• Title/Summary/Keyword: training parameters

Search Result 1,021, Processing Time 0.031 seconds

A vibration-based approach for detecting arch dam damage using RBF neural networks and Jaya algorithms

  • Ali Zar;Zahoor Hussain;Muhammad Akbar;Bassam A. Tayeh;Zhibin Lin
    • Smart Structures and Systems
    • /
    • v.32 no.5
    • /
    • pp.319-338
    • /
    • 2023
  • The study presents a new hybrid data-driven method by combining radial basis functions neural networks (RBF-NN) with the Jaya algorithm (JA) to provide effective structural health monitoring of arch dams. The novelty of this approach lies in that only one user-defined parameter is required and thus can increase its effectiveness and efficiency, as compared to other machine learning techniques that often require processing a large amount of training and testing model parameters and hyper-parameters, with high time-consuming. This approach seeks rapid damage detection in arch dams under dynamic conditions, to prevent potential disasters, by utilizing the RBF-NNN to seamlessly integrate the dynamic elastic modulus (DEM) and modal parameters (such as natural frequency and mode shape) as damage indicators. To determine the dynamic characteristics of the arch dam, the JA sequentially optimizes an objective function rooted in vibration-based data sets. Two case studies of hyperbolic concrete arch dams were carefully designed using finite element simulation to demonstrate the effectiveness of the RBF-NN model, in conjunction with the Jaya algorithm. The testing results demonstrated that the proposed methods could exhibit significant computational time-savings, while effectively detecting damage in arch dam structures with complex nonlinearities. Furthermore, despite training data contaminated with a high level of noise, the RBF-NN and JA fusion remained the robustness, with high accuracy.

Development of Fine Denier Silkworm Hybrid $CSR48{\times}CSR5$ of Bombyx mori L. for Superior Quality Silk

  • Kalpana G. V.;Kumar N. Suresh;Basavaraja H. K.;Reddy N. Mal;Palit A. K.
    • International Journal of Industrial Entomology and Biomaterials
    • /
    • v.10 no.2
    • /
    • pp.147-151
    • /
    • 2005
  • Serious attempt for the improvement of quality parameters in silkworm hybrids came rather very late in India. Realising the need for productive breeds to the field and reorientation in breeding methodology, the silkworm breeders of CSRTI, Mysore were able to develop silkworm breeds with fine denier namely, JPN7, CSR48, B63 and B65 of specific industrial requirement through directional selection. As the success of silkworm breeds mainly depends on their combining ability, the developed breeds were subjected for hybrid evaluation. Out of 42 bivoltine hybrids studied, one hybrid, $CSR48{\times}CSR5$ was identified for its superiority over the existing bivoltine hybrids namely $CSR2{\times}CSR4,\;CSR2{\times}CSR5\;and\;CSR18{\times}CSR19$ for majority of qualitative traits. Post cocoon testing of large quantity of cocoons of $CSR48{\times}CSR5$ resulted in the production of high quality '3A'grade silk. It is for the first time in the Indian Sericulture industry that high quality silk with longer filament length of 1474 m, denier of 2.47, standard size deviation of 0.983 d, maximum size deviation of 1.322, neatness of 96 p, reelability of $85\%$, tenacity of 3.87 g/d, elongation of $22.32\%$ and cohesion of 110 strokes was produced. The superiority of fine denier silkworm breeds and their hybrids are discussed.

Gaussian Mixture Model using Minimum Classification Error for Environmental Sounds Recognition Performance Improvement (Minimum Classification Error 방법 도입을 통한 Gaussian Mixture Model 환경음 인식성능 향상)

  • Han, Da-Jeong;Park, Aa-Ron;Park, Jun-Qyu;Baek, Sung-June
    • The Journal of the Korea Contents Association
    • /
    • v.11 no.12
    • /
    • pp.497-503
    • /
    • 2011
  • In this paper, we proposed the MCE as a GMM training method to improve the performance of environmental sounds recognition. We model the environmental sounds data with newly defined misclassification function using the log likelihood of the corresponding class and the log likelihood of the rest classes for discriminative training. The model parameters are estimated with the loss function using GPD(generalized probabilistic descent). For recognition performance comparison, we extracted the 12 degrees features using preprocessing and MFCC(mel-frequency cepstral coefficients) of the 9 kinds of environmental sounds and carry out GMM classification experiments. According to the experimental results, MCE training method showed the best performance by an average of 87.06% with 19 mixtures. This result confirmed us that MCE training method could be effectively used as a GMM training method in environmental sounds recognition.

Effects of silica fume, superplasticizer dosage and type of superplasticizer on the properties of normal and self-compacting concrete

  • Mazloom, Moosa;Soltani, Abolfazl;Karamloo, Mohammad;Hassanloo, Ahmad;Ranjbar, Asadollah
    • Advances in materials Research
    • /
    • v.7 no.1
    • /
    • pp.45-72
    • /
    • 2018
  • In the present study, a special attention has been paid to the effects regarding the use of different superplasticizers in different dosages. To do so, 36 mixes of normal and self-compacting concrete with two water/binder ratios of 0.35 and 0.45, four different types of superplasticizer including melamine-formaldehyde, naphthalene-formaldehyde, carboxylic-ether and poly-carboxylate, four different superplasticizer/cement ratios of 0.4%, 0.8%, 1.2% and 1.6% and two silica fume/cement ratios of 0% and 10% have been cast. Moreover, the initial and final setting time of the pastes have been tested. For self-compacting mixes, flow time, slump flow, V-funnel, J-ring and L-box tests have been carried out as well as testing the compressive strength and rupture modulus. For normal concrete mixes,slump test has been conducted to assess the workability of the mix and then for each mix, the compressive strength and rupture modulus have been determined. The results indicate that in addition to the important role of superplasticizer type and dosage on fresh state properties of concrete, these parameters as well as the use of silica fume could affect the hardened state properties of the mixes. For instance, the mixes whose superplasticizer were poly-carboxylic-ether based showed better compressive and tensile strength than other mixes. Besides, the air contents showed robust dependency to the type of the superplasticizer. However, the use of silica fume decreased the air contents of the mixes.

The Effects of Stair Climbing Training with Functional Electrical Stimulation on Muscle Strength, Balance, and Gait in Patients with Chronic Stroke

  • Koh, Sieun;Choi, Wonjae;Lee, Seungwon
    • Physical Therapy Rehabilitation Science
    • /
    • v.10 no.1
    • /
    • pp.32-39
    • /
    • 2021
  • Objective: The weakness of muscle strength due to stroke affects the posture control and gait in the patients with stroke. Stroke This study examined the effects of the stair climbing training with functional electrical stimulation on muscle strength, dynamic balance, and gait in individuals with chronic stroke. Design: Randomized controlled trial. Methods: Total forty-eight patients were randomly assigned to the 3 groups. Participants randomly divided to stair climbing training with functional electrical stimulation group (SCT+FES group, n=16), stair climbing training group (SCT group, n=16) and control group (n=16). Subjects in the SCT+FES group and SCT group performed stair walking training with and without functional electrical stimulation for 30 minutes, 3 sessions per week for 4 weeks and all subjects received conventional physical therapy for 30 minutes with 5 sessions per week for 4 weeks. Outcome measurements were assessed using the sit-to stand Test for strength, timed up and go test and modified-timed up and go test for dynamic balance, and 10m walk test and GaitRite system for gait. Results: In the SCT+FES group, subjects have been shown the significant increase in lower extremity strength (p<0.05), significantly improve in dynamic balance (p<0.05), and significantly improve in their temporal gait parameter (p<0.05). The SCT+FES group was significantly better than other groups in all parameters (p<0.05). Conclusions: This result suggested that the SCT+FES may be effective strategy to improve muscle strength, dynamic balance, and gait for individuals with chronic stroke.

Collaborative Modeling of Medical Image Segmentation Based on Blockchain Network

  • Yang Luo;Jing Peng;Hong Su;Tao Wu;Xi Wu
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.17 no.3
    • /
    • pp.958-979
    • /
    • 2023
  • Due to laws, regulations, privacy, etc., between 70-90 percent of providers do not share medical data, forming a "data island". It is essential to collaborate across multiple institutions without sharing patient data. Most existing methods adopt distributed learning and centralized federal architecture to solve this problem, but there are problems of resource heterogeneity and data heterogeneity in the practical application process. This paper proposes a collaborative deep learning modelling method based on the blockchain network. The training process uses encryption parameters to replace the original remote source data transmission to protect privacy. Hyperledger Fabric blockchain is adopted to realize that the parties are not restricted by the third-party authoritative verification end. To a certain extent, the distrust and single point of failure caused by the centralized system are avoided. The aggregation algorithm uses the FedProx algorithm to solve the problem of device heterogeneity and data heterogeneity. The experiments show that the maximum improvement of segmentation accuracy in the collaborative training mode proposed in this paper is 11.179% compared to local training. In the sequential training mode, the average accuracy improvement is greater than 7%. In the parallel training mode, the average accuracy improvement is greater than 8%. The experimental results show that the model proposed in this paper can solve the current problem of centralized modelling of multicenter data. In particular, it provides ideas to solve privacy protection and break "data silos", and protects all data.

Correlation Between Functional Movement Screen Scores, Lower Limb Strength, Y-Balance Test, Grip Strength, and Vertical Jump and Incidence of Injury Due to Musculoskeletal Injury Among Abu Dhabi Police Recruits

  • Hamad Alkaabi;Everett Lohman;Mansoor Alameri;Noha Daher;Aleksandar Cvorovic;Hatem Jaber
    • Physical Therapy Rehabilitation Science
    • /
    • v.12 no.3
    • /
    • pp.222-228
    • /
    • 2023
  • Objective: Training-related injuries and attrition put an additional burden on police and military institutions. Preventing and minimizing musculoskeletal injuries is the primary concern of the Abu Dhabi Police. Therefore, this study aimed to evaluate the correlation between functional movement screen, lower-limb strength, Y-balance test, grip strength and vertical jump and the incidence of musculoskeletal injuries among Abu Dhabi police recruits. Design: Observational analytical study. Methods: An observational study was conducted on 400 male police recruits of Abu Dhabi Police Academy. Physical performance was assessed before the 16-weeks basic police training. Spearman's correlation evaluated the correlation between the performance parameters and the outcome measures and logistic regression predicted the risk factors associated with musculoskeletal injuries. Results: 149 (34.4%) participants reported at least one injury during the basic police training. Comparison between injured and non-injured participants showed significant difference in mean right Y-balance, back-leg-chest dynamometer, and vertical jump (p=0.02, p=0.02, and p=0.04, respectively). Spearman's correlation showed a significant negative correlation between risk of injury and back-leg-chest dynamometer and right Y balance (ρ= -0.11, p=0.03). Logistic regression showed that back-leg-chest dynamometer and right Y balance were significant predictors of injury (p =.036 and p=0.037; Odds ratio=0.96; 95% CI (0.92, 0.99) and Odds ratio=0.99; 95% CI (0.98,0.99). Conclusions: Our findings suggest functional movement screen and grip strength may not independently predict injury rates, balance and lower-limb strength needs to be considered in injury prevention strategies to reduce musculoskeletal injuries.

Behavioral, physiological, and hormonal responses during pre-slaughter handling in goats: a comparison between trained and untrained handlers

  • Pavan Kumar;Ahmed Abubakar Abubakar;Muideen Adewale Ahmed;Muhammad Nizam Hayat;Fakhrullah Abd Halim;Md. Moklesur Rahman;Mokrish Ajat;Ubedullah Kaka;Yong-Meng Goh;Awis Qurni Sazili
    • Animal Bioscience
    • /
    • v.37 no.11
    • /
    • pp.2000-2007
    • /
    • 2024
  • Objective: The livestock handler attitude and their handling of animals is crucial for improving animal welfare standards, minimizing stress, improving productivity and meat quality. The present study was undertaken to assess the effect of training livestock handlers on behavioral, physiological, and hormonal responses during preslaughter handling in goats. Methods: A total of 6 handlers were divided into trained (trained in basic animal handling practices, animal behavior, and animal welfare), contact trained (not trained directly but interacted and saw the working of trained handlers), and untrained groups (no formal training). The handling experiment was conducted on 18 male goats by following a crossover design. The goats were moved from lairage to slaughter point by trained, contact-trained, and untrained handlers. Various behavioral, physiological, and hormonal parameters were recorded at the lairage before handling and at the slaughter point after handling the goats. Results: The training of livestock handlers had a significant effect on behavioral, physiological, and hormonal responses in goats. The goats handled by untrained and contact-trained handlers were recorded with intense vocalization, significant (p<0.05) increase in heart rate and blood glucose, and catecholamines (adrenaline and nor-adrenaline), thereby indicating stress and poor animal welfare. The trained handlers were observed to use visual interactions (waving of hands or objects, blocking, hand raising, etc), and lower stress responses were recorded in the goats handled by this group. Conclusion: The present study highlights the importance of training to livestock handlers in improving animal welfare and minimizing stress in goats during pre-slaughter stress.

Legal Status of Government Ships Operated for Non-Commercial Purpose in International Law of the Sea - Forcusing on Training Ship of National University (비상업용 정부선박의 국제해양법적 지위 - 국립대학 실습선을 중심으로 -)

  • Lim, Jee-Hyung;Lee, Yong-Hee
    • Journal of the Korean Society of Marine Environment & Safety
    • /
    • v.26 no.2
    • /
    • pp.156-162
    • /
    • 2020
  • Since the early 20th century, there have been reviews and legislations regarding the legal status of the Government ships operated for non-commercial purposes. In particular, as criticized in the absolute theory of immunity in conventional international law, the sovereign immunity theory has become more vital as a restrictive theory for immunity. As per the customary international law and international law of the sea, non-commercial government vessels, including warships, are provided with sovereign immunity on the sea. National universities of Korea have built and operated training ships and survey ships for educational purposes, such as training high-grade mariners and fishing practices. These training ships sail not only on the national maritime jurisdictions but also on the maritime jurisdictions of other States and the high sea. Therefore, clarifying the legal status of national university training ships is one of the important factors in international navigation according to international law. However, it is not easy to answer the question of the legal status of the training ship. Hence, this article analyzes the parameters that define the Government ship operated for non-commercial purposes and examines whether national university training ships are in line with the relevant criterion. Furthermore, the article analyzes the scope of sovereign immunity in conventional international law and international conventions and identifies the scope of sovereign immunity enjoyed by the national university training ships according to international law.

The Effect of Speed-dependent with Body Weight Supported Treadmill Training on the Ambulation of Stroke (속도-의존적 체중지지 트레드밀 보행이 뇌졸중 환자의 보행에 미치는 영향)

  • Kim, Jwa-Jun;Rho, Min-He;Goo, Bong-Oh;Ahn, So-Youn
    • The Journal of Korean Physical Therapy
    • /
    • v.17 no.3
    • /
    • pp.339-350
    • /
    • 2005
  • This study is the quasi-experimental study on the gait training rehabilitation. The purpose of this study is to prepare the baseline data for most suitable of gait while we were scrutinizing how the walking characters, functional walking ability, gait quality of stroke patients were affected by the gait on BWSTT (Body Weight Supported Treadmill Training) through the change of treadmill velocity and body weight support. To accomplish this purpose, this study used thirty subjects, more than 3 months post stroke, for rehabilitation who were divided between two gait training groups they received the neurophysiological physical therapy. For 6 weeks, 5 times a week for 15 minutes per session, the BWSTT group participated in 30 sessions structured speed-dependent treadmill training with 30% body weight supported, and the ratio of body weight support was gradually decreased as the patients advanced the capability of more self-support. The OGT(Over Ground Training) group received the same quantity of equal sessions like BWSTT. Firstly, we measured the absolute improvement of walking velocity (m/s), capacity(min/m) and cadence(steps/min) among walking characters. Secondly, we measured the functional walking ability such as Functional Ambulatory Category(FAC, score out of 5), Modified Motor Assesment Scale(MMAS, score out of 6) and Gait Quality Chart(score out of 41). Data analysis was performed with using SPSS 10.0 win program. The descriptive analysis was used to obtain average and standard deviation. The independent t-test and the paired t-test were used to compare both the groups about pre and post training test. Treatment effects were established by pre and post assessment. Subjects tolerated the training well without side-effects. Therefore, the results of this study were as follows; 1. There was a more significant difference from the improvement of walking velocity(0.09m/s), endurance(4.53min/m), cadence(4.20steps/min), FAC(0.26score), MMAS(0.33 score) and hip joint and pelvic of gait quality(0.39 score) ever before in the BWSTT group(p<.05). 2. There was a more significant increase from the walking velocity(0.01m/s) in the OGT group(p<.05). 3. There was a more statistical significant increase from comparing the average of walking velocity in both groups ever before(0.42m/s in BWSTT group and 0.31m/s in OGT group)(p<.05). There was a statistical significant difference from the average of cadence in both groups(61.87step/min in BWSTT group and 3.60steps/min in OGT group)(p<.05). As we can see from above, the findings suggest that BWSTT may be more effective than the OGT for improving some gait parameters such as gait velocity and cadency. This conclusion also suggest that BWSTT is more effective for the improvement of gait of stroke patients.

  • PDF