New advancements in the technology of wireless sensors have contributed to the development of special protocols which are unique to sensor networks where minimal energy consumption is vital and very important. As a result, the focus and effort of researchers is on designing better routing algorithms for a given application and network architecture of interest. Flat-based routing protocols have been found to be less advantageous to clustering routing protocols when their performance are compared in a large-scale wireless sensor network scenario. This is due to the fact that clustering operation reduces the amount of redundant messages that are transmitted all over the network when an event is detected. This paper is an investigation of cluster-based routing protocols for wireless sensor networks.

No abstract

This paper presents a new algorithm for detecting and characterizing potholes and bumps directly from noisy signals acquired using an Accelerometer. A wavelet transformation based filter was used to decompose the signals into multiple scales. These coefficients were correlated across adjacent scales and filtered using a spatial filter. Road anomalies were then detected based on a fixed threshold system, while characterization was achieved using unique features extracted from the filtered wavelet coefficients. Our analyses show that the proposed algorithm detects and characterizes road anomalies with high levels of accuracy, precision and low false alarm rates.

No abstract

No abstract

No abstract

Hyperparameter tuning is a critical function necessary for the effective deployment of most machine learning (ML) algorithms. It is used to find the optimal hyperparameter settings of an ML algorithm in order to improve its overall output performance. To this effect, several optimization strategies have been studied for fine-tuning the hyperparameters of many ML algorithms, especially in the absence of model-specific information. However, because most ML training procedures need a significant amount of computational time and memory, it is frequently necessary to build an optimization technique that converges within a small number of fitness evaluations. As a result, a simple deterministic selection genetic algorithm (SDSGA) is proposed in this article. The SDSGA was realized by ensuring that both chromosomes and their accompanying fitness values in the original genetic algorithm are selected in an elitist-like way. We assessed the SDSGA over a variety of mathematical test functions. It was then used to optimize the hyperparameters of two well-known machine learning models, namely, the convolutional neural network (CNN) and the random forest (RF) algorithm, with application on the MNIST and UCI classification datasets. The SDSGA’s efficiency was compared to that of the Bayesian Optimization (BO) and three other popular metaheuristic optimization algorithms (MOAs), namely, the genetic algorithm (GA), particle swarm optimization (PSO) and biogeography-based optimization (BBO) algorithms. The results obtained reveal that the SDSGA performed better than the other MOAs in solving 11 of the 17 known benchmark functions considered in our study. While optimizing the hyperparameters of the two ML models, it performed marginally better in terms of accuracy than the other methods while taking less time to compute.

Recently, the Internet of Things (IoT) is widely considered in vehicular ad-hoc networks (VANETs) for use in intelligent transportation systems. In particular, the pervasive deployment of different sensors in modern vehicles has unlocked interesting possibilities for improving routing performance in VANETs. Nevertheless, the discovery of short single loop-free routes for effective and efficient information dissemination in VANETs remains a challenge. This challenge proves more difficult to solve since it reduces to the case of finding the shortest Hamiltonian path for effective routing in VANETs. Consequently, in this paper, we propose two discretized variants of the cuckoo search optimization (CSO) algorithm, namely, the Lévy flight-based discrete CSO (LF-DCSO) and the random walk-based discrete CSO (RW-DCSO) for effective route discovery in VANETs. In addition, we investigated the inverse mutation operator gleaned from genetic algorithm (GA) in order to improve the exploration properties of our DCSO variants. We describe a new objective function that effectively models the reliability of individual links between nodes that comprise a single route. A detailed report of the routing protocol that controls the routing process is presented. Our proposed methods were compared against the roulette wheel-based GA and the improved kmeans-based GA termed IGAROT. Specifically, our findings reveal that there was no significant difference in the performance of the different methods in the low vehicle density scenario, however, in the medium vehicle density scenario, the RW-DCSO algorithm achieved 2.56%, 100%, and 128.57% percentage increment in its route reliability score over the LF-DCSO, RW-GA, and IGAROT algorithms, respectively. Whereas in the high vehicle density scenario, the LF-DCSO algorithm achieved a percentage increment of 42.85%, 525%, and 733.33% in the route reliability score obtained over the RW-DCSO, IGAROT, and RW-GA algorithms, respectively. Such results suggest that our methods are able to guarantee effective routing in VANETs.