1,720,968 research outputs found
Novel Architectures and Networking Solutions for Intelligent Mobile Edge Computing Networks
Full text linkUniversity of Technology Sydney. Faculty of Engineering and Information Technology.Mobile edge computing (MEC) has emerged as a highly-effective solution to address the proliferation of smart devices and growing demands for computationally-intensive applications. The key idea of MEC networks is to distribute computing resources closer to mobile users (MUs) by deploying servers at the ``edge'' of the networks, i.e., mobile edge nodes (MENs). Nonetheless, the development of MEC networks has been facing various challenges including the decentralized nature, small coverage, unreliable computing/communication resources, and limited storage capacity of the MENs. This thesis aims to address the above challenges through developing novel collaborative architectures and intelligent networking strategies for MEC networks.
Firstly, we introduce a novel MEC network architecture that leverages an optimal joint caching-delivering with horizontal cooperation among MENs. Particularly, we first formulate the content-access delay minimization problem by jointly optimizing content caching and delivering decisions under various network constraints, aiming at minimizing the total average delay for the MEC network. Then, we design centralized and distributed solutions to find the decisions of joint caching and delivering policy for the transformed problem.
As the second contribution, we propose a novel economic-efficiency framework for the MEC network to maximize the profits for MENs. Specifically, we first introduce a demand prediction method for MENs leveraging federated learning (FL) approaches. Based on the predicted demands, each MEN can reserve demands from the MEC service provider (MSP) in advance to optimize its profit. Nonetheless, due to the competition among the MENs as well as unknown information from the MSP, we develop a multi-principal one-agent (MPOA) contract-based utility optimization under the MSP's constraints as well as other MENs' contracts. We then develop an iterative algorithm to find the optimal contracts for the MENs.
Finally, we propose a novel dynamic FL-based framework leveraging dynamic selection of MENs for the FL process in the MEC network. Particularly, the MSP first implements an MU selection method to determine a set of the best MUs for the FL process according to the location and information significance at each learning round. Then, each selected MU can collect information and offer a payment contract to the MSP based on its collected QoI. For that, we develop an MPOA contract-based policy to maximize the profits of the MSP and learning MUs under the MSP's limited payment budget and asymmetric information between the MSP and MUs
Quality of Service Analysis on Tomato Plant Disease Detection Design Based on CNN and Telegram Application
Full text linkPeningkatan tanaman tomat terjadi secara konsisten dari tahun ke tahun dan berkontribusi signifikan terhadap perekonomian nasional. Peningkatan kepadatan tanaman dan perluasan area panen dapat menciptakan kondisi yang ideal untuk penyebaran penyakit pada tanaman tomat, yang berpotensi mengancam hasil panen. Penelitian ini merancang model machine learning menggunakan algoritme Convolutional Neural Networks (CNN) untuk mendeteksi penyakit tanaman tomat dengan tingkat akurasi yang diperoleh mencapai 96%. Tingkat loss dari model tergolong rendah yaitu sekitar 13%, membuktikan bahwa prediksi model cukup dekat dengan kondisi sebenarnya. Hasil ini menunjukkan bahwa kinerja model efektif untuk mencegah penyebaran penyakit tanaman tomat dengan membantu mengidentifikasi penyakit lebih awal. Model machine learning diimplementasikan melalui Bot Telegram sebagai antarmuka pengguna, yang tidak hanya efektif dalam memberikan informasi deteksi penyakit tanaman tomat, tetapi juga memastikan informasi tersampaikan dengan efisien dan tepat. Analisis Quality of Service (QoS) dilakukan terhadap komunikasi antara pengguna dan server Telegram dengan mempertimbangkan parameter throughput, delay, dan packet delivery. Nilai QoS secara keseluruhan adalah berindeks 3 kategori “Memuaskan” sesuai standarisasi versi TIPHON. Nilai QoS tersebut didapatkan dari nilai parameter throughput dengan indeks 4 kategori “Sangat Bagus”, nilai parameter packet delivery dengan indeks 4 kategori “Sangat Bagus”, serta nilai parameter delay dengan indeks 4 kategori “Sangat Bagus”.The increase in tomato cultivation has been consistent over the years and significantly contributes to the national economy. The increase in plant density and the expansion of harvesting areas can create ideal conditions for the spread of diseases in tomato plants, potentially threatening crop yields. This study presents a machine learning model using Convolutional Neural Networks (CNN) algorithms to detect tomato plant diseases, achieving an accuracy rate of 96%. The model demonstrates a relatively low loss rate of approximately 13%, indicating that the predictions closely align with actual conditions. These results indicate that the model\u27s performance is effective in preventing the spread of tomato plant diseases by helping to identify diseases earlier. The machine learning model is implemented through a Telegram Bot as a user interface, which is not only effective in providing information on tomato plant disease detection, but also ensures that the information is delivered efficiently and accurately. A Quality of Service (QoS) analysis was conducted on the communication between users and the Telegram server, considering parameters such as throughput, delay, and packet delivery. The overall QoS score is indexed at 3 in the "Satisfactory" category according to TIPHON standards. This QoS score is derived from the throughput parameter with an index of 4 in the "Very Good" category, the packet delivery parameter with an index of 4 in the "Very Good" category, and the delay parameter with an index of 4 in the "Very Good" category
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Privacy aware-based federated learning framework for data sharing protection of internet of things devices
Get PDFFederated learning (FL) has emerged as one of the most effective solutions to deal with the rapid utilization of internet of things (IoT) in big data markets. Through FL, local data at each IoT device can be trained locally without sharing the local data to the cloud server. However, this conventional FL may still suffer from privacy leakage when the local data are trained, and the trained model is shared to the cloud server to update the global prediction model. This paper proposes a FL framework with privacy awareness to protect data including the trained model for IoT devices. First, a data/model encryption method using fully homomorphic encryption is introduced, aiming at protecting the data/model privacy. Then, the FL framework for the IoT with the encryption method leveraging logistic regression approach is discussed. Experimental results using random datasets show that the proposed framework can obtain higher global model accuracy (up to 4.84%) and lower global model loss (up to 66.4%) compared with other baseline methods
Image classification-based transfer learning framework for image detection of IoT devices
Get PDFFor artificial intelligence (AI) applications, centralized learning on a cloud server and local learning on an internet-of-things device may suffer from data privacy leakage due to data sharing and inaccurate prediction due to limited computing resources. Transfer learning has been proposed as one potential solution to the world's big data problems. Transfer learning eliminates the need for each internet-of-things device to share local data with the cloud server during the training process. Instead, it can go through the training process on its own, using a cloud server's pre-trained model with high accuracy. As a result, despite its limited computing resources, the internet of things device can still predict with high accuracy. This paper proposes a transfer learning model for improving image detection accuracy on IoT devices with restricted computation. To obtain accurate image classification, a deep learning approach based on convolutional neural networks is used. The proposed method with freeze and unfreeze approaches achieves a higher validation accuracy (up to 43.6%) and a lower validation loss (up to 6.5 times) than the non-transfer learning method, according to simulation results using three relevant internet-of-things datasets
Dispelling the Myths Behind First-author Citation Counts
Full text linkWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
- …
