Efficient Energy Conservation and Faulty Node Detection on Machine Learning-Based Wireless Sensor Networks

This paper introduces a centralized approach to data gathering and communication for wireless sensor networks. Inspired by the social behaviors of natural ants, we clearly partition the task for the base station and sensor nodes in a wireless sensor network according to their different functions and capabilities. An ant colony optimization method is employed at the base station to form a near-optimal chain for sensor nodes to transmit collected data. Sensor nodes in the network then form a bi-direction chain structure, which is self-adaptive to any minor changes of the network topology. The simulation results show that the developed algorithm, which we call AntChain algorithm, performs much better than many other protocols in terms of energy efficiency, data integrity and life time when the base station is near where the sensor nodes are deployed.

Automatic urban sound classification is a desirable capability for urban monitoring systems, allowing real-time monitoring of urban environments and recognition of events. Current embedded systems provide enough computational power to perform real-time urban audio recognition. Using such devices for the edge computation when acting as nodes of Wireless Sensor Networks (WSN) drastically alleviates the required bandwidth consumption. In this paper, we evaluate classical Machine Learning (ML) techniques for urban sound classification on embedded devices with respect to accuracy and execution time. This evaluation provides a real estimation of what can be expected when performing urban sound classification on such constrained devices. In addition, a cascade approach is also proposed to combine ML techniques by exploiting embedded characteristics such as pipeline or multi-thread execution present in current embedded devices. The accuracy of this approach is similar to the traditional solutions, but provides in addition more flexibility to prioritize accuracy or timing.

À Load-balancing and Self-adaptation Clustering for Lifetime Prolonging in Large Scale Wireless Sensor Networks

Localization of mobile nodes in wireless sensor network gets more and more important, because many applications need to locate the source of incoming measurements as precise as possible. Many previous approaches to the location-estimation problem need know the theories and experiential signal propagation model and collect a large number of labeled samples. So, these approaches are coarse localization because of the inaccurate model, and to obtain such data requires great effort. In this paper, a semi-supervised manifold learning is used to estimate the locations of mobile nodes in a wireless sensor network. The algorithm is used to compute a subspace mapping function between the signal space and the physical space by using a small amount of labeled data and a large amount of unlabeled data. This mapping function can be used online to determine the location of mobile nodes in a sensor network based on the signals received. We use independent development nodes to setup the network in metallurgical industry environment, outdoor and indoor. Experimental results show that we can achieve a higher accuracy with much less calibration effort as compared with RADAR localization systems.

Machine learning has achieved remarkable success across diverse domains. Nevertheless, concerns about interpretability in black-box models, especially within Deep Neural Networks (DNNs), have become pronounced in safety-critical fields like healthcare and finance. Classical machine learning (ML) classifiers, known for their higher interpretability, are preferred in these domains. Similar to DNNs, classical ML classifiers can exhibit bugs that could lead to severe consequences in practice. Test input prioritization has emerged as a promising approach to ensure the quality of an ML system, which prioritizes potentially misclassified tests so that such tests can be identified earlier with limited manual labeling costs. However, when applying to classical ML classifiers, existing DNN test prioritization methods are constrained from three perspectives: 1) Coverage-based methods are inefficient and time-consuming; 2) Mutation-based methods cannot be adapted to classical ML models due to mismatched model mutation rules; 3) Confidence-based methods are restricted to a single dimension when applying to binary ML classifiers, solely depending on the model’s prediction probability for one class. To overcome the challenges, we propose MLPrior, a test prioritization approach specifically tailored for classical ML models. MLPrior leverages the characteristics of classical ML classifiers (i.e., interpretable models and carefully engineered attribute features) to prioritize test inputs. The foundational principles are: 1) tests more sensitive to mutations are more likely to be misclassified, and 2) tests closer to the model’s decision boundary are more likely to be misclassified. Building on the first concept, we design mutation rules to generate two types of mutation features (i.e., <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">model mutation features</b> and <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">input mutation features</b> ) for each test. Drawing from the second notion, MLPrior generates <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">attribute features</b> of each test based on its attribute values, which can indirectly reveal the proximity between the test and the decision boundary. For each test, MLPrior combines all three types of features of it into a final vector. Subsequently, MLPrior employs a pre-trained ranking model to predict the misclassification probability of each test based on its final vector and ranks tests accordingly. We conducted an extensive study to evaluate MLPrior based on 185 subjects, encompassing natural datasets, mixed noisy datasets, and fairness datasets. The results demonstrate that MLPrior outperforms all the compared test prioritization approaches, with an average improvement of 14.74%∼66.93% on natural datasets, 18.55%∼67.73% on mixed noisy datasets, and 15.34%∼62.72% on fairness datasets.

We study the scaling capacity of wireless sensor networks in case of multiple gateways are presented. In such a heterogeneous network, many gateways are needed to gather data from the sensor nodes in network. Different from the previously studied single-gateway model, our proposed gateway access model allows multiple gateway nodes being seamlessly connected with high speed wire-line or wide-band radios. Once the data from the sensor node is sent to any gateway node, it can be collaboratively sent to the appropriate sink node among multiple gateways, which could effectively avoid throughput reduction due to multi-hop routing among the sensor node. This mechanism is called ``Destination-hub", which could ensure the bounded time delay and network capacity. However under such a cooperative scheme, two research issues need to be tackled. One is the number of nodes in network and the second is the scaling capacity for each node when multiple gateway nodes are presented. Our proposed model is a fundamental research work for scaling capacity, which could also provide an instructive proposal for future gateway deployment. In this paper, we characterize the scaling capacity between gateways and sensor nodes under different gateway access model. If gateway nodes are randomly deployed, the number is Omega(log n), and there are at least 4 log l gateway nodes are needed in each squarelet region so as to keep the gateway connectivity, where r is the transmitting range of sensor nodes, and l is the side length of the deployed square region. And we can conclude that, the gateway nodes can be tightly bounded by Theta(log n). For random placement, the scaling capacity for such a scheme is (n). And we have also proposed an optimized scheme for reducing the number of gateway nodes. Considering the interference Voronoi cell, the reduced gateway nodes can be 2 lnl, and still bounded by Theta(log n).

In this paper, an anomaly detection approach that fuses data gathered from different nodes in a distributed sensor network is proposed and evaluated. The emphasis of this work is placed on the data integrity and accuracy problem caused by compromised or malfunctioning nodes. The proposed approach utilizes and applies Principal Component Analysis simultaneously on multiple metrics received from various sensors. One of the key features of the proposed approach is that it provides an integrated methodology of taking into consideration and combining effectively correlated sensor data, in a distributed fashion, in order to reveal anomalies that span through a number of neighboring sensors. Furthermore, it allows the integration of results from neighboring network areas to detect correlated anomalies/attacks that involve multiple groups of nodes. The efficiency and effectiveness of the proposed approach is demonstrated for a real use case that utilizes meteorological data collected from a distributed set of sensor nodes

Mobility of sensor nodes in wireless sensor network (WSN) has posed new challenges particularly in packet delivery ratio and energy consumption. Some real applications impose combined environments of fixed and mobile sensor nodes in the same network, while others demand a complete mobile sensors environment. Packet loss that occurs due to mobility of the sensor nodes is one of the main challenges which comes in parallel with energy consumption. In this paper, we use cross layer design between medium access control (MAC) and network layers to overcome these challenges. Thus, a cluster based routing protocol for mobile sensor nodes (CBR-Mobile) is proposed. The CBR-Mobile is mobility and traffic adaptive protocol. The timeslots assigned to the mobile sensor nodes that had moved out of the cluster or have not data to send will be reassigned to incoming sensor nodes within the cluster region. The protocol introduces two simple databases to achieve the mobility and traffic adaptively. The proposed protocol sends data to cluster heads in an efficient manner based on received signal strength. In CBR-Mobile protocol, cluster based routing collaborates with hybrid MAC protocol to support mobility of sensor nodes. Schedule timeslots are used to send the data message while the contention timeslots are used to send join registration messages. The performance of proposed CBR-Mobile protocol is evaluated using MATLAB and was observed that the proposed protocol improves the packet delivery ratio, energy consumption, delay and fairness in mobility environment compared to LEACH-Mobile and AODV protocols.

A scheme for WSNs (wireless sensor networks) security is given by dividing sensing tetrahedron into clusters and using the symmetric polynomials in this paper.The sensing tetrahedron is divided into a number of small grids.All those sensor nodes, both ordinary sensor nodes and heterogeneous sensor nodes are distributed in the sensing tetrahedron.In a grid, all ordinary sensor nodes and heterogeneous sensor nodes establish their shared keys through using the symmetric polynomials.All the heterogeneous sensor nodes establish their shared keys through using the symmetric polynomials.At last, all sensor nodes establish their keys directly or indirectly in the whole sensing tetrahedron.Analysis and comparison demonstrate this scheme enhances the WSN security, has good network connectivity, saves node storage, reduces network computing load, and extends the network lifetime.

Fall prevention has always been a crucial topic for injury prevention. Research shows that real-time posture monitoring and subsequent fall prevention are important for the prevention of fall-related injuries. In this research, we determine a real-time posture classifier by comparing classical and deep machine learning classifiers in terms of their accuracy and robustness for posture classification. For this, multiple classical classifiers, including classical machine learning, support vector machine, random forest, neural network, and Adaboost methods, were used. Deep learning methods, including LSTM and transformer, were used for posture classification. In the experiment, joint data were obtained using an RGBD camera. The results show that classical machine learning posture classifier accuracy was between 75% and 99%, demonstrating that the use of classical machine learning classification alone is sufficient for real-time posture classification even with missing joints or added noise. The deep learning method LSTM was also effective in classifying the postures with high accuracy, despite incurring a significant computational overhead cost, thus compromising the real-time posture classification performance. The research thus shows that classical machine learning methods are worthy of our attention, at least, to consider for reuse or reinvention, especially for real-time posture classification tasks. The insight of using a classical posture classifier for large-scale human posture classification is also given through this research.

Existing work on placing additional relay nodes in wireless sensor networks to improve network connectivity typically assumes homogeneous wireless sensor nodes with an identical transmission radius. In contrast, this paper addresses the problem of deploying relay nodes to provide fault-tolerance with higher network connectivity in heterogeneous wireless sensor networks, where sensor nodes possess different transmission radii. Depending on the level of desired fault-tolerance, such problems can be categorized as: (1) full fault-tolerance relay node placement, which aims to deploy a minimum number of relay nodes to establish k (k ges 1) vertex-disjoint paths between every pair of sensor and/or relay nodes; (2) partial fault-tolerance relay node placement, which aims to deploy a minimum number of relay nodes to establish k (k ges 1) vertex-disjoint paths only between every pair of sensor nodes. Due to the different transmission radii of sensor nodes, these problems are further complicated by the existence of two different kinds of communication paths in heterogeneous wireless sensor networks, namely two-way paths, along which wireless communications exist in both directions; and one-way paths, along which wireless communications exist in only one direction. Assuming that sensor nodes have different transmission radii, while relay nodes use the same transmission radius, this paper comprehensively analyzes the range of problems introduced by the different levels of fault-tolerance (full or partial) coupled with the different types of path (one-way or two-way). Since each of these problems is NP-hard, we develop O(sigmak <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> )-approximation algorithms for both one-way and two-way partial fault-tolerance relay node placement, as well as O(sigmak <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> )-approximation algorithms for both one-way and two-way full fault-tolerance relay node placement (sigma is the best performance ratio of existing approximation algorithms for finding a minimum k-vertex connected spanning graph). To facilitate the applications in higher dimensions, we also extend these algorithms and derive their performance ratios in d-dimensional heterogeneous wireless sensor networks (d ges 3). Finally, heuristic implementations of these algorithms are evaluated via simulations.

The detection accuracy and model building time of machine learning (ML) classifiers are vital aspects for an intrusion detection system (IDS) to predict attacks in real life. Recently, researchers have introduced feature selection methods to increase the detection accuracy and minimize the model building time of a limited number of ML classifiers. Therefore, identifying more ML classifiers with very high detection accuracy and the lowest possible model building time is necessary. In this study, the authors tested six supervised classifiers on a full NSL-KDD training dataset (a benchmark record for Internet traffic) using 10-fold cross-validation in the Weka tool with and without feature selection/reduction methods. The authors aimed to identify more options to outperform and secure classifiers with the highest detection accuracy and lowest model building time. The results show that the feature selection/reduction methods, including the wrapper method in combination with the discretize filter, the filter method in combination with the discretize filter, and the discretize filter, can significantly decrease model building time without compromising detection accuracy. The suggested ML algorithms and feature selection/reduction methods are automated pattern recognition approaches to detect network attacks, which are within the scope of the Symmetry journal.

Malware detection at the hardware level has emerged recently as a promising solution to improve the security of computing systems. Hardware-based malware detectors take advantage of Machine Learning (ML) classifiers to detect pattern of malicious applications at run-time. These ML classifiers are trained using low-level features such as processor Hardware Performance Counters (HPCs) data which are captured at run-time to appropriately represent the application behaviour. Recent studies show the potential of standard ML-based classifiers for detecting malware using analysis of large number of microarchitectural events, more than the very limited number of HPC registers available in today’s microprocessors which varies from 2 to 8. This results in executing the application more than once to collect the required data, which in turn makes the solution less practical for effective run-time malware detection. Our results show a clear trade-off between the performance of standard ML classifiers and the number and diversity of HPCs available in modern microprocessors. This paper proposes a machine learning-based solution to break this trade-off to realize effective run-time detection of malware. We propose ensemble learning techniques to improve the performance of the hardware-based malware detectors despite using a very small number of microarchitectural events that are captured at run-time by existing HPCs, eliminating the need to run an application several times. For this purpose, eight robust machine learning models and two well-known ensemble learning classifiers applied on all studied ML models (sixteen in total) are implemented for malware detection and precisely compared and characterized in terms of detection accuracy, robustness, performance (accuracy × robustness), and hardware overheads. The experimental results show that the proposed ensemble learning-based malware detection with just 2 HPCs using ensemble technique outperforms standard classifiers with 8 HPCs by up to 17%. In addition, it can match the robustness and performance of standard ML-based detectors with 16 HPCs while using only 4 HPCs allowing effective run-time detection of malware.

The sensor nodes in wireless sensor network (WSN) come with limited battery life, thus energy usage in WSN is to be handled with great care. The routing protocols are the major research area to work on the QoS of the network such as network lifetime, scalability, energy consumption, packet overhead, etc. Since sensor node posses limited battery life, to use nodes efficiently yet not loosing connectivity in the network becomes a major issue in designing the routing protocols. To achieve energy efficiency and better network lifetime, grouping of sensor nodes into small clusters and selecting one cluster head seems to have more advantages in comparison with other network models to get better scalability, robustness and end-to-end data delivery. In this paper, we have discussed and studied the different energy-efficient routing protocols for clustering of sensor nodes in wireless sensor network, its merits, demerits and applications.

We consider in-network computation of an arbitrary function over an arbitrary communication network. A network with capacity constraints on the links is given. Some nodes in the network generate data, e.g., like sensor nodes in a sensor network. An arbitrary function of this distributed data is to be obtained at a terminal node. The structure of the function is described by a given computation schema, which in turn is represented by a directed tree. We design computing and communicating schemes to obtain the function at the terminal at the maximum rate. For this, we formulate linear programs to determine network flows that maximize the computation rate. We then develop a fast combinatorial primal-dual algorithm to obtain near-optimal solutions to these linear programs. As a subroutine for this, we develop an algorithm for finding the minimum cost embedding of a tree in a network with any given set of link costs. We then briefly describe extensions of our techniques to the cases of multiple terminals wanting different functions, multiple computation schemas for a function, computation with a given desired precision, and to networks with energy constraints at nodes.