Algorithm-Augmented Work and Domain Experience: The Countervailing Forces of Ability and Aversion

Past research offers mixed perspectives on whether domain experience helps or hurts algorithm-augmented worker performance. Reconciling these perspectives, we theorize that intermediate levels of domain experience are optimal for algorithm-augmented performance, due to the interplay between two countervailing forces—ability and aversion. Although domain experience can increase performance via increased ability to complement algorithmic advice (e.g., identifying inaccurate predictions), it can also decrease performance via increased aversion to accurate algorithmic advice. Because ability developed through learning by doing increases at a decreasing rate, and algorithmic aversion is more prevalent among experts, we theorize that algorithm-augmented performance will first rise with increasing domain experience, then fall. We test this by exploiting a within-subjects experiment in which corporate information technology support workers were assigned to resolve problems both manually and using an algorithmic tool. We confirm that the difference between performance with the algorithmic tool versus without the tool was characterized by an inverted U-shape over the range of domain experience. Only workers with moderate domain experience did significantly better using the algorithm than resolving tickets manually. These findings highlight that, even if greater domain experience increases workers’ ability to complement algorithms, domain experience can also trigger other mechanisms that overcome the positive ability effect and inhibit performance. Additional analyses and participant interviews suggest that, even though the highest experience workers had the greatest ability to complement the algorithmic tool, they rejected its advice because they felt greater accountability for possible unintended consequences of accepting algorithmic advice.

The Effect of Quality of Work Life on Worker Performance When Work from Home through Job Satisfaction and Organizational Commitment as Intervening Variables (Case Study at PT Patra Jasa Head Office)

This study aims to determine the effect of quality of work life on worker performance when working from home (WFH) with job satisfaction and organizational commitment as intervening variables at PT Patra Jasa Head Office. The research method used is a quantitative method. The research population is all employees of PT Patra Jasa with a minimum working period of 1 year, which is 144 people. All members of the population are used as members of the sample (census technique). Primary data collection using a questionnaire instrument. The technique of analyzing and testing the hypothesis is using the Structural Equation Model (SEM) with the SmartPLS version 3.0 application. Partial results of hypothesis testing prove that the quality of work life, organizational commitment, and quality of work life through organizational commitment have no positive and significant effect on worker performance when WFH. Job satisfaction and quality of work life through job satisfaction have a positive and significant effect on worker performance when WFH. Furthermore, simultaneous hypothesis testing with multiple linear regression models has a coefficient of determination (R2) of 67%, quality of work life through job satisfaction and organizational commitment has a strong effect on worker performance when WFH.

Collaborative Augmented Digital Twin: A Novel Open-Source Augmented Reality Solution for Training and Maintenance Processes in the Shipyard of the Future

Large companies use a lot of resources on workshop operator training and industrial machinery maintenance since the lack of this practice or its poor implementation increases the cost and risks of operating and handling sensitive and/or hazardous machinery. Industrial Augmented Reality (IAR), a major technology in the Industry 4.0 paradigm that may enhance worker performance, minimize hazards and improve manufacturing processes, could be beneficial in this situation. This paper presents an IAR solution that allows for visualizing and interacting with the digital twin of a critical system. Specifically, the augmented digital twin of an industrial cooler was developed. The proposed IAR system provides a dynamic way to perform operator training with a full-size model of the actual equipment and to provide step-by-step guidance so that maintenance processes can be performed more safely and efficiently. The proposed system also allows several users to use devices at the same time, creating a new type of collaborative interaction by viewing the model in the same place and state. Performance tests with many simultaneous users have been conducted, with response latency being measured as the number of connected users grows. Furthermore, the suggested IAR system has been thoroughly tested in a real-world industrial environment.

Increasing workers comfort: experiment of the effect of color and lighting in assembly manufacture

Color and light are the main factors in the car manufacturing industry, with not much research, conducted on this topic, related to employee physical comfort. The factor affecting employee work comfort is the color factor and lighting time in their workplace environment. Color is the light, reflected by an object, then interpreted by the eye based on the light that hits the object. The value of the color wavelength in the spectrum of 380 nm to780 nm impacts worker performance. Good lighting will affect whether or not the room’s light conditions affect the illumination’s value. A good working room condition will affect the physical comfort of employees. Employee physical comfort has developed in many previous studies. However, research on the configuration of colors and lighting in the manufacturing industry’s work environment is still underdeveloped. This research aims to measure and determine the impact of color and lighting at specific color wavelengths on the illumination value and the employee’s physical comfort. It starts with studying the color, light, human comfort, then examines the effect on the manufacturing industry employees’ performance in the wiring installation assembly industry. Color and light settings are proven essential to get better human comfort. Green color with a wavelength of 490 nm to 570 can increase the highest illuminate average lux value of 12.43 %. Yellow can increase the heart rate by 4.85 %, while green can reduce Diastole by 2.95 % and Systole by 1.29 %. Pupillary size changes L by 23.17 % and R by 21.43 %. The effect of green color and lighting time can increase the value of illumination and decrease heart rate, blood pressure, and pupil size so that it impacts the physical comfort of employees.

Validation and tuning of in situ transcriptomics image processing workflows with crowdsourced annotations

Recent advancements in in situ methods, such as multiplexed in situ RNA hybridization and in situ RNA sequencing, have deepened our understanding of the way biological processes are spatially organized in tissues. Automated image processing and spot-calling algorithms for analyzing in situ transcriptomics images have many parameters which need to be tuned for optimal detection. Having ground truth datasets (images where there is very high confidence on the accuracy of the detected spots) is essential for evaluating these algorithms and tuning their parameters. We present a first-in-kind open-source toolkit and framework for in situ transcriptomics image analysis that incorporates crowdsourced annotations, alongside expert annotations, as a source of ground truth for the analysis of in situ transcriptomics images. The kit includes tools for preparing images for crowdsourcing annotation to optimize crowdsourced workers’ ability to annotate these images reliably, performing quality control (QC) on worker annotations, extracting candidate parameters for spot-calling algorithms from sample images, tuning parameters for spot-calling algorithms, and evaluating spot-calling algorithms and worker performance. These tools are wrapped in a modular pipeline with a flexible structure that allows users to take advantage of crowdsourced annotations from any source of their choice. We tested the pipeline using real and synthetic in situ transcriptomics images and annotations from the Amazon Mechanical Turk system obtained via Quanti.us. Using real images from in situ experiments and simulated images produced by one of the tools in the kit, we studied worker sensitivity to spot characteristics and established rules for annotation QC. We explored and demonstrated the use of ground truth generated in this way for validating spot-calling algorithms and tuning their parameters, and confirmed that consensus crowdsourced annotations are a viable substitute for expert-generated ground truth for these purposes.