Intelligent decision-making plays a crucial role in artificial intelligence systems, as it enables effective problem-solving and resource allocation. To enhance the decision-making process, this paper proposes the utilization of the Moth Flame Optimization (MFO) algorithm, a metaheuristic optimization technique inspired by the behavior of moths. The MFO algorithm simulates the attraction of moths to light sources and their interaction with other moths, providing a novel approach for intelligent decision-making. This study explores the application of the MFO algorithm in optimizing decision-making parameters, variables, or features within artificial intelligence systems. The algorithm’s iterative process updates the positions of moths based on predefined rules, taking into account the moths’ attraction to light and movement towards other moths. By effectively exploring the search space and converging towards the optimal solution, the MFO algorithm enhances the efficiency and effectiveness of decision-making algorithms in artificial intelligence systems. Through experimentation and evaluation, this paper demonstrates the applicability and benefits of the MFO algorithm in improving decision-making performance in various domains, such as feature selection, image processing, data clustering, and neural network training. The results highlight the simplicity, robustness, and versatility of the MFO algorithm, positioning it as a valuable tool for intelligent decision-making in artificial intelligence systems.
Nowadays, the Internet of Things plays a vital role in data collection that eliminates human intervention in technology. However, without the appearance of Big Data Analytics, the massive volume of data collected from IoT seems meaningless. This review paper aims to explore the significance of big data in the development and functionality of smart cities. The early section of the paper reviews the current technological landscape for IoT devices within smart cities, focusing on domains such as smart transportation, smart healthcare, and smart public safety. The following section of the paper explores the fundamental aspects of big data within the context of smart cities. In addition, this review emphasizes the need to comprehend user behavior patterns in order to derive meaningful insights from the collected data. Finally, the paper addresses the crucial issue of data privacy and investigates methods for ensuring the preservation of private and sensitive information. This paper offers valuable insights and recommendations for researchers, policymakers, and practitioners involved in the field of smart city development and data analytics.
A rectangular slot microstrip antenna with a coplanar waveguide feedline for RF energy harvesting is presented in this paper. The novel antenna design works as a harvester antenna, is designed to match the 50 Ω impedance, and is integrated with an L-type matching voltage doubler rectifier circuit. The designed antenna provides an omnidirectional antenna covering the 2.45 GHz and 5 GHz bands, aiming to suit the application of Wi-Fi RF energy harvesting. The performance of the harvester antenna is analyzed by connecting it to the rectifier circuit with two different Schottky diode models. The performance exhibits good performance in terms of return loss and transfer coefficient for both comparisons. The antenna achieves UWB frequency ranges of 2.1436 GHz to 6.6113 GHz with an operating bandwidth of 4.4677 GHz, which covers the ultra-wideband fractional bandwidth of 102%.
The study proposes an IoT-based system for measuring road roughness using a combination of accelerometer and GPS sensors. The system collects data on road surface roughness and location, which is processed by a microcontroller and transmitted to a cloud-based MQTT broker. The data is analyzed and visualized via Node-RED and MATLAB, allowing for the calculation of IRI values for different road segments and the creation of IRI maps. The average IRI values for the eight segmented data, along with the corresponding pavement conditions, were analyzed in this study. The results indicated that Segmented Data 2 had the lowest mean IRI value of 1.24 m/km, which indicated a good pavement condition. Segmented Data 1, 3, 4, 6, 7, and 8 had IRI values ranging from 2.04 to 2.79 m/km, which indicated a fair pavement condition. On the other hand, Segmented Data 5 had the highest IRI value of 6.50 m/km, which indicated a bad pavement condition. The results demonstrate the IoT-based system’s capability of assessing the road roughness of different pavement conditions. The IRI mapping is based on real-time data collected from the IoT-based system, which allows for efficient measurement of road roughness. The information obtained can be useful for road management authorities to plan and prioritize road maintenance and repair works, improving road safety.
The identification of fish and beef components in gelatin is of utmost importance to prevent allergic reactions. Surface Enhanced Raman Spectroscopy (SERS) combined with Principal Component Analysis (PCA) exhibits the capabilities to effectively separate food samples including these gelatins. The paper focuses on the separation of fish and beef gelatin using SERS and PCA. The gelatin samples were meticulously prepared prior to data acquisition. Raman Spectra Analysis was subsequently conducted, followed by PCA. It was found that the amplitude of beef gelatin raman spectrum is higher than that of the fish gelatin and both gelatin could be distinguished. The results clearly demonstrated that Surface Enhanced Raman Spectroscopy can effectively reveal the characteristics and compounds of fish and beef gelatin, while Principal Component Analysis proves to be a valuable tool for distinguishing between the two gelatins.
