STAMP: Simultaneous Training and Model Pruning for Low Data Regimes in Medical Image Segmentation

Acquisition of high quality manual annotations is vital for the development of segmentation algorithms. However, to create them we require a substantial amount of expert time and knowledge. Large numbers of labels are required to train convolutional neural networks due to the vast number of parameters that must be learned in the optimisation process. Here, we develop the STAMP algorithm to allow the simultaneous training and pruning of a UNet architecture for medical image segmentation with targeted channelwise dropout to make the network robust to the pruning. We demonstrate the technique across segmentation tasks and imaging modalities. It is then shown that, through online pruning, we are able to train networks to have much higher performance than the equivalent standard UNet models while reducing their size by more than 85% in terms of parameters. This has the potential to allow networks to be directly trained on datasets where very low numbers of labels are available.

Comparison of the Effect of Eight Week Training Program Schedule With Two Different Stretching Patterns Strengthening on Changes in the Status of Lower Cross Syndrome

Objective: Different timing of performing stretching and strengthening exercises can have different effects on the condition of Lower Crossed Syndrome (LCS). This study aims to compare the effects of eight-week training using stretching and strengthening exercises intermittently and simultaneously on the status of LCS in female college students. Methods: In this quasi-experimental study, the study population consists of 300 female students of Guilan University aged 19-25 years. To assess LCS, the New York Posture Rating tool was used. 120 patients who had hyperlordosis were re-evaluated using flexible ruler for precise measurement of LCS. Finally, 45 students with a lumbar curvature angle of >45 degrees were selected and randomly divided into three groups of intermittent training (n=15), simultaneous training (n=15), and control (n=15). The training program consisted of corrective exercises for 8 weeks, 3 sessions per week, each for 60 minutes. One-way ANOVA was used for data analysis in SPSS v. 20 software Results: The difference between the intermittent training and control groups was significant (P=0.30), while no significant difference was observed between the simultaneous training and control groups (P=0.68). Conclusion: Performing stretching and strengthening exercises intermittently has a greater effect on reducing LCS than performing these exercises simultaneously.

EXPRESS: Inhibitory causal structures in serial and simultaneous feature negative learning

We have previously reported that human participants trained with a simultaneous feature negative discrimination (intermixed A+ / AB- trials) show only modest transfer of inhibitory properties of the feature B to a separately trained excitor in a summation test (Lee & Lovibond, 2021). Self-reported causal structure suggested that many participants learned that the effect of the feature B was somewhat specific to the excitor it had been trained with (modulation), rather than learning that the feature prevented the outcome (prevention). This pattern is reminiscent of the distinction between negative occasion-setting and conditioned inhibition in the animal conditioning literature. However, in animals, occasion-setting is more commonly seen with a serial procedure in which the feature (B) precedes the training excitor (A). Accordingly, we ran three experiments to compare serial with simultaneous training in an allergist causal judgment task. Transfer in a summation test was stronger to a previously modulated test excitor compared to a simple excitor after both simultaneous and serial training. There was a numerical trend towards a larger effect in the serial group, but it failed to reach significance and the Bayes Factor indicated support for the null. Serial training had no differential effect on self-reported causal structure, and did not significantly reduce overall transfer. After both simultaneous and serial training, transfer was strongest in participants who reported a prevention structure, replicating and extending our previous results to a previously modulated excitor. These results suggest that serial feature negative training does not promote a qualitatively different inhibitory causal structure compared to simultaneous training in humans.

Multi-Task Learning for Medical Image Inpainting Based on Organ Boundary Awareness

Distorted medical images can significantly hamper medical diagnosis, notably in the analysis of Computer Tomography (CT) images and organ segmentation specifics. Therefore, improving diagnostic imagery accuracy and reconstructing damaged portions are important for medical diagnosis. Recently, these issues have been studied extensively in the field of medical image inpainting. Inpainting techniques are emerging in medical image analysis since local deformations in medical modalities are common because of various factors such as metallic implants, foreign objects or specular reflections during the image captures. The completion of such missing or distorted regions is important for the enhancement of post-processing tasks such as segmentation or classification. In this paper, a novel framework for medical image inpainting is presented by using a multi-task learning model for CT images targeting the learning of the shape and structure of the organs of interest. This novelty has been accomplished through simultaneous training for the prediction of edges and organ boundaries with the image inpainting, while state-of-the-art methods still focus only on the inpainting area without considering the global structure of the target organ. Therefore, our model reproduces medical images with sharp contours and exact organ locations. Consequently, our technique generates more realistic and believable images compared to other approaches. Additionally, in quantitative evaluation, the proposed method achieved the best results in the literature so far, which include a PSNR value of 43.44 dB and SSIM of 0.9818 for the square-shaped regions; a PSNR value of 38.06 dB and SSIM of 0.9746 for the arbitrary-shaped regions. The proposed model generates the sharp and clear images for inpainting by learning the detailed structure of organs. Our method was able to show how promising the method is when applying it in medical image analysis, where the completion of missing or distorted regions is still a challenging task.

Studi Empiris Faktor Determinan Prestasi Kerja Pegawai

Job performance is a result of work in quality and quantity achieved by an employee in carrying out his duties by the responsibilities that have been given to him. An employee is said to be successful in carrying out his job if the work obtained is higher than the predetermined standard. The purpose of this study was to determine and analyze the effect of training, promotion, and transfer on the work performance of the employees of the Social and Village Empowerment Service Office of Wonosobo Regency. This study uses a quantitative approach. The population of this study was all employees of the Social and Village Empowerment Office of Wonosobo Regency. Methods of data analysis using multiple linear regression. The conclusion of this study is (1) partially training has a significant effect on job performance. (2) partially, job promotion has a significant effect on work performance. (3) partially, the mutation has a significant effect on work performance. (4) simultaneous training, promotion, and transfer have a significant effect on work performance.

Application of digital twins in the management of socio-economic systems

The article describes the use of digital twins in socio-economic processes using the example of predictive asset maintenance management. For this, the architecture of a distributed forecasting information system is proposed that collects data from digital twins and provides them with a pre-trained neural network model to obtain forecasts about the need for predictive maintenance. The article discusses two types of forecasts - about the remaining useful life and the possible failure of an asset in the considered time window. Computational experiments have been carried out, confirming that the proposed neural network model allows, due to the simultaneous training of solving two problems, to obtain more accurate forecasts than models trained to solve one problem.

Improving Work Productivity Through Training, Discipline And Communication At PT. Linewin

The purpose in this study is to analyze the influence of both partial and simultaneous training, discipline and communication on productivity. This research was conducted on PT. Linewin selected 117 production employees to sample. data collection using questionnaires with data analysis using SPSS 22. The results showed that training, discipline and communion had a positive and significant effect on productivity in PT. Linewin. Discipline variables have the most dominant influence in improving employee work productivity in PT. Linewin. Furthermore, the result of a determination coefficient of 69.1% of productivity variables can be explained by variations in training, discipline and communication variables and the remaining 40.9% is another variable not studied in this study

Analisis Kompetensi, Sarana Prasarana Dan Perencanaan Program Pelatihan Terhadap Kualitas Tenaga Kerja Pada Dinas Tenaga Kerja Dan Transmigrasi Kabupaten Balangan Kalimantan Selatan

Abstrak : Fitri Efendi, Npm. 1811.32202.4732, Analisis Kompetensi, Sarana Prasarana Dan Perencanaan Program Pelatihan Terhadap Kualitas Tenaga Kerja Pada Dinas Tenaga Kerja Dan Transmigrasi Kabupaten Balangan Kalimantan Selatan, Dibawah Bimbingan Rosadiro Cahyono Dan Yudi Rahman, 2020. Tujuan penelitian yang ingin dicapai dalam penelitian ini, adalah Untuk mengetahui dan menganalisis pengaruh kompetensi terhadap kualitas tenaga kerja, Untuk mengetahui dan menganalisis pengaruh sarana prasarana terhadap kualitas tenaga kerja, Untuk mengetahui dan menganalisis pengaruh perencanaan program pelatihan terhadap kualitas tenaga kerja dan untuk mengetahui dan menganalisis pengaruh kompetensi, sarana prasarana dan perencanaan program pelatihan secara simultan terhadap kualitas tenaga kerja pada Dinas Tenaga Kerja Dan Transmigrasi Kabupaten Balangan Kalimantan Selatan. Populasi dari penelitian ini adalah tenaga kerja yang ikut pelatihan di Dinas Tenaga Kerja dan Transmigrasi Kabupaten Balangan Kalimantan Selatan yang berjumlah 224 orang sedangkan sampel dalam penelitian ini sebanyak 56 orang responden. Teknik pengolahan data yang akan dilakukan menggunakan metode kuantitatif dengan analisis regresi berganda dengan perangkat lunak spss. Hasil penelitian hiipotesis pertama menyebutkan secara parsial antara variabel kompetensi berpengaruh signifikan terhadap kualitas tenaga kerja, hipotesis kedua menyebutkan secara parsial antara variabel sarana prasarana berpengaruh signifikan terhadap kualitas tenaga kerja, hipotesis ketiga yang menyebutkan secara parsial antara variabel perencanaan program pelatihan berpengaruh signifikan terhadap kualitas tenaga kerja dan pengujian hipotesis keempat menunjukkan bahwa variabel kompentensi, sarana prasarana dan perencanaan program pelatihan secara simultan berpengaruh signifikan terhadap kualitas tenaga kerja pada Dinas Tenaga Kerja Dan Transmigrasi Kabupaten Balangan Kalimantan Selatan. Kata Kunci : Kompetensi, Sarana Prasarana, Perencanaan Program Pelatihan dan Kualitas Tenaga Kerja Abstract : Fitri Efendi, Npm. 1811.32202.4732, Competency Analysis, Infrastructure Facilities And Planning Of Training Programs To On The Quality Of The Workforce At The Department Manpower And Transmigration Of Balangan District, South Kalimantan, Under The Guidance Of Rosadiro Cahyono Dan Yudi Rahman, 2020. Research objectives to be achieved in this study, are to find out and analyze the effect of competence on the quality of labor, to find out and analyze the influence of infrastructure on the quality of labor, to know and analyze the effect of planning training programs on labor quality and to find out and analyze the effect of competency, infrastructure and planning of a simultaneous training program on the quality of the workforce at the Balangan Manpower and Transmigration Office of South Kalimantan Regency. The population of this study was the workforce who participated in training at the Department of Manpower and Transmigration of Balangan Regency, South Kalimantan, which numbered 224 people, while the sample in this study were 56 respondents. Data processing techniques will be performed using quantitative methods with multiple regression analysis with SPSS software. The results of the first hypotheses research mentioned partially between the competency variables significantly influence labor quality, the second hypothesis partially stated that between infrastructure variables had a significant effect on labor quality, the third hypothesis that partially mentioned training program planning variables had a significant effect on labor quality and testing the fourth hypothesis shows that the competency variables, infrastructure and planning of training programs simultaneously have a significant effect on the quality of the workforce at the Department of Manpower and Transmigration, Balangan Regency, South Kalimantan. Keywords: Competence, Infrastructure, Program Planning Workforce Training and Quality