scholarly journals A Dynamically Reconfigurable BbNN Architecture for Scalable Neuroevolution in Hardware

Electronics ◽  
2020 ◽  
Vol 9 (5) ◽  
pp. 803 ◽  
Author(s):  
Alberto García ◽  
Rafael Zamacola ◽  
Andrés Otero ◽  
Eduardo de la Torre
Keyword(s):  
Evolutionary Algorithm ◽  
Performance Indicators ◽  
State Of The Art ◽  
Classification Problems ◽  
Dynamically Reconfigurable ◽  
Training Stage ◽  
System On A Chip ◽  
Block Based ◽  
Synchronization Scheme

In this paper, a novel hardware architecture for neuroevolution is presented, aiming to enable the continuous adaptation of systems working in dynamic environments, by including the training stage intrinsically in the computing edge. It is based on the block-based neural network model, integrated with an evolutionary algorithm that optimizes the weights and the topology of the network simultaneously. Differently to the state-of-the-art, the proposed implementation makes use of advanced dynamic and partial reconfiguration features to reconfigure the network during evolution and, if required, to adapt its size dynamically. This way, the number of logic resources occupied by the network can be adapted by the evolutionary algorithm to the complexity of the problem, the expected quality of the results, or other performance indicators. The proposed architecture, implemented in a Xilinx Zynq-7020 System-on-a-Chip (SoC) FPGA device, reduces the usage of DSPs and BRAMS while introducing a novel synchronization scheme that controls the latency of the circuit. The proposed neuroevolvable architecture has been integrated with the OpenAI toolkit to show how it can efficiently be applied to control problems, with a variable complexity and dynamic behavior. The versatility of the solution is assessed by also targeting classification problems.

scholarly journals HYBRID NSGA-II OPTIMIZATION FOR IMPROVING THE THREE-TERM BP NETWORK FOR MULTICLASS CLASSIFICATION PROBLEMS

2015 ◽  
Author(s):  
Ashraf Osman Ibrahim ◽  
Siti Mariyam Shamsuddin ◽  
Sultan Noman Qasem
Keyword(s):  
Genetic Algorithm ◽  
Evolutionary Algorithm ◽  
Hybrid Algorithm ◽  
Search Algorithm ◽  
Classification Performance ◽  
Classification Problems ◽  
Nsga Ii ◽  
Bp Network ◽  
Multiobjective Evolutionary Algorithm

Recently, hybrid algorithms have received considerable attention from a number of researchers. This paper presents a hybrid of the multiobjective evolutionary algorithm to gain a better accuracy of the fi nal solutions. The aim of using the hybrid algorithm is to improve the multiobjective evolutionary algorithm performance in terms of the enhancement of all the individuals in the population and increase the quality of the Pareto optimal solutions. The multiobjective evolutionary algorithm used in this study is a nondominated sorting genetic algorithm-II (NSGA-II) together with its hybrid, the backpropagation algorithm (BP), which is used as a local search algorithm to optimize the accuracy and complexity of the three-term backpropagation (TBP) network. The outcome positively demonstrates that the hybrid algorithm is able to improve the classification performance with a smaller number of hidden nodes and is effective in multiclass classifi cation problems. Furthermore, the results indicate that the proposed hybrid method is a potentially useful classifi er for enhancing the classification process ability when compared with the multiobjective genetic algorithm based on the TBP network (MOGATBP) and certain other methods found in the literature.  

scholarly journals Comparison of Attention-based Deep LearningModels for EEG Classification

2021 ◽  
Author(s):  
Giulia Cisotto ◽  
Alessio Zanga ◽  
Joanna Chlebus ◽  
Italo Zoppis ◽  
Sara Manzoni ◽  
...  
Keyword(s):  
Deep Learning ◽  
State Of The Art ◽  
Classification Performance ◽  
Classification Problems ◽  
Large Variability ◽  
Eeg Classification ◽  
Time Frequency ◽  
Promising Strategy ◽  
Complex Reasoning

Abstract Deep Learning (DL) has recently shown promising classification performance in Electroencephalography (EEG) in many different scenarios. However, the complex reasoning of such models often prevent the user to explain their classification abilities. Attention, one of the most recent and influential ideas in DL, allows the models to learn which portions of the data are relevant to the final classification output. In this work, we compared three attention-enhanced DL models, the brand-new InstaGATs , an LSTM with attention and a CNN with attention. We used these models to classify normal and abnormal, including artifactual and pathological, EEG patterns in three different datasets. We achieved the state of the art in all classification problems, regardless the large variability of the datasets and the simple architecture of the attention-enhanced models. Additionally, we proved that, depending on how the attention mechanism is applied and where the attention layer is located in the model, we can alternatively leverage the information contained in the time, frequency or space domain of the EEG dataset. Therefore, attention represents a promising strategy to evaluate the quality of the EEG information, and its relevance for classification, in different real-world scenarios.

Data science in economics: comprehensive review of advanced machine learning and deep learning methods

2020 ◽  
Author(s):  
Saeed Nosratabadi ◽  
Amir Mosavi ◽  
Puhong Duan ◽  
Pedram Ghamisi ◽  
Ferdinand Filip ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Data Science ◽  
State Of The Art ◽  
Science Methods ◽  
Learning Models ◽  
Diverse Range ◽  
Hybrid Machine ◽  
Economics Research

This paper provides a state-of-the-art investigation of advances in data science in emerging economic applications. The analysis was performed on novel data science methods in four individual classes of deep learning models, hybrid deep learning models, hybrid machine learning, and ensemble models. Application domains include a wide and diverse range of economics research from the stock market, marketing, and e-commerce to corporate banking and cryptocurrency. Prisma method, a systematic literature review methodology, was used to ensure the quality of the survey. The findings reveal that the trends follow the advancement of hybrid models, which, based on the accuracy metric, outperform other learning algorithms. It is further expected that the trends will converge toward the advancements of sophisticated hybrid deep learning models.

Computable metrics of personal performance in software development teams

2019 ◽  
Author(s):  
Andriy Lishchytovych ◽  
Volodymyr Pavlenko
Keyword(s):  
Life Cycle ◽  
Software Development ◽  
Product Quality ◽  
Performance Indicators ◽  
Key Performance Indicators ◽  
Project Manager ◽  
Development Life Cycle ◽  
Software Product ◽  
Software Development Life Cycle

The present article describes setup, configuration and usage of the key performance indicators (KPIs) of members of project teams involved into the software development life cycle. Key performance indicators are described for the full software development life cycle and imply the deep integration with both task tracking systems and project code management systems, as well as a software product quality testing system. To illustrate, we used the extremely popular products - Atlassian Jira (tracking development tasks and bugs tracking system) and git (code management system). The calculation of key performance indicators is given for a team of three developers, two testing engineers responsible for product quality, one designer, one system administrator, one product manager (responsible for setting business requirements) and one project manager. For the key members of the team, it is suggested to use one integral key performance indicator per the role / team member, which reflects the quality of the fulfillment of the corresponding role of the tasks. The model of performance indicators is inverse positive - the initial value of each of the indicators is zero and increases in the case of certain deviations from the standard performance of official duties inherent in a particular role. The calculation of the proposed key performance indicators can be fully automated (in particular, using Atlassian Jira and Atlassian Bitbucket (git) or any other systems, like Redmine, GitLab or TestLink), which eliminates the human factor and, after the automation, does not require any additional effort to calculate. Using such a tool as the key performance indicators allows project managers to completely eliminate bias, reduce the emotional component and provide objective data for the project manager. The described key performance indicators can be used to reduce the time required to resolve conflicts in the team, increase productivity and improve the quality of the software product.

State-of-the-Art: A Systematic Literature Review on Image Segmentation in Latent Fingerprint Forensics

2019 ◽  
Vol 12 ◽  
Author(s):  
Megha Chhabra ◽  
Manoj Kumar Shukla ◽  
Kiran Kumar Ravulakollu
Keyword(s):  
Image Segmentation ◽  
Background Noise ◽  
State Of The Art ◽  
Recognition Rate ◽  
Poor Quality ◽  
Latent Fingerprint ◽  
In The Beginning ◽  
The Comparative Study ◽  
Finger Skin

: Latent fingerprints are unintentional finger skin impressions left as ridge patterns at crime scenes. A major challenge in latent fingerprint forensics is the poor quality of the lifted image from the crime scene. Forensics investigators are in permanent search of novel outbreaks of the effective technologies to capture and process low quality image. The accuracy of the results depends upon the quality of the image captured in the beginning, metrics used to assess the quality and thereafter level of enhancement required. The low quality of the image collected by low quality scanners, unstructured background noise, poor ridge quality, overlapping structured noise result in detection of false minutiae and hence reduce the recognition rate. Traditionally, Image segmentation and enhancement is partially done manually using help of highly skilled experts. Using automated systems for this work, differently challenging quality of images can be investigated faster. This survey amplifies the comparative study of various segmentation techniques available for latent fingerprint forensics.

Principals’ Policy Preferences concerning Accountability: Implications for Key Competencies, Performance Indicators, and Professional Development

1995 ◽  
Vol 5 (5) ◽  
pp. 448-481 ◽  
Author(s):  
R. J. S. Mac Macpherson ◽  
Margaret Taplin
Keyword(s):  
Professional Development ◽  
Performance Indicators ◽  
Policy Preferences ◽  
Development Programs ◽  
Stakeholder Groups ◽  
Key Competencies ◽  
Professional Development Programs ◽  
Accountability Practices ◽  
State Schools

In this paper, we examine the policy preferences of Tasmania's principals concerning accountability criteria and processes, compare their views to other stakeholder groups, and identify issues that warrant attention in principals’ professional development programs. We show that there are many criteria and processes related to the quality of learning, teaching, and leadership that are valued by all stakeholder groups, including principals. We conclude that Tasmanian state schools probably need to review and develop their accountability policies, and that the professional development will need to prepare leaders for specific forms of performance and generate key competencies if more educative forms of accountability practices are to be realised in practice.

UBAR

2021 ◽  
Vol 20 (3) ◽  
pp. 1-25
Author(s):  
Elham Shamsa ◽  
Alma Pröbstl ◽  
Nima TaheriNejad ◽  
Anil Kanduri ◽  
Samarjit Chakraborty ◽  
...  
Keyword(s):  
Resource Management ◽  
Quality Of Experience ◽  
State Of The Art ◽  
State Of Charge ◽  
User Preference ◽  
Management Approach ◽  
High Quality ◽  
Trade Off ◽  
Run Time

Smartphone users require high Battery Cycle Life (BCL) and high Quality of Experience (QoE) during their usage. These two objectives can be conflicting based on the user preference at run-time. Finding the best trade-off between QoE and BCL requires an intelligent resource management approach that considers and learns user preference at run-time. Current approaches focus on one of these two objectives and neglect the other, limiting their efficiency in meeting users’ needs. In this article, we present UBAR, User- and Battery-aware Resource management, which considers dynamic workload, user preference, and user plug-in/out pattern at run-time to provide a suitable trade-off between BCL and QoE. UBAR personalizes this trade-off by learning the user’s habits and using that to satisfy QoE, while considering battery temperature and State of Charge (SOC) pattern to maximize BCL. The evaluation results show that UBAR achieves 10% to 40% improvement compared to the existing state-of-the-art approaches.

scholarly journals Smoothing additive manufactured parts using ns-pulsed laser radiation

2021 ◽  
Author(s):  
Florian Kuisat ◽  
Fernando Lasagni ◽  
Andrés Fabián Lasagni
Keyword(s):  
Surface Roughness ◽  
Mechanical Performance ◽  
State Of The Art ◽  
Pulsed Laser ◽  
Industrial Applications ◽  
Laser Source ◽  
Pulsed Laser Radiation ◽  
Current State ◽  
The Impact

AbstractIt is well known that the surface topography of a part can affect its mechanical performance, which is typical in additive manufacturing. In this context, we report about the surface modification of additive manufactured components made of Titanium 64 (Ti64) and Scalmalloy®, using a pulsed laser, with the aim of reducing their surface roughness. In our experiments, a nanosecond-pulsed infrared laser source with variable pulse durations between 8 and 200 ns was applied. The impact of varying a large number of parameters on the surface quality of the smoothed areas was investigated. The results demonstrated a reduction of surface roughness Sa by more than 80% for Titanium 64 and by 65% for Scalmalloy® samples. This allows to extend the applicability of additive manufactured components beyond the current state of the art and break new ground for the application in various industrial applications such as in aerospace.

scholarly journals Galileo L10 Satellites: Orbit, Clock and Signal-in-Space Performance Analysis

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1695
Author(s):  
Constantin-Octavian Andrei ◽  
Sonja Lahtinen ◽  
Markku Poutanen ◽  
Hannu Koivula ◽  
Jan Johansson
Keyword(s):  
Performance Indicators ◽  
Satellite System ◽  
Short Term ◽  
Orbital Inclination ◽  
Navigation Data ◽  
Periodic Signals ◽  
Global Navigation Satellite ◽  
Minor Correction ◽  
Very High

The tenth launch (L10) of the European Global Navigation Satellite System Galileo filled in all orbital slots in the constellation. The launch carried four Galileo satellites and took place in July 2018. The satellites were declared operational in February 2019. In this study, we report on the performance of the Galileo L10 satellites in terms of orbital inclination and repeat period parameters, broadcast satellite clocks and signal in space (SiS) performance indicators. We used all available broadcast navigation data from the IGS consolidated navigation files. These satellites have not been reported in the previous studies. First, the orbital inclination (56.7±0.15°) and repeat period (50680.7±0.22 s) for all four satellites are within the nominal values. The data analysis reveals also 13.5-, 27-, 177- and 354-days periodic signals. Second, the broadcast satellite clocks show different correction magnitude due to different trends in the bias component. One clock switch and several other minor correction jumps have occurred since the satellites were declared operational. Short-term discontinuities are within ±1 ps/s, whereas clock accuracy values are constantly below 0.20 m (root-mean-square—rms). Finally, the SiS performance has been very high in terms of availability and accuracy. Monthly SiS availability has been constantly above the target value of 87% and much higher in 2020 as compared to 2019. Monthly SiS accuracy has been below 0.20 m (95th percentile) and below 0.40 m (99th percentile). The performance figures depend on the content and quality of the consolidated navigation files as well as the precise reference products. Nevertheless, these levels of accuracy are well below the 7 m threshold (95th percentile) specified in the Galileo service definition document.

scholarly journals Ensemble-Based Out-of-Distribution Detection

Electronics ◽  
2021 ◽  
Vol 10 (5) ◽  
pp. 567
Author(s):  
Donghun Yang ◽  
Kien Mai Mai Ngoc ◽  
Iksoo Shin ◽  
Kyong-Ha Lee ◽  
Myunggwon Hwang
Keyword(s):  
Detection Method ◽  
State Of The Art ◽  
Metric Learning ◽  
Feature Space ◽  
Confidence Score ◽  
Distance Metric Learning ◽  
Current State ◽  
Overall Performance ◽  
Deep Learning Model

To design an efficient deep learning model that can be used in the real-world, it is important to detect out-of-distribution (OOD) data well. Various studies have been conducted to solve the OOD problem. The current state-of-the-art approach uses a confidence score based on the Mahalanobis distance in a feature space. Although it outperformed the previous approaches, the results were sensitive to the quality of the trained model and the dataset complexity. Herein, we propose a novel OOD detection method that can train more efficient feature space for OOD detection. The proposed method uses an ensemble of the features trained using the softmax-based classifier and the network based on distance metric learning (DML). Through the complementary interaction of these two networks, the trained feature space has a more clumped distribution and can fit well on the Gaussian distribution by class. Therefore, OOD data can be efficiently detected by setting a threshold in the trained feature space. To evaluate the proposed method, we applied our method to various combinations of image datasets. The results show that the overall performance of the proposed approach is superior to those of other methods, including the state-of-the-art approach, on any combination of datasets.

Sign in / Sign up

Export Citation Format

Share Document