A Dynamic Genetic-Based Context Modeling Approach in Internet of Things Environments

Internet of Things (IoT) is a paradigm that has been explored in various domains, as it facilitates the automation of many tedious processes with more efficiency and robustness. This technology can be applied to effectively mitigate the rising cases of building collapse in Nigeria. Traditional means of monitoring civil structures and determining their health seems inadequate, expensive and out of reach to many, hence a novel means of Structural Health Monitoring (SHM) which IoT provides. IoT facilitates the monitoring and measurement of several structural parameters with a high degree of precision through sensors while enabling these 'things' to communicate effectively through the designed protocol. It has proved to be a cost-effective alternative to traditional SHM while providing the flexibility of alerting users when there is any damage to the structure. In this paper, an IoT platform for structural integrity evaluation and monitoring in civil buildings was developed using piezoelectric transducers (PZT), some microcontrollers, and a SIM800L. These PZTs were deployed at determined nodes to read data continually while some digital signal processing techniques were used to manipulate these data towards determining the health of the structure being monitored. In the end, a system that reads signals from structures, store the signals on the cloud and notify users if any structural damage arises were developed.

Section: Related Workmentioning

confidence: 99%

Internet of Things Framework for Structural Health Monitoring in Nigeria

O.K¹

2020

“…The digitization of multimedia details with the establishment of computer techniques and systems have resulted in better efficiency in production, memory, and broadcasting the digital contents, like images, audios, and videos. In particular, network bandwidth as well as computer memory were enhanced using Moore's law [1]. At the same time, with the help of Internet, multimedia details are interchanged and induced globally.…”

Section: Introductionmentioning

confidence: 99%

An Efficient Chaotic Encryption with Video Watermarking Technique using Improved Whale Optimization Algorithm

2020

Due to the advancements and familiarity of the Internet and the rise of different live broadcasting environments, digital videos have become a part of every day's life. On the other hand, security of videos poses a major threat in the common public networks. Digital watermarking is an effective approach commonly used to secure the digital information. Watermarking is a process of hiding data into multimedia content with no loss of the quality of the content in such a way that the watermark can be extracted by the legal user. This paper proposes a new digital video watermarking with encryption (DVWE) technique using improved whale optimization algorithm. The proposed model initially splits the input video into a sequence of frames and watermark data is hidden into every individual frame. Then, the image frames are decomposed using multi-level discrete wavelet transform (DWT). Besides, improved whale optimization algorithm (IWOA) is derived by incorporating the benefits of whale optimization algorithm (WOA) with levy flight (LF) concept for optimal pixel selection in the cover image. Followed by, the R, G and B components in the watermark data is encrypted by three encryption techniques namely elliptic curve cryptography (ECC), double logistic chaotic map (DLCM) and signcryption. As a result, the encrypted watermark image data is embedded into the cover image and then converted into a watermarked video. At the receiving end, the reverse process takes place to retrieve the secret watermark video. In order to assess the performance of the proposed model, an extensive experimental results analysis takes place. The simulation outcome depicted the effective performance of the presented model over the existing models.

“…Recently, Electroencephalography (EEG) signal is applied as a major tool utilized for epilepsy prediction. The EEG signal captures the electrical brain activities [1] in an effective manner. In general, EEG is considered as a remarkable device used for epilepsy analysis and it is a cheaper machine for both long as well as short term patient's observation using any suspected epileptic syndrome [2].…”

Section: Introductionmentioning

confidence: 99%

Epileptic Seizure Detection using Simulated Annealing based Optimal Feature Subset Selection with Kernel Extreme Learning Machine Classification Model

2020

Electroencephalogram (EEG) signal based epileptic seizure detection is a hot research area, which identifies the non-stationary progresses of brain actions. Typically, the epilepsy is detected by doctors based on the visual examination of EEG signals consumes more time and highly sensitive to noise. Presently, machine learning (ML) techniques finds useful to predict the existence of epileptic seizure from EEG signals. This paper aims to develop a ML based Epileptic seizure detection model in EEG signals. The proposed model involves three major processes namely preprocessing, feature selection and classification. Initially, the EEG signal undergoes preprocessing in two ways namely data normalization, and class labeling. Next, simulated annealing (SA) is applied as a feature selector to choose an optimal set of features. At last, kernel extreme learning machine (KELM) based classification process takes place to detect and classify the existence of EEG. A detailed simulation analysis takes place to inspect the performance of the SA-KELM model. The experimental outcome stated that the SA-KELM model has offered maximum detection performance under the classification of multiple classes with the maximum sensitivity of 57.27%, specificity of 89.32%, accuracy of 82.91%, F-score of 57.29% and kappa of 46.62%.