IFIP Open Access Digital Library
Not a member yet
22614 research outputs found
Sort by
Automated Indigenous Plant Recognition and Medicinal Value Extraction System
No full textPart 2: Applications of AI/ML in Image ProcessingInternational audienceIn an age where environmental awareness and exploration of natural resources are paramount, identifying traditional and indigenous plant species has become crucial across diverse domains. This aim of this work is ultimately develop a mobile application framework that detects and recognizes indigenous medicinal plants of our country, its medicinal value and usage in indigenous food preparation. Moreover the key component essential is the right machine learning model which is scalable, incremental and more accurate. The proposed work is developing a robust and scalable machine learning model for detecting and recognizing indigenous medicinal plants species. Image data set pertaining to whole plant and parts like flower, leaf, fruit, stem, bark, root of unique 2626 Indian plant species were collected and used for training and testing three deep learning CNN models like Resnet50, MobileNetV2 and VGG16 for plant species identification. These three models performed with 85%, 82% and 87% accuracy individually. Finally stochastic weight averaging ensemble of the three independent approaches resulted an overall accuracy of 95%
An Exploration of Object Detection and Vehicular Communication for Autonomous Vehicles
No full textPart 2: Applications of AI/ML in Image ProcessingInternational audienceAutonomous vehicles represent a transformative technology with the best implications for transportation systems. The key component of their success is their capability to detect and respond to their surroundings. For the benefits to be realized, the fusion of advanced computer vision techniques, such as object detection and vehicular communication, is essential. This paper explains the techniques in object detection and vehicular communication in autonomous vehicle applications for future advancements based on related works. The research highlights the need for creative solutions in integrating communication and computer vision tasks and presents idea of work flow for combining object detection with vehicular communication. The main motive of this research is to present about idea of integrating object detection model and vehicular communication. Additionally, we explore vehicular communication systems and their integral role in ensuring safe and efficient autonomous driving. The idea of object detection and vehicular communication is not only for autonomous vehicles but also for ADAS (Advanced Driver Assistance System)-equipped vehicles
CNN-Based Skin Lesion Classification for Melanoma Detection
No full textPart 2: Applications of AI/ML in Image ProcessingInternational audienceThe significant worldwide health risk posed by skin cancer, especially melanoma, highlights the urgent need for sophisticated diagnostic techniques to facilitate early diagnosis. The goal of this research is to improve the efficiency and accuracy of melanoma diagnosis by doing a thorough analysis of dermatological pictures using CNNs. Two different CNN models are implemented: one uses the ResNet50 architecture for feature extraction, while the other is a specially created CNN for the classification of skin lesions. Thorough preparation of the data, including rotation, flipping, and sophisticated methods like loading, scaling, and normalizing of images, guarantees the best possible model performance. Treating the underlying imbalances in skin lesion datasets is one of the main goals. This is accomplished by computing and adding class weights during training, which is especially important for data that isn’t balanced. Properly calibrated learning rates, accuracy as the evaluation measure, categorical cross-entropy loss, and the Adam optimizer are all used in the model optimization process. One special feature of this project is the incorporation of a progress indicator based on TQDM, which offers real-time information about model convergence when training. Through the careful preparation of data, careful CNN designs, and efficient techniques for handling unbalanced data, this program seeks to substantially enhance the field of skin cancer diagnosis. As the fight against skin cancer never ends, the conclusive goal is to enhance patient outcomes through more precise and early melanoma detection
Navigating Through the Unknowns-Organizational Readiness Assessment Model for Quantum-Safe Transition
No full textPart 6: Emerging TopicsInternational audienceWhen implementing and adopting new technologies, knowing the level of organizational readiness is crucial. By assessing the readiness levels, organizations can focus on areas with low readiness levels and prepare for the change processes. Due to the increasing vulnerabilities presented by the advancement of quantum computing technology, today’s widely used cryptographic algorithms and encryption methods need to be modified with quantum-safe (QS) ones. However, organizations currently lack tools to understand the complexity of implementing and adopting QS technology, and there is no readiness assessment model available in the context of QS transition. By including different dimensions that organizations should consider when implementing and adopting QS technology, we develop an organizational readiness assessment model for QS transition. The dimensions used in the model include collaboration, governance, policy & regulation, awareness, QS solution standards, hybrid QS solutions, cryptographic agility strategies and knowledge on QS transition. While the organizational readiness assessment model with different dimensions shows the complexity involved in implementing and adopting QS technology, it acts as a guidance tool for organizations to navigate and prepare for uncertainties surrounding QS transition
What Public Services are Suitable for Digitalization? - A Classification of Public Service Characteristics
No full textPart 3: Public ServicesInternational audienceDigital self-service solutions work well for a large variety of citizen-government interactions. However, empirical research illustrate that many citizens need support when using digital services and thus use other communication channels in parallel (e.g., telephone, chat, face-to-face meetings), especially for welfare benefits. Public organizations must therefore consider the total cost of digitalizing citizen-government interactions, including the support needed in multiple and parallel communication channels. In this paper, we contribute with new knowledge that can support such considerations. The aim is to develop knowledge on how public services can be characterized as to inform assessment of the suitability for digitalization and automation of a particular service. Our study is set in the Scandinavian context, and we use welfare benefits as our empirical example of public service. We build on previous research on public encounters and outline aspects that can be used to discuss different types of welfare benefits. These aspects are used to analyze four different welfare benefits, resulting in additional and inductively generated aspects. Last, we present criteria that can guide the assessment of digitalization suitability for a particular service. Our study contributes with empirical illustrations, theoretical development, and a deeper understanding of what makes some welfare benefits more suitable for digitalization and automation than others
GaLaPaGoS: A Design Pattern for Sustainability of ICT Interactive Software and Services
No full textPart 1: Full Research PapersInternational audienceICT is an enabler for sustainable development and contributes to sustainability problems arising from different human activities aided by ICT interactive software and services. Consequently, these ICT-aided activities contribute to a vast amount of electronics and paper package waste at different stages of production, usage, and disposal. Some of these wastes can be attributed to a lack of understanding from ICT designers on how to design ICT interactive software and services for a green user experience. This paper explores design patterns as a tool to capture and incorporate sustainability concerns into the design of ICT interactive software and services for green user experience, where users become more conscious of the sustainability impacts of their actions. The Design science research method was applied to create and validate three sustainability design patterns. The results show that the proposed design patterns can guide ICT designers to engage and influence user behavior toward sustainability awareness
User-Centred Design: Experiences from Toolbox-Based Learning
No full textPart 3: PhD Student Discussion ForumInternational audienceThis doctoral research delves into the domain of User-Centered Design (UCD) skills acquisition among software engineering and computer science students and early professionals. Ground the literature, it addresses the challenges faced by novices in understanding complex problems and empathising with diverse user groups. The proposed publications address structured “toolboxes” comprising various UCD methods tailored to different demographics and design contexts. Through a mixed-methods approach, incorporating qualitative and quantitative data collection methods and iterative process optimisation based on student feedback, the study aims to explore the experiences, benefits, and challenges associated with toolbox-based learning of UCD. Notably, the research has progressed with the dissemination of findings through scholarly publications, showcasing the evolution and application of these toolboxes in educational and professional settings. Four publications detail the iterative refinement and application of the toolboxes proposed. The final dissertation is set to offer insights into UCD skill acquisition and application across diverse educational and professional contexts
InterView: A System to Support Interaction-Driven Visualization Systems Design
No full textPart 5: DemosInternational audienceIn the design of a visualization system for exploratory data analysis, a designer faces several issues: (i) the recognition of the causes behind excessive latency experienced by end users, who become quickly disengaged in the exploration if the response time is below a desired threshold (i.e., 500 ms); (ii) the discovery of portions of the visualization system that are poorly explored or may not work as intended; (iii) the lack of precise feedback from the end users who, struggling from excessive latency, become disinterested in the exploration and report high-level feedback that is too broad and generic for the designer to understand and transform into actionable changes to the design. To address these issues and provide more guidance to visualization system designers, we contributed a general framework to model and assess user interactions in big data visualization systems. It models the interaction space of the visualization system with the concept of augmented statecharts that label interactions with their latency thresholds. It is implemented in a system, InterView (the name relates to the collaboration between visualization designers and end users), composed of two software components, one to automatically generate the interaction space of a visualization system using a statechart, and one to replay user traces, reproducing each interaction an end user performed in the interaction log. In this paper, we demonstrate the capabilities of InterView applying it to a well-known crossfilter interface, Falcon, to guide the visualization system designers in discovering the root causes behind excessive latency, coupled with a complete understanding of the interaction space of their visualization system. In such a way, designers can finally acknowledge the problems of their visualization system with higher granularity and precision, giving more context to the feedback received by the end users
Coconut: Typestates for Embedded Systems
No full textPart 4: Tool PapersInternational audienceTypestate programming defines object states and actions to improve software safety by ensuring operations on objects follow the correct sequence. While its adoption in object-oriented languages has increased, limitations persist in the features supported. Typestates are particularly useful in embedded systems for operation sequencing, yet examples in this area are scarce. We introduce Coconut, a C++ tool that leverages typestate programming with templates for specifying typestates and combining static type checking and dynamic analysis to ensure proper class instance behaviour. It uniquely supports advanced programming features like branching, recursion, aliasing, concurrency, and optional typestate visualisation, facilitating idiomatic object-oriented programming with inheritance. Illustrating its effectiveness, we apply Coconut to actual embedded system projects, advancing the field by introducing a comprehensive set of features and practical examples for implementing typestate programming
Graded Semantics and Graded Logics for Eilenberg-Moore Coalgebras
No full textInternational audienceCoalgebra, as the abstract study of state-based systems, comes naturally equipped with a notion of behavioural equivalence that identifies states exhibiting the same behaviour. In many cases, however, this equivalence is finer than the intended semantics. Particularly in automata theory, behavioural equivalence of nondeterministic automata is essentially bisimilarity, and thus does not coincide with language equivalence. Language equivalence can be captured as behavioural equivalence on the determinization, which is obtained via the standard powerset construction. This construction can be lifted to coalgebraic generality, assuming a so-called Eilenberg-Moore distributive law between the functor determining the type of accepted structure (e.g. word languages) and a monad capturing the branching type (e.g. nondeterministic, weighted, probabilistic). Eilenberg-Moore-style coalgebraic semantics in this sense has been shown to be essentially subsumed by the more general framework of graded semantics, which is centrally based on graded monads. Graded semantics comes with a range of generic results, in particular regarding invariance and, under suitable conditions, expressiveness of dedicated modal logics for a given semantics; notably, these logics are evaluated on the original state space. We show that the instantiation of such graded logics to the case of Eilenberg-Moore-style semantics works extremely smoothly, and yields expressive modal logics in essentially all cases of interest. We additionally parametrize the framework over a quantale of truth values, thus in particular covering both the two-valued notions of equivalence and quantitative ones, i.e. behavioural distances