CDN is a crucial Internet infrastructure ensuring quick access to Internet content. With the expansion of CDN scenarios, beyond delay, resource types like bandwidth and CPU are also important for CDN performance. Our measurements highlight the distinct impacts of various resource types on different CDN requests. Unfortunately, mainstream CDN server selection schemes only consider a single resource type and are unable to choose the most suitable servers when faced with diverse resource types. To fill this gap, we propose Polygon, a QUIC-powered CDN server selection system that is aware of multiple resource demands. Being an advanced transport layer protocol, QUIC equips Polygon with customizable transport parameters to enable the seamless handling of resource requirements in requests. Its 0-RTT and connection migration mechanisms are also utilized to minimize delays in connection and forwarding. A set of collaborative measurement probes and dispatchers are designed to support Polygon, being responsible for capturing various resource information and forwarding requests to suitable CDN servers. Real-world evaluations on the Google Cloud Platform and extensive simulations demonstrate Polygon’s ability to enhance QoE and optimize resource utilization. The results show up to a 54.8% reduction in job completion time, and resource utilization improvements of 13% in bandwidth and 7% in CPU.

Parkinson’s Disease (PD) is a prevalent and progressive neurodegenerative condition. Previous research has primarily identified the hippocampus as a key affected brain region in PD, with or without dementia, and even in cases without cognitive impairment. However, most earlier studies have treated the hippocampus as a singular global structure, focusing mainly on its overall volume or surface area alterations. There is a notable gap in detailed research on local morphological changes in the hippocampus during the early stages of PD. Our study involved T1-weighted MRI scans of forty-eight early-stage PD patients and forty-eight age-and sex-matched healthy controls. Initially, we assessed the global volume and surface area of the bilateral hippocam-pus. Subsequently, we delved into the detailed morphometric changes at the subfield scale of the bilateral hippocampus using a novel surface-based morphometric approach. Our findings indicate no significant global differences, except in the surface area ratio between the left and right hippocampus. However, significant deformations, primarily atrophic regions, were observed at the subfield level, particularly in the CA1 subfield, followed by the CA2-CA3 and Subiculum subfields. In summary, our study reveals that the CA1 sub-field is most vulnerable in early-stage PD, with atrophy likely progressing from CA1 to other subfields. This study also underscores that global metrics, such as volume or surface area, lack the sensitivity to accurately detect hippocampal deformations in early-stage PD.

Network function virtualization (NFV) is a promising technology that decouples network functions from hardware. Connecting virtual network functions (VNFs) in series to form a service function chain (SFC) can flexibly orchestrate and expand network functions. However, there are higher availability requirements for SFCs. This paper aims to solve the SFC placement problem under availability and resource constraints. This paper proposes the sideway cross (SC) backup model, which considers the availability of both VNFs and physical machines (PMs) in a data center. The SC model cross-arranges the backup instances of VNFs to guarantee availability and optimize resource consumption. Then, this paper proposes the heuristic meteor shower optimization (MSO) algorithm to place SFCs. Compared to traditional heuristic algorithms, MSO can improve the execution time by approximately 200%. Combined with the SC backup model, MSO can effectively improve the availability and resource overhead. The evaluation results show that the proposed approach can guarantee higher availability and consumes fewer resources. The proposed approach only needs 75% of the resources to achieve the same availability as the state-of-the-art models.

Positron Emission Tomography (PET) has been widely used in the early diagnosis and treatment monitoring of Alzheimer’s Disease (AD). As two radiotracers of neurodegeneration, [18F]Fluorodeoxyglucose ([18F]FDG) and [18F]Florbetapir ([18F]AV45) PET have been used to measure cerebral glucose metabolism and $\beta$-amyloid $(A\beta)$ deposition, respectively. The combination of different modality PET images, such as FDG PET and AV45 PET, can provide complementary information for clinical diagnosis and evaluation. However, compared to the actual and available FDG PET data, AV45 PET data is always deficient due to the institution-specific tracers. In this paper, we propose a lightweight Generative Adversarial Network (GAN)-based model, which is termed “dual perceptual loss based generative adversarial network (DPGAN) for fast 2. 5D-based cross-modality generation of AV45 PET from FDG PET. This model provides a potential supplementary solution to those clinical situations that only the FDG PET image is acquired, but the AV45 PET is missing. Our experimental results showed that the DPGAN outperformed recent CycleGAN and pGAN, given its stronger ability in capturing the $A \beta$ deposition patterns on the whole-brain scale. All qualitative and quantitative metrics demonstrated the strong similarity between the generated AV45 PET images using DPGAN and the original AV45 PET images.

Depression is one of the most common mental health disorders, it’s crucial to design an effective and robust model for automatic depression detection (ADD). Although current approaches rely on extra topic models or manually topic-selection procedures which is time-consuming, they still haven’t thoroughly explored the sufficient context information among clinical interviews. In this paper, we propose HCAG, a novel Hierarchical Context-Aware Graph attention model for ADD. Our model mirrors the hierarchical structure of depression assessment and leverages the Graph Attention Network (GAT) to grasp relational contextual information of text/audio modality. Experiments on the DAIC-WOZ dataset show a great performance improvement, with the Fl-score of 0.92, a Mean Absolute Error (MAE) of 2.94, and a Root Mean Square Error (RMSE) of 3.80. To the best of our knowledge, our model outperforms the existing state-of-the-art methods.

Cloud computing is expanding to distributed edge computing(or known as fog computing). Connecting edge and cloud open great potential for real-time and mobility support workflow applications. However, scheduling workflow on a hybrid edge-cloud environment is an NP-hard problem. This paper proposes the Geo-Aware Multi-Agents-System-Based Workflow Allocation Approach(GMAS). Leveraging a novel geo-aware negotiation mechanism, GMAS addresses resource location caused transmission delays, which are the primary sources of workflow bottlenecks. In Multi-Agents-System(MAS), this paper proposes a geo-aware cost model and a dynamic workflow re-structuring strategy that decrease the impact of resource locations on workflow cost. Finally, this paper evaluates GMAS on Cloudsim, and the result shows that GMAS decreases the workflow makespan and traffic overheads.

Network function virtualization (NFV) plays a vital role in 5G mobile networks. Concatenating virtual network functions (VNFs) into service function chains (SFCs) provides flexible and diverse network support for intelligent applications. However, the mobile network connection is very unreliable. A reasonable SFC composition mechanism is essential for stable service providing. This paper proposes a high availability service function chain composition approach, TSFCC. TSFCC includes real-time road marking strategy, bi-composition mechanism, and VNF reallocation mechanism. Evaluation results prove that TSFCC can adapt to the mobile network environment and provide users with efficient and highly available SFC service.

Since its outbreak in December 2019, the persistent coronavirus disease (COVID-19) became a global health emergency. It is imperative to develop a prognostic tool to identify high-risk patients and assist in the formulation of treatment plans. We retrospectively collected 366 severe or critical COVID-19 patients from four centers, including 70 patients who died within 14 days (labeled as high-risk patients) since their initial CT scan and 296 who survived more than 14 days or were cured (labeled as low-risk patients). We developed a 3D densely connected convolutional neural network (termed De-COVID19-Net) to predict the probability of COVID-19 patients belonging to the high-risk or low-risk group, combining CT and clinical information. The area under the curve (AUC) and other evaluation techniques were used to assess our model. The De-COVID19-Net yielded an AUC of 0.952 (95% confidence interval, 0.928-0.977) on the training set and 0.943 (0.904-0.981) on the test set. The stratified analyses indicated that our model's performance is independent of age, sex, and with/without chronic diseases. The Kaplan-Meier analysis revealed that our model could significantly categorize patients into high-risk and low-risk groups (p < 0.001). In conclusion, De-COVID19-Net can non-invasively predict whether a patient will die shortly based on the patient's initial CT scan with an impressive performance, which indicated that it could be used as a potential prognosis tool to alert high-risk patients and intervene in advance.

Scientific workflow scheduling is one of the most challenging problems in cloud computing because of the large-scale computing tasks and massive data volumes involved. A cloud system is a distributed system that follows the on-demand resource provisioning and pay-per-use billing model. Therefore, practical scheduling approaches are essential for good workflow performance and low overheads. This paper proposes a novel workflow allocation approach, the Geo-aware Multiagent Task Allocation Approach (GMTA), which aims to optimize large-scale scientific workflow execution in container-based clouds. GMTA is an agent-based workflow allocation method that includes a market-like agent negotiation mechanism and a dynamic workflow restructuring strategy. It decreases workflow makespans and traffic overheads by reasonable task replications. Furthermore, the performance of GMTA is verified on real scientific workflows in the CloudSim environment.

The cloud computing simplifies application development into the orchestration of virtual-services workflow. However, network latency between geographically distributed hosts would slow down the workflow's makespan time. This paper proposes a geo-aware task allocation approach (GTAA). GTAA partitions the workflow for geo-distributed data centers(DCs) and reduces sub-workflows across DCs. GTAA aims to optimize overall workflow makespan time and improves the efficiency of workflow.

With the explosive growth of large scale services, traditional mobile networks have become increasingly unable to guarantee the efficient operation of services. However in the fifth generation (5G), supported by Software Defined Network (SDN) and Network Function Virtualization (NFV), network slicing technology [1] makes mobile networks more intelligent and flexible. 5G network slicing allows a set of logically independent virtual networks to be created on a common physical infrastructure and provides appropriate monitoring, management and resource allocation for a variety of different types of communication services [2].

Customizable mobile services are usually expressed with complex services composed of different atomic services. Fine-grained atomic mobile services are not so convenient for end users to reuse. Considering that in identical or similar service domains, a great deal of the business logics and functions are reusable within the scope. So we present a template-based framework to allow reuse of services and to achieve rapid mobile application development. The reusable fine-grained service logics and functions are encapsulated into comparatively coarse-grained templates, from which the designers can create the personalized composite services and edit the templates efficiently.

Internet of Things(IoT) was first coined in 1999 by Kevin Ashton. However with the technologies advancement, it seems that intelligent devices will invisibly be embedded in our life in few years. Enormous amounts of data need be exchanged every seconds. It calls for a seamless effect and easily interpretable communicating architecture. The research proposal will try to address some challenges and possible path in IoT enabled smarthome. It focuses primarily on two categories. Firstly, devices in IoT field is always distributed. So, there is a distributed IoT services architecture instead of traditional control-center solution. However, those devices are also limited in a certain area (such as a home local network). In order to reduce delay and burden, those distributed devices collect context information though a self-organizing broadcast network, and determine their next action based on that context data. Secondly, using Docker (a lightweight hardware-agnostic and platform-agnostic container) to package services. In our smarthome network, IoT services are distributed across different home electronics. Docker shields all the differences, so that we can quickly deploy and update module in the smarthome network after purchasing new electronics.

In this paper, we show an end-user oriented tool suite for mobile application development. The advantages of this tool suite are that the graphical user interface (GUI), as well as the application logic can both be developed in a rapid and simple way, and web-based services on the Internet can be integrated into our platform by end-users. This tool suite involves three sub-systems, namely ServiceAccess, EasyApp and LSCE. ServiceAccess takes charge of the registration and management of heterogeneous services, and can export different form of services according to the requirements of the other sub-systems. EasyApp is responsible for developing GUI in the form of mobile app. LSCE takes charge of creating the application logic that can be invoked by mobile app directly. Finally, a development case is presented to illustrate the development process using this tool suite. The URL of demo video: https://youtu.be/mM2WkU1_k-w

BACKGROUND: Although dozens of algorithms and tools have been developed to find a set of cis-regulatory binding sites called a motif in a set of intergenic sequences using various approaches, most of these tools focus on identifying binding sites that are significantly different from their background sequences. However, some motifs may have a similar nucleotide distribution to that of their background sequences. Therefore, such binding sites can be missed by these tools. RESULTS: Here, we present a graph-based polynomial-time algorithm, MotifClick, for the prediction of cis-regulatory binding sites, in particular, those that have a similar nucleotide distribution to that of their background sequences. To find binding sites with length k, we construct a graph using some 2(k-1)-mers in the input sequences as the vertices, and connect two vertices by an edge if the maximum number of matches of the local gapless alignments between the two 2(k-1)-mers is greater than a cutoff value. We identify a motif as a set of similar k-mers from a merged group of maximum cliques associated with some vertices. CONCLUSIONS: When evaluated on both synthetic and real datasets of prokaryotes and eukaryotes, MotifClick outperforms existing leading motif-finding tools for prediction accuracy and balancing the prediction sensitivity and specificity in general. In particular, when the distribution of nucleotides of binding sites is similar to that of their background sequences, MotifClick is more likely to identify the binding sites than the other tools.