis. Sensitivity of 100%and specificity of 71%were achieved using a Random Forest classifier. Conclusion: ML is a potential tool for automatic prediction of MNCD which can be applied to relatively small preclinical and clinical data sets. These results can be interpreted to support the influence of the environment on the development of AD.

Power of d Choices for Large-Scale Bin Packing

2015 ◽  
Vol 43 (1) ◽  
pp. 321-334 ◽  
Author(s):  
Qiaomin Xie ◽  
Xiaobo Dong ◽  
Yi Lu ◽  
Rayadurgam Srikant
Keyword(s):  
Large Scale ◽  
Bin Packing
Sign in / Sign up

Export Citation Format

Share Document