检索结果-内蒙古大学图书馆

system Modelling, Numerical Simulations and Experimental Validation of High Capacity FSO Data Transmission in DWDM Communication Employing Optical Frequency Comb

学校读者我要写书评

暂无评论

System Modelling, Numerical Simulations and Experimental Val...

International Conference on Numerical Simulation of Optoelectronic Devices, (NUSOD)

作者： Narmada Rajaram Mahrokh Avazpour Liam Barry Karin Hinzer Trevor Hall Ahmad Atieh School of Electrical Engineering and Computer Science University of Ottawa Ottawa Canada Radio and Optics Communications Laboratory School of Electronic Engineering Dublin City University Glasnevin Dublin 9 Ireland Optiwave System Inc 7 Capella Court University of Ottawa Ottawa Canada

ISBN: (数字)9798350390537

ISBN: (纸本)9798350390544

Dense Wavelength Division Multiplexing (DWDM) optical technology allows transmission of many wavelengths in a single optical channel. In this paper, system modelling and numerical simulations are demonstrated for high-capacity data transmission using an Optical Frequency Comb (OFC). An OFC is generated using fiber loop modulation technique and simulations are carried out using commercially available simulation software –Optisystem. An OFC with excellent flatness is obtained, which is essential for noise and error reduction. Each comb line is modulated with data and the DWDM multiplexed signal is transmitted over a free-space optical (FSO) channel. The system performance is assessed in terms of Bit Error Rate (BER) and range of the FSO channel. Our experimental results demonstrate that our system aligns well with simulation and can generate an OFC confirming the potential of our approach for applications such as optical communication networks.

关键词： Optical fibers Bit error rate Wavelength division multiplexing Numerical simulation Optical harmonic generation Data models Adaptive optics Numerical models Optical modulation Data communication

MoCoLSK: Modality Conditioned High-Resolution Downscaling for Land Surface Temperature

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Dai, Qun Yuan, Chunyang Dai, Yimian Li, Yuxuan Li, Xiang Ni, Kang Xu, Jianhui Shu, Xiangbo Yang, Jian School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China School of Computer Science and Technology Nanjing University of Posts and Telecommunications Nanjing China PCA Lab VCIP College of Computer Science Nankai University China NKIARI Futian Shenzhen China Guangdong Provincial Key Laboratory of Utilization Remote Sensing and Geographical Information System Guangzhou Institute of Geography Guangdong Academy of Sciences Guangzhou510070 China

Land Surface Temperature (LST) is a critical parameter for environmental studies, but directly obtaining high spatial resolution LST data remains challenging due to the spatio-temporal trade-off in satellite remote sensing. Guided LST downscaling has emerged as an alternative solution to overcome these limitations, but current methods often neglect spatial non-stationarity, and there is a lack of an open-source ecosystem for deep learning methods. In this paper, we propose the Modality-Conditional Large Selective Kernel (MoCoLSK) Network, a novel architecture that dynamically fuses multi-modal data through modality-conditioned projections. MoCoLSK achieves a confluence of dynamic receptive field adjustment and multi-modal feature fusion, leading to enhanced LST prediction accuracy. Furthermore, we establish the GrokLST project, a comprehensive open-source ecosystem featuring the GrokLST dataset, a high-resolution benchmark, and the GrokLST toolkit, an open-source PyTorch-based toolkit encapsulating MoCoLSK alongside 40+ state-of-the-art approaches. Extensive experimental results validate MoCoLSK’s effectiveness in capturing complex dependencies and subtle variations within multispectral data, outperforming existing methods in LST downscaling. Our code, dataset, and toolkit are available at https://***/GrokCV/GrokLST. Copyright © 2024, The Authors. All rights reserved.

关键词： Surface temperature

An Investigation of the Current State of Digital Platforms and Their Prospects for the Future

学校读者我要写书评

暂无评论

An Investigation of the Current State of Digital Platforms a...

Interdisciplinary Humanitarian Conference for Sustainability (IIHC), International

作者： Mahainder Rao S Rakesh Kumar Department of Computer & System Sciences School of Computer & System Sciences Jaipur National University Jaipur India Department of Computer Science and Engineering Galgotias University Greater Noida Uttar Pradesh India

Researchers in the field of information systems are becoming more interested in this subject as a result of the increased use of digital platforms as a new way to organise social and commercial activities. As a result, over the past ten years, the literature on digital platforms has greatly increased. However, as platforms change and a number of problems remain unsolved, academics call for greater research on the subject. Therefore, a review of the existing literature is necessary to better understand what has been accomplished and the potential avenues for future study. A thorough review of the literature on digital platforms, which included 100 publications from IS and management journals, was done by our team. The study's key findings point to some ambiguity in how digital platforms are currently conceptualised. They also emphasise how multifaceted digital platforms are, which reflects the variety of ways they are used in real life.

关键词： Planning Econometrics Sustainable development Information systems

Decoupling anomaly discrimination and representation learning: self-supervised learning for anomaly detection on attributed graph

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hu, YanMing Chen, Chuan Deng, BoWen Lai, YuJing Lin, Hao Zheng, ZiBin Bian, Jing School of Computer Science and Engineering Sun Yat-sen University Guangzhou China School of Software Engineering Sun Yat-sen University Zhuhai China School of System Science and Engineering Sun Yat-sen University Guangzhou China Merchants Union Consumer Finance Co. Ltd China

Anomaly detection on attributed graphs is a crucial topic for its practical application. Existing methods suffer from semantic mixture and imbalance issue because they mainly focus on anomaly discrimination, ignoring representation learning. It conflicts with the assortativity assumption that anomalous nodes commonly connect with normal nodes directly. Additionally, there are far fewer anomalous nodes than normal nodes, indicating a long-tailed data distribution. To address these challenges, a unique algorithm, Decoupled Self-supervised Learning for Anomaly Detection (DSLAD), is proposed in this paper. DSLAD is a self-supervised method with anomaly discrimination and representation learning decoupled for anomaly detection. DSLAD employs bilinear pooling and masked autoencoder as the anomaly discriminators. By decoupling anomaly discrimination and representation learning, a balanced feature space is constructed, in which nodes are more semantically discriminative, as well as imbalance issue can be resolved. Experiments conducted on various six benchmark datasets reveal the effectiveness of DSLAD. Copyright © 2023, The Authors. All rights reserved.

关键词： Anomaly detection

Modelling and Simulation of COVID-19 Outbreak Prediction Using Supervised Machine Learning

学校读者我要写书评

暂无评论

computers, Materials & Continua 2021年第3期66卷 2397-2407页

作者： Rachid Zagrouba Muhammad Adnan Khan Atta-ur-Rahman Muhammad Aamer Saleem Muhammad Faheem Mushtaq Abdur Rehman Muhammad Farhan Khan Department of Computer Information System College of Computer Science and Information TechnologyImam Abdulrahman Bin Faisal UniversityDammam31441Saudi Arabia Department of Computer Science Riphah International UniversityLahore CampusLahore54000Pakistan Hamdard Institute of Engineering and Technology Hamdard UniversityIslamabad44000Pakistan Department of Information Technology Khwaja Fareed University of Engineering and Information TechnologyRahim Yar Khan64200Pakistan School of Computer Science NCBA&ELahore54000Pakistan Department of Forensic Sciences University of Health SciencesLahore54000Pakistan

Novel Coronavirus-19(COVID-19)is a newer type of coronavirus that has not been formally detected in *** is established that this disease often affects people of different age groups,particularly those with body disorders,blood pressure,diabetes,heart problems,or weakened immune *** epidemic of this infection has recently had a huge impact on people around the globe with rising mortality *** levels of mortality are attributed to their transmitting behavior through physical contact between *** is extremely necessary to monitor the transmission of the infection and also to anticipate the early stages of the disease in such a way that the appropriate timing of effective precautionary measures can be *** latest global coronavirus epidemic(COVID-19)has brought new challenges to the scientific *** Intelligence(AI)-motivated methodologies may be useful in predicting the conditions,consequences,and implications of such an *** forecasts may help to monitor and prevent the spread of these *** article proposes a predictive framework incorporating Support Vector Machines(SVM)in the forecasting of a potential outbreak of *** findings indicate that the suggested system outperforms cutting-edge *** method could be used to predict the long-term spread of such an outbreak so that we can implement proactive measures in *** findings of the analyses indicate that the SVM forecasting framework outperformed the Neural Network methods in terms of accuracy and computational *** proposed SVM system model exhibits 98.88%and 96.79%result in terms of accuracy during training and validation respectively.

关键词： Coronavirus outbreak machine learning artificial intelligence

AdvSwap: Covert Adversarial Perturbation with High Frequency Info-swapping for Autonomous Driving Perception

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Huang, Yuanhao Zhang, Qinfan Xing, Jiandong Cheng, Mengyue Yu, Haiyang Ren, Yilong Xiong, Xiao School of Transportation Science and Engineering Beihang University Beijing100191 China State Key Lab of Intelligent Transportation System Beijing100191 China Zhongguancun Laboratory Beijing100094 China Department of Electrical and Computer Engineering University of Alberta Edmonton Canada

Perception module of Autonomous vehicles (AVs) are increasingly susceptible to be attacked, which exploit vulnerabilities in neural networks through adversarial inputs, thereby compromising the AI safety. Some researches focus on creating covert adversarial samples, but existing global noise techniques are detectable and difficult to deceive the human visual system. This paper introduces a novel adversarial attack method, AdvSwap, which creatively utilizes wavelet-based high-frequency information swapping to generate covert adversarial samples and fool the camera. AdvSwap employs invertible neural network for selective high-frequency information swapping, preserving both forward propagation and data integrity. The scheme effectively removes the original label data and incorporates the guidance image data, producing concealed and robust adversarial samples. Experimental evaluations and comparisons on the GTSRB and nuScenes datasets demonstrate that AdvSwap can make concealed attacks on common traffic targets. The generates adversarial samples are also difficult to perceive by humans and algorithms. Meanwhile, the method has strong attacking robustness and attacking transferability. © 2025, CC BY-NC-ND.

关键词：

Enhancing Deep Knowledge Tracing via Diffusion Models for Personalized Adaptive Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Kuo, Ming Sarker, Shouvon Qian, Lijun Fu, Yujian Li, Xiangfang Dong, Xishuang The Department of Electrical and Computer Engineering Prairie View A&M University Texas A&M University System Prairie ViewTX77446 United States Department of Electrical Engineering and Computer Science School of Engineering Technology & Physical Sciences Alabama A&M University MadisonAL United States

In contrast to pedagogies like evidence-based teaching, personalized adaptive learning (PAL) distinguishes itself by closely monitoring the progress of individual students and tailoring the learning path to their unique knowledge and requirements. A crucial technique for effective PAL implementation is knowledge tracing, which models students' evolving knowledge to predict their future performance. Based on these predictions, personalized recommendations for resources and learning paths can be made to meet individual needs. Recent advancements in deep learning have successfully enhanced knowledge tracking through Deep Knowledge Tracing (DKT). This paper introduces generative AI models to further enhance DKT. Generative AI models, rooted in deep learning, are trained to generate synthetic data, addressing data scarcity challenges in various applications across fields such as natural language processing (NLP) and computer vision (CV). This study aims to tackle data shortage issues in student learning records to enhance DKT performance for PAL. Specifically, it employs TabDDPM, a diffusion model, to generate synthetic educational records to augment training data for enhancing DKT. The proposed method's effectiveness is validated through extensive experiments on ASSISTments datasets. The experimental results demonstrate that the AI-generated data by TabDDPM significantly improves DKT performance, particularly in scenarios with small data for training and large data for testing. Copyright © 2024, The Authors. All rights reserved.

关键词： Students

Low-complexity Multi-Channel Speaker Extraction with Pure Speech Cues

学校读者我要写书评

暂无评论

Low-complexity Multi-Channel Speaker Extraction with Pure Sp...

Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)

作者： Bang Zeng Hongbin Suo Yulong Wan Ming Li Data Science Research Center Duke Kunshan University Kunshan China School of Computer Science Wuhan University Wuhan China Data&AI Engineering System OPPO Beijing China

Most multi-channel speaker extraction schemes use the target speaker’s location information as a reference, which must be known in advance or derived from visual cues. In addition, memory and computation costs are enormous when the model deals with the fusion input. In this paper, we propose Speaker-extraction-and-filter Network (SeafNet), which is a low-complexity multi-channel speaker extraction network with only speech cues. Specifically, the SeafNet separates the mixture by utilizing the correlation between an estimation of target speaker on reference channel and the mixed input on rest channels. Experimental results show that compared with the baseline, the SeafNet model achieves 6.4% relative SISNRi improvement on the fixed geometry array and 8.9% average relative SISNRi improvement on the ad-hoc array. Meanwhile, the SeafNet achieves 60% relative reduction in the number of parameters and 42% relative reduction in the computational cost.

关键词：

Highly integrated reconfigurable radiofrequency filter based on microcomb and a silicon photonic processor

学校读者我要写书评

暂无评论

Highly integrated reconfigurable radiofrequency filter based...

CLEO: science and Innovations, S and I 2022

作者： Tao, Yuansheng Chang, Lin Shen, Bitao Shu, Haowen Xie, Weiqiang Jin, Ming Tao, Zihan Bai, Bowen Yu, Shaohua Wang, Xingjun Bowers, John E. State Key Laboratory of Advanced Optical Communications System and Networks Department of Electronics School of Electronics Engineering and Computer Science Peking University Beijing100871 China Department of Electrical and Computer Engineering University of California Santa BarbaraCA93106 United States Peng Cheng Laboratory Shenzhen518055 China Frontiers Science Center for Nano-optoelectronics Peking University Beijing100871 China

We demonstrate a novel chip-scale reconfigurable radiofrequency filter by using AlGaAs-on-insulator microcomb and silicon photonics in combination, simultaneously bypassing the employment of bulky pulse shaper and lon... 详细信息

ISBN: (纸本)9781557528209

关键词： Silicon photonics