In urban transportation systems such as metro networks, commuter travel routes have become more diversified due to the increasing complexity of network structures, including multiple metro lines, stations, junctions, ...
详细信息
ISBN:
(数字)9798331521691
ISBN:
(纸本)9798331521707
In urban transportation systems such as metro networks, commuter travel routes have become more diversified due to the increasing complexity of network structures, including multiple metro lines, stations, junctions, and convoluted train schedules. This work presents a comprehensive solution that integrates advanced pathfinding algorithms with efficient scheduling techniques to create a seamless metro experience for commuters. The proposed system generates the shortest and most effective routes for commuters as well as administrators. In conjunction with pathfinding, a sophisticated scheduler has been developed to minimize waiting times at stations and to facilitate smooth transitions between metro lines. The synergy between routing algorithms and sophisticated scheduling optimization not only enhances the operational efficiency of metro train lines, but also significantly reduces overall travel time for commuters, which will lead to increased commuter satisfaction.
In vision-language models (VLMs), prompt tuning has shown its effectiveness in adapting models to downstream tasks. However, learned prompts struggle to generalize to unseen classes, as they tend to overfit to the cla...
详细信息
Table Structure Recognition (TSR) is vital for various downstream tasks like information retrieval, table reconstruction, and document understanding. While most state-of-the-art (SOTA) research predominantly focuses o...
详细信息
The SARS-CoV-2 coronavirus strain’s introduction in December 2019 resulted in the development of the new coronavirus disease, COVID-19. Following its first appearance, the virus quickly spread throughout the world an...
详细信息
The SARS-CoV-2 coronavirus strain’s introduction in December 2019 resulted in the development of the new coronavirus disease, COVID-19. Following its first appearance, the virus quickly spread throughout the world and is now considered to be a pandemic. There were 6,885,962 recorded deaths and 689,853,908 confirmed cases as of April 4, 2023. It is essential to put in place a thorough testing strategy in order to stop the disease from spreading. Nonetheless, a number of testing approaches are presently under consideration due to a restricted inventory and a limited supply of testing equipment. Recent expert analysis suggests that images from chest computed tomography (CT) scans could reveal important information about COVID-19, which is why we are using this modality as a focus of our investigation. Moreover, numerous recent studies have demonstrated that selecting the most informative features from the subject images improves the classification models’ efficiency and shortens the time needed for training and testing. All of this encourages us to present a study that suggests a novel, efficient, and fast feature selection system as the core of the proposed highly competent clinical decision support system for COVID-19 infection prediction. Using a publicly accessible CT image dataset, this four-phase system divides the images into two categories: "COVID-19-infected human" and "healthy human". Pre-processing is the first step in the study, after which features from different categories in the images are extracted in the next phase. In the third phase, the most influential features are then selected using three algorithms: the Teaching Learning-Based Optimization Algorithm (TLBO), the Cuckoo Search Optimization Algorithm (CSO), and a proposed hybrid of these two. To the best of the authors’ knowledge, these algorithms have rarely been applied to feature selection for COVID-19 infection prediction, which highlights the originality and inventiveness of the work. Followin
Large language models (LLMs) are increasingly deployed across diverse domains, yet they are prone to generating factually incorrect outputs—commonly known as "hallucinations." Among existing mitigation stra...
详细信息
The 5G core is an important part of a 5G network, and with the exponential growth of connected devices and dynamic traffic conditions, it is essential for the 5G core to be scalable and fault-tolerant. This requiremen...
详细信息
ISBN:
(数字)9798331531195
ISBN:
(纸本)9798331531201
The 5G core is an important part of a 5G network, and with the exponential growth of connected devices and dynamic traffic conditions, it is essential for the 5G core to be scalable and fault-tolerant. This requirement is even more important with the softwarization of the packet core and cloud-based deployments. This paper presents a comparison of design choices when building a scalable and fault-tolerant 5G core on a Kubernetes-orchestrated cloud platform. Prior work in this direction does not fully explore all design choices, or is not compliant with 3GPP standards. In contrast, we start with a 3GPP-compliant production-grade 5G core, and build multiple variants of cloud-native 5G core components. We leverage Kubernetes’ automatic failover, and auto-scaling capabilities in different ways to make the 5G core scalable and fault-tolerant. We conduct extensive experiments to evaluate the scalability and resilience of various design choices, and to quantify the overheads of cloud deployments. Our work exposes tradeoffs between performance and fault tolerance, and provides insights on how best to design a scalable and fault-tolerant 5G core on Kubernetes.
Effective management of semi-perishable food items is essential for minimising waste, maintaining food safety, and supporting sustainability efforts. This paper introduces the Responsibility Index for Sustainability a...
详细信息
ISBN:
(数字)9798331531195
ISBN:
(纸本)9798331531201
Effective management of semi-perishable food items is essential for minimising waste, maintaining food safety, and supporting sustainability efforts. This paper introduces the Responsibility Index for Sustainability and Efficiency (RISE), a set of modular components designed to seamlessly integrate with existing invoicing systems and enhance their performance by improving transparency, accountability, and waste management practices in retail stores. Semi-perishable food items, such as flour, bread, packaged meals, and beverages made from unprocessed grains, have a shorter shelf life than their raw counterparts, which can be stored for longer periods before processing. Ineffective management of these items often results in wastage and inflates the prices of raw materials due to imbalanced demand. Our solution holds retailers accountable for their role in demand creation and food waste by integrating a Responsibility Index Score, encouraging them to optimise their product offerings and reduce waste. These modules enhance consumption practices, supporting UN Sustainable Development Goals 2 (Zero Hunger) and 12 (Responsible Consumption and Production). They also help build consumer trust and reinforce retail stores’ economic and social accountability. The modular approach ensures adaptability and ease of adoption across various invoicing platforms without requiring a complete system overhaul.
Quantum entanglement serves as a foundational resource for various quantum technologies. In optical systems, entanglement distribution relies on the indistinguishability and spatial overlap of photons. Heralded scheme...
详细信息
The smart stick has been termed as an innovative tool to help the visually and physically challenged, and it is far from the traditional white canes in that its framework avails an advanced technology to provide a ful...
详细信息
ISBN:
(数字)9798331515683
ISBN:
(纸本)9798331515690
The smart stick has been termed as an innovative tool to help the visually and physically challenged, and it is far from the traditional white canes in that its framework avails an advanced technology to provide a full and instant sensory experience. This paper introduces a new concept of a smart walking stick designed to assist blind and visually impaired individuals, offering greater independence and safety. This unique cane offers better navigation guidance than standard tools, so users can travel comfortably through a variety of surroundings. In order to guarantee quick assistance when needed, it also has a mechanism for issuing emergency notifications. While current solutions provide some basic support, they frequently areunable to offer comprehensive help in complex situations. Our suggested smart cane overcomes these drawbacks and provides an affordable way to raise the standard of living for those who are blind or visually impaired.
Skin cancer, a severe condition, requires early and accurate detection to improve survival rates. This study presents a hybrid framework combining deep learning (DL) and machine learning (ML) models for enhanced skin ...
详细信息
暂无评论