scholarly journals CG-GAN: An Interactive Evolutionary GAN-Based Approach for Facial Composite Generation

2020 ◽  
Vol 34 (03) ◽  
pp. 2544-2551 ◽  
Author(s):  
Nicola Zaltron ◽  
Luisa Zurlo ◽  
Sebastian Risi
Keyword(s):  
High Resolution ◽  
Evolutionary Computation ◽  
Expert Knowledge ◽  
Multiple Representations ◽  
Digital Systems ◽  
Graphical Representations ◽  
The Novel ◽  
Novel Approach ◽  
Human Faces ◽  
Facial Composite

Facial composites are graphical representations of an eyewitness's memory of a face. Many digital systems are available for the creation of such composites but are either unable to reproduce features unless previously designed or do not allow holistic changes to the image. In this paper, we improve the efficiency of composite creation by removing the reliance on expert knowledge and letting the system learn to represent faces from examples. The novel approach, Composite Generating GAN (CG-GAN), applies generative and evolutionary computation to allow casual users to easily create facial composites. Specifically, CG-GAN utilizes the generator network of a pg-GAN to create high-resolution human faces. Users are provided with several functions to interactively breed and edit faces. CG-GAN offers a novel way of generating and handling static and animated photo-realistic facial composites, with the possibility of combining multiple representations of the same perpetrator, generated by different eyewitnesses.

scholarly journals Gaudii: An Automated Graphic Design Expert System

2021 ◽  
Vol 24 (2) ◽  
pp. 1775-1780
Author(s):  
Carlos Glez-Morcillo ◽  
Victor Martin ◽  
David Vallejo Fernandez ◽  
Jose Castro-Schez ◽  
Javier Albusac
Keyword(s):  
Fuzzy Logic ◽  
Expert System ◽  
Evolutionary Computation ◽  
Graphic Design ◽  
Expert Knowledge ◽  
Trial And Error ◽  
Design Elements ◽  
Design Expert ◽  
Novel Approach ◽  
Design Activities

Graphic design is the process of creating graphics to meet specific commercial needs based on knowledge of layout principles and esthetic concepts. This is usually an iterative trial and error process which requires a lot of time even for expert designers. This expert knowledge can be modelled, represented and used by a computer to perform design activities. This paper describes a novel approach named Gaudii (standing for "Intelligent Automated Graphic Design Generator") which utilizes principles and techniques known from the fields of Evolutionary Computation and Fuzzy Logic to automatically obtain design elements. Experimental results that demonstrate the potential of the proposed approach are presented in the area of poster design.

scholarly journals A novel approach in the free-electron laser diagnosis based on a pixelated phosphor detector

2016 ◽  
Vol 23 (1) ◽  
pp. 29-34 ◽  
Author(s):  
Alessia Matruglio ◽  
Simone Dal Zilio ◽  
Rudi Sergo ◽  
Riccardo Mincigrucci ◽  
Cristian Svetina ◽  
...  
Keyword(s):  
High Resolution ◽  
Silicon Substrate ◽  
Free Electron ◽  
Free Electron Laser ◽  
High Performance ◽  
Spot Size ◽  
The Novel ◽  
Etching Technique ◽  
Novel Approach ◽  
Focused Beam

A new high-performance method for the free-electron laser (FEL) focused beam diagnosis has been successfully tested at the FERMI FEL in Trieste, Italy. The novel pixelated phosphor detector (PPD) consists of micrometric pixels produced by classical UV lithography and dry etching technique, fabricated on a silicon substrate, arranged in a hexagonal geometry and filled with suitable phosphors. It has been demonstrated that the overall resolution of the system has increased by reducing the diffusion of the light in the phosphors. Various types of PPD have been produced and tested, demonstrating a high resolution in the beam profile and the ability to measure the actual spot size shot-to-shot with an unprecedented resolution. For these reasons, the proposed detector could become a reference technique in the FEL diagnosis field.

Exploring normative perceptions and misperceptions of private, environmentally impactful behaviours

2020 ◽  
Author(s):  
Elaine Gallagher ◽  
Bas Verplanken ◽  
Ian Walker
Keyword(s):  
Social Norms ◽  
Behaviour Change ◽  
Social Contexts ◽  
The Novel ◽  
Normative Influence ◽  
Change Mechanism ◽  
Novel Approach ◽  
Classical Studies ◽  
Referent Group

Social norms have been shown to be an effective behaviour change mechanism across diverse behaviours, demonstrated from classical studies to more recent behaviour change research. Much of this research has focused on environmentally impactful actions. Social norms are typically utilised for behaviour change in social contexts, which facilitates the important element of the behaviour being visible to the referent group. This ensures that behaviours can be learned through observation and that deviations from the acceptable behaviour can be easily sanctioned or approved by the referent group. There has been little focus on how effective social norms are in private or non-social contexts, despite a multitude of environmentally impactful behaviours occurring in the home, for example. The current study took the novel approach to explore if private behaviours are important in the context of normative influence, and if the lack of a referent groups results in inaccurate normative perceptions and misguided behaviours. Findings demonstrated variance in normative perceptions of private behaviours, and that these misperceptions may influence behaviour. These behaviours are deemed to be more environmentally harmful, and respondents are less comfortable with these behaviours being visible to others, than non-private behaviours. The research reveals the importance of focusing on private behaviours, which have been largely overlooked in the normative influence literature.

The Novel Dopant Profile Inspection Methodology by FIB

2010 ◽  
Author(s):  
Po Fu Chou ◽  
Li Ming Lu
Keyword(s):  
High Resolution ◽  
Focused Ion Beam ◽  
Ion Beam ◽  
Real Sample ◽  
Physical Analysis ◽  
The Novel ◽  
High Contrast ◽  
Dopant Profile ◽  
P Type

Abstract Dopant profile inspection is one of the focused ion beam (FIB) physical analysis applications. This paper presents a technique for characterizing P-V dopant regions in silicon by using a FIB methodology. This technique builds on published work for backside FIB navigation, in which n-well contrast is observed. The paper demonstrates that the technique can distinguish both n- and p-type dopant regions. The capability for imaging real sample dopant regions on current fabricated devices is also demonstrated. SEM DC and FIB DC are complementary methodologies for the inspection of dopants. The advantage of the SEM DC method is high resolution and the advantage of FIB DC methodology is high contrast, especially evident in a deep N-well region.

scholarly journals Towards human distance estimation using a thermal sensor array

2021 ◽  
Author(s):  
Abdallah Naser ◽  
Ahmad Lotfi ◽  
Joni Zhong
Keyword(s):  
High Resolution ◽  
Independent Living ◽  
Sensor Array ◽  
Distance Estimation ◽  
Thermal Sensor ◽  
Indoor Environments ◽  
Contagious Diseases ◽  
Novel Approach ◽  
Thermal Cameras ◽  
Distance Estimator

AbstractHuman distance estimation is essential in many vital applications, specifically, in human localisation-based systems, such as independent living for older adults applications, and making places safe through preventing the transmission of contagious diseases through social distancing alert systems. Previous approaches to estimate the distance between a reference sensing device and human subject relied on visual or high-resolution thermal cameras. However, regular visual cameras have serious concerns about people’s privacy in indoor environments, and high-resolution thermal cameras are costly. This paper proposes a novel approach to estimate the distance for indoor human-centred applications using a low-resolution thermal sensor array. The proposed system presents a discrete and adaptive sensor placement continuous distance estimators using classification techniques and artificial neural network, respectively. It also proposes a real-time distance-based field of view classification through a novel image-based feature. Besides, the paper proposes a transfer application to the proposed continuous distance estimator to measure human height. The proposed approach is evaluated in different indoor environments, sensor placements with different participants. This paper shows a median overall error of $$\pm 0.2$$ ± 0.2  m in continuous-based estimation and $$96.8\%$$ 96.8 % achieved-accuracy in discrete distance estimation.

scholarly journals A Novel Approach to EEG Speech Activity Detection with Visual Stimuli and Mobile BCI

2021 ◽  
Vol 11 (2) ◽  
pp. 674
Author(s):  
Marianna Koctúrová ◽  
Jozef Juhár
Keyword(s):  
Visual Stimuli ◽  
Computer Interface ◽  
Single Subject ◽  
Detection Accuracy ◽  
The Novel ◽  
Activity Detection ◽  
Speech Activity ◽  
Novel Approach ◽  
Eeg Data ◽  
Speech Activity Detection

With the ever-progressing development in the field of computational and analytical science the last decade has seen a big improvement in the accuracy of electroencephalography (EEG) technology. Studies try to examine possibilities to use high dimensional EEG data as a source for Brain to Computer Interface. Applications of EEG Brain to computer interface vary from emotion recognition, simple computer/device control, speech recognition up to Intelligent Prosthesis. Our research presented in this paper was focused on the study of the problematic speech activity detection using EEG data. The novel approach used in this research involved the use visual stimuli, such as reading and colour naming, and signals of speech activity detectable by EEG technology. Our proposed solution is based on a shallow Feed-Forward Artificial Neural Network with only 100 hidden neurons. Standard features such as signal energy, standard deviation, RMS, skewness, kurtosis were calculated from the original signal from 16 EEG electrodes. The novel approach in the field of Brain to computer interface applications was utilised to calculated additional set of features from the minimum phase signal. Our experimental results demonstrated F1 score of 86.80% and 83.69% speech detection accuracy based on the analysis of EEG signal from single subject and cross-subject models respectively. The importance of these results lies in the novel utilisation of the mobile device to record the nerve signals which can serve as the stepping stone for the transfer of Brain to computer interface technology from technology from a controlled environment to the real-life conditions.

ChemInform Abstract: The Novel Approach to Indole Alkaloids by Using Pd(II)-Catalyzed Cyclization.

ChemInform ◽  
2015 ◽  
Vol 46 (17) ◽  
pp. no-no
Author(s):  
Hajime Yokoyama ◽  
Takayoshi Kubo ◽  
Yosuke Matsumura ◽  
Junichi Hosokawa ◽  
Masahiro Miyazawa ◽  
...  
Keyword(s):  
Indole Alkaloids ◽  
The Novel ◽  
Novel Approach

scholarly journals Caffeine-Induced Effects on Human Skeletal Muscle Contraction Time and Maximal Displacement Measured by Tensiomyography

Nutrients ◽  
2021 ◽  
Vol 13 (3) ◽  
pp. 815
Author(s):  
Przemysław Domaszewski ◽  
Paweł Pakosz ◽  
Mariusz Konieczny ◽  
Dawid Bączkowicz ◽  
Ewa Sadowska-Krępa
Keyword(s):  
Skeletal Muscle ◽  
Muscle Activation ◽  
Electric Pulse ◽  
Professional Athletes ◽  
Mechanical Activity ◽  
The Novel ◽  
Contraction Time ◽  
Novel Approach ◽  
Skeletal Muscle Contraction ◽  
Maximal Displacement

Studies on muscle activation time in sport after caffeine supplementation confirmed the effectiveness of caffeine. The novel approach was to determine whether a dose of 9 mg/kg/ body mass (b.m.) of caffeine affects the changes of contraction time and the displacement of electrically stimulated muscle (gastrocnemius medialis) in professional athletes who regularly consume products rich in caffeine and do not comply with the caffeine discontinuation period requirements. The study included 40 professional male handball players (age = 23.13 ± 3.51, b.m. = 93.51 ± 15.70 kg, height 191 ± 7.72, BMI = 25.89 ± 3.10). The analysis showed that in the experimental group the values of examined parameters were significantly reduced (p ≤ 0.001) (contraction time: before = 20.60 ± 2.58 ms/ after = 18.43 ± 3.05 ms; maximal displacement: before = 2.32 ± 0.80 mm/after = 1.69 ± 0.51 mm). No significant changes were found in the placebo group. The main achievement of this research was to demonstrate that caffeine at a dose of 9 mg/kg in professional athletes who regularly consume products rich in caffeine has a direct positive effect on the mechanical activity of skeletal muscle stimulated by an electric pulse.

Sign in / Sign up

Export Citation Format

Share Document