Online Training Method Research Articles

PELATIHAN CARA MENGUKUR KINERJA TENAGA PENJUALAN

The strategic role of salespeople in achieving success in selling company products cannot be underestimated. Improving the performance of salespeople is crucial, with the hope that it can make a significant contribution to increasing sales volume and achieving predetermined goals. The focus of this community service activity is to provide assistance to business owners so that they have a deep understanding of sales force performance measurement methods, enabling business owners to optimize their sales. The partner selected for this community service project is a honey business with the brand "Madu Pakcik" located in Jambi. Initial observations of the partner showed a major problem related to sales force performance measurement in the context of partner sales. Therefore, this PKM activity is implemented through an online training method using the Zoom Meeting platform. This training aims to provide partners with a comprehensive understanding of the key aspects of measuring sales force performance. Hopefully, with the knowledge gained through this activity, partners can significantly improve the quality and number of their sales. In addition to providing training, this activity also produces outputs in the form of scientific publications submitted to relevant journals as well as Intellectual Property Rights (IPR). Thus, this project not only has an impact on improving partner performance in practical terms, but also contributes to scientific knowledge and innovation in the field of sales force performance measurement.

Skill-Learning Method of Dual Peg-in-Hole Compliance Assembly for Micro-Device.

For the dual peg-in-hole compliance assembly task of upper and lower double-hole structural micro-devices, a skill-learning method is proposed. This method combines offline training in a simulation space and online training in a realistic space. In this paper, a dual peg-in-hole model is built according to the results of a force analysis, and contact-point searching methods are provided for calculating the contact force. Then, a skill-learning framework is built based on deep reinforcement learning. Both expert action and incremental action are used in training, and a reward system considers both efficiency and safety; additionally, a dynamic exploration method is provided to improve the training efficiency. In addition, based on experimental data, an online training method is used to optimize the skill-learning model continuously so that the error caused by the deviation in the offline training data from reality can be reduced. The final experiments demonstrate that the method can effectively reduce the contact force while assembling, improve the efficiency and reduce the impact of the change in position and orientation.

Two-dimensional iterative learning control with deep reinforcement learning compensation for the non-repetitive uncertain batch processes

Iterative learning control (ILC) is an advantage control strategy widely used in batch systems. Nevertheless, designing an effective iterative learning control scheme remains crucial for complex batch systems with model mismatch and non-repetitive nature. In this paper, we propose a two-dimensional iterative learning control-reinforcement learning (2D ILC-RL) control scheme composed of a two-dimensional ILC controller and a two-dimensional DRL compensator. Based on the 2D system theory, the 2D ILC controller is proposed to ensure the primary control performance and its stability and convergence are verified. Meanwhile, the DRL compensator counteracts the negative impact of the model mismatch and the non-repetitive nature. In addition, we proposed a real-time implementation scheme to guarantee the safety of the practical batch systems compared to the conventional online training method. Finally, the simulation results in the injection molding batch process and the nonlinear continuously stirred tank reactor demonstrate the proposed control scheme’s effectiveness, significant control performance, and strong robustness.

OODT: LOS Signal Identification for Acoustic Indoor Localization From Stream Perspective

Acoustic-based technologies have attracted more attention in indoor ranging-based localization and tracking applications. To achieve high-accuracy ranging measurements, the precise identification of line-of-sight(LOS) acoustic signals is essential. This paper proposes a novel Off-Online Dynamic Training method(OODT) to identify LOS acoustic signals from stream perspective based on a few training data in dynamic indoor environment. The dynamic online training method is proposed to identify the unlabeled acoustic feature stream by the Parent-Child model, utilizing the dynamic prior probability from time series information and a selection strategy based on the prediction risk. Then, the trustworthy pseudo-labeled streaming samples are accumulated into the Child-Models by online learning in real-time. To reduce the impact of discarding the untrustworthy LOS signals, the Off-Online retraining method is proposed to incorporate the spatial information into the Parent-Models, which uses the category distribution of all pseudo-labeled streaming samples as the prior probability for iterative retraining. Subsequently, a new round of the dynamic online training is conducted to update the pseudo-labels of feature stream. Experiments demonstrate that the dynamic online training method has a higher identification precision of LOS acoustic signals from stream perspective, reaching 98% and more than 93.06% in above-ground and underground experimental scenarios. Moreover, the adaption for the concept drift is also verified with identification precision of 97.98% and 98.23%, respectively. The Off-Online retraining method further optimize the performance of the Parent-Child models in a single scenario. In conclusion, the proposed OODT method can autonomously identify dynamic acoustic signals with strong robustness and scenario drift adaptability.

Channelformer: Attention Based Neural Solution for Wireless Channel Estimation and Effective Online Training

In this paper, we propose an encoder-decoder neural architecture (called Channelformer) to achieve improved channel estimation for orthogonal frequency-division multiplexing (OFDM) waveforms in downlink scenarios. The self-attention mechanism is employed to achieve input precoding for the input features before processing them in the decoder. In particular, we implement multi-head attention in the encoder and a residual convolutional neural architecture as the decoder, respectively. We also employ a customized weight-level pruning to slim the trained neural network with a fine-tuning process, which reduces the computational complexity significantly to realize a low complexity and low latency solution. This enables reductions of up to 70% in the parameters, while maintaining an almost identical performance compared with the complete Channelformer. We also propose an effective online training method based on the fifth generation (5G) new radio (NR) configuration for the modern communication systems, which only needs the available information at the receiver for online training. Using industrial standard channel models, the simulations of attention-based solutions show superior estimation performance compared with other candidate neural network methods for channel estimation.

Workshop on writing essay and introduction to the Zotero application for compiling references

This community service is intended to improve the skills of students, researchers, lecturers, and the public who are interested in writing essays. This community service was carried out for two days through the online training method. The training was carried out by providing material on the introduction of Zotero as an automatic citation application for writing scientific papers and strategies for writing quality essays. This program attended by participants from various universities in Indonesia. From this activity, it can be seen that the event went smoothly and the participants were enthusiastic. However, the lack of participants meant that the program did not have a broad impact on the community. Some of the influencing factors include because this activity is carried out on Saturday - Sunday and people are already bored with online activities.

LiveSR: Enabling Universal HD Live Video Streaming With Crowdsourced Online Learning

The high-definition (HD) live video streaming has gained significant popularity due to the rapid growth of 4G/5G and social media. However, for devices with constrained bandwidth, they still have no sufficient bandwidth to support HD live video streaming. In this paper, we propose a neural-enhanced HD live video streaming framework called LiveSR to provide universal HD live video streaming for both bandwidth-constrained and bandwidth-rich devices. For bandwidth-constrained devices, LiveSR delivers low-quality video streams and then boosts video quality at the device side with super-resolution (SR) techniques. The difficulty lies in how to train the SR model with low cost and conduct quality enhancement in real time. To address these challenges, we design a crowdsourced online training method by exploiting computation resources and HD video data on bandwidth-rich devices in the same video channel. We also propose an imitation learning-based decision making algorithm to make downloading decisions for video chunks and SR models under limited bandwidth. We implement and evaluate our proposed LiveSR framework using real network traces, and the experiment results show that LiveSR outperforms all the other baseline approaches, with 65.5% improvement in terms of the average QoE and 5.7% in terms of video quality (i.e., PSNR), and the achieved frame rate can be as high as 30 frames per second.

Deep Learning Based Successive Interference Cancellation for the Non-Orthogonal Downlink

Non-orthogonal communications are expected to play a key role in future wireless systems. In downlink transmissions, the data symbols are broadcast from a base station to different users, which are superimposed with different power to facilitate high-integrity detection using successive interference cancellation (SIC). However, SIC requires accurate knowledge of both the channel model and channel state information (CSI), which may be difficult to acquire. We propose a deep learning-aided SIC detector termed SICNet, which replaces the interference cancellation blocks of SIC by deep neural networks (DNNs). Explicitly, SICNet jointly trains its internal DNN-aided blocks for inferring the soft information representing the interfering symbols in a data-driven fashion, rather than using hard-decision decoders as in classical SIC. As a result, SICNet reliably detects the superimposed symbols in the downlink of non-orthogonal systems without requiring any prior knowledge of the channel model, while being less sensitive to CSI uncertainty than its model-based counterpart. SICNet is also robust to changes in the number of users and to their power allocation. Furthermore, SICNet learns to produce accurate soft outputs, which facilitates improved soft-input error correction decoding compared to model-based SIC. Finally, we propose an online training method for SICNet under block fading, which exploits the channel decoding for accurately recovering online data labels for retraining, hence, allowing it to smoothly track the fading envelope without requiring dedicated pilots. Our numerical results show that SICNet approaches the performance of classical SIC under perfect CSI, while outperforming it under realistic CSI uncertainty.

Machine learning-based impedance system for real-time recognition of antibiotic-susceptible bacteria with parallel cytometry

Impedance cytometry has enabled label-free and fast antibiotic susceptibility testing of bacterial single cells. Here, a machine learning-based impedance system is provided to score the phenotypic response of bacterial single cells to antibiotic treatment, with a high throughput of more than one thousand cells per min. In contrast to other impedance systems, an online training method on reference particles is provided, as the parallel impedance cytometry can distinguish reference particles from target particles, and label reference and target particles as the training and test set, respectively, in real time. Experiments with polystyrene beads of two different sizes (3 and 4.5 µm) confirm the functionality and stability of the system. Additionally, antibiotic-treated Escherichia coli cells are measured every two hours during the six-hour drug treatment. All results successfully show the capability of real-time characterizing the change in dielectric properties of individual cells, recognizing single susceptible cells, as well as analyzing the proportion of susceptible cells within heterogeneous populations in real time. As the intelligent impedance system can perform all impedance-based characterization and recognition of particles in real time, it can free operators from the post-processing and data interpretation.

Safety-critical Policy Iteration Algorithm for Control under Model Uncertainty

Safety is an important aim in designing safe-critical systems. To design such systems, many policy iterative algorithms are introduced to find safe optimal controllers. Due to the fact that in most practical systems, finding accurate information from the system is rather impossible, a new online training method is presented in this paper to perform an iterative reinforcement learning based algorithm using real data instead of identifying system dynamics. Also, in this paper the impact of model uncertainty is examined on control Lyapunov functions (CLF) and control barrier functions (CBF) dynamic limitations. The Sum of Square program is used to iteratively find an optimal safe control solution. The simulation results which are applied on a quarter car model show the efficiency of the proposed method in the fields of optimality and robustness.

Modelling and online training method for digital twin workshop

Aiming at the difficulties in modelling, simulation and verification in digital twin workshop, a modelling and online training method for digital twin workshop is proposed. This paper describes a multi-level digital twin aggregate modelling method, including the status attributes, the static performance attributes and the fluctuation performance attributes, and designs a digital twin organisation system, namely, digital twin graph. According to the data demand for digital twin aggregates, a spatio-temporal data model is constructed. The digital twin model training method using truncated normal distribution is presented. Furthermore, a verification method based on real-virtual error for a digital twin model is proposed. The effectiveness of real-time status monitoring, online model training and simulation for production is verified by a case.

Online midwife's training on psychoeducation of perinatal mental health during COVID-19 Pandemic

Psychoeducation is an effort to prevent maternal anxiety which should be integrated into maternal health services. Puskesmas (Community Health Center) Sukorejo 1 Kendal in collaboration with Motherhope Indonesia held an online training program and psychoeducation for pregnant women for midwives. However, there are no reports related to the implementation of online training for the midwife to increase their knowledge and skills. The purpose of this study was to determine the implementation of psychoeducation online training for midwives during the COVID-19 pandemic. The method applied qualitative research with a case study approach. The informants in this study were 1 head of the Puskesmas and 5 midwives. Data collection used online interviews (synchronous and asynchronous) and the WhatsApp platform. The interview guide was used as a guide for interviews that were previously conducted by pilot interviews. The data was then analyzed using thematic analysis with the Miles and Huberman framework. It can be concluded that the benefits of training could be felt by midwives, namely improving mental health literacy, enhancing skill, and changing the midwife’s paradigm. So, needed to improve the online training method of midwives about psychoeducation to rise the psychoeducation midwife’s role for a pregnant woman.

Efficient Training of the Memristive Deep Belief Net Immune to Non‐Idealities of the Synaptic Devices

The tunability of conductance states of various emerging nonvolatile memristive devices emulates the plasticity of biological synapses, making it promising in the hardware realization of large‐scale neuromorphic systems. The inference of the neural network can be greatly accelerated by the vector‐matrix multiplication (VMM) performed within a crossbar array of memristive devices in one step. Nevertheless, the implementation of the VMM needs complex peripheral circuits, and the complexity further increases as non‐idealities of memristive devices prevent precise conductance tuning (especially for the online training) and largely degrade the performance of the deep neural networks (DNNs). Herein, an efficient online training method of the memristive deep belief net (DBN) is presented. The proposed memristive DBN uses stochastically binarized activations, reducing the complexity of peripheral circuits, and uses the contrastive divergence (CD)‐based gradient descent learning algorithm. The analog VMM and digital CD are performed separately in a mixed‐signal hardware arrangement, making the memristive DBN highly immune to non‐idealities of synaptic devices. The number of write operations on memristive devices is reduced by two orders of magnitude. The recognition accuracy of 95–97% can be achieved for the MNIST dataset using pulsed synaptic behaviors of various memristive synaptic devices.

Pelatihan Aplikasi Game Edukasi Kahoot Untuk Meningkatkan Motivasi Belajar Siswa Di Era Pandemi Covid 19

Community Service Activities carried out at the Integrated Islamic Elementary School (SDIT) Insan Rabbani in the Bekasi area, aimed at providing training in the learning method of the Kahoot educational game method which can be used as an alternative online learning media by taking advantage of opportunities to play games that can support the improvement of educational services. to teachers and students so that they can motivate teaching and learning activities and can support educational services at SDIT Insan Rabbani to be more fun and be able to evaluate the results of learning activities through giving assignments or quizzes and displaying answers to grades for each student and ranking the best three in each assignments or quizzes given so that with the Kahoot application learning objectives are achieved for each subject, especially during the current covid 19 pandemic. In this training, the method used is the online training method using the zoom application by providing exposure related to the Kahoot application and direct practice on the Kahoot application. So that it is hoped that through this training, it is hoped that the ability to achieve an even understanding and mastery of the teacher council supports learning using the Kahoot application as an alternative learning method to create a more interesting, fun and effective learning process.
 Keywords: educational game, kahoot application, online, zoom application

Online learning of neural networks using random projections and sliding window: A case study of a real industrial process

Online Learning of non-stationary data streams is a challenging task. This work presents an online training method for a Single hidden Layer Feedforward neural Network (SLFN) that learns sample-by-sample, using an adjustable sliding window to adapt the network when data has changed. The method presents a fast training procedure, estimating hidden and output layer parameters independently. Tests with four synthetic datasets showed a good accuracy and quick recovery after drift occurrences. The proposed method is also applied to a real dataset from an industrial process in order to address the anomaly detection task, with the network acting as a classifier. Results show that the method is able to detect drifts prior to anomalies in the pre-fault periods, in the real situation that appeared in the industrial dataset.

Robust Visual Tracking with Reliable Object Information and Kalman Filter.

Object information significantly affects the performance of visual tracking. However, it is difficult to obtain accurate target foreground information because of the existence of challenging scenarios, such as occlusion, background clutter, drastic change of appearance, and so forth. Traditional correlation filter methods roughly use linear interpolation to update the model, which may lead to the introduction of noise and the loss of reliable target information, resulting in the degradation of tracking performance. In this paper, we propose a novel robust visual tracking framework with reliable object information and Kalman filter (KF). Firstly, we analyze the reliability of the tracking process, calculate the confidence of the target information at the current estimated location, and determine whether it is necessary to carry out the online training and update step. Secondly, we also model the target motion between frames with a KF module, and use it to supplement the correlation filter estimation. Finally, in order to keep the most reliable target information of the first frame in the whole tracking process, we propose a new online training method, which can improve the robustness of the tracker. Extensive experiments on several benchmarks demonstrate the effectiveness and robustness of our proposed method, and our method achieves a comparable or better performance compared with several other state-of-the-art trackers.

Permanent-Magnet Synchronous Motor Drive System Using Backstepping Control with Three Adaptive Rules and Revised Recurring Sieved Pollaczek Polynomials Neural Network with Reformed Grey Wolf Optimization and Recouped Controller

Owing to some nonlinear characteristics in the permanent-magnet synchronous motor (SM), such as nonlinear friction, cogging torque, wind stray torque, external load torque, and unmodeled systems, fine control performances cannot be accomplished by utilizing the general linear controllers. Thereby, the backstepping approach adopting three adaptive rules and a swapping function is brought forward for controlling the rotor motion in the permanent-magnet SM drive system to reduce nonlinear uncertainties effects. To improve the chattering phenomenon, the backstepping control with three adaptive rules using a revised recurring sieved Pollaczek polynomials neural network (RRSPPNN) with reformed grey wolf optimization (RGWO) and a recouped controller is proposed to estimate the internal collection and external collection torque uncertainties, and to recoup the smallest fabricated error of the appraised rule. In the light of the Lyapunov stability, the on-line parametric training method of the RRSPPNN can be derived through an adaptive rule. Furthermore, to obtain a beneficial learning rate and improve the convergence of the weights, the RGWO algorithm adopting two exponential-functional adjustable factors is applied to adjust the two learning rates of the weights. Then, the efficiency of the used controller is validated by test results.

Pattern recognition based on machine learning identifies oil adulteration and edible oil mixtures

Previous studies have shown that each edible oil type has its own characteristic fatty acid profile; however, no method has yet been described allowing the identification of oil types simply based on this characteristic. Moreover, the fatty acid profile of a specific oil type can be mimicked by a mixture of 2 or more oil types. This has led to fraudulent oil adulteration and intentional mislabeling of edible oils threatening food safety and endangering public health. Here, we present a machine learning method to uncover fatty acid patterns discriminative for ten different plant oil types and their intra-variability. We also describe a supervised end-to-end learning method that can be generalized to oil composition of any given mixtures. Trained on a large number of simulated oil mixtures, independent test dataset validation demonstrates that the model has a 50th percentile absolute error between 1.4–1.8% and a 90th percentile error of 4–5.4% for any 3-way mixtures of the ten oil types. The deep learning model can also be further refined with on-line training. Because oil-producing plants have diverse geographical origins and hence slightly varying fatty acid profiles, an online-training method provides also a way to capture useful knowledge presently unavailable. Our method allows the ability to control product quality, determining the fair price of purchased oils and in-turn allowing health-conscious consumers the future of accurate labeling.

Fault-Tolerant Training Enabled by On-Line Fault Detection for RRAM-Based Neural Computing Systems

An resistive random-access memory (RRAM)-based computing system (RCS) is an attractive hardware platform for implementing neural computing algorithms. On-line training for RCS enables hardware-based learning for a given application and reduces the additional error caused by device parameter variations. However, a high occurrence rate of hard faults due to immature fabrication processes and limited write endurance restrict the applicability of on-line training for RCS. We propose a fault-tolerant on-line training method that alternates between a fault-detection phase and a fault-tolerant training phase. In the fault-detection phase, a quiescent-voltage comparison method is utilized. In the training phase, a threshold-training method and a remapping scheme is proposed. Our results show that, compared to neural computing without fault tolerance, the recognition accuracy for the Cifar-10 dataset improves from 37% to 83% when using low-endurance RRAM cells, and from 63% to 76% when using RRAM cells with high endurance but a high percentage of initial faults.

Effects of Face-To-Face and Online Training on Self-Care of Middle-Aged and Elderly People with Type 2 Diabetes: A Comparative Study.

BACKGROUND:Self-care training is one of the strategies used to control diabetes. There is some ambiguity about the appropriate method for educating middle-aged and older adults about self-care.AIM:This study aimed to compare the effects of face-to-face and online training on self-care levels in middle-aged and older adults with type 2 diabetes.MATERIAL AND METHODS:In a randomised clinical trial, 84 middle-aged and older adults with type 2 diabetes who had been referred to the Diabetes Clinic of Esfarayen in Iran, were evaluated. Patients who meet the inclusion criteria were randomly assigned into two groups. Diabetes self-care education (DSCE) was provided using a face-to-face training method in one group and using online training method in the other group. The summary of diabetes self-care activities (SDSCA) questionnaire was completed at baseline and 1 month after training.RESULTS:The mean and standard deviation of self-care scores before and 1 month after training were 43.16 ± 14.94 and 65.76 ± 10.65 in the face-to-face training group, and 37 ± 10.75 and 56.82 ± 12.06 in the online training group, respectively. The differences in the self-care scores were significant both before and after the intervention in the two groups (p < 0.05). Although the difference was greater in the face-to-face training group than in the online training group, it was not statistically significant (P > 0.05).CONCLUSION:Both face-to-face and online training had a similar effect on the self-care levels in middle-aged and older adults with type 2 diabetes. Therefore, both training methods could be used as effective techniques to meet the needs and educational requirements of middle-aged and older adults with type 2 diabetes.