Search the digital library catalog

Abstract: This study focuses on the segmentation part in the development of a potato-sorting system that utilizes camera input for the segmentation and classification of potatoes. The key challenge addressed is the need for efficient segmentation to allow the sorter to handle a higher volume of potatoes simultaneously. To achieve this, the study employs a region-based convolutional neural network (R-CNN) approach for the segmentation task, while trying to achieve more precise segmentation than with classic CNN-based object detectors. Specifically, Mask R-CNN is implemented and evaluated based on its performance with different parameters in order to achieve the best segmentation results. The implementation and methodologies used are thoroughly detailed in this work. The findings reveal that Mask R-CNN models can be utilized in the production process of potato sorting and can improve the process.
Keywords: image segmentation, potato sorting, neural network, mask RCNN, object detection, production process, machine learning, AI
Published in DKUM: 27.03.2025; Views: 0; Downloads: 10
Full text (5,97 MB)
This document has many files! More...

Abstract: With the rise of deep learning technology, the field of medical image segmentation has undergone rapid development. In recent years, convolutional neural networks (CNNs) have brought many achievements and become the consensus in medical image segmentation tasks. Although many neural networks based on U-shaped structures and methods, such as skip connections have achieved excellent results in medical image segmentation tasks, the properties of convolutional operations limit their ability to effectively learn local and global features. To address this problem, the Transformer from the field of natural language processing (NLP) was introduced to the image segmentation field. Various Transformer-based networks have shown significant performance advantages over mainstream neural networks in different visual tasks, demonstrating the huge potential of Transformers in the field of image segmentation. However, Transformers were originally designed for NLP and ignore the multidimensional nature of images. In the process of operation, they may destroy the 2D structure of the image and cannot effectively capture low-level features. Therefore, we propose a new multi-scale cross-attention method called M-VAN Unet, which is designed based on the Visual Attention Network (VAN) and can effectively learn local and global features. We propose two attention mechanisms, namely MSC-Attention and LKA-Cross-Attention, for capturing low-level features and promoting global information interaction. MSC-Attention is designed for multi-scale channel attention, while LKA-Cross-Attention is a cross-attention mechanism based on the large kernel attention (LKA). Extensive experiments show that our method outperforms current mainstream methods in evaluation metrics such as Dice coefficient and Hausdorff 95 coefficient.
Keywords: CNNs, deep learning, medical image processing, NLP, semantic segmentation
Published in DKUM: 14.03.2024; Views: 496; Downloads: 311
Full text (1,46 MB)
This document has many files! More...

Abstract: Nowadays, through organisational and technological changes, organizations expect availability and work from their employees not just during working hours, but also in their free time. Work can be done from anywhere and at any time, also with the help of smartphones, which is one of the main constructs of the current research. If the employee is working from home on their smartphone, this can have an important contribution to managing work and private life, and also to strain. The individual’s preference of whether to segment his or her work from home also plays an important role in experiencing internal conflicts. As the motivation for work-related smartphone use is not fully clear, job insecurity was additionally explored as a potential predictor. In an online study, conducted in Austria, we collected data from 454 participants of different ages, gender and working backgrounds. For the analysis, multiple moderated regression and mediation analyses were used. Results showed significant relations between work-home interference and strain but no significant results between those constructs while adding work-related smartphone use. Segmentation preferences did not have an influence on the relationship between work-home interference and strain. Job insecurity was revealed to be related to work-related smartphone use and smartphone use to work-home interference. Smartphone use was also found to partially mediate the path from job insecurity to work-home interference. Finally, to prevent negative outcomes of strain, work-home interference and job insecurity, organizations should focus on: providing culture that fits their employees, try to plan availability free time and provide a clear communication.
Keywords: Smartphone use, work-home interference, strain, stress, job insecurity, segmentation preferences
Published in DKUM: 14.01.2019; Views: 1847; Downloads: 144
Full text (863,72 KB)

Abstract: This paper presents a novel feature for online speech/music segmentation basedon the variance mean of filter bank energy (VMFBE). The idea that encouraged the feature's construction is energy variation in a narrow frequency sub-band. The energy varies more rapidly, and to a greater extent for speech than for music. Therefore, an energy variance in such a sub-band isgreater for speech than for music. The radio broadcast database and the BNSIbroadcast news database were used for feature discrimination and segmentation ability evaluation. The calculation procedure of the VMFBE feature has 4 out of 6 steps in common with the MFCC feature calculation procedure. Therefore, it is a very convenient speech/music discriminator for use in real-time automatic speech recognition systems based on MFCC features, because valuable processing time can be saved, and computation load is only slightly increased. Analysis of the feature's speech/music discriminative ability shows an average error rate below 10% for radio broadcast material and it outperforms other features used for comparison, by more than 8%. The proposed feature as a stand-alone speech/music discriminator in a segmentation system achieves an overall accuracy of over 94% on radio broadcast material.
Keywords: online speech segmentation, algorithm, speech techniques
Published in DKUM: 26.06.2017; Views: 1337; Downloads: 453
Full text (1,49 MB)
This document has many files! More...

Abstract: The paper describes a segmentation of risks to make each risk segment more manageable. The proposed approach is primarily intended to improve the confidentiality of risk simulations. The description of the approach is based on a logistics business process system which requires that its input is represented as a process graph. Each process is defined in terms of input and output; input comprises general input as well as risks; output comprises general output as well as impacts. The model takes into consideration internalas well as external input and output. Parameters can be used to define individual processes. Processes include functions that calculate new values of parameters and output on the bases of given input. Based on given tolerance levels for risks, impacts and process parameters, the model determines whether these levels are acceptable. The model assumes that parameters and functions are non-deterministic, i.e. parameters and functions may change in time. Although the approach is described on a very general level, each segment can be further subdivided into subsegments in order to include more characteristics of observed risks.
Keywords: risk, impact, segmentation, risk management, process parameters, logistics, model, simulation tools, non-deterministic
Published in DKUM: 05.06.2012; Views: 2069; Downloads: 55
Link to full text