Explainable Learning-Based Timeout Optimization for Accurate and Efficient Elephant Flow Prediction in SDNs.

Accurately and efficiently predicting elephant flows (elephants) is crucial for optimizing network performance and resource utilization. Current prediction approaches for software-defined networks (SDNs) typically rely on complete traffic and statistics moving from switches to controllers. This leads to an extra control channel bandwidth occupation and network delay. To address this issue, this paper proposes a prediction strategy based on incomplete traffic that is sampled by the timeouts for the installation or reactivation of flow entries. The strategy involves assigning a very short hard timeout (Tinitial) to flow entries and then increasing it at a rate of r until flows are identified as elephants or out of their lifespans. Predicted elephants are switched to an idle timeout of 5 s. Logistic regression is used to model elephants based on a complete dataset. Bayesian optimization is then used to tune the trained model Tinitial and r over the incomplete dataset. The process of feature selection, model learning, and optimization is explained. An extensive evaluation shows that the proposed approach can achieve over 90% generalization accuracy over 7 different datasets, including campus, backbone, and the Internet of Things (IoT). Elephants can be correctly predicted for about half of their lifetime. The proposed approach can significantly reduce the controller-switch interaction in campus and IoT networks, although packet completion approaches may need to be applied in networks with a short mean packet inter-arrival time.

Personalized Federated Learning Algorithm with Adaptive Clustering for Non-IID IoT Data Incorporating Multi-Task Learning and Neural Network Model Characteristics.

The proliferation of IoT devices has led to an unprecedented integration of machine learning techniques, raising concerns about data privacy. To address these concerns, federated learning has been introduced. However, practical implementations face challenges, including communication costs, data and device heterogeneity, and privacy security. This paper proposes an innovative approach within the context of federated learning, introducing a personalized joint learning algorithm for Non-IID IoT data. This algorithm incorporates multi-task learning principles and leverages neural network model characteristics. To overcome data heterogeneity, we present a novel clustering algorithm designed specifically for federated learning. Unlike conventional methods that require a predetermined number of clusters, our approach utilizes automatic clustering, eliminating the need for fixed cluster specifications. Extensive experimentation demonstrates the exceptional performance of the proposed algorithm, particularly in scenarios with specific client distributions. By significantly improving the accuracy of trained models, our approach not only addresses data heterogeneity but also strengthens privacy preservation in federated learning. In conclusion, we offer a robust solution to the practical challenges of federated learning in IoT environments. By combining personalized joint learning, automatic clustering, and neural network model characteristics, we facilitate more effective and privacy-conscious machine learning in Non-IID IoT data settings.

A Trusted Reputation Management Scheme for Cross-Chain Transactions.

Blockchain has become a well-known, secured, decentralized datastore in many domains, including medical, industrial, and especially the financial field. However, to meet the requirements of different fields, platforms that are built on blockchain technology must provide functions and characteristics with a wide variety of options. Although they may share similar technology at the fundamental level, the differences among them make data or transaction exchange challenging. Cross-chain transactions have become a commonly utilized function, while at the same time, some have pointed out its security loopholes. It is evident that a secure transaction scheme is desperately needed. However, what about those nodes that do not behave? It is clear that not only a secure transaction scheme is necessary, but also a system that can gradually eliminate malicious players is of dire need. At the same time, integrating different blockchain systems can be difficult due to their independent architectures, and cross-chain transactions can be at risk if malicious attackers try to control the nodes in the cross-chain system. In this paper, we propose a dynamic reputation management scheme based on the past transaction behaviors of nodes. These behaviors serve as the basis for evaluating a node's reputation to support the decision on malicious behavior and enable the system to intercept it in a timely manner. Furthermore, to establish a reputation index with high precision and flexibility, we integrate Particle Swarm Optimization (PSO) into our proposed scheme. This allows our system to meet the needs of a wide variety of blockchain platforms. Overall, the article highlights the importance of securing cross-chain transactions and proposes a method to prevent misbehavior by evaluating and managing node reputation.

The Efficient Mobile Management Based on Metaheuristic Algorithm for Internet of Vehicle.

With the low latency, high transmission rate, and high reliability provided by the fifth-generation mobile communication network (5G), many applications requiring ultra-low latency and high reliability (uRLLC) have become a hot research topic. Among these issues, the most important is the Internet of Vehicles (IoV). To maintain the safety of vehicle drivers and road conditions, the IoV can transmit through sensors or infrastructure to maintain communication quality and transmission. However, because 5G uses millimeter waves for transmission, a large number of base stations (BS) or lightweight infrastructure will be built in 5G, which will make the overall environment more complex than 4G. The lightweight infrastructure also has to be considered together. For these reasons, in 5G, there are two mechanisms for handover, horizontal, and vertical handover; hence, it must be discussed how to handle handover to obtain the best performance for the whole network. In this paper, to address handover selection, we consider delay time, energy efficiency, load balancing, and energy consumption and formulate it as a multi-objective optimization (MOO) problem. At the same time, we propose the handover of the mobile management mechanism based on location prediction combined with heuristic algorithms. The results show that our proposed mechanism is better than the distance-based one for energy efficiency, load, and latency. It optimizes by more than about 20% at most.

A Possible World-Based Fusion Estimation Model for Uncertain Data Clustering in WBNs.

In data clustering, the measured data are usually regarded as uncertain data. As a probability-based clustering technique, possible world can easily cluster the uncertain data. However, the method of possible world needs to satisfy two conditions: determine the data of different possible worlds and determine the corresponding probability of occurrence. The existing methods mostly make multiple measurements and treat each measurement as deterministic data of a possible world. In this paper, a possible world-based fusion estimation model is proposed, which changes the deterministic data into probability distribution according to the estimation algorithm, and the corresponding probability can be confirmed naturally. Further, in the clustering stage, the Kullback-Leibler divergence is introduced to describe the relationships of probability distributions among different possible worlds. Then, an application in wearable body networks (WBNs) is given, and some interesting conclusions are shown. Finally, simulations show better performance when the relationships between features in measured data are more complex.

Fast Utility Mining on Sequence Data.

High-utility sequential pattern (HUSP) mining is an emerging topic in the field of knowledge discovery in databases. It consists of discovering subsequences that have a high utility (importance) in sequences, which can be referred to as HUSPs. HUSPs can be applied to many real-life applications, such as market basket analysis, e-commerce recommendations, click-stream analysis, and route planning. Several algorithms have been proposed to efficiently mine utility-based useful sequential patterns. However, due to the combinatorial explosion of the search space for low utility threshold and large-scale data, the performances of these algorithms are unsatisfactory in terms of runtime and memory usage. Hence, this article proposes an efficient algorithm for the task of HUSP mining, called HUSP mining with UL-list (HUSP-ULL). It utilizes a lexicographic q -sequence (LQS)-tree and a utility-linked (UL)-list structure to quickly discover HUSPs. Furthermore, two pruning strategies are introduced in HUSP-ULL to obtain tight upper bounds on the utility of the candidate sequences and reduce the search space by pruning unpromising candidates early. Substantial experiments on both real-life and synthetic datasets showed that HUSP-ULL can effectively and efficiently discover the complete set of HUSPs and that it outperforms the state-of-the-art algorithms.

A Stacked Human Activity Recognition Model Based on Parallel Recurrent Network and Time Series Evidence Theory.

As the foundation of Posture Analysis, recognizing human activity accurately in real time assists in using machines to intellectualize living condition and monitor health status. In this paper, we focus on recognition based on raw time series data, which are continuously sampled by wearable sensors, and a fine-grained evidence reasoning approach has been proposed to produce a timely and reliable result. First, the basic time unit of input data is selected by finding a tradeoff between accuracy and time cost. Then, the approach uses Long Short Term Memory to extract features and project raw multidimensional data into probability assignments, followed by trainable evidence combination and inference network that reduce uncertainly to improve the classification accuracy. Experiments validate the effectiveness of fine granularity and evidence reasoning while the final results indicate that the recognition accuracy of this approach can reach 96.4% with no additional complexity in training.

HUOPM: High-Utility Occupancy Pattern Mining.

Mining useful patterns from varied types of databases is an important research topic, which has many real-life applications. Most studies have considered the frequency as sole interestingness measure to identify high-quality patterns. However, each object is different in nature. The relative importance of objects is not equal, in terms of criteria, such as the utility, risk, or interest. Besides, another limitation of frequent patterns is that they generally have a low occupancy, that is, they often represent small sets of items in transactions containing many items and, thus, may not be truly representative of these transactions. To extract high-quality patterns in real-life applications, this paper extends the occupancy measure to also assess the utility of patterns in transaction databases. We propose an efficient algorithm named high-utility occupancy pattern mining (HUOPM). It considers user preferences in terms of frequency, utility, and occupancy. A novel frequency-utility tree and two compact data structures, called the utility-occupancy list and frequency-utility table, are designed to provide global and partial downward closure properties for pruning the search space. The proposed method can efficiently discover the complete set of high-quality patterns without candidate generation. Extensive experiments have been conducted on several datasets to evaluate the effectiveness and efficiency of the proposed algorithm. Results show that the derived patterns are intelligible, reasonable, and acceptable, and that HUOPM with its pruning strategies outperforms the state-of-the-art algorithm, in terms of runtime and search space, respectively.

A Method of HBase Multi-Conditional Query for Ubiquitous Sensing Applications.

Big data gathered from real systems, such as public infrastructure, healthcare, smart homes, industries, and so on, by sensor networks contain enormous value, and need to be mined deeply, which depends on a data storing and retrieving service. HBase is playing an increasingly important part in the big data environment since it provides a flexible pattern for storing extremely large amounts of unstructured data. Despite the fast-speed reading by RowKey, HBase does not natively support multi-conditional query, which is a common demand and operation in relational databases, especially for data analysis of ubiquitous sensing applications. In this paper, we introduce a method to construct a linear index by employing a Hilbert space-filling curve. As a RowKey generating schema, the proposed method maps multiple index-columns into a one-dimensional encoded sequence, and then constructs a new RowKey. We also provide a R-tree-based optimization to reduce the computational cost of encoding query conditions. Without using a secondary index mode, experimental results indicate that the proposed method has better performance in multi-conditional queries.

Data Privacy Protection Based on Micro Aggregation with Dynamic Sensitive Attribute Updating.

With the rapid development of information technology, large-scale personal data, including those collected by sensors or IoT devices, is stored in the cloud or data centers. In some cases, the owners of the cloud or data centers need to publish the data. Therefore, how to make the best use of the data in the risk of personal information leakage has become a popular research topic. The most common method of data privacy protection is the data anonymization, which has two main problems: (1) The availability of information after clustering will be reduced, and it cannot be flexibly adjusted. (2) Most methods are static. When the data is released multiple times, it will cause personal privacy leakage. To solve the problems, this article has two contributions. The first one is to propose a new method based on micro-aggregation to complete the process of clustering. In this way, the data availability and the privacy protection can be adjusted flexibly by considering the concepts of distance and information entropy. The second contribution of this article is to propose a dynamic update mechanism that guarantees that the individual privacy is not compromised after the data has been subjected to multiple releases, and minimizes the loss of information. At the end of the article, the algorithm is simulated with real data sets. The availability and advantages of the method are demonstrated by calculating the time, the average information loss and the number of forged data.

Classification of Incomplete Data Based on Evidence Theory and an Extreme Learning Machine in Wireless Sensor Networks.

In wireless sensor networks, the classification of incomplete data reported by sensor nodes is an open issue because it is difficult to accurately estimate the missing values. In many cases, the misclassification is unacceptable considering that it probably brings catastrophic damages to the data users. In this paper, a novel classification approach of incomplete data is proposed to reduce the misclassification errors. This method uses the regularized extreme learning machine to estimate the potential values of missing data at first, and then it converts the estimations into multiple classification results on the basis of the distance between interval numbers. Finally, an evidential reasoning rule is adopted to fuse these classification results. The final decision is made according to the combined basic belief assignment. The experimental results show that this method has better performance than other traditional classification methods of incomplete data.

Mixed H2/H∞-Based Fusion Estimation for Energy-Limited Multi-Sensors in Wearable Body Networks.

In wireless sensor networks, sensor nodes collect plenty of data for each time period. If all of data are transmitted to a Fusion Center (FC), the power of sensor node would run out rapidly. On the other hand, the data also needs a filter to remove the noise. Therefore, an efficient fusion estimation model, which can save the energy of the sensor nodes while maintaining higher accuracy, is needed. This paper proposes a novel mixed H2/H∞-based energy-efficient fusion estimation model (MHEEFE) for energy-limited Wearable Body Networks. In the proposed model, the communication cost is firstly reduced efficiently while keeping the estimation accuracy. Then, the parameters in quantization method are discussed, and we confirm them by an optimization method with some prior knowledge. Besides, some calculation methods of important parameters are researched which make the final estimates more stable. Finally, an iteration-based weight calculation algorithm is presented, which can improve the fault tolerance of the final estimate. In the simulation, the impacts of some pivotal parameters are discussed. Meanwhile, compared with the other related models, the MHEEFE shows a better performance in accuracy, energy-efficiency and fault tolerance.

A collaborative computing framework of cloud network and WBSN applied to fall detection and 3-D motion reconstruction.

As cloud computing and wireless body sensor network technologies become gradually developed, ubiquitous healthcare services prevent accidents instantly and effectively, as well as provides relevant information to reduce related processing time and cost. This study proposes a co-processing intermediary framework integrated cloud and wireless body sensor networks, which is mainly applied to fall detection and 3-D motion reconstruction. In this study, the main focuses includes distributed computing and resource allocation of processing sensing data over the computing architecture, network conditions and performance evaluation. Through this framework, the transmissions and computing time of sensing data are reduced to enhance overall performance for the services of fall events detection and 3-D motion reconstruction.

Design and analysis of self-adapted task scheduling strategies in wireless sensor networks.

In a wireless sensor network (WSN), the usage of resources is usually highly related to the execution of tasks which consume a certain amount of computing and communication bandwidth. Parallel processing among sensors is a promising solution to provide the demanded computation capacity in WSNs. Task allocation and scheduling is a typical problem in the area of high performance computing. Although task allocation and scheduling in wired processor networks has been well studied in the past, their counterparts for WSNs remain largely unexplored. Existing traditional high performance computing solutions cannot be directly implemented in WSNs due to the limitations of WSNs such as limited resource availability and the shared communication medium. In this paper, a self-adapted task scheduling strategy for WSNs is presented. First, a multi-agent-based architecture for WSNs is proposed and a mathematical model of dynamic alliance is constructed for the task allocation problem. Then an effective discrete particle swarm optimization (PSO) algorithm for the dynamic alliance (DPSO-DA) with a well-designed particle position code and fitness function is proposed. A mutation operator which can effectively improve the algorithm's ability of global search and population diversity is also introduced in this algorithm. Finally, the simulation results show that the proposed solution can achieve significant better performance than other algorithms.

An environmental-adaptive fall detection system on mobile device.

When facing damages caused by falls, a well designed smart sensor system to detect falls can be both medically and economically helpful. This research introduces a portable terrain adaptable fall detection system, by placing accelerometers and gyroscopes in parts of the body and transmit data through wireless transmitter modules to mobile devices to get the related information and combining it with the center of gravity clustering algorithm introduced in this research which computes the human body behavior patterns according the relationship between the center of gravity in the body and the feet portion of the body. Compared with the research in the past, this system is not only highly accurate and robust, but also able to adapt to different types of terrains, which solves the problems that other researches have for detection errors when the client is climbing the stairs or walking on a slant.

Acquiring authentic data in unattended wireless sensor networks.

An Unattended Wireless Sensor Network (UWSN) can be used in many applications to collect valuable data. Nevertheless, due to the unattended nature, the sensors could be compromised and the sensor readings would be maliciously altered so that the sink accepts the falsified sensor readings. Unfortunately, few attentions have been given to this authentication problem. Moreover, existing methods suffer from different kinds of DoS attacks such as Path-Based DoS (PDoS) and False Endorsement-based DoS (FEDoS) attacks. In this paper, a scheme, called AAD, is proposed to Acquire Authentic Data in UWSNs. We exploit the collaboration among sensors to address the authentication problem. With the proper design of the collaboration mechanism, AAD has superior resilience against sensor compromises, PDoS attack, and FEDoS attack. In addition, compared with prior works, AAD also has relatively low energy consumption. In particular, according to our simulation, in a network with 1,000 sensors, the energy consumed by AAD is lower than 30% of that consumed by the existing method, ExCo. The analysis and simulation are also conducted to demonstrate the superiority of the proposed AAD scheme over the existing methods.