Self-Organizing Democratized Learning: Toward Large-Scale Distributed Learning Systems.

Emerging cross-device artificial intelligence (AI) applications require a transition from conventional centralized learning systems toward large-scale distributed AI systems that can collaboratively perform complex learning tasks. In this regard, democratized learning (Dem-AI) lays out a holistic philosophy with underlying principles for building large-scale distributed and democratized machine learning systems. The outlined principles are meant to study a generalization in distributed learning systems that go beyond existing mechanisms such as federated learning (FL). Moreover, such learning systems rely on hierarchical self-organization of well-connected distributed learning agents who have limited and highly personalized data and can evolve and regulate themselves based on the underlying duality of specialized and generalized processes. Inspired by Dem-AI philosophy, a novel distributed learning approach is proposed in this article. The approach consists of a self-organizing hierarchical structuring mechanism based on agglomerative clustering, hierarchical generalization, and corresponding learning mechanism. Subsequently, hierarchical generalized learning problems in recursive forms are formulated and shown to be approximately solved using the solutions of distributed personalized learning problems and hierarchical update mechanisms. To that end, a distributed learning algorithm, namely DemLearn, is proposed. Extensive experiments on benchmark MNIST, Fashion-MNIST, FE-MNIST, and CIFAR-10 datasets show that the proposed algorithm demonstrates better results in the generalization performance of learning models in agents compared to the conventional FL algorithms. The detailed analysis provides useful observations to further handle both the generalization and specialization performance of the learning models in Dem-AI systems.

Fuzzy-Assisted Mobile Edge Orchestrator and SARSA Learning for Flexible Offloading in Heterogeneous IoT Environment.

In the era of heterogeneous 5G networks, Internet of Things (IoT) devices have significantly altered our daily life by providing innovative applications and services. However, these devices process large amounts of data traffic and their application requires an extremely fast response time and a massive amount of computational resources, leading to a high failure rate for task offloading and considerable latency due to congestion. To improve the quality of services (QoS) and performance due to the dynamic flow of requests from devices, numerous task offloading strategies in the area of multi-access edge computing (MEC) have been proposed in previous studies. Nevertheless, the neighboring edge servers, where computational resources are in excess, have not been considered, leading to unbalanced loads among edge servers in the same network tier. Therefore, in this paper, we propose a collaboration algorithm between a fuzzy-logic-based mobile edge orchestrator (MEO) and state-action-reward-state-action (SARSA) reinforcement learning, which we call the Fu-SARSA algorithm. We aim to minimize the failure rate and service time of tasks and decide on the optimal resource allocation for offloading, such as a local edge server, cloud server, or the best neighboring edge server in the MEC network. Four typical application types, healthcare, AR, infotainment, and compute-intensive applications, were used for the simulation. The performance results demonstrate that our proposed Fu-SARSA framework outperformed other algorithms in terms of service time and the task failure rate, especially when the system was overloaded.

Dynamic Task Offloading for Cloud-Assisted Vehicular Edge Computing Networks: A Non-Cooperative Game Theoretic Approach.

Vehicular edge computing (VEC) is one of the prominent ideas to enhance the computation and storage capabilities of vehicular networks (VNs) through task offloading. In VEC, the resource-constrained vehicles offload their computing tasks to the local road-side units (RSUs) for rapid computation. However, due to the high mobility of vehicles and the overloaded problem, VEC experiences a great deal of challenges when determining a location for processing the offloaded task in real time. As a result, this degrades the quality of vehicular performance. Therefore, to deal with these above-mentioned challenges, an efficient dynamic task offloading approach based on a non-cooperative game (NGTO) is proposed in this study. In the NGTO approach, each vehicle can make its own strategy on whether a task is offloaded to a multi-access edge computing (MEC) server or a cloud server to maximize its benefits. Our proposed strategy can dynamically adjust the task-offloading probability to acquire the maximum utility for each vehicle. However, we used a best response offloading strategy algorithm for the task-offloading game in order to achieve a unique and stable equilibrium. Numerous simulation experiments affirm that our proposed scheme fulfills the performance guarantees and can reduce the response time and task-failure rate by almost 47.6% and 54.6%, respectively, when compared with the local RSU computing (LRC) scheme. Moreover, the reduced rates are approximately 32.6% and 39.7%, respectively, when compared with a random offloading scheme, and approximately 26.5% and 28.4%, respectively, when compared with a collaborative offloading scheme.

Efficient Solution for Large-Scale IoT Applications with Proactive Edge-Cloud Publish/Subscribe Brokers Clustering.

Large-scale IoT applications with dozens of thousands of geo-distributed IoT devices creating enormous volumes of data pose a big challenge for designing communication systems that provide data delivery with low latency and high scalability. In this paper, we investigate a hierarchical Edge-Cloud publish/subscribe brokers model using an efficient two-tier routing scheme to alleviate these issues when transmitting event notifications in wide-scale IoT systems. In this model, IoT devices take advantage of proximate edge brokers strategically deployed in edge networks for data delivery services in order to reduce latency. To deliver data more efficiently, we propose a proactive mechanism that applies collaborative filtering techniques to efficiently cluster edge brokers with geographic proximity that publish and/or subscribe to similar topics. This allows brokers in the same cluster to exchange data directly with each other to further reduce data delivery latency. In addition, we devise a coordinative scheme to help brokers discover and bridge similar topic channels in the whole system, informing other brokers for data delivery in an efficient manner. Extensive simulation results prove that our model can adeptly support event notifications in terms of low latency, small amounts of relay traffic, and high scalability for large-scale, delay-sensitive IoT applications. Specifically, in comparison with other similar Edge-Cloud approaches, our proposal achieves the best in terms of relay traffic among brokers, about 7.77% on average. In addition, our model's average delivery latency is approximately 66% of PubSubCoord-alike's one.

Fuzzy Decision-Based Efficient Task Offloading Management Scheme in Multi-Tier MEC-Enabled Networks.

Multi-access edge computing (MEC) is a new leading technology for meeting the demands of key performance indicators (KPIs) in 5G networks. However, in a rapidly changing dynamic environment, it is hard to find the optimal target server for processing offloaded tasks because we do not know the end users' demands in advance. Therefore, quality of service (QoS) deteriorates because of increasing task failures and long execution latency from congestion. To reduce latency and avoid task failures from resource-constrained edge servers, vertical offloading between mobile devices with local-edge collaboration or with local edge-remote cloud collaboration have been proposed in previous studies. However, they ignored the nearby edge server in the same tier that has excess computing resources. Therefore, this paper introduces a fuzzy decision-based cloud-MEC collaborative task offloading management system called FTOM, which takes advantage of powerful remote cloud-computing capabilities and utilizes neighboring edge servers. The main objective of the FTOM scheme is to select the optimal target node for task offloading based on server capacity, latency sensitivity, and the network's condition. Our proposed scheme can make dynamic decisions where local or nearby MEC servers are preferred for offloading delay-sensitive tasks, and delay-tolerant high resource-demand tasks are offloaded to a remote cloud server. Simulation results affirm that our proposed FTOM scheme significantly improves the rate of successfully executing offloaded tasks by approximately 68.5%, and reduces task completion time by 66.6%, when compared with a local edge offloading (LEO) scheme. The improved and reduced rates are 32.4% and 61.5%, respectively, when compared with a two-tier edge orchestration-based offloading (TTEO) scheme. They are 8.9% and 47.9%, respectively, when compared with a fuzzy orchestration-based load balancing (FOLB) scheme, approximately 3.2% and 49.8%, respectively, when compared with a fuzzy workload orchestration-based task offloading (WOTO) scheme, and approximately 38.6%% and 55%, respectively, when compared with a fuzzy edge-orchestration based collaborative task offloading (FCTO) scheme.

Flexible computation offloading in a fuzzy-based mobile edge orchestrator for IoT applications.

In the Internet of Things (IoT) era, the capacity-limited Internet and uncontrollable service delays for various new applications, such as video streaming analysis and augmented reality, are challenges. Cloud computing systems, also known as a solution that offloads energy-consuming computation of IoT applications to a cloud server, cannot meet the delay-sensitive and context-aware service requirements. To address this issue, an edge computing system provides timely and context-aware services by bringing the computations and storage closer to the user. The dynamic flow of requests that can be efficiently processed is a significant challenge for edge and cloud computing systems. To improve the performance of IoT systems, the mobile edge orchestrator (MEO), which is an application placement controller, was designed by integrating end mobile devices with edge and cloud computing systems. In this paper, we propose a flexible computation offloading method in a fuzzy-based MEO for IoT applications in order to improve the efficiency in computational resource management. Considering the network, computation resources, and task requirements, a fuzzy-based MEO allows edge workload orchestration actions to decide whether to offload a mobile user to local edge, neighboring edge, or cloud servers. Additionally, increasing packet sizes will affect the failed-task ratio when the number of mobile devices increases. To reduce failed tasks because of transmission collisions and to improve service times for time-critical tasks, we define a new input crisp value, and a new output decision for a fuzzy-based MEO. Using the EdgeCloudSim simulator, we evaluate our proposal with four benchmark algorithms in augmented reality, healthcare, compute-intensive, and infotainment applications. Simulation results show that our proposal provides better results in terms of WLAN delay, service times, the number of failed tasks, and VM utilization.

Time Slot Utilization for Efficient Multi-Channel MAC Protocol in VANETs.

In vehicular ad hoc networks (VANETs), many schemes for a multi-channel media access control (MAC) protocol have been proposed to adapt to dynamically changing vehicle traffic conditions and deliver both safety and non-safety packets. One such scheme is to employ both time-division multiple access (TDMA) and carrier-sense multiple access (CSMA) schemes (called a hybrid TDMA/CSMA scheme) in the control channel (CCH) interval. The scheme can adjust the length of the TDMA period depending on traffic conditions. In this paper, we propose a modified packet transmitted in the TDMA period to reduce transmission overhead under a hybrid TDMA/CSMA multi-channel MAC protocol. Simulation results show that a MAC protocol with a modified packet supports an efficient packet delivery ratio of control packets in the CCH. In addition, we analyze the hybrid TDMA/CSMA multi-channel MAC protocol with the modified packet under saturated throughput conditions on the service channels (SCHs). The analysis results show that the number of neighbors has little effect on the establishment of the number of time slots in TDMA periods and on SCHs under saturated throughput conditions.

Comprehensible knowledge model creation for cancer treatment decision making.

BACKGROUND: A wealth of clinical data exists in clinical documents in the form of electronic health records (EHRs). This data can be used for developing knowledge-based recommendation systems that can assist clinicians in clinical decision making and education. One of the big hurdles in developing such systems is the lack of automated mechanisms for knowledge acquisition to enable and educate clinicians in informed decision making. MATERIALS AND METHODS: An automated knowledge acquisition methodology with a comprehensible knowledge model for cancer treatment (CKM-CT) is proposed. With the CKM-CT, clinical data are acquired automatically from documents. Quality of data is ensured by correcting errors and transforming various formats into a standard data format. Data preprocessing involves dimensionality reduction and missing value imputation. Predictive algorithm selection is performed on the basis of the ranking score of the weighted sum model. The knowledge builder prepares knowledge for knowledge-based services: clinical decisions and education support. RESULTS: Data is acquired from 13,788 head and neck cancer (HNC) documents for 3447 patients, including 1526 patients of the oral cavity site. In the data quality task, 160 staging values are corrected. In the preprocessing task, 20 attributes and 106 records are eliminated from the dataset. The Classification and Regression Trees (CRT) algorithm is selected and provides 69.0% classification accuracy in predicting HNC treatment plans, consisting of 11 decision paths that yield 11 decision rules. CONCLUSION: Our proposed methodology, CKM-CT, is helpful to find hidden knowledge in clinical documents. In CKM-CT, the prediction models are developed to assist and educate clinicians for informed decision making. The proposed methodology is generalizable to apply to data of other domains such as breast cancer with a similar objective to assist clinicians in decision making and education.

GUDM: Automatic Generation of Unified Datasets for Learning and Reasoning in Healthcare.

A wide array of biomedical data are generated and made available to healthcare experts. However, due to the diverse nature of data, it is difficult to predict outcomes from it. It is therefore necessary to combine these diverse data sources into a single unified dataset. This paper proposes a global unified data model (GUDM) to provide a global unified data structure for all data sources and generate a unified dataset by a "data modeler" tool. The proposed tool implements user-centric priority based approach which can easily resolve the problems of unified data modeling and overlapping attributes across multiple datasets. The tool is illustrated using sample diabetes mellitus data. The diverse data sources to generate the unified dataset for diabetes mellitus include clinical trial information, a social media interaction dataset and physical activity data collected using different sensors. To realize the significance of the unified dataset, we adopted a well-known rough set theory based rules creation process to create rules from the unified dataset. The evaluation of the tool on six different sets of locally created diverse datasets shows that the tool, on average, reduces 94.1% time efforts of the experts and knowledge engineer while creating unified datasets.

ATHENA: a personalized platform to promote an active lifestyle and wellbeing based on physical, mental and social health primitives.

Technology provides ample opportunities for the acquisition and processing of physical, mental and social health primitives. However, several challenges remain for researchers as how to define the relationship between reported physical activities, mood and social interaction to define an active lifestyle. We are conducting a project, ATHENA(activity-awareness for human-engaged wellness applications) to design and integrate the relationship between these basic health primitives to approximate the human lifestyle and real-time recommendations for wellbeing services. Our goal is to develop a system to promote an active lifestyle for individuals and to recommend to them valuable interventions by making comparisons to their past habits. The proposed system processes sensory data through our developed machine learning algorithms inside smart devices and utilizes cloud infrastructure to reduce the cost. We exploit big data infrastructure for massive sensory data storage and fast retrieval for recommendations. Our contributions include the development of a prototype system to promote an active lifestyle and a visual design capable of engaging users in the goal of increasing self-motivation. We believe that our study will impact the design of future ubiquitous wellness applications.

Congestion prediction modeling for quality of service improvement in wireless sensor networks.

Information technology (IT) is pushing ahead with drastic reforms of modern life for improvement of human welfare. Objects constitute "Information Networks" through smart, self-regulated information gathering that also recognizes and controls current information states in Wireless Sensor Networks (WSNs). Information observed from sensor networks in real-time is used to increase quality of life (QoL) in various industries and daily life. One of the key challenges of the WSNs is how to achieve lossless data transmission. Although nowadays sensor nodes have enhanced capacities, it is hard to assure lossless and reliable end-to-end data transmission in WSNs due to the unstable wireless links and low hard ware resources to satisfy high quality of service (QoS) requirements. We propose a node and path traffic prediction model to predict and minimize the congestion. This solution includes prediction of packet generation due to network congestion from both periodic and event data generation. Simulation using NS-2 and Matlab is used to demonstrate the effectiveness of the proposed solution.

A survey on virtualization of Wireless Sensor Networks.

Wireless Sensor Networks (WSNs) are gaining tremendous importance thanks to their broad range of commercial applications such as in smart home automation, health-care and industrial automation. In these applications multi-vendor and heterogeneous sensor nodes are deployed. Due to strict administrative control over the specific WSN domains, communication barriers, conflicting goals and the economic interests of different WSN sensor node vendors, it is difficult to introduce a large scale federated WSN. By allowing heterogeneous sensor nodes in WSNs to coexist on a shared physical sensor substrate, virtualization in sensor network may provide flexibility, cost effective solutions, promote diversity, ensure security and increase manageability. This paper surveys the novel approach of using the large scale federated WSN resources in a sensor virtualization environment. Our focus in this paper is to introduce a few design goals, the challenges and opportunities of research in the field of sensor network virtualization as well as to illustrate a current status of research in this field. This paper also presents a wide array of state-of-the art projects related to sensor network virtualization.

A novel addressing scheme for PMIPv6 based global IP-WSNs.

IP based Wireless Sensor Networks (IP-WSNs) are being used in healthcare, home automation, industrial control and agricultural monitoring. In most of these applications global addressing of individual IP-WSN nodes and layer-three routing for mobility enabled IP-WSN with special attention to reliability, energy efficiency and end to end delay minimization are a few of the major issues to be addressed. Most of the routing protocols in WSN are based on layer-two approaches. For reliability and end to end communication enhancement the necessity of layer-three routing for IP-WSNs is generating significant attention among the research community, but due to the hurdle of maintaining routing state and other communication overhead, it was not possible to introduce a layer-three routing protocol for IP-WSNs. To address this issue we propose in this paper a global addressing scheme and layer-three based hierarchical routing protocol. The proposed addressing and routing approach focuses on all the above mentioned issues. Simulation results show that the proposed addressing and routing approach significantly enhances the reliability, energy efficiency and end to end delay minimization. We also present architecture, message formats and different routing scenarios in this paper.

Sensor proxy mobile IPv6 (SPMIPv6)--a novel scheme for mobility supported IP-WSNs.

IP based Wireless Sensor Networks (IP-WSNs) are gaining importance for their broad range of applications in health-care, home automation, environmental monitoring, industrial control, vehicle telematics and agricultural monitoring. In all these applications, mobility in the sensor network with special attention to energy efficiency is a major issue to be addressed. Host-based mobility management protocols are not suitable for IP-WSNs because of their energy inefficiency, so network based mobility management protocols can be an alternative for the mobility supported IP-WSNs. In this paper we propose a network based mobility supported IP-WSN protocol called Sensor Proxy Mobile IPv6 (SPMIPv6). We present its architecture, message formats and also evaluate its performance considering signaling cost, mobility cost and energy consumption. Our analysis shows that with respect to the number of IP-WSN nodes, the proposed scheme reduces the signaling cost by 60% and 56%, as well as the mobility cost by 62% and 57%, compared to MIPv6 and PMIPv6, respectively. The simulation results also show that in terms of the number of hops, SPMIPv6 decreases the signaling cost by 56% and 53% as well as mobility cost by 60% and 67% as compared to MIPv6 and PMIPv6 respectively. It also indicates that proposed scheme reduces the level of energy consumption significantly.