检索结果-内蒙古大学图书馆

Web Application to predict Skin Disease: An Approach Using Deep Learning Algorithm

学校读者我要写书评

暂无评论

Web Application to predict Skin Disease: An Approach Using D...

Human-computer Interaction, Optimization and Robotic Applications (HORA), International Congress on

作者： Eelanila Thayalan Ayingaran Arumugavel Sharujan Ganeshan Makenthiran Dalaxshan Harinda Fernando Kaushalya Rajapakse Department of Information Technology Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Computer Systems Engineering Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Computer Science and Software Engineering Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka

ISBN: (数字)9798350394634

ISBN: (纸本)9798350394641

The Disease Prediction System revolutionizes healthcare with advanced machine learning techniques for early detection of skin diseases, notably focusing on skin cancer. Through image processing and Transfer Learning, it excels in identifying potential malignancies, enabling timely interventions. Its capabilities extend to benign tumors and growth disorders, utilizing the ResNet50 Model for precise identification. Additionally, it predicts skin reactions associated with various dermatological conditions, such as Urticaria Hives and Warts, leveraging the efficientnetB0 Model. Integration of the VGG16 Model enhances diagnostic accuracy for inflammatory skin conditions. This holistic approach prioritizes patient-centric care, leveraging diverse datasets and intricate pattern recognition in medical images. The system’s proactive nature embodies personalized solutions for early detection, timely intervention, and improved patient outcomes. Its versatility and accuracy underscore itstransformative potential in healthcare delivery. By harnessing diverse datasets and recognizing intricate patterns within medical images, it heralds a new era of personalized healthcare solutions. In essence, the Disease Prediction System exemplifies the transformative potential of machine learning in healthcare, ensuring the highest standards of diagnostic accuracy and efficacy, while prioritizing patient well-being and quality oflife.

关键词： Transfer learning Medical services Skin Pattern recognition Medical diagnostic imaging Standards Robots

Minimizing Occlusion Effect on Multi-View Camera Perception in BEV with Multi-Sensor Fusion

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Kumar, Sanjay Truong, Hiep Sharma, Sushil Sistu, Ganesh Scanlan, Tony Grua, Eoin Eising, Ciarán Department of Electronic and Computer Engineering University of Limerick Ireland Research Centre University of Limerick Ireland Lero The Irish Software Research Centre University of Limerick Ireland DSW Valeo Kronach Germany Valeo Vision Systems Ireland

Autonomous driving technology is rapidly evolving, offering the potential for safer and more efficient transportation. However, the performance of these systems can be significantly compromised by the occlusion on sensors due to environmental factors like dirt, dust, rain, and fog. These occlusions severely affect vision-based tasks such as object detection, vehicle segmentation, and lane recognition. In this paper, we investigate the impact of various kinds of occlusions on camera sensor by projecting their effects from multi-view camera images of the nuScenes dataset into the Bird’s-Eye View (BEV) domain. This approach allows us to analyze how occlusions spatially distribute and influence vehicle segmentation accuracy within the BEV domain. Despite significant advances in sensor technology and multi-sensor fusion, a gap remains in the existing literature regarding the specific effects of camera occlusions on BEV-based perception systems. To address this gap, we use a multi-sensor fusion technique that integrates LiDAR and radar sensor data to mitigate the performance degradation caused by occluded cameras. Our findings demonstrate that this approach significantly enhances the accuracy and robustness of vehicle segmentation tasks, leading to more reliable autonomous driving systems. https://***/OmX2NEeOzAE © 2025, CC BY.

关键词： Image segmentation

An Automated Solution for Securing Confidential Documents in a BYOD Environment 3

学校读者我要写书评

暂无评论

An Automated Solution for Securing Confidential Documents in...

3rd International Conference on Advancements in Computing, ICAC 2021

作者： Abisheka, P. A. C Azra, M. A. F Poobalan, A. V Wijekoon, Janaka Yapa, Kavinga Murthaja, Mifraz Sri Lanka Institute of Information Technology Department of Computer Systems and Engineering Sri Lanka WSO2 Senior Software Engineer Colombo Sri Lanka

ISBN: (纸本)9781665408622

BYOD or Bring Your Own Device is a set of policies that allow employees of an organization to use their own devices for official work purposes. BYOD is an immensely popular concept in the present day due to the many advantages it provides. However, the implementation of BYOD policies entail diverse problems and as a result, the confidentiality of documents can be breached. Furthermore, employees without security awareness and training are highly vulnerable to endpoint attacks, network attacks, and zero-day attacks that lead to a breach of confidentiality, integrity, and availability (CIA). In this context, this paper proposes a comprehensive solution;'BYODENCE', for the detection and prevention of unauthorized access to organizational documents. BYODENCE is an efficient BYOD solution which can produce competitive results in terms of accuracy and speed. © 2021 IEEE.

关键词： Zero-day attack

Reinforcement Learning for Blind Stair Climbing with Legged and Wheeled-Legged Robots

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chamorro, Simon Klemm, Victor de la Iglesia Valls, Miguel Pal, Christopher Siegwart, Roland Department of Computer and Software Engineering École Polytechnique de Montréal 2900 Boul. Édouard-Montpetit QC Canada Autonomous Systems Lab ETH Zurich Switzerland Robotic Systems Lab ETH Zurich Switzerland Ascento Robotics Zurich Switzerland

In recent years, legged and wheeled-legged robots have gained prominence for tasks in environments predominantly created for humans across various domains. One significant challenge faced by many of these robots is their limited capability to navigate stairs, which hampers their functionality in multi-story environments. This study proposes a method aimed at addressing this limitation, employing reinforcement learning to develop a versatile controller applicable to a wide range of robots. In contrast to the conventional velocity-based controllers, our approach builds upon a position-based formulation of the RL task, which we show to be vital for stair climbing. Furthermore, the methodology leverages an asymmetric actor-critic structure, enabling the utilization of privileged information from simulated environments during training while eliminating the reliance on exteroceptive sensors during real-world deployment. Another key feature of the proposed approach is the incorporation of a boolean observation within the controller, enabling the activation or deactivation of a stair-climbing mode. We present our results on different quadrupeds and bipedal robots in simulation and showcase how our method allows the balancing robot Ascento to climb 15cm stairs in the real world, a task that was previously impossible for this robot. Copyright © 2024, The Authors. All rights reserved.

关键词： Stairs

Stop-and-go wave super-resolution reconstruction via iterative refinement

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ji, Junyi Richardson, Alex Gloudemans, Derek Zachár, Gergely Nice, Matthew Barbour, William Sprinkle, Jonathan Piccoli, Benedetto Work, Daniel B. Department of Civil and Environmental Engineering Vanderbilt University United States Institute for Software Integrated Systems Vanderbilt University United States Department of Computer Science Vanderbilt University United States Department of Mathematical Sciences Rutgers University Camden United States

Stop-and-go waves are a fundamental phenomenon in freeway traffic flow, contributing to inefficiencies, crashes, and emissions. Recent advancements in high-fidelity sensor technologies have improved the ability to capture detailed traffic dynamics, yet such systems remain scarce and costly. In contrast, conventional traffic sensors are widely deployed but suffer from relatively coarse-grain data resolution, potentially impeding accurate analysis of stop-and-go waves. This article explores whether generative AI models can enhance the resolution of conventional traffic sensor to approximate the quality of high-fidelity observations. We present a novel approach using a conditional diffusion denoising model, designed to reconstruct fine-grained traffic speed field from radar-based conventional sensors via iterative refinement. We introduce a new dataset, WaveX, comprising 132 hours of data from both low and high-fidelity sensor systems, totaling over 2 million vehicle miles traveled. Our approach leverages this dataset to formulate the traffic measurement refinement problem as a spatio-temporal super-resolution task. We demonstrate that our model can effectively reproduce the patterns of stop-and-go waves, achieving high accuracy in capturing these critical traffic dynamics. Our results show promising advancements in traffic data refinement, offering a cost-effective way to leverage existing low spatio-temporal resolution sensor networks for improved traffic analysis and management. We also open-source our dataset, trained model and code to enable further research and applications. Copyright © 2024, The Authors. All rights reserved.

关键词： Highway administration

Optimizing User Data Privacy and Confidentiality in Cloud Storage systems Through Advanced Obfuscrypt Encryption Methods for Enhanced Security and Efficient Data Protection

学校读者我要写书评

暂无评论

Optimizing User Data Privacy and Confidentiality in Cloud St...

Recent Advances in Science and engineering Technology (ICRASET), International Conference on

作者： P.S. Ramesh I. Sudha J. Jagannathan Rajkumar Pandiarajan A. Ponmalar Department of Computer Science and Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai Tamilnadu India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences SIMATS University Chennai Tamil Nadu India Department of Software and Systems Engineering School of Computer Science Engineering and Information Systems Vellore Institute of Technology Katpadi Vellore India Department of Information and Technology School of Computing Kalasalingam Academy Of Research and Education Krishnankoil Virudhunagar India R.M.K. Engineering College Chennai Tamilnadu India

ISBN: (数字)9798350388602

ISBN: (纸本)9798350388619

With a steady increase in the adoption of cloud storage systems, the client’s data are at risk of being leaked. There are several methods of encrypting data which are quite useful but they lack some of the features of today’s sophisticated threats. The methodology used in this research propose an encryption framework known as Obfuscrypt to improve the issues of data privacy as well as confidentiality of data stored in cloud storage systems. Obfuscrypt uses conventional encryption strategies incorporated with obfuscation and post-quantum cryptographic algorithms to provide a complex security plan immune to classic and quantum approaches. Some of the proposed other innovations include the decentralised key management with multi-factor authentication and RBAC-ABE as the fine-grained access control techniques. These features make it possible for only the authorized personnel to be in a position to be in a position of decrypting and retrieving the stored data thereby minimizing the possibility of the data being accessed by unauthorized people. The work also considers the issue of performance efficiency of the cloud storage systems. Similar to other symmetric encryption programs, Obfuscrypt uses light encryption algorithms and brings in to play the hardware acceleration so that it may infuse lesser computational overhead in the process of encryption and decryption. As can be clearly seen from the results, the actual work proves that the proposed framework not only offers a higher level of security but does not affect the system performance to a great extent. Also, the study addresses the post-quantum cryptographic algorithm for making the system resistant to an attack that can be posed by quantum computing systems. With the help of these improved algorithms, Obfuscrypt guarantees the permanent data security in the world of constantly emerging cyber threats.

关键词： Resistance Cloud computing Technological innovation Multi-factor authentication Quantum computing System performance Memory management software performance Encryption Protection

F2NAS: Flexible Federated Neural Architecture Search in Green Edge Computing

学校读者我要写书评

暂无评论

F2NAS: Flexible Federated Neural Architecture Search in Gree...

IEEE International Conference on Communications (ICC)

作者： Zebo Zhao Chao Qiu Yunfeng Zhao Xiaofei Wang Haipeng Yao Xiuhua Li F. Richard Yu College of Intelligence and Computing Tianjin University Tianjin China Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China School of Big Data & Software Engineering Chongqing University Chongqing China Department of Systems and Computer Engineering Carleton University Ottawa Canada

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

The rapid growth of edge computing calls for fine-tuned deep neural network (DNN) deployment that emphasizes energy-efficient implementation, due to the resource constraints of edge devices. Traditional Federated Learning-based Neural Architecture Search (FL-based NAS) has been instrumental in the complexities of this deployment, particularly in addressing constraints posed by device heterogeneity, limited resources, and privacy preservation. However, it is hindered by issues such as suboptimal aggregation of homogeneous neural blocks, significant knowledge waste in disregarding heterogeneous neural blocks, and excessive communication energy consumption. This paper introduces F 2 NAS in green edge computing, a novel energy-efficient approach that addresses these limitations by ensuring flexible and energy-efficient model design and training for edge devices. Firstly, F 2 NAS introduces an innovative aggregation strategy that enhances the integration of homogeneous neural blocks by using inter-block distances to optimize weight allocation. Further, it employs a unique parameter extraction technique that recaptures valuable insights from previously overlooked heterogeneous neural blocks. Finally, F 2 NAS meticulously calibrates communication energy consumption by balancing loss function and model interaction, setting and refining an upper limit for model communication. Experimental results reveal F 2 NAS enhances model accuracy by 2.8% to 4.7%, simultaneously reducing the energy consumption by nearly 50% through optimizing the communication cost.

关键词： Training Energy consumption Privacy Accuracy Computational modeling Refining Energy efficiency

Distributionally Robust Control for Chance-Constrained Signal Temporal Logic Specifications

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Kordabad, Arash Bahari Vlahakis, Eleftherios E. Lindemann, Lars Dimarogonas, Dimos V. Soudjani, Sadegh Max Planck Institute for Software Systems Kaiserslautern Germany Division of Decision and Control Systems KTH Royal Institute of Technology Stockholm Sweden Thomas Lord Department of Computer Science Viterbi School of Engineering University of Southern California Los Angeles United States

We consider distributionally robust optimal control of stochastic linear systems under signal temporal logic (STL) chance constraints when the disturbance distribution is unknown. By assuming that the underlying predicate functions are Lipschitz continuous and the noise realizations are drawn from a distribution having a concentration of measure property, we first formulate the underlying chance-constrained control problem as stochastic programming with constraints on expectations and propose a solution using a distributionally robust approach based on the Wasserstein metric. We show that by choosing a proper Wasserstein radius, the original chance-constrained optimization can be satisfied with a user-defined confidence level. A numerical example illustrates the efficacy of the method. © 2024, CC BY-NC-ND.

关键词： Stochastic systems

Application of Data Science and Machine Learning in the Prediction of College Dropout: A Data-Driven Predictive Approach

学校读者我要写书评

暂无评论

Application of Data Science and Machine Learning in the Pred...

International Conference on software Process Improvement (CIMPS)

作者： Axel Frederick Félix Jiménez Vania Stephany Sanchéz Lee Isaul Ibarra Belmonte Ezra Federico Parra González Engineering in Computer Systems National Polytechnic Institute Zacatecas México Software Engineer Center for Research in Mathematics Zacatecas México Computer Science Department Center for Research in Mathematics Zacatecas México

ISBN: (数字)9798350358568

ISBN: (纸本)9798350358575

This paper presents a study on the prediction of student graduation or failure using two predictive models: K-Nearest Neighbors (KNN) and a forward sequential Artificial Neural Network (ANN). The models, built with a well-chosen set of independent variables, were assessed using metrics like precision and accuracy. The results obtained revealed that both the KNN model and the sequential forward ANN model achieved high efficiency in predicting student graduation or failure, achieving accuracies of 0.9133% (K=3) and 0.9312% (after 50 epochs), respectively. Providing a valuable tool to identify early on students at risk of not graduating and to take preventive measures to improve their academic performance. Comparisons with related research showed consistent outcomes, underscoring the credibility and importance of the employed predictive models.

关键词： Measurement Artificial neural networks Machine learning Predictive models Data science software