Mark R. Lehto

Purdue University | Purdue · School of Industrial Engineering

Effective utilization of product quality and reliability intellectual capital assists companies to avoid expensive errors, allows for streamlined product development, provides better customer satisfaction, creates better issue/process management and results in more robust and reliable products. For large multinational organizations, it is often cha...

Automated systems can provide tremendous benefits to users; however, there are also potential hazards that users must be aware of to safely operate and interact with them. To address this need, safety warnings are often provided to operators and others who might be placed at risk by the system. This chapter discusses some of the roles safety warnin...

Physical inactivity has been an increasing sub-health condition. Nudging people to participate in physical activities consequently becomes a public health priority. This study aims to showcase how color as a design factor can work to nudge city travelers to take on walking. Alongside the color effect, this experimental study incorporates another tw...

Background Emergency department (ED)-based injury surveillance systems across many countries face resourcing challenges related to the validation and coding of data, which largely rely on manual coding. This presentation describes the evaluation of a machine learning-based Decision Support Tool (DST) to assist injury surveillance departments in the...

Injury surveillance plays an important role in understanding the underlying factors leading to different types of injuries and accordingly developing effective prevention strategies. Multi-dimensional injury-related data are captured in computerized systems at hospital emergency rooms in various fields such as the presenting problem/triage text (or...

Background: Emergency department (ED)-based injury surveillance systems across many countries face resourcing challenges related to manual validation and coding of data. Objective: This study describes the evaluation of a machine learning (ML)-based decision support tool (DST) to assist injury surveillance departments in the validation, coding,...

This study compares attitudes toward the use of biometrics data-enabled services in hotels of prospective travelers before and after receiving information about the risks and benefits of disclosing biometric data and about how the disclosed data are being utilized. This was done based on a sample of 579 U.S. respondents, using a split-plot scenario...

This chapter provides an overall perspective on human decision making to human factors practitioners, developers of decision tools, product designers, and others who are interested in how people make decisions and how decision making might be improved. It presents a broad set of prescriptive and descriptive approaches. The chapter introduces princi...

This paper presents the results of a pilot study examining the effectiveness of an interpretive nutrition label as an information nudge in the context of Human-Computer Interaction (HCI) with a mobile Health application (mHealth app). Thirty subjects from two age groups were recruited to complete a healthy food discrimination task on the web-based...

Self-service technology (SST) has been increasingly integrated into today’s service industry. The ability to understand how customers perceive SST and improve its quality is therefore important for both researchers and practitioners. Applying the Quality Function Deployment (QFD) methodology, this research established an SST House of Quality (HoQ)...

In injury surveillance, different aspects of an injury event are captured using injury codes such as the External-cause-of-injury (E-code), Major Injury Factor (MIF), and Intent. These are usually assigned by human coders based on accident narratives. Previous studies have examined automated and semi-automated filtering approaches that use machine...

This study aimed to use healthcare professionals’ assessments to calculate expected risk of intravenous (IV) infusion harm for simulated high‐risk medications that exceed soft limits and to investigate the impact of relevant risk factors. We designed 30 infusion scenarios for four high‐risk medications, propofol, morphine, insulin, and heparin, inf...

Many ranking algorithms rank a set of alternatives based on their performance in a set of pairwise comparisons. In this study, a special scenario is observed in which the objective is to rate and rank a set of groups in a traditional recruiting situation, in which the groups extend offers to the set of individuals, and the individuals will select o...

In today’s technology-driven configuration of work and life systems, wellness imbalances underscore the need for time away from sources of stress in the workplace, school, and other living scenarios. Increasingly, consumers are turning to vacation travel for health and wellness enhancement. The tourism and hospitality industries can design experien...

While ecolabels are increasingly used for different products, their effectiveness in informing consumers on choosing environmentally-friendly products is still unclear. Existing research using surveys or choice experiments in the lab environment may not be able to capture actual consumer behaviors and preferences. This study examines the effectiven...

Human coders, in many organizations conducting injury surveillance, routinely assign External-cause-of-injury codes (E-codes) to short narratives describing the incident, transcribed by triage nurses or others in hospital emergency rooms or other settings. Machine learning (ML) models trained on coded injury narratives can accurately assign E-codes...

The website of luxury hotel brands is regarded as a great platform for marketers to create positive brand identity. The underlying architecture of information, as well as the design of graphics, navigation system, and user interface could have an influence on user experience with a hotel brand. Utilizing a conjoint design, this research assessed us...

Introduction: Classical Machine Learning (ML) models have been found to assign the external-cause-of-injury codes (E-codes) based on injury narratives with good overall accuracy but often struggle with rare categories, primarily due to lack of enough training cases and heavily skewed nature of injurdata. In this paper, we have: a) studied the effe...

Injury narratives are now available real time and include useful information for injury surveillance and prevention. However, manual classification of the cause or events leading to injury found in large batches of narratives, such as workers compensation claims databases, can be prohibitive. In this study we compare the utility of four machine lea...

E-commerce websites are increasingly interested in how to effectively utilize online reviews to positively influence consumer decisions. One potential mechanism is providing socio-demographic information about reviewers along with the reviews. This study investigates how consumer decision outcome variables (e.g., perceived usefulness, trust and pur...

Background Emergency departments (ED) around the world collect valuable injury data with potential to inform consumer product regulators. However, many of these systems store key information in unstructured text fields, making case identification and analysis difficult. Machine learning approaches allow autocoding of large amounts of data, increasi...

Introduction: Studies on autocoding injury data have found that machine learning algorithms perform well for categories that occur frequently but often struggle with rare categories. Therefore, manual coding, although resource-intensive, cannot be eliminated. We propose a Bayesian decision support system to autocode a large portion of the data, fi...

A major part of warehouse operations is related to the collection of parts from the warehouse which is called the Order Picking Problem. To improve order picking operations, the total travel distance and generally picking time must be reduced. In this paper, a two-level approach is proposed that determines the locations of parts in the warehouse. T...

Objective: Vast amounts of injury narratives are collected daily and are available electronically in real time and have great potential for use in injury surveillance and evaluation. Machine learning algorithms have been developed to assist in identifying cases and classifying mechanisms leading to injury in a much timelier manner than is possible...

Public health surveillance programs in the U.S. are undergoing landmark changes with the availability of electronic health records and advancements in information technology. Injury narratives gathered from hospital records, workers compensation claims or national surveys can be very useful for identifying antecedents to injury or emerging risks. H...

Many undergraduate industrial engineering programs offer a capstone senior design course that gives students an opportunity to apply the knowledge gained through their coursework to real-world projects. In this article, we present the results of a user requirements analysis of online collaboration tools containing Web 2.0 features for teaching such...

The purpose of this article is to review the key emerging innovations in laser and photonics systems as well as their design and integration, focusing on challenges and opportunities for solutions of societal challenges. Developments, their significance, and frontier challenges are explained in advanced manufacturing, biomedicine and healthcare, an...

Background: In occupational safety research, narrative text analysis has been combined with coded surveillance, data to improve identification and understanding of injuries and their circumstances. Injury data give, information about incidence and the direct cause of an injury, while near-miss data enable the, identification of various hazards wit...

This paper examines the feasibility of extracting useful information from customer comments using a Naïve Bayes classifier. This was done for a database, obtained from a large Korean mobile telephone service provider, of 533 customer calls to call centers in 2009. After eliminating calls not containing customer complaints or comments, the remaining...

The present study was framed using the Technology Acceptance Model (TAM) to identify determinants affecting behavioral intention to use YouTube. Most importantly, this research emphasizes the motives for using YouTube, which is notable given its extrinsic task goal of being used for procedural learning tasks. Our conceptual framework included two p...

Post implementation, HUBzero™ has been well accepted as a knowledge management and collaboration platform for the reliability engineering (RE) division of a large consumer goods company. RE tools such as Failure Mode Effects & Criticality Analysis (FMECA), Reliability Growth Curves, and Shakedown Testing are being used in the organization in form o...

IntroductionDecision-Making ModelsGroup Decision MakingDecision Support and Problem SolvingSummary and Conclusions References

HUBzero™ is a Web2.0 based scientific collaboration platform with various social networking and data management features like user groups, access controlled file sharing and review mechanism, content tagging, online discussions, wikis and blogs that can be used by researchers and commercial organizations. We have implemented the HUB-in-a-box versio...

Bayesian methods show promise for classifying injury narratives from large administrative datasets into cause groups. This study examined a combined approach where two Bayesian models (Fuzzy and Naïve) were used to either classify a narrative or select it for manual review. Injury narratives were extracted from claims filed with a worker's compensa...

This study aims to investigate a cost effective and efficient way of analyzing customer impressions on design alternatives by incorporating the benefits of virtual prototyping into the Internet-based experimental environment. It is hypothesized that the results of the Internet-based experiment using the images of virtual prototypes are comparable t...

This paper discusses a query-translation based cross-language diagnosis (Q-CLD) for print defects conducted by nonnative English users. The first step involved developing three fuzzy Bayesian models: one based on English descriptions provided by native English subjects (referred to as the native English model); the second on English des- criptions...

In the global economy, design of digital media often involves teams of individuals from a variety of cultures who must function together. Similarly, products must be designed and marketed taking specific cultural characteristics into account. Much is known about decision processes, culture and cognition, design of products and interfaces for human...

Current printing technologies enable customers to reproduce high quality, realistic, and colorful hard copies of their digital documents. Although the activity of printing is transparent to the customers, the progression of a customer's document through the color printing workflow (CPW) is a complex process that may alter the colors in the print jo...

This study aims to develop an effective and efficient method of analyzing user impressions of a product using virtual prototyping. A method to analyze the relationship between user impressions and design elements of a product using virtual prototyping was proposed, and then the method was applied to the case study of automobile interior design. Thi...

Objective: Computerized clinical reminder (CCR) systems can improve preventive service delivery by providing patient-specific reminders at the point of care. However, adherence varies between individ-ual CCRs and is correlated to resolution time amongst other factors. This study aimed to evaluate how a proposed CCR redesign providing information ex...

Print quality is an important factor for customer satisfaction. Resolving print quality issues poses special challenges for a manufacturer's support organization. The authors have developed a troubleshooting website to enable customers to self-solve many of their print quality issues. The diagnosis is based on images of printed test pages that cont...

To compare two Bayesian methods (Fuzzy and Naïve) for classifying injury narratives in large administrative databases into event cause groups, a dataset of 14 000 narratives was randomly extracted from claims filed with a worker's compensation insurance provider. Two expert coders assigned one-digit and two-digit Bureau of Labor Statistics (BLS) Oc...

A query translation-based Korean–English cross-language diagnosis (Q-KE-CLD) tool for assisting Korean users diagnosing print defects was developed and then evaluated as a case study of distributed decision making support for nonnative English users. The first step in developing the Q-KE-CLD tool involved collecting and analyzing print defect descr...

This paper describes an exploratory study that analyzes the impact of change in software on users by utilizing the Critical Incident Technique (CIT). A total of 102 critical incidents were collected from the survey. 77 participants reported both satisfactory and unsatisfactory experiences; 22 reported only satisfactory experiences; and 3 reported o...

A computerized clinical reminder (CCR) system is a type of decision support tool to remind healthcare providers of recommended actions. In our prior study, we found a linear correlation between resolution time and adherence rate. This correlation implies a potentially biased clinical decision making. This study aimed to redesign the Veterans Affair...

Automated systems can provide tremendous benefits to users; however, there are also potential hazards that users must be aware of to safely operate and interact with them. To address this need, safety warnings are often provided to operators and others who might be placed at risk by the system. This chapter discusses some of the roles safety warnin...

Objective: Computerized clinical reminders (CCRs) are useful tools for alerting healthcare providers of upcoming or overdue events. Previous studies have reported that clinicians will be more likely to comply with a CCR when it is perceived to be useful. We sought to identify and measure factors potentially important in affecting clinician's percei...

This study is an attempt to investigate the effects of document structure and knowledge level of the reader on reading comprehension, browsing, and perceived control. Four types of texts are distinguished, differing in structure (linear text, hierarchical hypertext, mixed hypertext, and generative text). All the materials were on a PC. In all condi...

This research utilized the critical incident technique (CIT) to identify factors influencing customer satisfaction and retention of customers participating in e-commerce transactions. Customers were asked in telephone interviews to discuss both particularly satisfying and dissatisfying (or critical) incidents they had experienced when using web sit...

Introduction Classical Decision Theory Decision Analysis Behavioral Decision Theory Dynamic and Naturalistic Decision Making Group Decision Making Summary Conclusions References

Objectives: Improve the sensitivity and specificity of computer assigned codes of narrative text from large administrative databases using a filtering routine. Methods: Narrative text contained in large administrative databases is underutilized due to resource constraints for manual classification. A previously developed method classified Workers...

Introduction Reliability Maintenance Safety Summary Acknowledgments References Additional Reading

Emphasizing customer oriented design and operation, Introduction to Human Factors and Ergonomics for Engineers explores the behavioral, physical, and mathematical foundations of the discipline and how to apply them to improve the human, societal, and economic well being of systems and organizations. The book discusses product design, such as tools,...

This research proposes a new task analysis methodology that combines the fuzzy Bayesian model with classic task analysis methods to develop a semi-automated task analysis tool to better help traditional task analysts identify subtasks. We hypothesize that this approach could help task analysts identify activity units performed by the call center ag...

This study investigates the effect of providing a Web-based diagnostic tool as a collaboration medium on remote customer troubleshooting tasks with and without the assistance of a customer call center agent. The study tested three troubleshooting modes (Web tool alone, call center agent alone, and Web tool + call center agent). The hypothesis that...

With the increasing complexity of systems and information overload, agent technology has become widely used to provide personalized advice (help message) to users with their computer-based tasks. The purpose of this study is to investigate the way to optimize advice provided by the intelligent agent from a decision theoretic perspective. The study...

This paper summarizes improvements to an earlier developed Fuzzy Bayes approach for assigning coding categories to injury narratives randomly extracted from a large U.S. insurer. Improvements to the model included: adding sequenced words as predictors and removing common subsets prior to calculation of word strengths. Removing subsets and adding wo...

The previous study [9], [10] showed the fuzzy Bayes model successfully predicted print defects with a 50% hit rate at the first top prediction and an 80% hit rate within the top five predictions. However, the previous study was limited to English. In this study, Korean and English descriptions in predicting print defects by Korean subjects were eva...

Keyword search is a very important method to find information on Web sites along with link-based browsing. How an information retrieval system displays search results is very important because users spend most of their time in finding, reading and understanding retrieved information. As an application of information retrieval systems, a self-help p...

This study uncovered critical domains and themes of compliments and complaints that influence consumers overall satisfaction with using virtual travel agencies. Four domains, namely, “customer Service & Support”, “trip schedule change”, “product experience” and “firm credibility” were identified as areas where problems arose and extreme dissatisfac...

This study compared the accuracy of three Singular Value Decomposition (SVD) based models developed for classifying injury narratives. Two SVD-Bayesian models and one SVD-Regression model were developed to classify bodies of free text. Injury narratives and corresponding E-codes assigned by human experts from the 1997 and 1998 US National Health In...

This paper demonstrates a successful application of a Fuzzy Bayes machine-learning tool for classifying large amounts of narrative text, involving the use of ROC curves to identify optimum prediction threshold values at which to filter predictions for manual review. Different thresholds were used for different categories to optimize results and eff...

Electronic decision support systems are an important tool for improving performance and improving quality of care. We investigated the relationship between physicians' estimated resolution times for computerized clinical reminders and adherence rates in VA outpatient settings. We surveyed 10 expert physician users to assess the resolution times of...

It is critical to understand user requirements in Web site development. As a method of user requirements analysis for a self-help technical support Web site, focus group interviews can be a very efficient and effective approach both before the interface has been designed and after it has been in use for some time. This article shows how focus group...

Computerized clinical reminders (CCR) are useful tools for alerting healthcare providers of upcoming or overdue medical labs, procedures, or exams, possible drug-drug interactions, and actions to take to support adherence to relevant clinical-practice guidelines. CCR have been effective in improving preventive service delivery, and have positively...

IntroductionClassical Decision TheoryDecision AnalysisBehavioral Decision TheoryDynamic and Naturalistic Decision MakingGroup Decision MakingDecision SupportSummary and Conclusions References

We are examining the workflow processes within a large, urban general internal medicine practice in order to understand task inefficiencies that can lead to medical errors. We are performing a time-motion study looking at task management of check-in, check-out clerks, nurses, nurse's aides and physicians. Our pilot data suggests that there is signi...

Print quality is an important factor for customer satisfaction. Resolving print quality issues poses special challenges for a manufacturer's support organization. We have developed a troubleshooting web site to enable customers to self-diagnose many of their print quality issues. The diagnosis is based on images of the printed test pages that conta...

ResultsOur prototype system consisted of a set of tabbed data display and data entry panes that organized information into logical workgroups with an underlying controlled vocabulary for specifying complaints/problems, diagnoses, physical exam findings, medications, lab and radiology tests and specialty care. A data entry mechanism based on body-pa...

This study investigates the effect of providing a Web-based diagnostic tool on customer troubleshooting with & without the assistance of a call center agent. The study tested three troubleshooting modes (Web tool, customer call center agent, and Web tool + customer call center agent) The results showed that the troubleshooting mode of Web tool + cu...

To investigate the accuracy of a computerized method for classifying injury narratives into external-cause-of-injury and poisoning (E-code) categories. This study used injury narratives and corresponding E-codes assigned by experts from the 1997 and 1998 US National Health Interview Survey (NHIS). A Fuzzy Bayesian model was used to assign injury de...

Customers using printers occasionally experience problems such as fuzzy images, bands, or streaks. The customer may call or otherwise contact the manufacturer, who attempts to diagnose the problem based on the customer's description of the problem. This study evaluated Bayesian inference as a tool for identifying or diagnosing 16 different types of...

The design of an effective warning sign or label is a complex and difficult task. For the working professional in ergonomics, it can be perplexing to decipher the vast amount of research that has been, and is being, performed in the field, as well as the regulations and standards that affect the design and use of warning signs or labels. The purpos...

Past research in safety belt use has primarily focused on describing the relationship between drivers' demographic characteristics and safety belt use. This study compared the impact of situational factors (the direction of collision, the type of road, and the presence of an airbag system), demographic factors, and constructs (criteria) elicited fr...

In the distributed signal detection theoretic (DSDT) model, the human operator and the warning mechanism are independent decision makers who work together as a team. The DSDT demonstrates that the optimal warning threshold, in general, differs from the signal detection theoretic (SDT) threshold, which assumes a single decision maker. This predictio...

Error Modes and Effects Analysis (EMEA) is a recently developed procedure intended to help practitioners systematically apply cognitive guidelines regarding the appropriate content and format of a warning sign or label. The EMEA procedure includes elements of Failure Modes and Effects Analysis (FMEA), task analysis, and Rasmussen's SRK levels of pe...

Hazard communications often contain adverbial or adjectival phrases that qualify the meaning of verbs or nouns. For example, a warning label might contain the phrase prolonged exposure. Fuzzy set theory provides a method of quantitatively describing the meaning of such phrases, using membership functions. For example, a membership function might ma...

This study introduces and evaluates the performance of two statistical models intended to support the automatic creation of a subject-based index containing links to hypertext documents. The fuzzy Bayes model makes strong dependence assumptions, and only considers the strongest evidence presented by single words occurring in a document, whereas the...

Due to the continual innovation in information technology, vast amounts of information in various forms have become available to people for the purpose of decision making and problem solving. Consequently, how to represent the information to facilitate the processes of decision making and problem solving becomes a significant issue. ^ The measureme...

The effects of warnings are analyzed using a distributed signal-detection theory model. It is established that selectivity always increases effectiveness. The implications to optimal warning design for intermittent versus continuous hazards are discussed. The changes in the behavior of the 6 human subjects in response to changes in the warning leve...

This study evaluated the influence of chemical label content and format on the speed and accuracy of information retrieval. A total of 111 engineering students participated in the study, and 27 labels were tested, corresponding to three chemical types, three labeling systems, and three label sizes. Questions were asked for each label regarding targ...

Eight participants (aged 18–28 yr olds) performing a simulated driving task received noisy information on a visual display regarding the likelihood of police being present. They also received an auditory warning signal when an independent assessment (by the warning system) of the probability of police being present exceeded a threshold probability....

A field study of 1146 drivers and passengers of vehicles equipped with motorized passive belts was conducted in shopping malls and other locations in the states of Arizona and Indiana. The Indiana data was collected the summer of 1994 and the Arizona data the summer of 1995. Shoulder belt use by drivers and passengers was 93.4% in Indiana and 87.8%...

Bayesian inferencing as a machine learning technique was evaluated for identifying pre-crash activity and crash type from accident narratives describing 3,686 motor vehicle crashes. It was hypothesized that a Bayesian model could learn from a computer search for 63 keywords related to accident categories. Learning was described in terms of the abil...

Numerous guidelines for the design of warning signs and warning labels have been developed throughout the world. Their primary focus has been on perceptual issues and rudimentary aspects of comprehension. Much less attention has been given to how people vary in the way they make decisions, as a function of task familiarity and user knowledge. This...

In this study, the repertory grid technique is used as the main research instrument for eliciting drivers' knowledge to explore the factors that have impact on seat belt use. Principal components analysis identified five factors underlying drivers' risk assessments: severity, predictability / foreseebility, fault, frequency / unsafe behavior, and h...

Determining the most appropriate Machine Learning (ML) method, system, or algorithm for a particular application is not trivial. This article reports on a survey of 103 experts specializing in ML who were asked to rate ML method appropriateness to intelligent tasks. Ratings were captured via a structured questionnaire including 12 ML methods and 9...

This study examined the use and misuse of home smoke detectors in three cities in the United States: Dayton, Ohio, Union City, New Jersey, and San Francisco, California. A sample of 300 households, 100 in each city, were reached in telephone interviews which were concluded with a request to test the smoke detector. For the sample, 86% had a smoke d...

The ways that warnings are administered vary greatly. A warning may come as a message broadcast on the radio about severe weather, as a flashing light in the cockpit of an airplane, or as an audible smoke alarm. Typically, warnings provide an auditory or visual signal to assist in the detection of an anticipated stimulus. However, warnings tend to...

Motor vehicle travel through roadway construction workzones has been shown to increase the risk of a crash. The number of workzones has increased due to recent congressional funding in 1991 for expanded roadway maintenance and repair. In this paper, we describe the characteristics and costs of motor vehicle crashes in roadway construction workzones...