• Electronics and Telecommunications Trends
• /
• v.37 no.5
• /
• pp.44-53
• /
• 2022

The Internet of Things (IoT) is growing exponentially, with the number of IoT devices multiplying annually. Accordingly, the paradigm is changing from cloud computing to edge computing and even tiny edge computing because of the low latency and cost reduction. Machine learning is also shifting its role from the cloud to edge or tiny edge according to the paradigm shift. However, the fragmented and resource-constrained features of IoT devices have limited the development of artificial intelligence applications. Edge MLaaS (Machine Learning as-a-Service) has been studied to easily and quickly adopt machine learning to products and overcome the device limitations. This paper briefly summarizes what Edge MLaaS is and what element of research it requires.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.12
• /
• pp.4345-4363
• /
• 2021

Deep Learning as a Service (DLaaS), utilizing the cloud-based deep neural network models to provide customer prediction services, has been widely deployed on mobile cloud computing (MCC). Such services raise privacy concerns since customers need to send private data to untrusted service providers. In this paper, we devote ourselves to building an efficient protocol to classify users' images using the convolutional neural network (CNN) model trained and held by the server, while keeping both parties' data secure. Most previous solutions commonly employ homomorphic encryption schemes based on Ring Learning with Errors (RLWE) hardness or two-party secure computation protocols to achieve it. However, they have limitations on large communication overheads and costs in MCC. To address this issue, we present LeHE4SCNN, a scalable privacy-preserving and communication-efficient framework for CNN-based DLaaS. Firstly, we design a novel low-expansion rate homomorphic encryption scheme with packing and unpacking methods (LeHE). It supports fast homomorphic operations such as vector-matrix multiplication and addition. Then we propose a secure prediction framework for CNN. It employs the LeHE scheme to compute linear layers while exploiting the data shuffling technique to perform non-linear operations. Finally, we implement and evaluate LeHE4SCNN with various CNN models on a real-world dataset. Experimental results demonstrate the effectiveness and superiority of the LeHE4SCNN framework in terms of response time, usage cost, and communication overhead compared to the state-of-the-art methods in the mobile cloud computing environment.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.1
• /
• pp.77-92
• /
• 2020

When automatic speech recognition (ASR) is provided as a cloud service, it is easy to collect voice and application domain data from users. Harnessing these data will facilitate the provision of more personalized services. In this paper, we demonstrate our transfer learning-based knowledge service that built with the user-generated data collected through our novel system that deliveries personalized ASR service. First, we discuss the motivation, challenges, and prospects of building up such a knowledge-based service-oriented system. Second, we present a Quadruple Transfer Learning (QTL) method that can learn a classification model from a source domain and transfer it to a target domain. Third, we provide an overview architecture of our novel system that collects voice data from mobile users, labels the data via crowdsourcing, utilises these collected user-generated data to train different machine learning models, and delivers the personalised real-time cloud services. Finally, we use the E-Book data collected from our system to train classification models and apply them in the smart TV domain, and the experimental results show that our QTL method is effective in two classification tasks, which confirms that the knowledge transfer provides a value-added service for the upper-layer mobile applications in different domains.

• Journal of Digital Convergence
• /
• v.19 no.3
• /
• pp.211-216
• /
• 2021

Information from various heterogeneous devices is steadily increasing in distributed cloud environments. This is because high-speed network speeds and high-capacity multimedia data are being used. However, research is still underway on how to minimize information errors in big data sent and received by heterogeneous devices. In this paper, we propose a deep learning-based asymmetric storage management technique for minimizing bandwidth and data errors in networks generated by information sent and received in cloud environments. The proposed technique applies deep learning techniques to optimize the load balance after asymmetric hash of the big data information generated by each device. The proposed technique is characterized by allowing errors in big data collected from each device, while also ensuring the connectivity of big data by grouping big data into groups of clusters of dogs. In particular, the proposed technique minimizes information errors when storing and managing big data asymmetrically because it used a loss function that extracted similar values between big data as seeds.

• Journal of Advanced Technology Convergence
• /
• v.1 no.2
• /
• pp.01-09
• /
• 2022

Recently, safety issues in companies and public institutions are no longer a task that can be postponed, and when a major safety accident occurs, not only direct financial loss, but also indirect loss of social trust in the company and public institution is greatly increased. In particular, in the case of a fatal accident, the damage is even more serious. Accordingly, as companies and public institutions expand their investments in industrial safety education and prevention, open AI learning model creation technology that enables safety management services without being affected by user behavior in industrial sites where high-risk situations exist, edge terminals System development using inter-AI collaboration technology, cloud-edge terminal linkage technology, multi-modal risk situation determination technology, and AI model learning support technology is underway. In particular, with the development and spread of artificial intelligence technology, research to apply the technology to safety issues is becoming active. Therefore, in this paper, an open cloud platform design method that can support AI model learning for high-risk site safety management is presented.

• International journal of advanced smart convergence
• /
• v.12 no.4
• /
• pp.126-133
• /
• 2023

Recent advancements in cloud service virtualization technologies have witnessed a shift from a Virtual Machine-centric approach to a container-centric paradigm, offering advantages such as faster deployment and enhanced portability. Container orchestration has emerged as a key technology for efficient management and scheduling of these containers. However, with the increasing complexity and diversity of heterogeneous workloads and service types, resource scheduling has become a challenging task. Various research endeavors are underway to address the challenges posed by diverse workloads and services. Yet, a systematic approach to container orchestration for effective cloud management has not been clearly defined. This paper proposes the DRA-Engine (Dynamic Resource Allocation Engine) for resource scheduling in container orchestration. The proposed engine comprises the Request Load Procedure, Required Resource Measurement Procedure, and Resource Provision Decision Procedure. Through these components, the DRA-Engine dynamically allocates resources according to the application's requirements, presenting a solution to the challenges of resource scheduling in container orchestration.

• Journal of Information Processing Systems
• /
• v.20 no.3
• /
• pp.360-374
• /
• 2024

A personalized course recommendation algorithm based on deep learning in an online education cloud platform is proposed to address the challenges associated with effective information extraction and insufficient feature extraction. First, the user potential preferences are obtained through the course summary, course review information, user course history, and other data. Second, by embedding, the word vector is turned into a low-dimensional and dense real-valued vector, which is then fed into the compressed interaction network-deep neural network model. Finally, considering that learners and different interactive courses play different roles in the final recommendation and prediction results, an attention mechanism is introduced. The accuracy, recall rate, and F1 value of the proposed method are 0.851, 0.856, and 0.853, respectively, when the length of the recommendation list K is 35. Consequently, the proposed strategy outperforms the comparison model in terms of recommending customized course resources.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.4
• /
• pp.1258-1275
• /
• 2023

Cloud computing is a new technology that has adapted to the traditional way of service providing. Service providers are responsible for managing the allocation of resources. Selecting suitable containers and bandwidth for job scheduling has been a challenging task for the service providers. There are several existing systems that have introduced many algorithms for resource allocation. To overcome these challenges, the proposed system introduces an Optimized Task Scheduling Algorithm with Deep Learning (OTS-DL). When a job is assigned to a Cloud Service Provider (CSP), the containers are allocated automatically. The article segregates the containers as' Long-Term Container (LTC)' and 'Short-Term Container (STC)' for resource allocation. The system leverages an 'Optimized Task Scheduling Algorithm' to maximize the resource utilisation that initially inquires for micro-task and macro-task dependencies. The bottleneck task is chosen and acted upon accordingly. Further, the system initializes a 'Deep Learning' (DL) for implementing all the progressive steps of job scheduling in the cloud. Further, to overcome container attacks and errors, the system formulates a Container Convergence (Fault Tolerance) theory with high-level security. The results demonstrate that the used optimization algorithm is more effective for implementing a complete resource allocation and solving the large-scale optimization problem of resource allocation and security issues.

• Journal of the Korea Society for Simulation
• /
• v.23 no.4
• /
• pp.111-119
• /
• 2014

The cloud environment need resource management method that to enable the big data issue and data analysis technology. Existing resource management uses the limited calculation method, therefore concentrated the resource bias problem. To solve this problem, the resource management requires the learning-based scheduling using resource history information. In this paper, we proposes the ART (Adaptive Resonance Theory)-based adaptive resource management. Our proposed method assigns the job to the suitable method with the resource monitoring and history management in cloud computing environment. The proposed method utilizes the unsupervised learning method. Our goal is to improve the data processing and service stability with the adaptive resource management. The propose method allow the systematic management, and utilize the available resource efficiently.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.10
• /
• pp.4204-4222
• /
• 2015

Cloud is the latest buzz word in the internet community among developers, consumers and security researchers. There have been many attacks on the cloud in the recent past where the services got interrupted and consumer privacy has been compromised. Denial of Service (DoS) attacks effect the service availability to the genuine user. Customers are paying to use the cloud, so enhancing the availability of services is a paramount task for the service provider. In the presence of DoS attacks, the availability is reduced drastically. Such attacks must be detected and prevented as early as possible and the power of computational approaches can be used to do so. In the literature, machine learning techniques have been used to detect the presence of attacks. In this paper, a novel approach is proposed, where intelligent rule based feature selection and classification are performed for DoS attack detection in the cloud. The performance of the proposed system has been evaluated on an experimental cloud set up with real time DoS tools. It was observed that the proposed system achieved an accuracy of 98.46% on the experimental data for 10,000 instances with 10 fold cross-validation. By using this methodology, the service providers will be able to provide a more secure cloud environment to the customers.