Recent studies have demonstrated that most commercial facial analysis systems are biased against certain categories of race, ethnicity, culture, age and gender. The bias can be traced in some cases to the algorithms used and in other cases to insufficient training of algorithms, while in still other cases bias can be traced to insufficient databases. To date, no comprehensive literature review exists which systematically investigates bias and discrimination in the currently available facial analysis software. To address the gap, this study conducts a systematic literature review (SLR) in which the context of facial analysis system bias is investigated in detail. The review, involving 24 studies, additionally aims to identify (a) facial analysis databases that were created to alleviate bias, (b) the full range of bias in facial analysis software and (c) algorithms and techniques implemented to mitigate bias in facial analysis.

Worker productivity is a major concern for the construction industry. Many studies assessed the effect of various factors, such as the work environment and worker health, on productivity. Nevertheless, the extent to which an automatic productive assessment can benefit from wearable electronic-based sensor technologies for physiological and psychological tracking purposes has not yet been fully investigated. This work assesses the ability of capturing the effect of construction workers' happiness on their productivity using physiological signals collected via wearable sensors. Data from both a traditional tracking process (human annotators) and an automated worker physiological signal tracking process that was designed for the purposes of this study were compiled. By considering the traditional tracking process as the baseline for the comparison, this study evaluated the effectiveness of automating happiness tracking as a leading indicator of construction workers' productivity. The physiological signal data collected included blood volume pulse (BVP), respiration rate (RR), heart rate (HR), galvanic skin response (GSR), and skin temperature (TEMP). These data were obtained from a 4-day field study conducted at a prefabricated stone construction factory. The study concluded that a moderate positive correlation exists between a worker's emotional status and his productivity exists, with a p-value = 5.5 × 10-8 and a Pearson's coefficient of 0.43.

No abstract

Annually, a huge number of pilgrims visit Mecca to perform Al Hajj ritual. Crowd management is critical in this occasion in order to avoid crowd disasters (e.g., stampede and suffocation). Recent studies stated that various factors, such as the environment, fatigue level, health condition and emotional status have a significant effect on crowded events. This calls for a need for an automated data analytics system that feeds event organizers with information about those factors on real-time, at least from a generalizable sample of crowd subjects, in which proactive crowd management decisions are made to reduce overall risks. This paper develops a novel methodology that fuses mobile GPS and physiological data of Hajj pilgrims collected through wearable sensors to train three classification models: (a) current performed Hajj activity, (b) fatigue level, and (c) emotional level. In a pilot experiment conducted against two subjects, promising results of a minimum of 75% accuracy levels were achieved for the activity recognition and fatigue level classifiers, whereas the emotional level classifier still requires further refinements.

Many web-based services such as email, search engines, and polling sites are being abused by spammers via computer programs known as bots. This problem has bred a new research area called Human Interactive Proofs (HIP) and a testing device called CAPTCHA, which aims to protect services from malevolent attacks by distinguishing bots from human users. In the past decade, researchers have focused on developing robust and safe HIP systems but have barely evaluated their usability. To begin to fill this gap, the authors report the results of a user study conducted to determine the extent that English language proficiency affects CAPTCHA usability for users whose native language is not English. The results showed a significant effect of participants’ English language proficiency level on the time the participant takes to solve CAPTCHA, which appear to be related to multiple usability issues including satisfaction and efficiency. Yet, they found that English language proficiency level does not affect the number of errors made while entering CAPTCHA or reCAPTCHA. The authors’ results have numerous implications that may inform future CAPTCHA design.