检索结果-内蒙古大学图书馆

An optimal relay scheme for outage minimization in fog-based internet-of-things (IoT) networks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Omoniwa, Babatunji Hussain, Riaz Adil, Muhammad Shakeel, Atif Tahir, Ahmed Kamal Ul Hasan, Qadeer Malik, Shahzad A. The Computer Science Programme National Mathematical Centre Abuja118 Nigeria The Department of Electrical Engineering COMSATS University Islamabad Pakistan

Fog devices are beginning to play a key role in relaying data and services within the Internet-of-Things (IoT) ecosystem. These relays may be static or mobile, with the latter offering a new degree of freedom for performance improvement via careful relay mobility design. Besides that, power conservation has been a prevalent issue in IoT networks with devices being power-constrained, requiring optimal power-control mechanisms. In this paper, we consider a multi-tier fog-based IoT architecture where a mobile/static fog node acts as an amplify and forward relay that transmits received information from a sensor node to a higher hierarchically-placed static fog device, which offers some localized services. The outage probability of the presented scenario was efficiently minimized by jointly optimizing the mobility pattern and the transmit power of the fog relay. A closed-form analytical expression for the outage probability was derived. Furthermore, due to the intractability and non-convexity of the formulated problem, we applied an iterative algorithm based on the steepest descent method to arrive at a desirable objective. Simulations reveal that the outage probability was improved by 62.7% in the optimized-location fixed-power (OLFP) scheme, 79.3% in the optimized-power fixed-location (OPFL) scheme, and 94.2% in the optimized-location optimized-power (OLOP) scheme, as against the fixed-location and fixed-power (FLFP) scheme (i.e., without optimization). Lastly, we present an optimal relay selection strategy that chooses an appropriate relay node from randomly distributed relaying candidates. Copyright © 2021, The Authors. All rights reserved.

关键词： Internet of things

Self-Supervised 3D Action Representation Learning with Skeleton Cloud Colorization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yang, Siyuan Liu, Jun Lu, Shijian Hwa, Er Meng Hu, Yongjian Kot, Alex C. The Rapid-Rich Object Search Lab Interdisciplinary Graduate Programme Nanyang Technological University Singapore The Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore The School of Computer Science & Engineering Nanyang Technological University Singapore The School of Electrical and Electronic Engineering Nanyang Technological University Singapore The South China University of Technology Guangzhou China

3D Skeleton-based human action recognition has attracted increasing attention in recent years. Most of the existing work focuses on supervised learning which requires a large number of labeled action sequences that are often expensive and time-consuming to annotate. In this paper, we address self-supervised 3D action representation learning for skeleton-based action recognition. We investigate self-supervised representation learning and design a novel skeleton cloud colorization technique that is capable of learning spatial and temporal skeleton representations from unlabeled skeleton sequence data. We represent a skeleton action sequence as a 3D skeleton cloud and colorize each point in the cloud according to its temporal and spatial orders in the original (unannotated) skeleton sequence. Leveraging the colorized skeleton point cloud, we design an auto-encoder framework that can learn spatial-temporal features from the artificial color labels of skeleton joints effectively. Specifically, we design a two-steam pretraining network that leverages fine-grained and coarse-grained colorization to learn multi-scale spatial-temporal features. In addition, we design a Masked Skeleton Cloud Repainting task that can pretrain the designed auto-encoder framework to learn informative representations. We evaluate our skeleton cloud colorization approach with linear classifiers trained under different configurations, including unsupervised, semi-supervised, fully-supervised, and transfer learning settings. Extensive experiments on NTU RGB+D, NTU RGB+D 120, PKU-MMD, NW-UCLA, and UWA3D datasets show that the proposed method outperforms existing unsupervised and semi-supervised 3D action recognition methods by large margins and achieves competitive performance in supervised 3D action recognition as well. Copyright © 2023, The Authors. All rights reserved.

关键词： Musculoskeletal system

Trusted-maximizers entropy search for efficient Bayesian optimization

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Nguyen, Quoc Phong Wu, Zhaoxuan Low, Bryan Kian Hsiang Jaillet, Patrick Department of Computer Science National University of Singapore Singapore Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology United States Institute of Data Science National University of Singapore Singapore NUSGS Integrative Sciences and Engineering Programme National University of Singapore Singapore

Information-based Bayesian optimization (BO) algorithms have achieved state-of-the-art performance in optimizing a black-box objective function. However, they usually require several approximations or simplifying assumptions (without clearly understanding their effects on the BO performance) and/or their generalization to batch BO is computationally unwieldy, especially with an increasing batch size. To alleviate these issues, this paper presents a novel trusted-maximizers entropy search (TES) acquisition function: It measures how much an input query contributes to the information gain on the maximizer over a finite set of trusted maximizers, i.e., inputs optimizing functions that are sampled from the Gaussian process posterior belief of the objective function. Evaluating TES requires either only a stochastic approximation with sampling or a deterministic approximation with expectation propagation, both of which are investigated and empirically evaluated using synthetic benchmark objective functions and real-world optimization problems, e.g., hyperparameter tuning of a convolutional neural network and synthesizing 'physically realizable' faces to fool a black-box face recognition system. Though TES can naturally be generalized to a batch variant with either approximation, the latter is amenable to be scaled to a much larger batch size in our experiments. Copyright © 2021, The Authors. All rights reserved.

关键词： Entropy

NeuroHeed: Neuro-Steered Speaker Extraction using EEG Signals

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Pan, Zexu Borsdorf, Marvin Cai, Siqi Schultz, Tanja Li, Haizhou The Integrative Sciences and Engineering Programme the Institute of Data Science National University of Singapore 119077 Singapore The Machine Listening Lab the University of Bremen Bremen28359 Germany The Department of Electrical and Computer Engineering National University of Singapore 119077 Singapore The Cognitive System Lab the University of Bremen Bremen28359 Germany The School of Data Science The Chinese University of Hong Kong Shenzhen518172 China The Machine Listening Lab University of Bremen Bremen28359 Germany

Humans possess the remarkable ability to selectively attend to a single speaker amidst competing voices and background noise, known as selective auditory attention. Recent studies in auditory neuroscience indicate a strong correlation between the attended speech signal and the corresponding brain’s elicited neuronal activities, which the latter can be measured using affordable and non-intrusive electroencephalography (EEG) devices. In this study, we present NeuroHeed, a speaker extraction model that leverages EEG signals to establish a neuronal attractor which is temporally associated with the speech stimulus, facilitating the extraction of the attended speech signal in a cocktail party scenario. We propose both an offline and an online NeuroHeed, with the latter designed for real-time inference. In the online NeuroHeed, we additionally propose an autoregressive speaker encoder, which accumulates past extracted speech signals for self-enrollment of the attended speaker information into an auditory attractor, that retains the attentional momentum over time. Online NeuroHeed extracts the current window of the speech signals with guidance from both attractors. Experimental results demonstrate that NeuroHeed effectively extracts brain-attended speech signals, achieving high signal quality, excellent perceptual quality, and intelligibility in a two-speaker scenario. Copyright © 2023, The Authors. All rights reserved.

关键词： Extraction

Cloud-based fault prediction using IoT in office automation for improvisation of the health of employees

学校读者我要写书评

暂无评论

Cloud-based fault prediction using IoT in office automation ...

Advance Computing and Innovative Technologies in engineering (ICACITE), International Conference on

作者： Nakul Shahdadpuri Somanchi Hari Krishna SathiJyothirmaye Reddy C. Ganesh Kirti Agarwal Sourabh Bhattacharya IPG Programme {(B.Tech + M.Tech (It)} IIITM Gwalior Department of Business Management Vignana Bharathi Institute of Technology Malkajigiri Telangana Department of Management Marwadi University Rajkot Gujarat Computer and Communication Engineering Sri Eshwar College of Engineering Anna University Chennai ITERC College Delhi (NCR) India Department of Management and Social Science Haldia Institute of Technology West Bengal

Modern technology is the best thing to be used in every commercial sector. The devices are well equipped to understand the problems of the users. The offices are now been maintained by technology the devices for daily monitoring even the electrical appliances are been monitored and maintained by technology. In previous times the best method of this work is to make it via cloud computing, but now as technology has evolved and evolved new adding devices are making system malfunction. The fault of cloud computing needs to be identified, So the best method is to automate the office with the introduction of IoT. it is a platform equipped with all the facilities for monitoring and maintaining the devices inside the office, even the working capacity of employees is also measured via this method. The study is showing the effectiveness of the IoT to identify the faults of cloud computing related to maintaining the working method of the office. The data collected for this study is secondary data like articles, books, journals and many more. Then gathered data is analyzed by qualitative data analysis. The results are quite positive about the use of it to automate the office and its working procedure.

关键词：

Clinical Domain Knowledge-Derived Template Improves Post Hoc AI Explanations in Pneumothorax Classification

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yuan, Han Hong, Chuan Jiang, Pengtao Zhao, Gangming Tran, Nguyen Tuan Anh Xu, Xinxing Yan, Yet Yen Liu, Nan Centre for Quantitative Medicine Duke-NUS Medical School Singapore Department of Biostatistics and Bioinformatics Duke University United States College of Computer Science Nankai University China Faculty of Engineering The University of Hong Kong Hong Kong Department of Diagnostic Radiology Singapore General Hospital Singapore Institute of High Performance Computing Agency for Science Technology and Research Singapore Department of Radiology Changi General Hospital Singapore Programme in Health Services and Systems Research Duke-NUS Medical School Singapore Institute of Data Science National University of Singapore Singapore

Background: Pneumothorax is an acute thoracic disease caused by abnormal air collection between the lungs and chest wall. Recently, artificial intelligence (AI), especially deep learning (DL), has been increasingly employed for automating the diagnostic process of pneumothorax. To address the opaqueness often associated with DL models, explainable artificial intelligence (XAI) methods have been introduced to outline regions related to pneumothorax diagnoses made by DL models. However, these explanations sometimes diverge from actual lesion areas, highlighting the need for further improvement. Method: We propose a template-guided approach to incorporate the clinical knowledge of pneumothorax into model explanations generated by XAI methods, thereby enhancing the quality of these explanations. Utilizing one lesion delineation created by radiologists, our approach first generates a template that represents potential areas of pneumothorax occurrence. This template is then superimposed on model explanations to filter out extraneous explanations that fall outside the template’s boundaries. To validate its efficacy, we carried out a comparative analysis of three XAI methods (Saliency Map, Grad-CAM, and Integrated Gradients) with and without our template guidance when explaining two DL models (VGG-19 and ResNet-50) in two real-world datasets (SIIM-ACR and ChestX-Det). Results: The proposed approach consistently improved baseline XAI methods across twelve benchmark scenarios built on three XAI methods, two DL models, and two datasets. The average incremental percentages, calculated by the performance improvements over the baseline performance, were 97.8% in Intersection over Union (IoU) and 94.1% in Dice Similarity Coefficient (DSC) when comparing model explanations and ground-truth lesion areas. We further visualized baseline and template-guided model explanations on radiographs to showcase the performance of our approach. Conclusions: In the context of pneumothorax diagnos

关键词： Diagnosis

Newton-2EGSOR Method for Unconstrained Optimization Problems with a Block Diagonal Hessian

学校读者我要写书评

暂无评论

SN computer science 2020年第1期1卷 1-11页

作者： Ghazali, Khadizah Sulaiman, Jumat Dasril, Yosza Gabda, Darmesah Faculty of Science and Natural Resources Mathematics with Economics Programme Universiti Malaysia Sabah Kota Kinabalu Sabah 88400 Malaysia Faculty of Electronic and Computer Engineering Universiti Teknikal Malaysia Melaka Melaka 76100 Malaysia

We find that finding the unconstrained optimizer for large-scale problems with the Newton method can be very expensive. Therefore, in this paper, we developed a new efficient method for solving large-scale unconstrained optimization problems with block diagonal Hessian matrices to reduce the cost of computing Newton’s direction. This method is a combination of the Newton method and the 2-point explicit group successive-over relaxation (2EGSOR) block iterative method. To calculate the performance of the developed method, we used a combination of the Newton method with Gauss–Seidel (Newton-GS) point iteration and the Newton method with successive-over relaxation (Newton-SOR) point iteration as reference methods. The numerical experiment has proven that the developed algorithms generate results that are more efficient compared to the reference methods with less execution time and fewer iterations. Through 90 test cases, we observe that the speedup ratio for our proposed method is up to 659.87 times faster compared to the Newton-SOR method and up to 1963.57 times more rapidly than the Newton-GS method. © 2019, Springer Nature Singapore Pte Ltd.

关键词： Explicit group iterative method Large-scale unconstrained optimization problems Newton method

PnP-DETR: Towards Efficient Visual Analysis with Transformers

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Tao Yuan, Li Chen, Yunpeng Feng, Jiashi Yan, Shuicheng Institute of Data Science National University of Singapore Singapore Yitu Technology Integrative Science and Engineering Programme NUS Graduate School National University of Singapore Singapore Department of Electrical and Computer Engineering National University of Singapore Singapore

Recently, DETR [3] pioneered the solution of vision tasks with transformers, it directly translates the image feature map into the object detection result. Though effective, translating the full feature map can be costly due to redundant computation on some area like the background. In this work, we encapsulate the idea of reducing spatial redundancy into a novel poll and pool (PnP) sampling module, with which we build an end-to-end PnP-DETR architecture that adaptively allocates its computation spatially to be more efficient. Concretely, the PnP module abstracts the image feature map into fine foreground object feature vectors and a small number of coarse background contextual feature vectors. The transformer models information interaction within the fine-coarse feature space and translates the features into the detection result. Moreover, the PnP-augmented model can instantly achieve various desired trade-offs between performance and computation with a single model by varying the sampled feature length, without requiring to train multiple models as existing methods. Thus it offers greater flexibility for deployment in diverse scenarios with varying computation constraint. We further validate the generalizability of the PnP module on panoptic segmentation and the recent transformer-based image recognition model ViT [7] and show consistent efficiency gain. We believe our method makes a step for efficient visual analysis with transformers, wherein spatial redundancy is commonly observed. Code will be available at https://***/twangnh/pnp-detr. Copyright © 2021, The Authors. All rights reserved.

关键词： Feature extraction

Drying and Extraction of Moringa Oleifera and Its Application in Wastewater Treatment 15

学校读者我要写书评

暂无评论

Drying and Extraction of Moringa Oleifera and Its Applicatio...

15th International engineering and Computing Research Conference, EURECA 2021

作者： Ibrahim, M. Ismail, N. Chua, B.L. Adnan, A.S.M. School of Computer Science and Engineering Faculty of Innovation and Technology Taylor's University Lakeside Campus Jalan Taylor's Selangor Darul Ehsan Subang Jaya47500 Malaysia Postharvest Handling Programme Paddy and Rice Research Centre MARDI Headquarters Persiaran MARDI-UPM Selangor Darul Ehsan Serdang43400 Malaysia

Conventional coagulants such as aluminum sulfate and ferric sulphate have proved to be harmful to human health as it may cause neurological diseases like Alzheimer and percentile dementia. These health concerns have led to the use of natural coagulants which are environmental friendly and not harmful to human health. In this study, Moringa Oleifera seeds are selected to study the preparation of the natural coagulant and further use it in dye wastewater treatment. The two important steps used in preparing the natural coagulants are drying of the raw materials and extraction of the protein content. Moringa Oleifera seeds were oven dried at 40°C, 50°C and 60°C and the drying data was recorded. The recorded data was then fitted into five thin layer kinetic models to obtain the most suitable drying temperature and its corresponding drying time. Using Microsoft Excel Solver 2011, values of (R2), (RMSE) and chi-square (X2 ) were calculated. Based on the highest value of (R2 ) and lowest value of (RMSE), Page kinetic model was selected. Moreover, for the selected Page kinetic model, values of (R2) and (X2) were also compared for all three temperatures and the temperature with the highest (R2) value and lowest chi-square value (X2) was selected as the most optimum drying temperature. The most optimum drying temperature for drying Moringa Oleifera seeds was obtained as 50°C as the seeds dried at this temperature holds the maximum protein content concentration which enhances its coagulation properties. Furthermore, the corresponding drying time of about 6.5 hours for seeds dried at 50°C was also taken as the most optimum drying time. In the next step, Moringa Oleifera seeds which have been dried at 50°C for 6.5 hours were used for protein extraction. Solid to solvent ratios of 0.5:100, 1:100, 2:100 and 5: 100 (g of dried Moringa oleifera seeds: ml of distilled water) were used to extract the protein by using a domestic blender for 2 minutes. Using the Bradford method, the abso

关键词： Sulfur compounds