Error Cost Research Articles

AI-Driven Quality Control in PCB Manufacturing: Enhancing Production Efficiency and Precision

This paper investigates the application of Artificial Intelligence (AI) in enhancing quality control within Printed Circuit Board (PCB) manufacturing processes, focusing on how AI-driven technologies improve production efficiency and precision. The research addresses traditional quality control methods, such as manual inspection and Automated Optical Inspection (AOI), highlighting their limitations in keeping up with the complexities and demand for high-precision PCBs in modern electronics. The study delves into how AI technologies, particularly machine learning, computer vision, and predictive analytics, are being leveraged to overcome these limitations. By automating defect detection, improving accuracy, and enabling real-time analysis, AI systems not only streamline the quality control process but also significantly reduce human error and production costs. AI-driven quality control systems are shown to increase defect detection rates, reduce inspection times, and enhance overall production throughput. The paper includes a comparative analysis between traditional and AI-based quality control methods, revealing a notable improvement in both detection accuracy and production speed when AI systems are employed. Additionally, cost efficiency is explored, demonstrating how AI systems reduce waste, minimize rework, and lower operational costs. The potential challenges of AI implementation, such as the high initial costs, data requirements, and integration with legacy systems, are also discussed. The paper concludes that despite these challenges, AI offers a transformative solution to the growing demands of the PCB manufacturing industry, with the ability to scale effectively and adapt to future technological advancements. Ultimately, this research underscores the significant role of AI in revolutionizing PCB quality control by providing a more efficient, precise, and cost-effective approach, paving the way for further innovation in the electronics manufacturing sector.

Identification of Concrete Crack Using Deep Learning Based Approach

Cracks reflect the safety and durability of concrete structures, and the existing artificial crack detection has the disadvantages of low efficiency and large error. However, the use of deep learning of images to identify cracks has the advantages of high efficiency, small error and low cost. This paper systematically discusses the deep learning in the identification of concrete structure cracks, expounds the deep learning technology, studies the SqueezeNet network model and YOLO (You Only Look Once) network model in the field of concrete structure crack identification, and improves the model according to the test results. In this paper, the classification accuracy based on crack trend is improved by increasing the width and depth of the Fire module of the SqueezeNet network. Secondly, the target detection accuracy is improved by the transfer learning of the YOLO model. The results show that the classification accuracy of the improved SqueezeNet model is more than 82% and the recognition accuracy of YOLO model is more than 92%.

Can expected error costs justify testing a hypothesis at multiple alpha levels rather than searching for an elusive optimal alpha?

Simultaneous testing of one hypothesis at multiple alpha levels can be performed within a conventional Neyman-Pearson framework. This is achieved by treating the hypothesis as a family of hypotheses, each member of which explicitly concerns test level as well as effect size. Such testing encourages researchers to think about error rates and strength of evidence in both the statistical design and reporting stages of a study. Here, we show that these multi-alpha level tests can deliver acceptable expected total error costs. We first present formulas for expected error costs from single alpha and multiple alpha level tests, given prior probabilities of effect sizes that have either dichotomous or continuous distributions. Error costs are tied to decisions, with different decisions assumed for each of the potential outcomes in the multi-alpha level case. Expected total costs for tests at single and multiple alpha levels are then compared with optimal costs. This comparison highlights how sensitive optimization is to estimated error costs and to assumptions about prevalence. Testing at multiple default thresholds removes the need to formally identify decisions, or to model costs and prevalence as required in optimization approaches. Although total expected error costs with this approach will not be optimal, our results suggest they may be lower, on average, than when "optimal" test levels are based on mis-specified models.

Full Quantity or Full Credit? Choosing the Right Buyback Policy for a Behavioral Retailer

Problem definition: Despite extensive research on buyback contracts in supply chain management, little attention has been given to a direct comparison between a traditional full-quantity, partial-credit (FQ) buyback contract and an alternative full-credit, partial-quantity (FC) contract, especially when considering the behavioral biases of the retailer. This study aims to fill this research gap by exploring how these biases influence contract performance and offer practical guidelines for suppliers. Methodology/results: Through controlled laboratory experiments and structural model estimation, we show that the ordering decisions made by human retailers are jointly affected by three behavioral biases—loss aversion, prospective accounting, and psychological cost of inventory error—and these biases differ in magnitude between the two contracts. Incorporating these biases into a behavioral retailer’s utility function, we then analytically examine which buyback policy the supplier should choose. When the wholesale price is exogenously given, the supplier should adopt the FC contract for high-margin (low-cost) products. Conversely, when the supplier has the power to set both the wholesale and buyback prices, the FC contract is generally more beneficial for low-margin products. Finally, when the product cost is sufficiently high, a wholesale price contract may be advantageous over buyback policies. Managerial implications: The managerial implication of this paper is significant for suppliers who have to choose between different buyback policies. The paper suggests that the supplier should carefully consider not just the economic, but also the behavioral dimensions when making contract decisions, particularly when dealing with a retailer influenced by behavioral biases. Specifically, the choice between FQ and FC contracts is influenced by two key environmental factors: the production cost of the product and the nature of wholesale pricing. Understanding these elements allows suppliers to be flexible in contract choices and design appropriate return policies for their downstream supply chain partners. Funding: P. Yu was supported by the National Natural Science Foundation of China [Grants 72371038 and 72033003] and the Fundamental Research Funds for the Central Universities [Grant 2024CDJSKPT16]. T. Feng was supported by the National Natural Science Foundation of China [Grant 72131004]. Supplemental Material: The online appendix is available at https://doi.org/10.1287/msom.2023.0574 .

“It’s a Battle You Can’t Win”: Domination and Class Differences in Real-World Trust among Black Families

How does class affect one’s propensity to trust? Previous research finds higher-status actors express less trust than lower-status actors in interpersonal and institutional contexts. Scholars explain this finding as an outcome of structural dependence—when people have few alternative means for accessing valuable resources. In contrast, I find dependence inadequate to explain the relationship I observe between class and institutional trust among black families whose children were recommended for special education and other remedial program placement in an affluent, predominantly white school district. Drawing on retrospective interviews from a community ethnography, findings show that real-world trust decision processes also involve domination. Empirical studies of trust have overlooked the ways trustees—those being given trust—exercise power to achieve deference in trust exchanges, and how trustors—those placing trust in others—deploy their power to withstand trustees’ influence. I argue that trust might best be conceptualized as a two-part decision process, because class and other status resources affect trustors’ freedom to choose at two key junctures: (1) in weighing options and costs of trust errors, and (2) in communicating distrust in face-to-face interactions, where the potential for domination is high. Focusing on intersecting systems of power in authentic trust exchanges, this study shows how middle-class black trustors use symbolic resources to “go up against” the institutional power of educational experts and refuse placement, whereas working-class trustors consent to placement.

A Bi-Objective Optimal Scheduling Method for the Charging and Discharging of EVs Considering the Uncertainty of Wind and Photovoltaic Output in the Context of Time-of-Use Electricity Price

With the increasing share of renewable energy generation and the integration of large-scale electric vehicles (EVs) into the grid, the reasonable charging and discharging scheduling of electric vehicles is essential for the stable operation of power grid. Therefore, this paper proposes a bi-objective optimal scheduling strategy for microgrids based on the participation of electric vehicles in vehicle-to-grid technology (V2G) mode. Firstly, the system structure for electric vehicles participating in the charging and discharging schedule was established. Secondly, a bi-objective optimization model was formulated, considering load mean square error and user charging cost. A heuristic method was employed to handle constraints related to system energy balance and equipment output. Then, the Monte Carlo method was employed to simulate electric vehicle loads and to facilitate the generation of and reduction in scenario scenes. Finally, the model was solved using an improved multi-objective barebones particle swarm optimization algorithm. The simulation results show that the proposed scheduling strategy has a lower charging cost (CNY 11,032.4) and lower load mean square error (12.84 × 105 kW2) than the strategy employed in the comparison experiment, which ensures the economic and stable operation of the microgrid.

Machine-learning aided calibration and analysis of porous media CFD models used for rotating packed beds

The proposed research is an attempt to advance the state-of-the-art of the numerical modelling of RPB by combining Computational Fluid Dynamics and Machine Learning approaches. The latter creates an accurate framework that should help quantify the potential of Rotating Packed Beds (RPB) technology to intensify conventional CO2 capture processes. To this end, a direct sensitivity analysis is detailed to supplement a machine-learning (ML) algorithm built for calibrating resistance coefficients needed for porous media modelling. The algorithm is used to improve CFD predictions of dry pressure drop in rotating packed beds (RPBs) for a wide range of operating conditions. The sensitivity derivatives with respect to the packing resistance coefficients are demonstrated for the first time in RPBs, which is not available in the current CFD open source and commercial codes. In this regard, sensitivity differential equations are derived from three-dimensional Navier-Stokes equations for porous media in a rotating reference frame. These sensitivity equations are discretized using a finite volume scheme and solved to obtain the sensitivity pressure drop differences at the packing edges. The results are validated against the predictions of the analytical sensitivity analysis and the finite difference approximation. After, the Newton – Gauss method that employs the sensitivity pressure drop derivatives, is used to minimize the error (cost function) between the pressure drop obtained from CFD simulations and the available experimental data. This is achieved by tuning the packing resistance coefficients to the RBPs' operating conditions (gas flowrate and rotating speed) and correlate them using an artificial neural network (ANN). The results of the proposed approach show a significant improvement in porous media-based CFD predictions of RPBs' pressure drop across a wide range of operating conditions and this over conventional porous media-based CFD models. This is necessary for CFD models to be reliably used as a tool that can efficiently improve existing RPBs' designs and/or participate in RPBs' design innovation.

Sequential three-way decision with automatic threshold learning for credit risk prediction

Machine learning algorithms treat credit risk prediction as a binary classification problem. However, two-way decisions with a single threshold force to make either a default or non-default decision may be inappropriate. To reduce the risk of decision errors, this study introduces three-way decisions and proposes a sequential three-way decision model with automatic threshold learning to evaluate credit risk. Initially, the model uses the loan amount and interest to determine the decision loss of the three-way decision, assigning distinct decision thresholds to different samples. Subsequently, the model employs decision cost and information gain to formulate an objective for threshold optimisation. Finally, the model continuously optimises the classification process by using the outcomes of certain decisions as supplementary information. In addition, to validate our model, we conduct comparative experiments with various methods on a real credit dataset from a Chinese bank. The results indicate that the model not only enhances classification performance across several metrics but also assists financial institutions in reducing decision error costs.

Application of type I and II error analysis to support economic decision-making of using an immunomodulator feed additive

The use of the immunomodulator OmniGen- AF® (OMN) feed supplement, where the response in milk yield, health, and reproduction is uncertain, allows for an application of type I (use the product when it is not profitable) and type II (do not use the product when it is profitable) analysis to aid decision making regarding its profitability. This study applies a type I and II error analysis to quantify the economic risk of investing in OMN feed supplementation using data from a controlled study and a field data set collected on dairy farms. Four prediction models were applied considering the expected value and standard deviation of the response in milk yield; milk and health; milk and reproduction; milk, health, and reproduction. Uncertainty in the milk response was modeled following a normal distribution with mean 0.15 kg/cow/d and standard deviation 0.81 kg/cow/d. This distribution was left-truncated at 0 kg, which resulted in a mean (expected) response of 0.7 kg/cow/d. Based on the field data set, the reduction in health costs and reproduction were estimated at $0.086 and $0.33/cow/day. All 3 responses were assumed to be present or not in the first 90 DIM. The increase in milk yields necessary to pay for the OMN supplementation considering a response in milk yield only, milk and health, milk and reproduction, and milk, health, and reproduction were 0.45, 0.19, -0.56, and -0.82 kg/cow/d respectively. The break-even OMN cost per cow per day when considering the increases in milk yield, milk and health, and milk and reproduction, milk, health, and reproduction were $0.23, $0.31, $0.56, and $0.65 respectively. Production responses resulted in costs exceeding revenue with a type I error cost of $2.62 for milk and $0.47 for milk and health response for the broke even. There was no type I error cost associated when considering the responses in milk and reproduction, and the combination of milk, health and reproduction which implies that there is no risk of using OMN when it is not profitable ( = the product is profitable for certain). Type II costs were associated with returns that are unrealized because of failing to use OMN when it is profitable with an opportunity cost of $9.92, $15.53, $37.23, and $45.08 per cow per day for the responses in milk yield; milk and health; milk and reproduction; and milk, health, and reproduction respectively. We concluded that a type I and II error analysis applied to the use of the OMN feed additive provided additional insights beyond a break-even analysis to support economic decision-making when the response on dairy farms is uncertain. The type I and II error analysis can aid in decision-making process to evaluate the adoption of a new technology.

Old tools for the new economy? Counterfactual causation in foreclosure assessment and choice of remedies on data-driven markets

Abstract Under the Digital Markets Act, gatekeeper platforms abide by numerous ex-ante rules, including narrow data-sharing obligations that address data-driven market tipping. Gatekeepers also remain subject to ex-post competition interventions. While interventions under both ex-ante and ex-post (antitrust) mandates are not novel, they must be approached with extra care in data-driven digital markets, where uncertainty and error costs are high. Therefore, we argue that post-DMA competition enforcement against gatekeepers requires rigorous ex-post economic effects analysis at two levels: foreclosure assessment and devising appropriate remedies. Regarding foreclosure assessment, we propose a ‘multiple-counterfactual-causation-test’ for establishing anticompetitive effects, which should ensure a nuanced analysis of the competitive landscape on data-driven digital markets in the post-DMA world. Regarding remedies, a fine-grained, proportionality-driven assessment of the need for ex-post data-related obligations is vital.

Estimation of the mean exponential survival time under a sequential censoring scheme

The exponential distribution can provide a simple and appealing survival-time model in reliability analysis and life tests. Due to certain experimental designs, time limitations, budgetary requirements, and other reasons, however, only censored data can be obtained. In this paper, we propose a novel estimation procedure for the mean survival time of an exponential distribution under a sequential censoring scheme, which can be treated as a combination of type I censoring and type II censoring. The procedure makes a trade-off between estimation error and sampling cost, using the minimum number of observations. An extensive set of Monte Carlo simulations is conducted to further validate its remarkable performance. To demonstrate the practical applicability, we then implement this newly proposed procedure to assess the reliability of various Backblaze's hard disk models.

Establishment and application of real-time monitoring system for mine ventilation resistance

The monitoring of ventilation resistance in domestic coal mines is generally faced with two problems: huge workload and lagging monitoring data behind production, which is due to the backward monitoring technology. In recent years, with the progress of technology and equipment in the coal industry, ventilation resistance monitoring products have appeared in the market one after another, but they still face the following main problems: (1) the sensor measurement error needs to be further improved; (2) The monitoring scheme is relatively simple, and the use of absolute pressure multi-parameter monitoring faces two problems: measurement error and construction cost; (3) There is a lack of successful application cases of ventilation resistance monitoring in the industry, and the analysis and application of ventilation resistance monitoring data by the upper computer is insufficient. In view of the above problems, this paper studies the principle, monitoring scheme, system framework and practical application of ventilation resistance monitoring, aiming to solve the problem of real-time online monitoring and analysis of ventilation resistance.

Undesired flows in lateral-intake multiple forebays and their hydraulic implications: case study for Asia’s largest urban water supply pumping station

Urban pumping stations often adopt the design of lateral-intake multiple forebays to accommodate multiple pump units in a limited space and to reduce interaction between the operating units. However, a full understanding of the undesired flows and hydraulic characteristics of lateral-intake multiple forebays remains limited, resulting in the design of flow-regulating measures relying on trial and error. This study numerically investigated the undesired flows in lateral-intake multiple forebays and their hydraulic implications, using Asia’s largest urban water supply pumping station as a case study. The results show that the undesired flows, including flow recirculation, helical mainstream and vortex strip, are the main reasons for the deterioration of hydraulic characteristics in the forebays. The undesired flows are more pronounced at higher inflow Froude numbers or for the forebay closer to the diversion channel inlet, resulting in lower flow uniformity and higher hydraulic loss. Further discussion shows that the flow-regulating measures improve the hydraulic characteristics by limiting the generation and development of undesired flows within the forebays. This provides references for the design of flow-regulating measures for similar forebays to reduce the cost of trial and error, which is of general value for the lateral-intake multiple forebays required for urban pumping stations.

Intelligent mutation based evolutionary optimization algorithm for genomics and precision medicine.

In this paper, genomics and precision medicine have witnessed remarkable progress with the advent of high-throughput sequencing technologies and advances in data analytics. However, because of the data's great dimensionality and complexity, the processing and interpretation of large-scale genomic data present major challenges. In order to overcome these difficulties, this research suggests a novel Intelligent Mutation-Based Evolutionary Optimization Algorithm (IMBOA) created particularly for applications in genomics and precision medicine. In the proposed IMBOA, the mutation operator is guided by genome-based information, allowing for the introduction of variants in candidate solutions that are consistent with known biological processes. The algorithm's combination of Differential Evolution with this intelligent mutation mechanism enables effective exploration and exploitation of the solution space. Applying a domain-specific fitness function, the system evaluates potential solutions for each generation based on genomic correctness and fitness. The fitness function directs the search toward ideal solutions that achieve the problem's objectives, while the genome accuracy measure assures that the solutions have physiologically relevant genomic properties. This work demonstrates extensive tests on diverse genomics datasets, including genotype-phenotype association studies and predictive modeling tasks in precision medicine, to verify the accuracy of the proposed approach. The results demonstrate that, in terms of precision, convergence rate, mean error, standard deviation, prediction, and fitness cost of physiologically important genomic biomarkers, the IMBOA consistently outperforms other cutting-edge optimization methods.

A survey on node localization technologies in UWSNs: Potential solutions, recent advancements, and future directions

SummaryLocation‐based underwater communication applications such as strategic surveillance, disaster prevention, marine research, and mine detection have given the field of underwater wireless sensor networks (UWSN) a head start. Node localization is a prerequisite for accurate data collection, target monitoring, and network management in UWSNs. However, the unique characteristics of the underwater environment, such as signal attenuation, multipath propagation, and variable acoustic properties, pose a major challenge to effective node localization. Accurate sensor node location data is essential for successful underwater data collection, but difficult to achieve as the GPS system cannot be used in an underwater environment. In this paper, existing node localization techniques such as ALS, SLUM, MASL, SLMP, UDB, USP, etc., and recent advances such as the fusion of range‐based and range‐free techniques, the fusion of RSSI and AoA to improve localization accuracy by using directional information in addition to signal strength, and the use of optimization techniques such as PSO, COA, and WOA algorithms to improve the accuracy of the applied node localization algorithm, e.g., TP‐TSFLA, and challenges related to UWSN are discussed. Also, different localization algorithms that affect the accuracy of UWSN localization techniques have been evaluated and compared with NS2 in terms of localization error, localization coverage, energy consumption, and average communication cost metrics. In addition, this paper also provides an up‐to‐date investigation of localization techniques. Finally, the tools available for simulation are presented, followed by open research questions that need to be addressed in the localization of nodes.

Cost-effectiveness of preoperative pharmaceutical care consultations: a 5-year analysis

ObjectivesPreoperative medication errors can be prevented by screening patients through a preoperative pharmaceutical care consultation. The aim of this study was to analyse the cost-effectiveness of implementing such a consultation...

Beware stewardship in silos

With the WHO estimating that global medication errors cost approximately US$42 billion annually, it is perhaps not surprising that we hear a lot about medicines stewardship these days. Although the descriptions and goals of medicines stewardship vary, common themes are that it involves careful and responsible management, it is targeted at drug classes that are associated with a high risk of adverse outcomes and it aims to reduce variations in practice and improve patient outcomes.

Deep learning for enhanced index tracking

We develop a novel deep learning method for the enhanced index tracking problem, which aims to outperform an index while effectively controlling the tracking error. We generate a dynamic trading policy from a neural network that accepts a set of features as inputs. We design four blocks in the neural network architecture to handle different types of features, including regimes of the index and stocks, their short-term characteristics, and the current allocation. Outputs from the blocks are integrated into the final output that changes the portfolio allocation. We test our model on several indexes in empirical studies based on real market data. Out-of-sample results reveal the importance of different features and demonstrate the ability of our method in obtaining excess returns while effectively controlling the tracking error, downside risk, and transaction costs.

Impact of pharmacist‐led discharge medication reconciliation on error and patient harm prevention at a large academic medical center

AbstractIntroductionMedication errors during hospital discharge can lead to adverse outcomes, medication‐related readmissions, and increased health care costs. Pharmacist‐led medication reconciliation at discharge is a potential solution to mitigate poor outcomes and optimize medication safety.ObjectivesThis study aimed to quantify medication errors identified at discharge and characterize the severity of patient harm prevented following pharmacist‐led discharge medication reconciliation. Cost avoidance analysis was conducted to determine its associated financial impact.MethodsPatients, who were discharged from an adult internal medicine service during October 2022, were included in this one‐month pilot prospective quality improvement study. The number of errors at discharge were documented, categorized by type, and adjudicated for severity of potential harm. Error severity was classified based on a modified National Coordinating Council for Medication Error Reporting and Prevention Medication Error Index. Cost avoidance was calculated based on whether each error would have resulted in additional medical encounters and length of stay.ResultsThirty‐one patients were included in the analysis. Forty errors were identified by pharmacist‐led medication reconciliation at discharge, with a mean of 1.3 ± 1.9 errors per patient and 68% of patients having at least one error. The most common errors were duplication of therapy (25%) and medication access barriers at discharge (25%). The severity of errors included low (22.5%), serious (75%), and life‐threatening harm (2.5%). Thirty‐five percent of errors could have led to emergency visits or hospital readmissions. The estimated total cost for errors was $25 600. Pharmacist labor cost for reconciliation was $816. Cost avoidance was $24 784 from the 14 errors at discharge that could have resulted in additional emergency or inpatient visits.ConclusionPharmacist‐led medication reconciliation at discharge may prevent harm from reaching patients, decrease cost from unnecessary health encounters, and stop the error from continuing across transitions of care.

The Innovative Role and Practical Exploration of Virtual Simulation Driven by Artificial Intelligence

This paper discusses the innovative role and practical application of artificial intelligence (AI) and virtual simulation technology in the field of art design. The article first outlines the impact of AI on art designers, including data analysis and prediction, adaptive optimization and independent innovation and creation. The application advantages of virtual simulation technology in art design are discussed, such as intuitive preview effects and freer creative space. The article further analyzes the development prospects of the integration of AI and virtual simulation technology, including the intelligent, immersive experience and intelligent creation of art design.AI has broad application prospects in art design, which can shorten the design cycle, provide personalized design optimization solutions, and reduce the cost of trial and error through simulation and prediction. Virtual simulation technology brings an immersive experience to users through a three-dimensional interactive environment, and combined with the personalized adjustment of AI,it can further enhance the user experience. Finally, the article looks forward to the future of AI and virtual simulation technology in art design, indicating that art design will develop in a more intelligent and humanized direction, bringing more innovative and personalized experiences to designers and users.