Evaluating the learning and performance characteristics of self-organizing systems with different task features

2021 ◽  
pp. 1-19
Author(s):  
Hao Ji ◽  
Yan Jin
Keyword(s):  
Systematic Evaluation ◽  
Full Potential ◽  
Learning Capability ◽  
Reward Function ◽  
Reward Functions ◽  
Good Learning ◽  
And Performance ◽  
Generation Problem ◽  
Self Organizing

Abstract Self-organizing systems (SOS) are developed to perform complex tasks in unforeseen situations with adaptability. Predefining rules for self-organizing agents can be challenging, especially in tasks with high complexity and changing environments. Our previous work has introduced a multiagent reinforcement learning (RL) model as a design approach to solving the rule generation problem of SOS. A deep multiagent RL algorithm was devised to train agents to acquire the task and self-organizing knowledge. However, the simulation was based on one specific task environment. Sensitivity of SOS to reward functions and systematic evaluation of SOS designed with multiagent RL remain an issue. In this paper, we introduced a rotation reward function to regulate agent behaviors during training and tested different weights of such reward on SOS performance in two case studies: box-pushing and T-shape assembly. Additionally, we proposed three metrics to evaluate the SOS: learning stability, quality of learned knowledge, and scalability. Results show that depending on the type of tasks; designers may choose appropriate weights of rotation reward to obtain the full potential of agents’ learning capability. Good learning stability and quality of knowledge can be achieved with an optimal range of team sizes. Scaling up to larger team sizes has better performance than scaling downwards.

scholarly journals PORF-DDPG: Learning Personalized Autonomous Driving Behavior with Progressively Optimized Reward Function

Sensors ◽  
2020 ◽  
Vol 20 (19) ◽  
pp. 5626
Author(s):  
Jie Chen ◽  
Tao Wu ◽  
Meiping Shi ◽  
Wei Jiang
Keyword(s):  
Autonomous Vehicles ◽  
Autonomous Driving ◽  
Driving Behavior ◽  
Human Observer ◽  
Learning Capability ◽  
The Road ◽  
Human In The Loop ◽  
Reward Function ◽  
Artificial Intelligence Technology ◽  
Reward Functions

Autonomous driving with artificial intelligence technology has been viewed as promising for autonomous vehicles hitting the road in the near future. In recent years, considerable progress has been made with Deep Reinforcement Learnings (DRLs) for realizing end-to-end autonomous driving. Still, driving safely and comfortably in real dynamic scenarios with DRL is nontrivial due to the reward functions being typically pre-defined with expertise. This paper proposes a human-in-the-loop DRL algorithm for learning personalized autonomous driving behavior in a progressive learning way. Specifically, a progressively optimized reward function (PORF) learning model is built and integrated into the Deep Deterministic Policy Gradient (DDPG) framework, which is called PORF-DDPG in this paper. PORF consists of two parts: the first part of the PORF is a pre-defined typical reward function on the system state, the second part is modeled as a Deep Neural Network (DNN) for representing driving adjusting intention by the human observer, which is the main contribution of this paper. The DNN-based reward model is progressively learned using the front-view images as the input and via active human supervision and intervention. The proposed approach is potentially useful for driving in dynamic constrained scenarios when dangerous collision events might occur frequently with classic DRLs. The experimental results show that the proposed autonomous driving behavior learning method exhibits online learning capability and environmental adaptability.

LIGHTING AND PERFORMANCE: AN ANALYSIS ON LIGHTING EFFICIENCY OF ARCHITECTURE STUDIO

2019 ◽  
Vol 1 (1) ◽  
pp. 92
Author(s):  
Fazidah Hanim Husain
Keyword(s):  
Learning Environment ◽  
Comfort Level ◽  
Artificial Lighting ◽  
Level Measurement ◽  
Acceptable Range ◽  
Creative Learning ◽  
Illuminance Level ◽  
And Performance ◽  
Effect Of Light

Lighting is one of the key elements in any space and building infrastructure. Good design for an area in the building requires sufficient light that contributes to the efficiency of the activities. The correct method allows natural light to transmit, reduce heat and glare in providing a conducive learning environment. Light plays a significant influence to the quality of space and contributes focus of the students in an architecture studio. Previous research has shown that the effect of light also controlled emotions, behavior, and mood of the students. The operations of artificial lighting that have been used most of the time in an architecture studio during day and night may create lavishness and inadequacy at the same time. Therefore, this paper focuses on the identifying the quality of light for the architecture studio in UiTM (Perak), to instill a creative learning environment. Several methodologies adopted in this study such as illuminance level measurement using lux meter (LM-8100), and a questionnaire survey in gauging the lighting comfort level from students’ perspective. The study revealed that the illuminance level in the architecture studio is insufficient and not in the acceptable range stated in the Malaysian: Standards 1525:2007 and  not evenly distributed.  The study also concluded that the current studio environment is not condusive and appears monotonous. 

Strategic threats to energy security as risks of quality of people's life

2020 ◽  
Vol 16 (4) ◽  
pp. 730-744
Author(s):  
V.I. Loktionov
Keyword(s):  
Quality Of Life ◽  
Energy Security ◽  
Well Being ◽  
Scientific Methods ◽  
Analysis And Synthesis ◽  
General Scientific ◽  
And Performance ◽  
Economic Well Being ◽  
The Way

Subject. The article reviews the way strategic threats to energy security influence the quality of people's life. Objectives. The study unfolds the theory of analyzing strategic threats to energy security by covering the matter of quality of people's life. Methods. To analyze the way strategic threats to energy security spread across cross-sectoral commodity and production chains and influences quality of people's living, I applied the factor analysis and general scientific methods of analysis and synthesis. Results. I suggest interpreting strategic threats to energy security as risks of people's quality of life due to a reduction in the volume of energy supply. I identified mechanisms reflecting how the fuel and energy complex and its development influence the quality of people's life. The article sets out the method to assess such quality-of-life risks arising from strategic threats to energy security. Conclusions and Relevance. In the current geopolitical situation, strategic threats to energy security cause long-standing adverse consequences for the quality of people's life. If strategic threats to energy security are further construed as risk of quality of people's life, this will facilitate the preparation and performance of a more effective governmental policy on energy, which will subsequently raise the economic well-being of people.

Return on Invesment (ROI) of Software Product: A Systematic Literature Review

2015 ◽  
Vol 6 (1) ◽  
pp. 50-57
Author(s):  
Rizqa Raaiqa Bintana ◽  
Putri Aisyiyah Rakhma Devi ◽  
Umi Laili Yuhana
Keyword(s):  
Return On Investment ◽  
Assessment Criteria ◽  
Software Product ◽  
And Performance ◽  
Rational Consideration ◽  
Actual Return ◽  
The Cost ◽  
Investment Models ◽  
The Impact

The quality of the software can be measured by its return on investment. Factors which may affect the return on investment (ROI) is the tangible factors (such as the cost) dan intangible factors (such as the impact of software to the users or stakeholder). The factor of the software itself are assessed through reviewing, testing, process audit, and performance of software. This paper discusses the consideration of return on investment (ROI) assessment criteria derived from the software and its users. These criteria indicate that the approach may support a rational consideration of all relevant criteria when evaluating software, and shows examples of actual return on investment models. Conducted an analysis of the assessment criteria that affect the return on investment if these criteria have a disproportionate effort that resulted in a return on investment of a software decreased. Index Terms - Assessment criteria, Quality assurance, Return on Investment, Software product

scholarly journals Manufacturing and development of a bolted GFRP flange joint for oil and gas applications

2021 ◽  
pp. 095440542198951
Author(s):  
Muhsin Aljuboury ◽  
Md Jahir Rizvi ◽  
Stephen Grove ◽  
Richard Cullen
Keyword(s):  
Pressure Vessel ◽  
Oil And Gas ◽  
Polyester Resin ◽  
High Strength ◽  
Adhesively Bonded ◽  
Acceptable Quality ◽  
Composite Pipe ◽  
And Performance ◽  
Composite Pipes

The goal of this experimental study is to manufacture a bolted GFRP flange connection for composite pipes with high strength and performance. A mould was designed and manufactured, which ensures the quality of the composite materials and controls its surface grade. Based on the ASME Boiler and Pressure Vessel Code, Section X, this GFRP flange was fabricated using biaxial glass fibre braid and polyester resin in a vacuum infusion process. In addition, many experiments were carried out using another mould made of glass to solve process-related issues. Moreover, an investigation was conducted to compare the drilling of the GFRP flange using two types of tools; an Erbauer diamond tile drill bit and a Brad & Spur K10 drill. Six GFRP flanges were manufactured to reach the final product with acceptable quality and performance. The flange was adhesively bonded to a composite pipe after chamfering the end of the pipe. Another type of commercially-available composite flange was used to close the other end of the pipe. Finally, blind flanges were used to close both ends, making the pressure vessel that will be tested under the range of the bolt load and internal pressure.

scholarly journals Toward an Automatic Quality Assessment of Voice-Based Telemedicine Consultations: A Deep Learning Approach

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 3279
Author(s):  
Maria Habib ◽  
Mohammad Faris ◽  
Raneem Qaddoura ◽  
Manal Alomari ◽  
Alaa Alomari ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Quality Assessment ◽  
Transcript Level ◽  
Assessment Process ◽  
Classification Model ◽  
Systematic Evaluation ◽  
Transcript Levels ◽  
Perceptual Evaluation

Maintaining a high quality of conversation between doctors and patients is essential in telehealth services, where efficient and competent communication is important to promote patient health. Assessing the quality of medical conversations is often handled based on a human auditory-perceptual evaluation. Typically, trained experts are needed for such tasks, as they follow systematic evaluation criteria. However, the daily rapid increase of consultations makes the evaluation process inefficient and impractical. This paper investigates the automation of the quality assessment process of patient–doctor voice-based conversations in a telehealth service using a deep-learning-based classification model. For this, the data consist of audio recordings obtained from Altibbi. Altibbi is a digital health platform that provides telemedicine and telehealth services in the Middle East and North Africa (MENA). The objective is to assist Altibbi’s operations team in the evaluation of the provided consultations in an automated manner. The proposed model is developed using three sets of features: features extracted from the signal level, the transcript level, and the signal and transcript levels. At the signal level, various statistical and spectral information is calculated to characterize the spectral envelope of the speech recordings. At the transcript level, a pre-trained embedding model is utilized to encompass the semantic and contextual features of the textual information. Additionally, the hybrid of the signal and transcript levels is explored and analyzed. The designed classification model relies on stacked layers of deep neural networks and convolutional neural networks. Evaluation results show that the model achieved a higher level of precision when compared with the manual evaluation approach followed by Altibbi’s operations team.

scholarly journals Modelling Exposure by Spraying Activities—Status and Future Needs

2021 ◽  
Vol 18 (15) ◽  
pp. 7737
Author(s):  
Stefan Hahn ◽  
Jessica Meyer ◽  
Michael Roitzsch ◽  
Christiaan Delmaar ◽  
Wolfgang Koch ◽  
...  
Keyword(s):  
Current Knowledge ◽  
Model Performance ◽  
Relevant Information ◽  
Systematic Evaluation ◽  
Model Accuracy ◽  
Efficient Manner ◽  
User Perspective ◽  
Model Predictions ◽  
Spray Applications

Spray applications enable a uniform distribution of substances on surfaces in a highly efficient manner, and thus can be found at workplaces as well as in consumer environments. A systematic literature review on modelling exposure by spraying activities has been conducted and status and further needs have been discussed with experts at a symposium. This review summarizes the current knowledge about models and their level of conservatism and accuracy. We found that extraction of relevant information on model performance for spraying from published studies and interpretation of model accuracy proved to be challenging, as the studies often accounted for only a small part of potential spray applications. To achieve a better quality of exposure estimates in the future, more systematic evaluation of models is beneficial, taking into account a representative variety of spray equipment and application patterns. Model predictions could be improved by more accurate consideration of variation in spray equipment. Inter-model harmonization with regard to spray input parameters and appropriate grouping of spray exposure situations is recommended. From a user perspective, a platform or database with information on different spraying equipment and techniques and agreed standard parameters for specific spraying scenarios from different regulations may be useful.

scholarly journals The effect of silica desiccation under different storage conditions on filter-immobilized environmental DNA

2021 ◽  
Vol 14 (1) ◽  
Author(s):  
Michael J. Allison ◽  
Jessica M. Round ◽  
Lauren C. Bergman ◽  
Ali Mirabzadeh ◽  
Heather Allen ◽  
...  
Keyword(s):  
Silica Gel ◽  
Storage Temperature ◽  
Environmental Dna ◽  
Cost Effective ◽  
Storage Conditions ◽  
Systematic Evaluation ◽  
Silica Bead ◽  
Gel Beads ◽  
Polymerase Chain

Abstract Objective Silica gel beads have promise as a non-toxic, cost-effective, portable method for storing environmental DNA (eDNA) immobilized on filter membranes. Consequently, many ecological surveys are turning to silica bead filter desiccation rather than ethanol preservation. However, no systematic evaluation of silica bead storage conditions or duration past 1 week has been published. The present study evaluates the quality of filter-immobilized eDNA desiccated with silica gel under different storage conditions for over a year using targeted quantitative real-time polymerase chain reaction (qPCR)-based assays. Results While the detection of relatively abundant eDNA target was stable over 15 months from either ethanol- or silica gel-preserved filters at − 20 and 4 °C, silica gel out-performed ethanol preservation at 23 °C by preventing a progressive decrease in eDNA sample quality. Silica gel filter desiccation preserved low abundance eDNA equally well up to 1 month regardless of storage temperature (18, 4, or − 20 °C). However only storage at − 20 °C prevented a noticeable decrease in detectability at 5 and 12 months. The results indicate that brief storage of eDNA filters with silica gel beads up to 1 month can be successfully accomplished at a range of temperatures. However, longer-term storage should be at − 20 °C to maximize sample integrity.

FRI0524 THE ACR’S RHEUMATOLOGY INFORMATICS SYSTEM FOR EFFECTIVENESS (RISE) REGISTRY SUPPORTS SMALL RHEUMATOLOGY PRACTICES FOR FEDERAL QUALITY REPORTING PROGRAM

2020 ◽  
Vol 79 (Suppl 1) ◽  
pp. 861-862
Author(s):  
Z. Izadi ◽  
T. Johansson ◽  
J. LI ◽  
G. Schmajuk ◽  
J. Yazdany
Keyword(s):  
Quality Measures ◽  
Quality Reporting ◽  
Practice Characteristics ◽  
Informatics System ◽  
Group Practices ◽  
Status Assessment ◽  
And Performance ◽  
Reporting Programs

Background:The Rheumatology Informatics System for Effectiveness (RISE) Registry was developed by the ACR to help rheumatologists improve quality of care and meet federal reporting requirements. In the current quality program administered by the U.S. Centers for Medicare and Medicaid services, rheumatologists are scored on quality measures, and performance is tied to financial incentives or penalties. Rheumatoid arthritis (RA)-specific quality measures can only be submitted through RISE to federal programs.Objectives:This study used data from the RISE registry to investigate rheumatologists’ federal reporting patterns on five RA-specific quality measures in 2018 and investigated the effect of practice characteristics on federal reporting of these measures.Methods:We analyzed data on all rheumatologists who continuously participated in RISE between Jan 2017 to Dec 2018 and who had patients eligible for at least one RA-specific measure. Five measures were examined: tuberculosis screening before biologic use, disease activity assessment, functional status assessment, assessment and classification of disease prognosis, and glucocorticoid management. We assessed whether or not rheumatologists reported specific quality measures via RISE. We investigated the effect of practice characteristics (practice structure; number of providers; geographic region) on the likelihood of reporting using adjusted analyses that controlled for measure performance (performance in 2018; change in performance from 2017; and performance relative to national average performance). Analyses accounted for clustering by practice.Results:Data from 799 providers from 207 practices managing 213,757 RA patients was examined. The most common practice structure was a single-specialty group practice (53%), followed by solo (28%) and multi-specialty group practice (12%). Most providers (73%) had patients eligible for all five RA quality measures. Federal reporting of quality measures through RISE varied significantly by provider, ranging from no reporting (60%) to reporting all eligible RA measures (12.2%). Reporting through RISE also varied significantly by quality measure and was highest for functional status assessment (36%) and lowest for assessment and classification of disease prognosis (20%). Small practices (1-4 providers) were more likely to report all eligible RA quality measures compared to larger practices (21%, 6%; p<0.001). In adjusted analyses, solo practices were more likely than single-specialty group practices to report RA measures (42%, 31%; p<0.027) while multispecialty group practices were less likely (18%, 31%; p<0.001). Additionally, higher performance in 2018 and performance ≥ the national average performance was associated with federal reporting of the measures through RISE (p≤0.004).Conclusion:Forty percent of U.S. rheumatologists participating in RISE used the registry for federal quality reporting. Physicians using RISE for reporting were disproportionately in small and solo practices, suggesting that the registry is fulfilling an important role in helping these practices participate in national quality reporting programs. Supporting small practices is especially important given the workforce shortages in rheumatology. We observed that practices reporting through RISE had higher measure performance than other participating practices, which suggests that the registry is facilitating quality improvement. Studies are ongoing to further investigate the impact of federal quality reporting programs and RISE participation on the quality of rheumatologic care in the United States.Disclaimer: This data was supported by the ACR’s RISE Registry. However, the views expressed represent those of the authors, not necessarily those of the ACR.Disclosure of Interests:Zara Izadi: None declared, Tracy Johansson: None declared, Jing Li: None declared, Gabriela Schmajuk Grant/research support from: Pfizer, Jinoos Yazdany Grant/research support from: Pfizer

scholarly journals Purchasing Quality Nursing Home Care in the Veterans Health Administration

2020 ◽  
Vol 4 (6) ◽  
Author(s):  
Orna Intrator ◽  
Edward Alan Miller ◽  
Portia Y Cornell ◽  
Cari Levy ◽  
Christopher W Halladay ◽  
...  
Keyword(s):  
The United States ◽  
Veterans Affairs ◽  
Nursing Home Care ◽  
Veterans Health ◽  
Health Administration ◽  
Star Rating ◽  
For Profit ◽  
Veterans Affairs Medical Centers ◽  
And Performance

Abstract Background and Objectives U.S. Department of Veterans Affairs Medical Centers (VAMCs) contract with nursing homes (NHs) in their community to serve Veterans. This study compares the characteristics and performance of Veterans Affairs (VA)-paid and non-VA-paid NHs both nationally and within local VAMC markets. Research Design and Methods VA-paid NHs were identified, characterized, and linked to VAMC markets using data drawn from VA administrative files. NHs in the United States in December 2015 were eligible for the analysis, including. 1,307 VA-paid NHs and 14,253 non-VA-paid NHs with NH Compare measures in 128 VAMC markets with any VA-paid NHs. Measurements were derived from the Centers for Medicare and Medicaid Services (CMS) five-star rating system, NH Compare. Results VA-paid NHs had more beds, residents per day, and were more likely to be for-profit relative to non-VA-paid NHs. Nationally, the average CMS NH Compare star rating was slightly lower among VA-paid NHs than non-VA-paid NHs (3.05 vs. 3.21, p = .04). This difference was seen in all 3 domains: inspection (3.11 vs. 3.23, p &lt; .001), quality (2.68 vs. 2.83, p &lt; .001), and total nurse staffing (3.36 vs. 3.42, p &lt; .10). There was wide variability across VAMC markets in the ratio of average star rating of VA-paid and non-VA-paid NHs (mean ratio = 0.93, interquartile range = 0.78–1.08). Discussion and Implications With increased community NH use expected following the implementation of the MISSION Act, comparison of the quality of purchased services to other available services becomes critical for ensuring quality, including for NH care. Methods presented in this article can be used to examine the quality of purchased care following the MISSION Act implementation. In particular, dashboards such as that for VA-paid NHs that compare to similar non-VA-paid NHs can provide useful information to quality improvement efforts.

Sign in / Sign up

Export Citation Format

Share Document