Land surveying has been one of the core operations in performing underground imaging. It is known that dynamic and continuous resistivity readings were employed through this technique using the array of capacitive electrodes being towed with a light vehicle. However, the main challenge in doing subsurface surveying is the change in speed of the system when there are inevitable obstacles and sloping road surfaces. To address it, this study will develop prediction models using different computational intelligence such as multigene symbolic regression genetic programming (MSRGP), regression-based decision tree (RTree), and feed forward neural network (FFNN) that will result in a smart speed controller system that can maintain the constant speed of the towed subterranean system. The best performing prediction model will be considered as the SpeedX. The expected output is a correction factor that will signal the speed controller in slow down or inclined plane road environment to maintain a constant speed of 1.6667 m/s for avoidance of data distortion on land surveying. Thus, the MSEs for MSRGP, FFNN, and RTree are 0.00163, 0.00178, and 0.00240, respectively. This results in MSRGP as the best performing model and was considered as the SpeedX model. Other evaluation metrics were employed such as the MAE and R² which signify the advantage of SpeedX. Furthermore, the comparison between the CI-controlled and uncontrolled towed subterranean imaging trailer system, as well as its advantages clearly highlight the advantage of embedded SpeedX in the system.

Electrical resistivity tomography (ERT) has been seen as an appropriate instrument in several works to monitor and aid in the control of seawater intrusion (SWI) in coastal groundwater systems. This study seeks to discuss the synthesis of a digital twin that couples information between the physical space through ERT as a monitoring sensor and the digital space using SWI simulations to accurately model the behavior of SWI in the present and future settings. To showcase the concept, a Python-based simulation was presented that shows (a) the joint forward modeling-simulation scheme for calculating expected ERT apparent resistivity values from simulated SWI and (b) the calibration of the digital coastal aquifer system through genetic algorithm to accurately match the outputs of the SWI simulations with the ERT measurements.

Genetic programming (GP) is an evolutionary algorithm used to produce high-quality solutions to various problems. It has seen few claims in circuitry and the development of antenna designs. The application of GP in the model of embedded digital systems on multi-channel antenna arrays of subsurface imaging equipment has not yet been investigated. This study focuses on designing and developing a digital multimeter embedded with a multigene genetic programming (MGGP) model for multi-array transmitter antenna used for subsurface imaging operating at a low frequency of 3.5 kHz to 18.5 kHz using Arduino microcontroller for prototyping. The electrical outputs of a transmitter antenna system employed in a subsurface imaging device require live measurement and monitoring during operation for data logging purposes. The amount of transmitted voltage, produced current, and operating frequency are significant parameters for mapping the underground resistivity, thus the produced GP models are functions of the three parameters. GP fitness function was determined through MATLAB software. The output current signal from the transmitter were imitated in Proteus simulation software using a current source in the designed current measuring circuit. This produced linear and nonlinear relationships of the electrical outputs where GP modeling was beneficially applied. The application of GP in with the microcontroller provided an accurate reading of frequency, current and voltage produced by the multi-array transmitter antenna. These measurements were displayed using LM016L LCD display. Moreover, this embedded digital multimeter on transmitter antenna avoids utilizing costly high voltage measuring devices.

In performing underground imaging surveying, applying a coating in the antenna dipole plates with robust and durable material to stay protected against rough road features is vital to consider. By doing this, the mechanical properties of the metallic antenna dipole can be improved and be shielded from deterioration. With that, this study has developed an indentation-flexure algorithm optimized using a hybrid Lichtenberg algorithm (LA) and artificial neural network (ANN) that can predict the indentation-flexure as a function of the coating material’s elastic modulus, Poisson ratio, and thickness as well as the load antenna weight. Acrylic, epoxy, nylon 101, high-density polyethylene, and polyvinyl chloride were chosen as the top five most popular coating materials. A 120° titanium cone indenter with a 0.5-inch-diameter, slightly rounded point, and a constant compressive force of 200 N in the center was employed to plot and use a nonlinear mechanical finite element analysis on an antenna dipole plate using SolidWorks. Nature-inspired and evolutionary metaheuristics such as African vultures, Lichtenberg, and gorilla troop optimization algorithm including genetic algorithm (GA) were employed as optimized models for the hardness indentation for capacitively coupled antenna dipoles. Based on the results, the hybrid LA-ANN solution with a hidden neurons of 3000 and a sigmoid activation function is the best performing model as it acquired a MSE score of 0.0061 in validation and 0.1478 in testing compare to the other model with 0.1610 for GA with 100 hidden neurons with sigmoid activation function. Thus, LA-ANN model is considered as the optIFnet as it exhibited the best prediction performance and fastest convergence among all optimizers used.

Grapes are prone to Pseudocercospora vitis fungus which causes Isariopsis leaf speck disease to the crop’s leaves, flower, and most importantly the fruit. Typical manual inspection of vineyard farmers is normally ineffective, destructive, and laborious. To address this, the use of integrated computer vision, machine learning, and computational intelligence techniques were realized to sort out healthy grape leaf image from a fungus-specked leaf image and to estimate the specked area percentage (SAP). A dataset made up of 343 normally healthy and 200 fungus-specked grape leaf images were initially pre-processed and segmented via graph cut prior to feature extraction and selection. Significant features were identified using classification tree (CTree). A multigene genetic programming tool called GPTIPSv2 was utilized to generate the fitness function needed for the optimization process done via genetic algorithm (GA). An optimal hidden neuron counts of 110, 50, and 10 were selected for a three-layered GA-optimized recurrent neural network (GA-RNN). Linear discriminant analysis (LDA) topped other disease recognition models with an accuracy of 99.99%. The developed GA-RNN model outperformed Gaussian process regression (GPR), regression tree (RTree), regression support vector machine (RSVM), and linear regression (RLinear) in performing leaf specked area estimation with an R² value of 0.822. The developed CTree-LDA₂-GA-RNN₂ hybrid model has been proven to be the most viable model for this task.

We have proposed a model of dynamic retrieval in associative memory based on temporal input/output correlations under a stimulus-response open scheme of neural networks. This mechanism is different from that of the conventional stationary Hopfield model in which the input signal is used only as information for the initial state of the network. Building upon the fundamental properties of the proposed model, in this paper, we newly evaluate the dependence of identification performance on the signal fluctuation level and on the number of stored patterns by introducing an accuracy rate for known (stored) and unknown (non-stored) patterns, based on the network correlation to the input signal with fluctuation. The results indicate that the dynamic scheme of network response to a fluctuating signal leads to increased efficacy and usefulness.

In recent years, several Japanese companies have attempted to improve the efficiency of their meetings, which has been a significant challenge. For instance, voice recognition technology is used to considerably improve meeting minutes creation. In an automatic minutes-creating system, identifying the speaker to add speaker information to the text would substantially improve the overall efficiency of the process. Therefore, a few companies and research groups have proposed speaker estimation methods; however, it includes challenges, such as requiring advance preparation, special equipment, and multiple microphones. These problems can be solved by using speech sections that are extracted from lip movements and voice information. When a person speaks, voice and lip movements occur simultaneously. Therefore, the speaker’s speech section can be extracted from videos by using lip movement and voice information. However, when this speech section contains only voice information, the voiceprint information of each meeting participant is required for speaker identification. When using lip movements, the speech section and speaker position can be extracted without the voiceprint information. Therefore, in this study, we propose a speech-section extraction method that uses image and voice information in Japanese for speaker identification. The proposed method consists of three processes: i) the extraction of speech frames using lip movements, ii) the extraction of speech frames using voices, and iii) the classification of speech sections using these extraction results. We used video data to evaluate the functionality of the method. Further, the proposed method was compared with state-of-the-art techniques. The average F-measure of the proposed method is determined to be higher than that of the conventional methods that are based on state-of-the-art techniques. The evaluation results showed that the proposed method achieves state-of-the-art performance using a simpler process compared to the conventional method.

It is becoming increasingly attractive to execute workflows in the cloud, as the cloud environment enables scientific applications to utilize elastic computing resources on demand. However, despite being a key to efficiently managing application execution in the cloud, traditional workflow scheduling algorithms face significant challenges in the cloud environment. The gradient-based optimizer (GBO) is a newly proposed evolutionary algorithm with a search engine based on the Newton’s method. It employs a set of vectors to search in the solution space. This study designs a gradient-based scheduler by using GBO for workflow scheduling to minimize the usage costs of workflows under given deadline constraints. Extensive experiments are conducted on well-known scientific workflows of different sizes and types using WorkflowSim. The experimental results show that the proposed scheduling algorithm outperforms five other state-of-the-art algorithms in terms of both the constraint satisfiability and cost optimization, thereby verifying its advantages in addressing workflow scheduling problems.

Optimal perimeter control is one of the effective control technologies to alleviate urban congestion, which is based on macroscopic fundamental diagrams (MFDs). However, most previous optimal perimeter control methods used a linearization model at the desired point to approximate a nonlinear MFDs system, which is vulnerable to causing a potential mismatch between the linearization model and the environmental dynamics. However, this mismatch often leads to performances degradation. To solve this problem, this paper uses a neural network trained from data to approximate the complex nonlinear urban traffic system globally. To facilitate the design and control, this framework linearizes the nonlinear neural network of the traffic system to an instantaneous linearization model. The optimal perimeter control problem is finally solved by generalized predictive control (GPC) with the instantaneous linearization model. A key advantage of the proposed framework is that the global instantaneous linearization model is more accurate than the linearization model around the desired point. Simulation results show that the proposed framework significantly alleviates congestion and reduces the total travel time spent (TTS) in the traffic system compared with no control, “greedy” feedback control and PID control.

Sentiment Analysis is probably one of the best-known area in text mining. However, in recent years, as big data rose in popularity more areas of text classification are being explored. Perhaps the next task to catch on is emotion detection, the task of identifying emotions. This is because emotions are the finer grained information which could be extracted from opinions. So besides writer sentiments, writer emotion is also a valuable data. Emotion detection can be done using text, facial expressions, verbal communications and brain waves; however, the focus of this review is on text-based sentiment analysis and emotion detection. The internet has provided an avenue for the public to express their opinions easily. These expressions not only contain positive or negative sentiments, it contains emotions as well. These emotions can help in social behaviour analysis, decision and policy makings for companies and the country. Emotion detection can further support other tasks such as opinion mining and early depression detection. This review provides a comprehensive analysis of the shift in recent trends from text sentiment analysis to emotion detection and the challenges in these tasks. We summarize some of the recent works in the last five years and look at the methods they used. We also look at the models of emotion classes that are generally referenced. The trend of text-based emotion detection has shifted from the early keyword-based comparisons to machine learning and deep learning algorithms that provide more flexibility to the task and better performance.

This paper considers that two transceivers exchange orthogonal frequency division multiplexing (OFDM) signals with the aid of multiple bidirectional amplify and forward (AF) relays. Unlike most researchers who care about sum rate maximization issues to improve transmission efficiency, we formulate a symbol error probability (SEP) minimization problem under total power constraint because high data rate may degrade SEP performance. A joint algorithm of power allocation and relay selection is proposed to study their impact on the SEP performance. The closed-form solution of power allocation is not a form of water filling widely used in the sum rate maximum problem. Both analytical and simulation results clearly demonstrate the superiority of our algorithm.

A graph G with acyclic coloring has no two adjacent vertices with the same color and no bichromatic cycle. Also, the coloring results in a forest when any two-color classes are combined. The concept of acyclic coloring plays a pivotal role in the computation of Hessians, Kekule structures classification, coding theory, and statistical mechanics. In this paper, the acyclic chromatic number of generalized fan graph, generalized Möbius ladder graph and flower snark graph have been determined.

As a new type of digital currency, Bitcoin is considered as “future gold” by various scholars. Therefore, this study considers Bitcoin and gold as a group of hedging assets to conduct investment research and it also discusses the investment rules between Bitcoin and gold: prediction of the rise and fall of Bitcoin, comparison of the characteristics of Bitcoin and gold, and the impact of the transaction procedures of Bitcoin and gold on the final trading results, and formulates trading strategies through optimization algorithms. Then, four machine learning algorithms, i.e., LSTM, BP neural network, Adaboost, and Bagging, are introduced to predict the rise and fall of gold and Bitcoin the next day, and then, the entropy weight method is used to synthesize four predicted results to ensure the robustness of the predicted results. To establish the optimal trading strategy, this study considers the maximum expected return as the goal to develop a single-objective optimization model and historical five-day price volatility as a risk factor. In this study, ant colony, simulated annealing, and genetic algorithms are used to solve the single-objective optimization model. Finally, we conclude that Bitcoin, similar to other financial assets, e.g., gold, is sensitive to shocks and volatile and possesses a relatively quiet cycle. When Bitcoin has an asymmetric impact, Bitcoin and gold can equally treat transactions.

The convexity induced by the geodesics in a graph G is called the geodesic convexity of G. Mycielski graphs preserve the property of being triangle-free and many parameters such as power domination number, coloring number, determining number and recently general position number have been determined for them. In this work, we determine the geodesic convexity parameters viz., convexity, geodetic iteration, geodetic, and hull numbers for Mycielski graphs for which the underlying graphs considered are path, cycle, star, and complete graph.