Search

Due to the rapid development of diversified technology, people may use multiple electronic devices, such as personal computers, tablets, and smartphones, to connect to the Internet in their daily lives. Switching between devices enables a user to use e-commerce on various platforms. The complexity of consumer behavior is directly proportional to the number of involved devices. Additionally, since the personal privacy regulations nowadays are getting more strict, the user data on the Internet starts to be anonymous. Thus, determining how the devices are related is an indispensable step in achieving precision marketing or developing customized applications. In this research, the dataset provided by the CIKM Cup 2016 Challenge is used. The representation of a device is created by extracting features from browsing logs. The computation cost is reduced by filtering candidates of a target device instead of comparing them in pairs. Latent semantic indexing representations and techniques of supervised learning are used to accomplish filtering. Performing word embedding can turn literature semantic into vectors through an unsupervised neural ensemble. The addition of feature engineering on the input vectors of supervised classification can enhance the classifier’s discrimination. The classification is used to determine the probability of any two instances belonging to the same user. The significant benefit of the implementation is to form the sequences mentioned above by a cross-device linking mechanism to provide a baseline for aligning with the computation limitation and boosting the performance.

For the Internet of things, having sensors in devices used for video surveillance services, such as cameras, is crucial. The advancement of edge computing technology has enabled high computing capacity and the handling of massive data sets. The concept of cloudlets is employed in edge computing for in-network processing, especially for large-size multimedia data processing. Cloudlets are essential for services with high computing costs. Contrary to traditional cloud computing, data can be offloaded to in-network devices and core clouds, thereby improving the quality of service and enhancing resource utilization. However, the trade-off between network transmissions and nodal processes with delay-aware multimedia traffic has been demonstrated to be an NP-complete problem. The problem is presented as a mathematical formula to maximize the minimal delay gap between the tolerable event delay, sending time, and processing time. The problem is subject to in-network processing node assignment, routing paths, transmission capacities, computing capacities, and the effective service period. The Lagrangian approach was employed to evaluate the method proposed in this study; a near-optimal solution was obtained, and several experiments were performed to demonstrate that the proposed method outperforms existing methods.

This paper proposes an encoder-decoder architecture for kidney segmentation. A hyperparameter optimization process is implemented, including the development of a model architecture, selecting a windowing method and a loss function, and data augmentation. The model consists of EfficientNet-B5 as the encoder and a feature pyramid network as the decoder that yields the best performance with a Dice score of 0.969 on the 2019 Kidney and Kidney Tumor Segmentation Challenge dataset. The proposed model is tested with different voxel spacing, anatomical planes, and kidney and tumor volumes. Moreover, case studies are conducted to analyze segmentation outliers. Finally, five-fold cross-validation and the 3D-IRCAD-01 dataset are used to evaluate the developed model in terms of the following evaluation metrics: the Dice score, recall, precision, and the Intersection over Union score. A new development and application of artificial intelligence algorithms to solve image analysis and interpretation will be demonstrated in this paper. Overall, our experiment results show that the proposed kidney segmentation solutions in CT images can be significantly applied to clinical needs to assist surgeons in surgical planning. It enables the calculation of the total kidney volume for kidney function estimation in ADPKD and supports radiologists or doctors in disease diagnoses and disease progression.

Deep learning technology is widely used in medicine. The automation of medical image classification and segmentation is essential and inevitable. This study proposes a transfer learning–based kidney segmentation model with an encoder–decoder architecture. Transfer learning was introduced through the utilization of the parameters from other organ segmentation models as the initial input parameters. The results indicated that the transfer learning–based method outperforms the single-organ segmentation model. Experiments with different encoders, such as ResNet-50 and VGG-16, were implemented under the same Unet structure. The proposed method using transfer learning under the ResNet-50 encoder achieved the best Dice score of 0.9689. The proposed model’s use of two public data sets from online competitions means that it requires fewer computing resources. The difference in Dice scores between our model and 3D Unet (Isensee) was less than 1%. The average difference between the estimated kidney volume and the ground truth was only 1.4%, reflecting a seven times higher accuracy than that of conventional kidney volume estimation in clinical medicine.

This paper presents a usage-based insurance (UBI) platform that incorporates Internet of Vehicles (IoV) and blockchain technologies, discussing the potential stakeholders, business models, and interaction modes involved in this platform. Existing UBI products mostly use data on the driver’s mileage, driving period, or driving region for more accurate insurance calculations. Automobile UBI encourages customers to continue improving their ability to drive safety and provides a means to smoothly, transparently, and rationally calculate insurance pricing and payout. This paper proposes blockchain architecture to remedy management problems in a UBI environment. A bidding mechanism suitable for the blockchain-based UBI platform was designed to close the information gap between the insurance company and consumer, thus increasing consumer trust in the platform.

This paper focuses on the use of an attention-based encoder-decoder model for the task of breathing sound segmentation and detection. This study aims to accurately segment the inspiration and expiration of patients with pulmonary diseases using the proposed model. Spectrograms of the lung sound signals and labels for every time segment were used to train the model. The model would first encode the spectrogram and then detect inspiratory or expiratory sounds using the encoded image on an attention-based decoder. Physicians would be able to make a more precise diagnosis based on the more interpretable outputs with the assistance of the attention mechanism.The respiratory sounds used for training and testing were recorded from 22 participants using digital stethoscopes or anti-noising microphone sets. Experimental results showed a high 92.006% accuracy when applied 0.5 second time segments and ResNet101 as encoder. Consistent performance of the proposed method can be observed from ten-fold cross-validation experiments.

In heterogeneous wireless networks, coordinated multipoint technology facilitates coordination and mutual cooperation among various types of networks and applications. The resource requirements of various applications differ considerably under the constraint of limited resources so that the allowable delay is considered. This study considered a centralized management scheme involving fourth-generation (4G) mobile networks Evolved Node B, access points, and back-end coordinated servers. The operator controls the flow and performs routing selection procedures through long-term evolution advanced and Wi-Fi in accordance with the 5G wireless networks. The problem was constructed as a mathematical programming model. A Lagrangian relaxation (LR) approach was adopted to maximize the revenue minus the penalty costs as objective to evaluate the resource allocation, tolerable delay, and multisession routing algorithm. The primal problem was decomposed into seven independent subproblems through LR procedures, and the combination of a subgradient method and a routing algorithm was used to obtain approximate solutions. A novel algorithm for flow control involving multisession routing is proposed for handling resource allocation. The algorithm involving a near-optimal approach was designed to solve the insufficient resource problem. The solution can be used by operators for improving resource utilization in next-generation wireless networks.

As wireless sensor networks have become more prevalent, data from sensors in daily life are constantly being recorded. Due to cost or energy consumption considerations, optimization-based approaches are proposed to reduce deployed sensors and yield results within the error tolerance. The correlation-aware method is also designed in a mathematical model that combines theoretical and practical perspectives. The sensor deployment strategies, including XGBoost, Pearson correlation, and Lagrangian Relaxation (LR), are determined to minimize deployment costs while maintaining estimation errors below a given threshold. Moreover, the results significantly ensure the accuracy of the gathered information while minimizing the cost of deployment and maximizing the lifetime of the WSN. Furthermore, the proposed solution can be readily applied to sensor distribution problems in various fields.

A combined edge and core cloud computing environment is a novel solution in 5G network slices. The clients’ high availability requirement is a challenge because it limits the possible admission control in front of the edge cloud. This work proposes an orchestrator with a mathematical programming model in a global viewpoint to solve resource management problems and satisfying the clients’ high availability requirements. The proposed Lagrangian relaxation-based approach is adopted to solve the problems at a near-optimal level for increasing the system revenue. A promising and straightforward resource management approach and several experimental cases are used to evaluate the efficiency and effectiveness. Preliminary results are presented as performance evaluations to verify the proposed approach’s suitability for edge and core cloud computing environments. The proposed orchestrator significantly enables the network slicing services and efficiently enhances the clients’ satisfaction of high availability.

In an emerging paradigm in 5G networks, the computations of various types of mobile applications are offloaded to cloud environments. Edge and core clouds provide computing, storage, and networking resources to serve as a generic computing platform. Network slicing techniques offer an effective way to boost various types of services, such as delay-sensitive or computationally intensive application, that are deployed on-demand in a shared resource infrastructure. This study proposes a resource management mechanism to optimize the quality of experience (QoE) of users in terms of the delay gap tolerance. The Min-Fit algorithm is a heuristic-based solution that flexibly chooses a server that has the maximum remaining CPU resources for satisfying user requirements. A mathematical model is formulated for 5G slicing capabilities to optimize the delay gap using a resource management approach to achieve QoE. Some computational experiments are demonstrated as performance evaluations for verifying the suitability of our proposed approach in terms of slicing capabilities. The results show that our approach outperforms other algorithms, which have larger delay gaps.

A distributed coordination function is a serial fundamental media access control (MAC) mechanism of the IEEE 802.11 wireless network standards for accessing a medium and reducing the probability of collisions. Before sending data, each sender must check whether the medium is available. However, asymmetric detection and collision-avoidance mechanisms create transmission starvation problems. Hence, this paper addresses starvation problems to improve the quality of service in multihop wireless networks by adapting the transmission power range and carrier-sense threshold to alleviate starvation problems and to improve system performance. The problem is modelled as a mathematical formulation, and a Lagrangian relaxation (LR) approach is applied to obtain the approximation solution. The performance of the proposed algorithm is verified by applying it to several simulated starvation-avoidance routing problems. The results show that the proposed algorithm can near-optimally solve these problems, with an average lower bound–upper bound gap of 12.4%.

Cloud radio access network (C-RAN) has been proposed as a core network in the fifth-gene rati on mobile communications system. The computing resources are clustered as a pool that is centralised management as a cloud. The pool provides flexible capabilities to satisfy variant demands with large scale processing. This work stands on an operator perspective to analyse a centralised management mechanism. The research problem is a type of knapsack and bin packing problems that is formulated as a mathematical formulation. The objective is to increase the revenue with minimal server operations cost. Two-phase approximation method is proposed. In phase I, a dynamic programming method is utilized for finding a set of tasks with maximum revenue. In Phase II, three modified Next-Fit, First-Fit, and Best-Fit schemes are developed for solving and evaluating the resource allocations to reduce the number of power-on servers. It presents a way to support operators determine how to allocate the cloud hosts by leveraging cloud technology. The finding can be used to improve resource utilization and achieve cost-effectiveness in C-RANs.

Wi-Fi wireless communication has become a basic service in public areas. However, the quality of service (QoS) might be inadequate in some areas because of the following influential factors: 1) the limited number of non-overlapping channels, 2) the interference caused by unplanned deployment and mobility, 3) the rapidly changing distribution of customers, and 4) access point (AP) failures. These factors result in non-uniform network traffic distribution and unavailability of service in some areas. Hence, this study focused on addressing the problems of AP failure and interference. We propose a self-healing algorithm to provide seamless and reliable service despite AP failures. The proposed water ripple algorithm maximizes the minimum delay difference, which is defined as the difference between transmission delay and tolerable delay, to satisfy requirements of multiple users simultaneously. Variable transmission power ranges (which involve cell breathing method types) and association management are adjusted to minimize the number of out-of-service mobile devices (MDs). Thus, fair allocation of resources to users and adequate QoS are satisfied.

Multicast Broadcast Service MBS applications can efficiently reduce the usage of network resources, still providing mobile users with real-time high-quality content. MBS capabilities are usually implemented by using a single frequency network; moreover, new features, such as connection identifier for broadcast/multicast messages and other MBS-enabled descriptors, are added to cope with already existent entities and services. With the intention to optimize performances and verify the on-field feasibility, we propose an MBS approach to Orthogonal Frequency Division Multiple Access systems based on superposition coding SPC. Because MBS features have a large impact in the architectural design of the network protocols, an integrated framework is mandatory to speed up the system simulation, verification, and redesign steps. This paper shows the design of an experimental testbed for performance evaluation of SPC-enabled physical PHY and medium access control MAC layers over Mobile WiMAX systems. In addition, it proposes some architectural modifications of the WiMAX protocols, by exploiting its core network capabilities. The experimental results obtained from the testbed confirm that augmented throughput capabilities can be achieved by SPC-enabled PHY/MAC layers. However, to fully exploit the additional available throughput, an integrated framework must be adopted to evaluate the protocol modifications for the MBS-enabled entities. Copyright © 2014 John Wiley & Sons, Ltd.