More Like this

1. Chemical composition effect on latent print development using black fingerprint powders

   Sara Moreno a, Glenna Brown (October 2021, Forensic chemistry)

   null (Ed.)

   Fingerprint development has been used to visualize latent prints since the 19th century, and several companies produce a variety of commercially available black fingerprint powders. While the method to develop fingerprints has been refined over the years, the composition of fingerprint powders that are used in print development has not been studied extensively. Six different black fingerprint powders were studied using X-ray photoelectron spectroscopy (XPS), scanning electron microscopy (SEM) with energy dispersive X-ray spectroscopy (EDS), dynamic light scattering (DLS) and zeta potential, attenuated total reflectance infrared spectroscopy (ATR-IR), Raman spectroscopy, powder X-ray diffraction (PXRD), and solution-phase nuclear magnetic resonance spectroscopy (NMR) in addition to a quality study involving certified latent print examiners. When comparing all chemical, physical, and morphological results for the fingerprint powder, this study determined that powders ranked best by latent print examiners are fingerprint powders that mainly contain carbon and oxygen with particle sizes around 50 nm and spherical morphology. Powders with large particle sizes, irregular shape, and elemental compositions consisting of many elements ranked poorly in the quality study performed. 

   more » « less
2. FairMatch: A Graph-based Approach for Improving Aggregate Diversity in Recommender Systems

   https://doi.org/10.1145/3340631.3394860  

   Mansoury, Masoud; Abdollahpouri, Himan; Pechenizkiy, Mykola; Mobasher, Bamshad; Burke, Robin (July 2020, Proceedings of the 28th ACM Conference on User Modeling, Adaptation and Personalization)

   Recommender systems are often biased toward popular items. In other words, few items are frequently recommended while the majority of items do not get proportionate attention. That leads to low coverage of items in recommendation lists across users (i.e. low aggregate diversity) and unfair distribution of recommended items. In this paper, we introduce FairMatch, a general graph-based algorithm that works as a post-processing approach after recommendation generation for improving aggregate diversity. The algorithm iteratively finds items that are rarely recommended yet are high-quality and add them to the users' final recommendation lists. This is done by solving the maximum flow problem on the recommendation bipartite graph. While we focus on aggregate diversity and fair distribution of recommended items, the algorithm can be adapted to other recommendation scenarios using different underlying definitions of fairness. A comprehensive set of experiments on two datasets and comparison with state-of-the-art baselines show that FairMatch, while significantly improving aggregate diversity, provides comparable recommendation accuracy. 

   more » « less
3. A Feasibility Study on Utilizing Toe Prints for Biometric Verification of Children

   https://doi.org/10.1109/ICB45273.2019.8987273  

   Yambay, David; Johnson, Morgan; Bahmani, Keivan; Schuckers, Stephanie (June 2019, 12th IAPR International Conference On Biometrics)

   Biometric recognition allows a person to be identified by comparing feature vectors derived from a person's physiological characteristics. Recognition is dependent on the permanence of the biometric characteristics over long periods of time. There was been limited work evaluating the footprint as a potential biometric. This paper presents a longitudinal study of toe prints in children to understand if this biometric modality could be used reliably as a child grows. Data was collected and analyzed in children ages 4-13 years over five visits, spaced approximately six months apart, giving two years of data. This is the first footprint collection spanning this broad age range in children. Footprints were segmented into separate toe prints to examine whether current fingerprint recognition technology can provide accurate results on toe prints. Data was analyzed using two available fingerprint matchers, Verifinger and Bo-zorth3 from NIST Biometric Image Software (NBIS). Ver-ifinger provides the best verification match scores using the toe prints, especially when using the hallux, the large toe. The hallux toe on Verifinger provides verification rates of 0% FAR and FRR for images collected on the same day and a FRR of 6.44% at a 1% FAR after two years have passed between collections. Additional longitudinal data is being collected to further these results. 

   more » « less
4. Investigating the impact of demographic factors on contactless fingerprints interoperability

   https://doi.org/10.1109/BIOSIG55365.2022.9897061  

   Berti, Aeddon; Nasrabadi, Nasser; Dawson, Jeremy (September 2022, IEEE 21th International Conference of the Biometrics Special Interest Group (BIOSIG'22))

   Contactless fingerprints have continued to grow interoperability as a faster and more convenient replacement for contact fingerprints, and with covid-19 now starting to be a past event the need for hygienic alternatives has only grown after the sudden focus during the pandemic. Though, past works have shown issues with the interoperability of contactless prints from both kiosk devices and phone fingerprint collection apps. The focus of the paper is the evaluation of match performance between contact and contactless fingerprints, and the evaluation of match score bias based on skin demographics. AUC results indicate contactless match performance is as good as contact fingerprints, while phone contactless fingerprints fall short. Additionally, bias found for melanin showed specific ranges affected in both low melanin values and high melanin values. 

   more » « less
5. One Size Does Not Fit All: Modeling Users’ Personal Curiosity in Recommender Systems

   Abbas, Fakhri; Niu, Xi (June 2019, ArXivorg)

   Today’s recommender systems are criticized for recommending items that are too obvious to arouse users’ interest. That is why the recommender systems research community has advocated some ”beyond accuracy” evaluation metrics such as novelty, diversity, coverage, and serendipity with the hope of promoting information discovery and sustain users’ interest over a long period of time. While bringing in new perspectives, most of these evaluation metrics have not considered individual users’ difference: an open-minded user may favor highly novel or diversified recommendations whereas a conservative user’s appetite for novelty or diversity may not be that large. In this paper, we developed a model to approximate an individual’s curiosity distribution over different levels of stimuli guided by the well-known Wundt curve in Psychology. We measured an item’s surprise level to assess the stimulation level and whether it is in the range of the user’s appetite for stimulus. We then proposed a recommendation system framework that considers both user preference and appetite for stimulus where the curiosity is maximally aroused. Our framework differs from a typical recommender system in that it leverages human’s curiosity to promote intrinsic interest with the system. A series of evaluation experiments have been conducted to show that our framework is able to rank higher the items with not only high ratings but also high response likelihood. The recommendation list generated by our algorithm has higher potential of inspiring user curiosity compared to traditional approaches. The personalization factor for assessing the stimulus (surprise) strength further helps the recommender achieve smaller (better) inter-user similarity. 

   more » « less