Search results
1 – 10 of over 1000
Worapan Kusakunniran, Sarattha Karnjanapreechakorn, Pitipol Choopong, Thanongchai Siriapisith, Nattaporn Tesavibul, Nopasak Phasukkijwatana, Supalert Prakhunhungsit and Sutasinee Boonsopon
This paper aims to propose a solution for detecting and grading diabetic retinopathy (DR) in retinal images using a convolutional neural network (CNN)-based approach. It could…
Abstract
Purpose
This paper aims to propose a solution for detecting and grading diabetic retinopathy (DR) in retinal images using a convolutional neural network (CNN)-based approach. It could classify input retinal images into a normal class or an abnormal class, which would be further split into four stages of abnormalities automatically.
Design/methodology/approach
The proposed solution is developed based on a newly proposed CNN architecture, namely, DeepRoot. It consists of one main branch, which is connected by two side branches. The main branch is responsible for the primary feature extractor of both high-level and low-level features of retinal images. Then, the side branches further extract more complex and detailed features from the features outputted from the main branch. They are designed to capture details of small traces of DR in retinal images, using modified zoom-in/zoom-out and attention layers.
Findings
The proposed method is trained, validated and tested on the Kaggle dataset. The regularization of the trained model is evaluated using unseen data samples, which were self-collected from a real scenario from a hospital. It achieves a promising performance with a sensitivity of 98.18% under the two classes scenario.
Originality/value
The new CNN-based architecture (i.e. DeepRoot) is introduced with the concept of a multi-branch network. It could assist in solving a problem of an unbalanced dataset, especially when there are common characteristics across different classes (i.e. four stages of DR). Different classes could be outputted at different depths of the network.
Details
Keywords
Sarah Franz, Axele Giroud and Inge Ivarsson
This study aims to analyse how multinational corporations (MNCs) organise value chain activities to penetrate new market segments. It contributes by expanding traditional…
Abstract
Purpose
This study aims to analyse how multinational corporations (MNCs) organise value chain activities to penetrate new market segments. It contributes by expanding traditional decisions regarding the vertical fine-slicing of value chain activities (whether performed internally or externally) and the consideration of resource-sharing decisions (integration or separation) for each value chain function.
Design/methodology/approach
The authors draw on primary data collected from two case study firms operating in the large emerging Chinese market: Volvo Construction Equipment AB and Epiroc AB. In-depth cases illustrate how foreign MNCs expand into new market segments and simultaneously target both the lower-priced mid-market and the premium segments in the Chinese mining and construction industry.
Findings
The results reveal that product diversification creates challenges for managers who must oversee new (vertical) value chains, often simultaneously. Beyond geography and modes of governance, managers must decide whether to integrate or separate value chain activities for the new product lines. The study identifies four main strategic choices for firms to address this complexity, focusing on the decision to internalise or externalise (i.e. within or across organisational boundaries) and integrate or separate value chain activities between different product lines.
Originality/value
This study builds upon the internalisation theory and recent international business contributions that focus on value chain configurations to explain MNCs’ product diversification as a growth strategy in a host emerging market. It also sheds light on the choice of conducting new activities in-house or externally and elucidates firms’ managerial decisions to operationally integrate or separate individual value chain activities. The study provides insights into the drivers explaining managerial decisions to configure value chain activities across product lines and contributes to the growing body of literature on MNC activities in emerging economies by highlighting that product diversification impacts entry mode diversity and resource sharing across units.
Details
Keywords
Abstract
Details
Keywords
Niloofar Kazemargi, Ernesto Tavoletti, Andrea Appolloni and Corrado Cerruti
The purpose of this paper is to investigate how focal firms in supply networks manage weak and strong ties for exploration and exploitation innovation in mature industries. In…
Abstract
Purpose
The purpose of this paper is to investigate how focal firms in supply networks manage weak and strong ties for exploration and exploitation innovation in mature industries. In doing so, the paper extends the understanding of how focal firms manage open innovation (OI).
Design/methodology/approach
The empirical base is a multiple case study conducted on three companies operating in mature industries in Europe.
Findings
Findings of this study reveal, analyze and explain a diverse set of OI practices in the supply networks of mature industries in which the focal firms integrate strong and weak supply ties to enhance innovation outcomes. This study provides a fine-grained view of the benefits of the additive and interactive effects of strong and weak ties in OI. More specifically, the analysis reveals an enhancing role of strong supply ties in exploration, which previously was associated solely with weak ties. Moreover, this study sheds light on the dominant and orchestrating roles of focal firms.
Practical implications
The findings provide insights to enhance OI practices beyond the limited role of the weak ties of the supply network and highlight the essential role of the strong supply ties in mature industries.
Originality/value
While previous studies have associated exploration with weak ties, findings of this study reveal that exploration-oriented activities in mature industries also extend to strong ties. In the strong ties of mature industries, this study finds there is not only the exploitation of existing knowledge but also the reconfiguration and innovation of products.
Details
Keywords
Pirouz Nourian, Samaneh Rezvani, Kotryna Valeckaite and Sevil Sariyildiz
The most sustainable forms of urban mobility are walking and cycling. These modes of transportation are the most environmental friendly, the most economically viable and the most…
Abstract
Purpose
The most sustainable forms of urban mobility are walking and cycling. These modes of transportation are the most environmental friendly, the most economically viable and the most socially inclusive and engaging modes of urban transportation. To measure and compare the effectiveness of alternative pedestrianization or cycling infrastructure plans, the authors need to measure the potential flows of pedestrians and cyclists. The paper aims to discuss this issue.
Design/methodology/approach
The authors have developed a computational methodology to predict walking and cycling flows and local centrality of streets, given a road centerline network and occupancy or population density data attributed to building plots.
Findings
The authors show the functionality of this model in a hypothetical grid network and a simulated setting in a real town. In addition, the authors show how this model can be validated using crowd-sensed data on human mobility trails. This methodology can be used in assessing sustainable urban mobility plans.
Originality/value
The main contribution of this paper is the generalization and adaptation of two network centrality models and a trip-distribution model for studying walking and cycling mobility.
Details