Age group and gender classification using convolutional neural networks with a fuzzy logic-based filter method for noise reduction

2021 ◽  
pp. 1-11
Author(s):  
Ali Tunc ◽  
Sakir Tasdemir ◽  
Murat Koklu ◽  
Ahmet Cevahir Cinar
Keyword(s):  
Fuzzy Logic ◽  
Matrix Completion ◽  
Recognition System ◽  
Filter Method ◽  
Age Group ◽  
Living Things ◽  
The Matrix ◽  
And Gender ◽  
Facial Recognition System ◽  
Matrix Expression

Biometry is the science that enables living things to be distinguished by examining their physical and behavioral characteristics. The facial recognition system (FCS) is a kind of biometric system. FCS provides a unique mathematical model by determining the distance between the cheekbones, chin, nose, eyes, jawline, and similar positions using the facial features of the persons. Determining the gender and age group of chosen persons’ from face images is the main purpose of this study. It is targeted to distinguish the gender of the person and to obtain information about the person is children or adults by making essential works on the images. Convolutional neural network (CNN) is one of the deep face recognition algorithms that widely used to recognize facial images. This study is suggested as a study that detects noise in images using the fuzzy logic-based filter method and classifies this cleared data by gender using the matrix completion and CNN. TensorFlow which is a machine learning library that used to train and tests deep learning methods is used for experiments. The customer photographs taken during using the system are transformed into a matrix expression through a system trained using this algorithm. The obtained results indicated that the offered technique detects age and gender with a 96% accuracy value and 1.145 seconds time.

scholarly journals Understanding Facial Recognition System Usage and Adaptation among Millennial and Non-millennial consumers

2019 ◽  
Vol 8 (4) ◽  
pp. 12779-12791
Keyword(s):  
Technology Adoption ◽  
Mobile Devices ◽  
Facial Recognition ◽  
Recognition System ◽  
The Self ◽  
Advanced Technology ◽  
High Tech ◽  
Age Group ◽  
Great Opportunity ◽  
Facial Recognition System

Facial recognition technology has proved its immense usefulness by being one of the most effective and nonintrusive means of authentication system. Privacy concerns are accompanying the development of the facial recognition system since its inception. However, the perception has changed remarkably over the last 6 decades. Rather than considering a facial recognition system as a part of a sci-fi imagination, it has become more realistic and brought convenience, safety, and security to our daily lives. Not only has the millennial, the understanding and adaptation rate of facial recognition system amongst all generations, through mobile devices, Governmental and private projects, reached a significant level. Apart from technical applications, facial recognition provides extensive opportunities in numerous other fields of business. The rate of cooperativeness for innovative usage of facial recognition system seems to rise amongst all the individuals, irrespective their age group. One of the biggest motivators being the self-interests in keeping up with technological advancement, which provides a great opportunity for the marketers and technology companies to provide relevant information for their target audience. This research will try to validate the theory proposed by Murray (2011) that millennial are most comfortable people to adaptation of technology, including the facial recognition system. It also tries to identify the usage and adaptation factors among all the age groups and to find out key business areas where facial recognition can be value addition. Objective: This paper elaborates the adoption of Facial Recognition System as device access and security enabling technology amongst millennial and non-millennial users. As the technology has seen rising adoption by Government, Business and Individual users; this study attempts to understand customer awareness about the technology as well as perceived challenges and benefits by users. User age group and generation have been used as an indicative parameter to determine if the technology adoption has seen some definitive preference by any one user group. Design/ Methodology/ Approach: This study entailed a secondary study about customer adoption of Facial recognition systems, followed by a questionnaire-based survey with a mixed population comprising of millennial and non-millennial respondents. Findings:Through this research work, we could conclude that the millennial age group shown the highest percentage of affinity toward adopting highly advanced technology. Facial recognition system would be a very effective piece of technology which could enhance the security, safety, and ease of accessibility in various fields. There is a tremendous opportunity for marketers to get benefitted out of this trend. Various measures can be taken to attract millennial and centennial. Though, the older generations showed a positive mindset toward adopting high-tech devices. One of the greatest motivational factors for purchasing a hightech device, the researchers have identified, is the self-awareness to find more about the technology. People are more willing to do their research and hands-on experience to know technology better, than relying on other’s opinion about the technology.Practical Implications:Understanding the adoption challenges about Facial recognition system and the motivating factors that can encourage customers to adopt, can help industries incorporate this technology in devices meant for business and personal use. Although this technology has vast application in security, surveillance and personal device management; this study can help manufacturers develop deeper insight into the positioning of the technology as a benefit desired by the end-users.Originality & Value: This paper has attempted to look at the challenges in facial recognition technology adoption from the age-based generation perspective. With increasing millennial users adopting mobile devices with facial recognition feature, the study has attempted to study the appeal of the technology to the millennial generation and the potential lack of appeal for the older generations.

Lichtenstein Versus Desarda’s Technique of Hernia Repair

2020 ◽  
Vol 22 (2) ◽  
pp. 99-103
Author(s):  
Md Fardhus ◽  
AMSM Sharfuzzaman ◽  
Md Nayeem Dewan ◽  
Md Abul Hossain ◽  
Ahmed Sami Al Hasan ◽  
...  
Keyword(s):  
Inguinal Hernia ◽  
Hernia Repair ◽  
Mesh Repair ◽  
Operative Time ◽  
Seroma Formation ◽  
Age Group ◽  
Serous Fluid ◽  
Medical College ◽  
Randomized Control ◽  
And Gender

Aim: To compare Desarda’s versus Lichtenstein’s mesh repair in patients with unilateral, primary, reducible inguinal hernia in terms of mean operative time and seroma formation Methods: This randomized control trial conducted at Department of Surgery, Patuakhali Medical College & Hospital, Patuakhali. Eighty patients with unilateral, primary, reducible inguinal hernia were randomly distributed into two groups to undergo hernia repair i.e. Lichtenstein (L) and Desarda’s (D). Outcome was measured in terms of mean operative time and seroma formation. Seroma formation was defined as presence of enclosed cavity containing serous fluid determined by ultrasonography at 30th post-operative day. Results: Thirty three patients (41.25%) were above 50 years of age, whereas remaining 47 patients (58.75%) were below 50 years of age. Five patients (6.25%) were female and 75 patients(93.75%) were male. Seroma formation was 5% in Desarda’s group while 7.5% in Lichtenstein group (P> 0.05). Similarly difference in mean operative time was statistically non-significant. Seroma formation was common in older age group. There was no effect of smoking, obesity, operative time and gender on seroma formation. Conclusion: It is concluded that there is no difference in frequency of seroma formation and mean operative time in Desarda’s or Lichtenstein’s technique of hernia repair. Journal of Surgical Sciences (2018) Vol. 22 (2) : 99-103

Preschoolers’ imitation of sentential complement sentences: Does the nature of the matrix clause matter?

2021 ◽  
pp. 014272372110242
Author(s):  
Ian Morton ◽  
C. Melanie Schuele
Keyword(s):  
Language Development ◽  
Age Group ◽  
Matrix Clause ◽  
Developmental Progression ◽  
Main Effect ◽  
Dependent Variables ◽  
The Matrix ◽  
Group 3 ◽  
Sentence Imitation ◽  
Experimental Findings

Preschoolers’ earliest productions of sentential complement sentences have matrix clauses that are limited in form. Diessel proposed that matrix clauses in these early productions are propositionally empty fixed phrases that lack semantic and syntactic integration with the clausal complement. By 4 years of age, however, preschoolers produce sentential complement sentences with matrix clauses that are more varied. Diessel proposed that the matrix clauses in these later productions semantically and syntactically embed the complement clause. We refer to these matrix clauses as formulaic and true, respectively. Diessel’s hypothesis about the development of sentential complement sentences was based on an analysis of spontaneous language. The purpose of this study was to evaluate Diessel’s hypothesis with an experimental sentence imitation task wherein stimuli varied in the nature of the matrix clause. Thirty children with typical language development participated; 10 children in each age group (3-, 4-, and 5-year-olds) imitated 50 sentential complement sentences that included either a true or a formulaic matrix clause; the structure of the dependent clauses did not vary. Dependent variables were percent sentence imitation and percent matrix clause imitation. There was a significant main effect for matrix clause type on imitation of sentences and matrix clauses. There was also a significant main effect for age on imitation of sentences and matrix clauses. Significant matrix clause type-by-age interactions were such that percent sentence imitation and percent matrix clause imitation varied by age. Three- and 4-year-olds were less proficient than 5-year-olds on imitation of sentences with true matrix clauses and on imitations of true matrix clauses. Only 3- and 4-year-olds were less proficient imitating true matrix clauses than formulaic matrix clauses. Experimental findings support Diessel’s hypothesis that there is a developmental progression in the nature of preschoolers’ production of sentential complement sentences.

scholarly journals Facial Recognition System for People with and without Face Mask in Times of the COVID-19 Pandemic

2021 ◽  
Vol 13 (12) ◽  
pp. 6900
Author(s):  
Jonathan S. Talahua ◽  
Jorge Buele ◽  
P. Calvopiña ◽  
José Varela-Aldás
Keyword(s):  
Facial Recognition ◽  
Face Mask ◽  
Recognition System ◽  
Classification Model ◽  
World Health ◽  
The Face ◽  
Recognition Systems ◽  
Facial Recognition System ◽  
Health Organization ◽  
Face Detector

In the face of the COVID-19 pandemic, the World Health Organization (WHO) declared the use of a face mask as a mandatory biosafety measure. This has caused problems in current facial recognition systems, motivating the development of this research. This manuscript describes the development of a system for recognizing people, even when they are using a face mask, from photographs. A classification model based on the MobileNetV2 architecture and the OpenCv’s face detector is used. Thus, using these stages, it can be identified where the face is and it can be determined whether or not it is wearing a face mask. The FaceNet model is used as a feature extractor and a feedforward multilayer perceptron to perform facial recognition. For training the facial recognition models, a set of observations made up of 13,359 images is generated; 52.9% images with a face mask and 47.1% images without a face mask. The experimental results show that there is an accuracy of 99.65% in determining whether a person is wearing a mask or not. An accuracy of 99.52% is achieved in the facial recognition of 10 people with masks, while for facial recognition without masks, an accuracy of 99.96% is obtained.

Future Costs of Long-term Care in Japan and Sweden

2017 ◽  
Vol 48 (1) ◽  
pp. 128-147 ◽  
Author(s):  
Mårten Lagergren ◽  
Noriko Kurube ◽  
Yasuhiko Saito
Keyword(s):  
Long Term Care ◽  
Population Change ◽  
Population Aging ◽  
Population Data ◽  
Epidemiological Data ◽  
The Other ◽  
Age Group ◽  
Term Care ◽  
And Gender

Population aging is expected to increase long-term care (LTC) costs in both Japan and Sweden. This study projected LTC costs for 2010 through 2040 for different assumptions of population change, LTC need by age group and gender, and LTC provided per level of need and cost in Japan and Sweden. Population data were taken from the official national forecasts. Needs projections were based on epidemiological data from the Nihon University Japanese Longitudinal Study of Aging and the Swedish Survey of Living Conditions. Data on LTC provision by need and cost were taken from nine Japanese municipalities collected by assessments in the LTC insurance system and from surveys in eight Swedish municipalities. Total initial costs were calibrated to official national figures. Two projections based on two different scenarios were made for each country from 2010 to 2040. The first scenario assumed a constant level of need for LTC by age group and gender, and the other assumed a continuation of the present LTC need trends until 2025. For Japan, this resulted in a projected cost increase of 93% for the one and 80% for the other; for Sweden it was 52% and 24%, respectively. The results reflected differences in population aging and health development.

The Occurrence of High Levels of Acute Behavioral Distress in Children and Adolescents Undergoing Routine Venipunctures

PEDIATRICS ◽  
1992 ◽  
Vol 90 (1) ◽  
pp. 87-91 ◽  
Author(s):  
G. Bennett Humphrey ◽  
Chris M. J. Boon ◽  
G. F. E. Chiquit van Linden van den Heuvell ◽  
Harry B. M. van de Wiel
Keyword(s):  
Children And Adolescents ◽  
Age Group ◽  
Loss Of Control ◽  
Strong Relation ◽  
And Gender ◽  
Trained Observers ◽  
Distress Scale ◽  
Insight Into

While there is no question that children dislike needles, there are very little data available on the occurrence of high levels of distress experienced by children undergoing routine venipunctures. To provide some insight into this problem, trained observers evaluated distress in 223 different children and adolescents undergoing this procedure. An observational distress scale of 1 to 5 was developed; 1 = calm, 2 = timid/nervous, 3 = serious distress, but still under control, 4 = serious distress with loss of control, and 5 = panic. We observed a strong relation between distress and age but not between distress and gender. During the actual venipuncture. half the subjects (113/223) were scored as having high levels of distress (3 or more). Our subjects were also grouped into three age ranges: toddlers; 2½ to 6 years, N = 70; preadolescents; 7 to 12 years, N = 55; and adolescents; 12 years and older, N = 98. The percent of subjects experiencing high levels of distress for each age group were: 83%, 51%, and 28%, respectively. We conclude that for venipunctures: 1) high levels of distress are common, and 2) age and not gender correlates with distress. Other correlations are discussed. Toddlers and pre-adolescents should be the targets for new interventions to reduce distress.

scholarly journals MC2: a two-phase algorithm for leveraged matrix completion

2018 ◽  
Vol 7 (3) ◽  
pp. 581-604 ◽  
Author(s):  
Armin Eftekhari ◽  
Michael B Wakin ◽  
Rachel A Ward
Keyword(s):  
Broad Class ◽  
Matrix Completion ◽  
A Priori ◽  
Total Sample ◽  
Second Phase ◽  
Sample Complexity ◽  
Two Phase ◽  
The Matrix ◽  
Leverage Scores ◽  
Uniform Random Sampling

Abstract Leverage scores, loosely speaking, reflect the importance of the rows and columns of a matrix. Ideally, given the leverage scores of a rank-r matrix $M\in \mathbb{R}^{n\times n}$, that matrix can be reliably completed from just $O (rn\log ^{2}n )$ samples if the samples are chosen randomly from a non-uniform distribution induced by the leverage scores. In practice, however, the leverage scores are often unknown a priori. As such, the sample complexity in uniform matrix completion—using uniform random sampling—increases to $O(\eta (M)\cdot rn\log ^{2}n)$, where η(M) is the largest leverage score of M. In this paper, we propose a two-phase algorithm called MC2 for matrix completion: in the first phase, the leverage scores are estimated based on uniform random samples, and then in the second phase the matrix is resampled non-uniformly based on the estimated leverage scores and then completed. For well-conditioned matrices, the total sample complexity of MC2 is no worse than uniform matrix completion, and for certain classes of well-conditioned matrices—namely, reasonably coherent matrices whose leverage scores exhibit mild decay—MC2 requires substantially fewer samples. Numerical simulations suggest that the algorithm outperforms uniform matrix completion in a broad class of matrices and, in particular, is much less sensitive to the condition number than our theory currently requires.

Sign in / Sign up

Export Citation Format

Share Document