检索结果-内蒙古大学图书馆

VOR Adaptation on a Humanoid iCub Robot using a Spiking Cerebellar Model

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Naveros, Francisco Luque, Niceto R. Ros, Eduardo Arleo, Angelo Department of Computer Architecture and Technology University of Granada Granada18014 Spain Sorbonne Université INSERM Institut de la Vision 17 rue Moreau ParisF-75012

We embed a spiking cerebellar model within an adaptive real-time control loop able to operate a real robotic body (iCub) when performing different Vestibulo-Ocular Reflex (VOR) tasks. The spiking neural network computation, including event- and time-driven neural dynamics, neural activity and spike-timing dependent plasticity (STDP) mechanisms, leads to a non-deterministic computation time caused by the neural activity volleys encountered during cerebellar simulation. This non-deterministic computation time motivates the integration of a real-time supervisor module able to ensure a well-orchestrated neural computation time and robot operation. Actually, our neurorobotic experimental set-up (VOR) benefits from the biological sensory motor delay between the cerebellum and the body to buffer the computational overloads as well as providing flexibility in adjusting the neural computation time and real-time operation. The real-time supervisor module provides for incremental countermeasures that dynamically slow down or speed-up the cerebellar simulation by either halting the simulation or disabling certain neural computation features (i.e STDP mechanisms, spike propagation, neural updates) to cope with the real-time constraints imposed by the real robot operation. This neurorobotic experimental set-up is applied to different horizontal and vertical VOR adaptive tasks that are widely used by the neuroscientific community to address cerebellar functioning. We aim to elucidate the manner in which the combination of the cerebellar neural substrate and the distributed plasticity shapes the cerebellar neural activity to mediate motor adaptation. This work underlies the need for a two-stage learning process to facilitate VOR acquisition. For Rev Copyright © 2020, The Authors. All rights reserved.

关键词： Neural networks

Satire Detection in Turkish News Articles: A Machine Learning Approach 5th

学校读者我要写书评

暂无评论

Satire Detection in Turkish News Articles: A Machine Learnin...

5th International Conference on Big Data Innovations and Applications, Innovate-Data 2019

作者： Toçoğlu, Mansur Alp Onan, Aytuğ Faculty of Technology Department of Software Engineering Manisa Celal Bayar University Manisa45400 Turkey Faculty of Engineering and Architecture Department of Computer Engineering İzmir Katip Çelebi University İzmir35620 Turkey

ISBN: (纸本)9783030273545

With the advances in information and communication technologies, an immense amount of information has been shared on social media and microblogging platforms. Much of the online content contains elements of figurative language, such as, irony, sarcasm and satire. The automatic identification of figurative language can be viewed as a challenging task in natural language processing, where linguistic entities, such as, metaphor, analogy, ambiguity, irony, sarcasm, satire, and so on, have been utilized to express more complex meanings. The predictive performance of sentiment classification schemes may degrade if figurative language within the text has not been properly addressed. Satirical text is a way of figurative communication, where ideas/opinions regarding a people, event or issue is expressed in a humorous way to criticize that entity. Satirical news can be deceptive and harmful. In this paper, we present a machine learning based approach to satire detection in Turkish news articles. In the presented scheme, we utilized three kinds of features to model lexical information, namely, unigrams, bigrams and tri-grams. In addition, term-frequency, term-presence and TF-IDF based schemes have been taken into consideration. In the classification phase, Naïve Bayes, support vector machines, logistic regression and C4.5 algorithms have been examined. © 2019, Springer Nature Switzerland AG.

关键词： Support vector machines

An anonymous and privacy-preserving lightweight authentication protocol for secure communication in UAV-assisted IoAV networks

学校读者我要写书评

暂无评论

computer Communications 2025年 239卷

作者： Shariq, Mohd Jamil, Norziana Rawat, Gopal Singh Chaudhry, Shehzad Ashraf Masud, Mehedi Cangelosi, Angelo Department of Information Systems and Security College of IT UAE University P.O.Box 15551 Al Ain Abu Dhabi United Arab Emirates Bennett University Greater Noida201310 India Department of Computer Science and Information Technology College of Engineering Abu Dhabi University Abu Dhabi United Arab Emirates Department of Software Engineering Faculty of Engineering and Architecture Nisantasi University Istanbul34398 Turkey Department of Computer Science College of Computers and Information Technology Taif University P.O. Box 11099 Taif21944 Saudi Arabia Manchester Centre for Robotics and AI University of Manchester United Kingdom

With the rapid proliferation of the Internet of Things (IoT), autonomous vehicles (AVs), or self-driving cars, rely heavily on real-time data sharing and message exchanges over wireless networks. AVs use sensors, artificial intelligence, machine learning, and advanced algorithms to perform various functions, enabling users to operate without human intervention. Owing to the flexibility and high mobility of drones, they could aid in the operations of AVs. However, the security and privacy are the main concerns;specifically, the threat of physical capture and violation of anonymity are the main hurdles for realization of secure communication among the AVs and drones. To address these challenges, we propose an anonymous and provably Secure Lightweight Authentication Protocol for unmanned-aerial-vehicle-assisted Internet of Autonomous Vehicles (SLAP-IoAV). The proposed protocol uses cryptographic primitives such as exclusive-OR operations, elliptic-curve cryptography, collision-resistant one-way hashing, and concatenation to ensure robust security. An informal security analysis found that SLAP-IoAV is secure against several known attacks, and a performance analysis established that the protocol has less computational and communication overhead than existing competitive protocols. Additionally, Scyther simulation results confirm that no security vulnerabilities are present. Overall, our protocol delivers superior security and performance, making it well-suited to real-world applications in the AV industry. © 2025 Elsevier B.V.

关键词： Authentication Protocol

Using the Model of a Functional Rationalizer of Consumer Behavior in Recommendation Systems for Managing the Transport Activity of the Urban Population 23

学校读者我要写书评

暂无评论

Using the Model of a Functional Rationalizer of Consumer Beh...

23rd International Conference on Soft Computing and Measurements, SCM 2020

作者： Seliverstov, Yaroslav A. Seliverstov, Svytoslav A. Podoprigora, Nikolay V. Starichenkov, Alexey L. Naryshkin, Roman S. Solomenko Institute of Transport Problems Russian Academy of Sciences Institute of Computer Science and Technology Peter the Great St.Petersburg Polytechnic University Laboratory of Intelligent Transport Systems St. Petersburg Russia Saint Petersburg State University of Architecture and Civil Engineering Department of Ground Transportation Technological Machines St. Petersburg Russia Saint Petersburg Electrotechnical University 'LETI' Department of Ship Control Systems St. Petersburg Russia Saint Petersburg State University Department of Programming Technology St. Petersburg Russia

ISBN: (纸本)9781728196923

An overview of existing urban software mobile applications of the transport and economic direction is given. A model of a functional rationalizer of consumer behavior is being built. The software model of the functional rationalizer of consumer behavior (SM FRCB) was developed for the first time. PMFRCB allows the user to expand the number of his preferred needs (occupations, activities) during the daily cycle through intelligent recommendations. Also, SM FRCB allows you to optimize needs (activities, activities) at the cost and rate of their use. The SM FRCB is made in Python_3 using the libraries matplotlib, collections, numpy, pyplot, mplot3d. The analysis of consumer behavior before and after using the functional rationalizer model is carried out. The graphical results of a structural analysis of the costs of old and new consumer behavior, analysis of consumer behavior within the boundaries of the theory of possibilities and the model of transport behavior of a resident before and after applying the functional rationalizer model are presented. The prospects of further improving the SM FRCB are considered. © 2020 IEEE.

关键词： Smart city

A Review on Current and Old SCADA Networks Applied to Water Distribution Systems 1

学校读者我要写书评

暂无评论

A Review on Current and Old SCADA Networks Applied to Water ...

1st International Conference of Intelligent Computing and Engineering, ICOICE 2019

作者： Franco, Daniel Jose Muhammed, Abdullah Bin Subramaniam, Shamala K. Abdullah, Azizol Silva, Rui Miguel Akram, Omar Khasro University Putra Malaysia Department of Communication Technology and Network Serdang Malaysia Lab Ubinet Computer Security and Cybercrime Polytechnic Institute of Beja Department of Engineering Beja Portugal University Putra Malaysia Department of Architecture Serdang Malaysia

ISBN: (纸本)9781728144870

Water is probably the oldest factor receiving attention from the population, since the beginning of the human race. The evolution of water supply systems is directly related to the urban growth of the cities and their geographical location. This study focuses on SCADA (Supervisory Control And Data Acquisition) systems used to control and managing water distribution systems all around the world, highlighting their components and deeply approaching SCADA networks and communication protocols. Based on the need of protection and security on SCADA networks, this study aims to provide a review of the existing literature, through the case study of water distribution systems, identifying the different components of a SCADA system, as well as its communication architectures and protocols and some known attacks, to design a framework on current and old SCADA networks. Results show that SCADA systems are not just applied to water distribution and water waste systems, but also to many other industrial automated systems that control on crucial systems. The security of such systems is yet weak and faces many vulnerabilities and threats, where security mechanisms must be applied. For this purpose, the study of SCADA networks and communications is considered a crucial point for the correct development of security tools. © 2019 IEEE.

关键词： SCADA systems

To talk or to work: Flexible communication compression for energy efficient federated learning over heterogeneous mobile edge devices

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Liang Shi, Dian Hou, Ronghui Li, Hui Pan, Miao Han, Zhu School of Cyber Engineering Xidian University Xi’an China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences China Department of Electrical and Computer Engineering University of Houston HoustonTX United States

Recent advances in machine learning, wireless communication, and mobile hardware technologies promisingly enable federated learning (FL) over massive mobile edge devices, which opens new horizons for numerous intelligent mobile applications. Despite the potential benefits, FL imposes huge communication and computation burdens on participating devices due to periodical global synchronization and continuous local training, raising great challenges to battery constrained mobile devices. In this work, we target at improving the energy efficiency of FL over mobile edge networks to accommodate heterogeneous participating devices without sacrificing the learning performance. To this end, we develop a convergence-guaranteed FL algorithm enabling flexible communication compression. Guided by the derived convergence bound, we design a compression control scheme to balance the energy consumption of local computing (i.e., "working") and wireless communication (i.e., "talking") from the long-term learning perspective. In particular, the compression parameters are elaborately chosen for FL participants adapting to their computing and communication environments. Extensive simulations are conducted using various datasets to validate our theoretical analysis, and the results also demonstrate the efficacy of the proposed scheme in energy saving. © 2020, CC BY.

关键词： Wireless networks

A scholarly backcasting approach to a novel model for smart sustainable cities of the future: strategic problem orientation

学校读者我要写书评

暂无评论

City, Territory and architecture 2019年第1期6卷 1页

作者： Bibri, Simon Elias Krogstie, John Department of Computer Science The Norwegian University of Science and Technology Sem Saelands veie 9 Trondheim 7491 Norway Department of Architecture and Planning Alfred Getz vei 3 Sentralbygg 1 5th Floor Trondheim 7491 Norway

Sustainable cities have, since the early 1990s, been the leading global paradigm of urban planning and development thanks to the different models of sustainable urban form proposed as new frameworks for redesigning and restructuring urban places to achieve sustainability. Indeed, huge advances in some areas of sustainability knowledge and a multitude of exemplary practical initiatives have been realized, thereby raising the profile of sustainable cities worldwide. The change is still inspiring and the challenge continues to induce scholars and practitioners to enhance existing, and propose new, models. Especially, sustainable urban forms have been problematic, whether in theory or practice, so is yet knowing to what extent progress has been made towards sustainable cities. They are associated with a number of problems, issues, and challenges and thus much more needs to be done considering the very fragmented, conflicting picture that arises of change on the ground in the face of the expanding urbanization. This involves the question of how they should be monitored, understood, analyzed, planned, and even integrated so as to improve, advance, and maintain their contribution to sustainability. This brings us to the issue of sustainable cities and smart cities being extremely fragmented as landscapes and weakly connected as approaches, despite the proven role and untapped potential of advanced ICT, especially big data technology, for advancing sustainability under what is labeled ‘smart sustainable cities.’ Essentially, there are multiple visions of, and pathways to achieving, such cities, which depends on how they can be conceptualized. This paper details the two parts of strategic problem orientation by answering the guiding questions for Steps 1 and 2 of the futures study being conducted. This study aims to analyze, investigate, and develop a novel model for smart sustainable cities of the future using backcasting as a scholarly approach. It involves a series of pap

关键词： Backcasting Big data science and analytics Compact cities Design principles and strategies Eco-cities Futures study Planning practices Smart cities Smart sustainable cities Sustainable cities Sustainable development

The Role of Open-Source LLMs in Shaping the Future of GeoAI

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Huang, Xiao Tu, Zhengzhong Ye, Xinyue Goodchild, Michael Department of Environmental Sciences Emory University AtlantaGA30322 United States Department of Computer Science and Engineering Texas A&M University College StationTX77840 United States Department of Landscape Architecture and Urban Planning Center for Geospatial Sciences Applications and Technology Texas A&M University College StationTX77840 United States Department of Geography University of California Santa BarbaraCA93106 United States

Large Language Models (LLMs) are transforming geospatial artificial intelligence (GeoAI), offering new capabilities in data processing, spatial analysis, and decision support. This paper examines the open-source paradigm's pivotal role in this transformation. While proprietary LLMs offer accessibility, they often limit the customization, interoperability, and transparency vital for specialized geospatial tasks. Conversely, open-source alternatives significantly advance Geographic Information Science (GIScience) by fostering greater adaptability, reproducibility, and community-driven innovation. Open frameworks empower researchers to tailor solutions, integrate cutting-edge methodologies (e.g., reinforcement learning, advanced spatial indexing), and align with FAIR principles. However, the growing reliance on any LLM necessitates careful consideration of security vulnerabilities, ethical risks, and robust governance for AI-generated geospatial outputs. Ongoing debates on accessibility, regulation, and misuse underscore the critical need for responsible AI development strategies. This paper argues that GIScience advances best not through a single model type, but by cultivating a diverse, interoperable ecosystem combining open-source foundations for innovation, bespoke geospatial models, and interdisciplinary collaboration. By critically evaluating the opportunities and challenges of open-source LLMs within the broader GeoAI landscape, this work contributes to a nuanced discourse on leveraging AI to effectively advance spatial research, policy, and decision-making in an equitable, sustainable, and scientifically rigorous manner. © 2025, CC BY-NC-ND.

关键词： Indexing (of information)

Linearization-based quantized stabilization of nonlinear systems under DoS attacks

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Kato, Rui Cetinkaya, Ahmet Ishii, Hideaki Department of Computer Science Tokyo Instutite of Technology Yokohama226-8502 Japan Information Systems Architecture Science Research Division National Institute of Informatics Tokyo101-8430 Japan

Motivated by recent security issues in cyber-physical systems, this technical note studies the stabilization problem of networked control systems under Denial-of-Service (DoS) attacks. In particular, we consider to stabilize a nonlinear system with limited data rate via linearization. We employ a deterministic DoS attack model constrained in terms of attacks’ frequency and duration, allowing us to cover a large class of potential attacks. To achieve asymptotic stabilization, we propose a resilient dynamic quantizer in the sense that it does not saturate in the presence of packet losses caused by DoS attacks. A sufficient condition for stability is derived by restricting the average DoS frequency and duration. In addition, because of the locality of linearization, we explicitly investigate an estimate of the region of attraction, which can be expected to be reduced depending on the strength of DoS attacks. A simulation example is presented for demonstration of our results. Copyright © 2020, The Authors. All rights reserved.

关键词： Denial-of-service attack