Data Pre-processing Stage Research Articles

MST-DGCN: A Multi-Scale Spatio-Temporal and Dynamic Graph Convolution Fusion Network for Electroencephalogram Recognition of Motor Imagery

The motor imagery brain-computer interface (MI-BCI) has the ability to use electroencephalogram (EEG) signals to control and communicate with external devices. By leveraging the unique characteristics of task-related brain signals, this system facilitates enhanced communication with these devices. Such capabilities hold significant potential for advancing rehabilitation and the development of assistive technologies. In recent years, deep learning has received considerable attention in the MI-BCI field due to its powerful feature extraction and classification capabilities. However, two factors significantly impact the performance of deep-learning models. The size of the EEG datasets influences how effectively these models can learn. Similarly, the ability of classification models to extract features directly affects their accuracy in recognizing patterns. In this paper, we propose a Multi-Scale Spatio-Temporal and Dynamic Graph Convolution Fusion Network (MST-DGCN) to address these issues. In the data-preprocessing stage, we employ two strategies, data augmentation and transfer learning, to alleviate the problem of an insufficient data volume in deep learning. By using multi-scale convolution, spatial attention mechanisms, and dynamic graph neural networks, our model effectively extracts discriminative features. The MST-DGCN mainly consists of three parts: the multi-scale spatio-temporal module, which extracts multi-scale information and refines spatial attention; the dynamic graph convolution module, which extracts key connectivity information; and the classification module. We conduct experiments on real EEG datasets and achieve an accuracy of 77.89% and a Kappa value of 0.7052, demonstrating the effectiveness of the MST-DGCN in MI-BCI tasks. Our research provides new ideas and methods for the further development of MI-BCI systems.

Evaluation of a Voltametric E-Tongue Combined with Data Preprocessing for Fast and Effective Machine Learning-Based Classification of Tomato Purées by Cultivar.

The potential of a voltametric E-tongue coupled with a custom data pre-processing stage to improve the performance of machine learning techniques for rapid discrimination of tomato purées between cultivars of different economic value has been investigated. To this aim, a sensor array with screen-printed carbon electrodes modified with gold nanoparticles (GNP), copper nanoparticles (CNP) and bulk gold subsequently modified with poly(3,4-ethylenedioxythiophene) (PEDOT), was developed to acquire data to be transformed by a custom pre-processing pipeline and then processed by a set of commonly used classifiers. The GNP and CNP-modified electrodes, selected based on their sensitivity to soluble monosaccharides, demonstrated good ability in discriminating samples of different cultivars. Among the different data analysis methods tested, Linear Discriminant Analysis (LDA) proved to be particularly suitable, obtaining an average F1 score of 99.26%. The pre-processing stage was beneficial in reducing the number of input features, decreasing the computational cost, i.e., the number of computing operations to be performed, of the entire method and aiding future cost-efficient hardware implementation. These findings proved that coupling the multi-sensing platform featuring properly modified sensors with the custom pre-processing method developed and LDA provided an optimal tradeoff between analytical problem solving and reliable chemical information, as well as accuracy and computational complexity. These results can be preliminary to the design of hardware solutions that could be embedded into low-cost portable devices.

Predicting game-induced emotions using EEG, data mining and machine learning

BackgroundEmotion is a complex phenomenon that greatly affects human behavior and thinking in daily life. Electroencephalography (EEG), one of the human physiological signals, has been emphasized by most researchers in emotion recognition as its specific properties are closely associated with human emotion. However, the number of human emotion recognition studies using computer games as stimuli is still insufficient as there were no relevant publicly available datasets provided in the past decades. Most of the recent studies using the Gameemo public dataset have not clarified the relationship between the EEG signal’s changes and the emotion elicited using computer games. Thus, this paper is proposed to introduce the use of data mining techniques in investigating the relationships between the frequency changes of EEG signals and the human emotion elicited when playing different kinds of computer games. The data acquisition stage, data pre-processing, data annotation and feature extraction stage were designed and conducted in this paper to obtain and extract the EEG features from the Gameemo dataset. The cross-subject and subject-based experiments were conducted to evaluate the classifiers’ performance. The top 10 association rules generated by the RCAR classifier will be examined to determine the possible relationship between the EEG signal's frequency changes and game-induced emotions.ResultsThe RCAR classifier constructed for cross-subject experiment achieved highest accuracy, precision, recall and F1-score evaluated with over 90% in classifying the HAPV, HANV and LANV game-induced emotions. The 20 experiment cases’ results from subject-based experiments supported that the SVM classifier could accurately classify the 4 emotion states with a kappa value over 0.62, demonstrating the SVM-based algorithm’s capabilities in precisely determining the emotion label for each participant’s EEG features’ instance.ConclusionThe findings in this study fill the existing gap of game-induced emotion recognition field by providing an in-depth evaluation on the ruleset algorithm’s performance and feasibility of applying the generated rules on the game-induced EEG data for justifying the emotional state prediction result.

Attention-Oriented CNN Method for Type 2 Diabetes Prediction

Diabetes is caused by insulin deficiency or impaired biological action, and long-term hyperglycemia leads to a variety of tissue damage and dysfunction. Therefore, the early prediction of diabetes and timely intervention and treatment are crucial. This paper proposes a robust framework for the prediction and diagnosis of type 2 diabetes (T2DM) to aid in diabetes applications in clinical diagnosis. The data-preprocessing stage includes steps such as outlier removal, missing value filling, data standardization, and assigning class weights to ensure the quality and consistency of the data, thereby improving the performance and stability of the model. This experiment used the National Health and Nutrition Examination Survey (NHANES) dataset and the publicly available PIMA Indian dataset (PID). For T2DM classification, we designed a convolutional neural network (CNN) and proposed a novel attention-oriented convolutional neural network (SECNN) through the channel attention mechanism. To optimize the hyperparameters of the model, we used grid search and K-fold cross-validation methods. In addition, we also comparatively analyzed various machine learning (ML) models such as support vector machine (SVM), logistic regression (LR), decision tree (DT), random forest (RF), and artificial neural network (ANN). Finally, we evaluated the performance of the model using performance evaluation metrics such as precision, recall, F1-Score, accuracy, and AUC. Experimental results show that the SECNN model has an accuracy of 94.12% on the NHANES dataset and an accuracy of 89.47% on the PIMA Indian dataset. SECNN models and CNN models show significant improvements in diabetes prediction performance compared to traditional ML models. The comparative analysis of the SECNN model and the CNN model has significantly improved performance, further verifying the advantages of introducing the channel attention mechanism. The robust diabetes prediction framework proposed in this article establishes an effective foundation for diabetes diagnosis and prediction, and has a positive impact on the development of health management and medical industries.

Particle Swarm Optimization for Optimizing Public Service Satisfaction Level Classification

This research aims to categorize survey data to determine the level of satisfaction with the services provided by the village government as a public service provider. Villages or sub-districts currently offer services in response to community demand, although only partially or as efficiently as possible. The data collection technique used was distributing questionnaires to the village community. The method used for classification is the machine learning method. Before the classification process, feature selection is carried out at the data pre-processing stage using Particle Swarm Optimization (PSO), which has been proven to increase the accuracy of the classification values. The classification methods employed include Decision Tree (DT), Naive Bayes, Support Vector Machine (SVM), and K-Nearest Neighbor (KNN) algorithms for classification purposes. This study achieves the maximum level of accuracy in decision tree classification, attaining an accuracy rate of 97.74%. Subsequently, the KNN algorithm achieved an accuracy of 77.90%, the Nave Bayes algorithm achieved 64.4%, and the SVM algorithm, which yielded the lowest accuracy value, achieved 59.90%. Following the application of Particle Swarm Optimization (PSO) for optimization, the accuracy of the SVM and KNN algorithms improved to 98.3%. The Decision Tree algorithm achieved a value of 97.77%, while the Naive Bayes technique yielded a value of 69.30%.

Exploring Feature Selection and Machine Learning Algorithms for Predicting Diabetes Disease

One of the most common diseases in the world is the chronic diabetes. Diabetes has a direct impact on the lives of millions of people worldwide. Diabetes can be controlled and improved with early diagnosis, but the majority of patients continue to live with it. There is a dispirit need to a system to anticipate and select the people who are most likely to be diabetes in the future. Diagnosing the future diseased person without taking any blood or glucose screening tests, is the main goal of this study. This paper proposed a deep-learning model for diabetes disease prediction. The proposed model consists of three main phases, data pre-processing, feature selection and finally different classifiers. Initially, during the data pre-processing stage, missing values are handled, and data normalization is applied to the data. Then, three techniques are used to select the most important features which are mutual information, chi-squared and Pearson correlation. After that, multiple machine learning classifiers are used. Four experiments are then conducted to test our models. Additionally, the effectiveness of the proposed model is evaluated against that of other well-known machine learning techniques. The accuracy, AUC, sensitivity, and F-measure of the linear regression classifier are higher than those of the other methods, according to experimental data, which show that it performs better. The suggested model worked better than traditional methods and had a high accuracy rate for predicting diabetic disease.

A Novel Data Preprocessing Model for Lightweight Sensory IoT Intrusion Detection

IoT devices or sensor nodes are essential components of the machine learning (ML) application workflow because they gather abundant information for building models with sensors. Uncontrollable factors may impact this process and add inaccuracies to the data, raising the cost of computational resources for data preparation. Choosing the best method for this data pre-processing stage can lessen the complexity of ML models and wasteful bandwidth use for cloud processing. Devices in the IoT ecosystem with limited resources provide an easy target for attackers, who can make use of these devices to create botnets and spread malware. To repel attacks directed towards IoT, robust and lightweight intrusion detection systems are the need of an hour. Furthermore, data preprocessing remains the first step for modish machine learning models, ensemble techniques, and hybrid methods in developing anti-intrusion applications for lightweight IoT. This article proposes a novel data preprocessing model as a core structure using an Extra Tree classifier for feature selection and two classifiers LSTM and 1D-CNN for classification. The dataset used in this research is CIC IoT 2023 with 34 attack classes and SMOTE (Synthetic Memory Oversampling Technique) has been used for class balancing. The article evaluates the performance of 1D-CNN and LSTM on the CIC IoT 23 dataset using classification metrics. The proposed ensemble approach using LSTM has obtained 92% accuracy and with 1D-CNN the model obtained 99.87% accuracy.

Multiple Classification of Brain MRI Autism Spectrum Disorder by Age and Gender Using Deep Learning

The fact that the rapid and definitive diagnosis of autism cannot be made today and that autism cannot be treated provides an impetus to look into novel technological solutions. To contribute to the resolution of this problem through multiple classifications by considering age and gender factors, in this study, two quadruple and one octal classifications were performed using a deep learning (DL) approach. Gender in one of the four classifications and age groups in the other were considered. In the octal classification, classes were created considering gender and age groups. In addition to the diagnosis of ASD (Autism Spectrum Disorders), another goal of this study is to find out the contribution of gender and age factors to the diagnosis of ASD by making multiple classifications based on age and gender for the first time. Brain structural MRI (sMRI) scans of participators with ASD and TD (Typical Development) were pre-processed in the system originally designed for this purpose. Using the Canny Edge Detection (CED) algorithm, the sMRI image data was cropped in the data pre-processing stage, and the data set was enlarged five times with the data augmentation (DA) techniques. The most optimal convolutional neural network (CNN) models were developed using the grid search optimization (GSO) algorism. The proposed DL prediction system was tested with the five-fold cross-validation technique. Three CNN models were designed to be used in the system. The first of these models is the quadruple classification model created by taking gender into account (model 1), the second is the quadruple classification model created by taking into account age (model 2), and the third is the eightfold classification model created by taking into account both gender and age (model 3). ). The accuracy rates obtained for all three designed models are 80.94, 85.42 and 67.94, respectively. These obtained accuracy rates were compared with pre-trained models by using the transfer learning approach. As a result, it was revealed that age and gender factors were effective in the diagnosis of ASD with the system developed for ASD multiple classifications, and higher accuracy rates were achieved compared to pre-trained models.

Enhancing IoT Security Development and Evaluation of a Predictive Machine Learning Model for Attack Detection

The research aims to develop and evaluate a model for Internet of Things (IoT) attack identification utilizing IoT data from the Global Cyber Alliance’s (GCA) Automated IoT Defense Ecosystem (AIDE). In the growing landscape of IoT security, the need for enhanced predictive solutions is vital. Our research leverages an enormous dataset, overall historical data from various IoT devices and network interactions, to develop a model to identify potential security threats. The key to our methodology concerns exploratory data analysis, which is focused on understanding complex patterns and anomalies in IoT data. This step is vital for feature engineering, where we meticulously select and transform data attributes to advance the model’s predictive strength. The data pre-processing stage further improves the dataset, ensuring the model training and testing on high-quality, relevant data. Model development is a composite process in this research. We tried out a few machine-learning algorithms, finally selecting the one that exhibited outstanding performance in preliminary tests. The chosen model endured strict training, with a basis on balancing accuracy and validity to effectively predict IoT attacks in various scenarios. The evaluation of our model is as durable as its development. We utilized a range of metrics, including accuracy, precision, recall, and F1 score, to evaluate the model’s behavior overall. The results show that our model not only attains high accuracy but also maintains a notable level of precision in predicting IoT attacks, which is crucial in minimizing false positives. In conclusion, our research contributes to the enhancement of IoT security by providing a very effective predictive model for IoT attack detection.

Handling incomplete data using Radial basis Kernelized Intuitionistic Fuzzy C-Means

Missing data imputation is a critical task in the data pre-processing stage to ensure the quality, stability, and reliability of machine learning models. If missing values are imputed incorrectly, it can result in erroneous predictions and inconsistent model performance. Traditional imputation methods often struggle with complex data patterns having non-linearity and uncertainties. By integrating soft clustering principles, the proposed work provides a flexible framework for imputing missing data by taking into account the underlying inherent data pattern. To address the missing data challenges, this paper presents a novel imputation technique called Radial Basis Kernel Intuitionistic Fuzzy Ⅽ-Means Imputation (KIFCMI), which builds upon the standard Intuitionistic Fuzzy Ⅽ-Means (IFCM) technique. KIFCMI explores the application of centroid-based imputation using IFCM by incorporating the RBF kernel-induced metric in the data space as a replacement for the original Euclidean norm metric. By employing a kernel function, KIFCMI enables the clustering of data that lacks linear separability within the original space, enabling the formation of homogeneous clusters in a space of higher dimensionality. The effectiveness of the proposed imputation technique is validated on ten diverse real-world datasets obtained from the Public Library UCI with 10% and 20% missing data. The comparative analyses of the proposed technique KIFCMI, is carried out with three conventional techniques, namely fuzzy c-means imputation (FCMI), kernelized fuzzy c-means imputation (KFCMI), and intuitionistic fuzzy c-means imputation (IFCMI). The experimental results using two performance measures, namely RMSE and MAE, showcase the robustness and versatility of the proposed technique across other imputation outcomes. This research paper contributes to the evolving landscape of missing data imputation, offering insights into the practical applications of fuzzy clustering techniques.

Fatal structure fire classification from building fire data using machine learning

PurposeThis study aims to develop a machine learning model to detect structure fire fatalities using a dataset comprising 11,341 cases from 2011 to 2019.Design/methodology/approachExploratory data analysis (EDA) was conducted prior to modelling, in which ten machine learning models were experimented with.FindingsThe main fatal structure fire risk factors were fires originating from bedrooms, living areas and the cooking/dining areas. The highest fatality rate (20.69%) was reported for fires ignited due to bedding (23.43%), despite a low fire incident rate (3.50%). Using 21 structure fire features, Random Forest (RF) yielded the best detection performance with 86% accuracy, followed by Decision Tree (DT) with bagging (accuracy = 84.7%).Research limitations/practical implicationsLimitations of the study are pertaining to data quality and grouping of categories in the data pre-processing stage, which could affect the performance of the models.Originality/valueThe study is the first of its kind to manipulate risk factors to detect fatal structure classification, particularly focussing on structure fire fatalities. Most of the previous studies examined the importance of fire risk factors and their relationship to the fire risk level.

Big Data and Machine Learning Framework for Temperature Forecasting

This research aims to develop a Supporting Big Data and ML with a Framework for temperature forecasting using Artificial Neural Networks (ANN). The proposed framework utilizes a massive amount of historical weather data to train the ANN model, which can effectively learn the complex non- correlations that are linear with the parameters and temperature. The input variables include various weather parameters, such as humidity, wind speed, precipitation, and pressure. The framework involves three main stages: data pre-processing, model training, and temperature forecasting. In the data pre-processing stage, the raw weather data is cleaned, normalized, and transformed into a suitable format for model training. The data is then split into training, validation, and testing sets to ensure model accuracy. In model instruction stage, the ANN trained model using a backpropagation algorithm to adjust affected by the inherent biases and model based on the input and output data. The training process is iterative, and Using the validation, the efficiency of the model is measured. set to prevent overfitting. Finally, in the temperature forecasting stage, the trained ANN model is used to predict the temperature for a given set of weather parameters. The accuracy of the temperature forecasting is evaluated using the testing set, and the results are compared to other forecasting methods, such as statistical methods and numerical weather prediction models. The proposed framework has several advantages over traditional temperature forecasting methods. Firstly, it utilizes a vast amount of data, which enhances the accuracy of the forecast. Secondly, the ANN model can learn the interactions between the input variables that are not linear and temperature, which cannot be captured by traditional statistical methods. Finally, the framework can be easily extended to incorporate additional weather parameters or to forecast other environmental variables. The results of this research show that the proposed framework can effectively forecast temperature with high accuracy, outperforming traditional statistical methods and numerical weather prediction models. Therefore, it has the potential to improve weather forecasting and contribute to various applications, such as agriculture, energy management, and transportation.

Performance of Various Naïve Bayes Using GridSearch Approach In Phishing Email Dataset

The background is the increasing cybersecurity threats in the form of phishing attacks that can be detrimental to individuals and organizations. The purpose of this research is to compare the performance of four Naive Bayes variants in classifying phishing emails with a method that involves a data pre-processing stage, phishing emails are collected, cleaned, and converted into appropriate numerical features. Next, the GridSearch approach was used to find the best parameters. This research objective is to understand how each Naive Bayes variant works on phishing email datasets. This phishing detection task is based on the following performance evaluation criteria such as accuracy, precision, recall, and F1-score. In this study, Bernoulli got the best accuracy of 97.34% but when the results obtained a hyperparameter, the results showed an increase with the most optimal results and the best performance is Bernoulli 97.38%. The research results are to provide an in-depth insight into the effectiveness of each variant of Naive Bayes in dealing with phishing email datasets and researchers in selecting the most suitable Naive Bayes variant for phishing detection tasks. In addition, the applied GridSearch method can guide how to find the best parameters for Naive Bayes models in other contexts. In summary, this study focuses on analyzing the performance of four variants of Naive Bayes Gaussian, Multinomial, Complement, and Bernoulli with the best algorithms Bernoulli 97.38%.

Analyzing Customers in E-Commerce Using Dempster-Shafer Method

This research explores the analysis of consumer sentiment in the context of e-commerce by applying the sophisticated Dempster-Shafer method. We started with the collection of more than 20,000 consumer reviews from various leading e-commerce platforms and continued with a detailed data pre-processing stage to obtain a clean and structured dataset. Next, we leverage the Dempster-Shafer method to represent and combine information from multiple sources, addressing uncertainty in diverse consumer opinions. The results of the sentiment analysis show that the Dempster-Shafer method achieves an accuracy of around 85%, with good evaluation metrics. Additionally, this research provides insight into the factors that influence consumers' views of products or services in the growing e-commerce context. The literature review also reveals the potential application of the Dempster-Shafer method in other aspects of e-commerce business, such as risk management and consumer trust. This research highlights the contribution of the Dempster-Shafer method in addressing uncertainty and complexity in consumer sentiment analysis, yielding a deep understanding of consumer perceptions, and enabling more accurate decision making in a dynamic e-commerce context. This research also provides a foundation for further development in consumer sentiment analysis and the application of the Dempster-Shafer method in e-commerce.

An adaptive serial cascaded autoencoder and LSTM with multivariate regression for ambient air quality prediction with improved flow direction algorithm

ABSTRACT Forecasting of air quality is an emerging process to evade the entailment of several defects for human as well as environmental resources. Because of the poor quality of air substances, air pollution occurs. Living beings and other economic resources get affected by this polluted air very frequently. Therefore, air quality prediction is a trendsetting method to maintain a healthy life and infrastructure. Though multiple existing models are implemented, managing high-level data and deploying such standard models become cumbersome. Rather than indoor air quality, the ambient (outdoor) air quality should require the prediction process as it exists in the open environment. Thus, an intelligent ambient air quality prediction model is needed, which is designed in this paper by adopting a heuristic-aided deep learning model. The original air data is initially fetched from the three diverse data sources. It is followed by the data pre-processing stage with standard techniques. Subsequently, the resultant data is given to Adaptive Serial Cascaded Autoencoder and Long Short-Term Memory (LSTM) with Multivariate Regression (ASCA-LSMR), in which some of the hyper-parameters are tuned by proposing the novel algorithm as Fitness-based Improved Flow Direction Algorithm (FIFDA) to produce the better prediction results. Finally, experimental results indicate that our method enables more accurate predictions than all the listed traditional models and performs better in predictive performance. The RMSE of the designed FIFDA-ASCA-LSMR method attains 31.9%, 33.5%, 6.66%, and 23.7% elevated than SSA-ASCA-LSMR, DHOA-ASCA-LSMR, EHO-ASCA-LSMR, and FDA-ASCA-LSMR, for dataset 2. Thus, the designed ambient air quality prediction model reveals better performance than the other baseline approaches.

A machine learning approach for the prediction of pore pressure using well log data of Hikurangi Tuaheni Zone of IODP Expedition 372, New Zealand

Pore pressure (PP) information plays an important role in analysing the geomechanical properties of the reservoir and hydrocarbon field development. PP prediction is an essential requirement to ensure safe drilling operations and it is a fundamental input for well design, and mud weight estimation for wellbore stability. However, the pore pressure trend prediction in complex geological provinces is challenging particularly at oceanic slope setting, where sedimentation rate is relatively high and PP can be driven by various complex geo-processes. To overcome these difficulties, an advanced machine learning (ML) tool is implemented in combination with empirical methods. The empirical method for PP prediction is comprised of data pre-processing and model establishment stage. Eaton's method and Porosity method have been used for PP calculation of the well U1517A located at Tuaheni Landslide Complex of Hikurangi Subduction zone of IODP expedition 372. Gamma-ray, sonic travel time, bulk density and sonic derived porosity are extracted from well log data for the theoretical framework construction. The normal compaction trend (NCT) curve analysis is used to check the optimum fitting of the low permeable zone data. The statistical analysis is done using the histogram analysis and Pearson correlation coefficient matrix with PP data series to identify potential input combinations for ML-based predictive model development. The dataset is prepared and divided into two parts: Training and Testing. The PP data and well log of borehole U1517A is pre-processed to scale in between [-1, +1] to fit into the input range of the non-linear activation/transfer function of the decision tree regression model. The Decision Tree Regression (DTR) algorithm is built and compared to the model performance to predict the PP and identify the overpressure zone in Hikurangi Tuaheni Zone of IODP Expedition 372.

Short-term PV power forecast using hybrid deep learning model and Variational Mode Decomposition

In recent decades, the dramatic transformation from conventional energy to renewables, such as photovoltaic (PV), has been extensively occurred to address the increasing electricity demand and environmental issues. Nevertheless, the operation of PV systems is adversely affected by the intermittence of meteorological factors, such as solar irradiance. Therefore, accurate PV power generation forecast has played a vital role to stimulate the integration of renewable energy sources into the power grid. This study proposes a novel scheme for short-term PV power forecast based on Transformer Neural Network (TransNN) integrated with Convolutional Neural Network (CNN). In addition, Variational Mode Decomposition (VMD) is adopted in the data pre-processing stage to enhance the forecast accuracy. The performance of the proposed model is validated utilizing two real-world datasets, and five benchmark models are dedicated to forecast outcome comparison. The predicted results indicated the superiority of the proposed model compared to the referenced models by achieving the Mean Absolute Error (MAE) values under 1 kW in all cases.

Hyperspectral image reconstruction via patch attention driven network.

Coded aperture snapshot spectral imaging (CASSI) captures 3D hyperspectral images (HSIs) with 2D compressive measurements. The recovery of HSIs from these measurements is an ill-posed problem. This paper proposes a novel, to our knowledge, network architecture for this inverse problem, which consists of a multilevel residual network driven by patch-wise attention and a data pre-processing method. Specifically, we propose the patch attention module to adaptively generate heuristic clues by capturing uneven feature distribution and global correlations of different regions. By revisiting the data pre-processing stage, we present a complementary input method that effectively integrates the measurements and coded aperture. Extensive simulation experiments illustrate that the proposed network architecture outperforms state-of-the-art methods.

Mobilenetv2_CA Lightweight Object Detection Network in Autonomous Driving

A lightweight network target detection algorithm was proposed, based on MobileNetv2_CA, focusing on the problem of high complexity, a large number of parameters, and the missed detection of small targets in the target detection network based on candidate regions and regression methods in autonomous driving scenarios. First, Mosaic image enhancement technology is used in the data pre-processing stage to enhance the feature extraction of small target scenes and complex scenes; second, the Coordinate Attention (CA) mechanism is embedded into the Mobilenetv2 backbone feature extraction network, combined with the PANet and Yolo detection heads for multi-scale feature fusion; finally, a Lightweight Object Detection Network is built. The experimental test results show that the designed network obtained the highest average detection accuracy of 81.43% on the Voc2007 + 2012 dataset, and obtained the highest average detection accuracy of 85.07% and a detection speed of 31.84 FPS on the KITTI dataset. The total amount of network parameters is only 39.5 M. This is beneficial to the engineering application of MobileNetv2 network in automatic driving.

Development of optimized ensemble classifier for dengue fever prediction and recommendation system

Dengue fever needs to be managed, which is considered as an important issue in health, nowadays. An efficient allocation of resources is mostly challenging owing to the external and internal components that have imposed non-linear fluctuations in the occurrence of dengue fever. Various machine learning and deep learning algorithms are developed for supporting the healthcare sector analysis, which has assured the efficiency and significance of the exact prediction of diseases and also ensured the minimal mortality rate. The core concept of this work is to implement an early-warning system for forecasting dengue fever and providing the proper recommendation system through intelligent techniques. Here, the enhanced prediction of dengue fever and recommendation is the main objective of this paper. In the data pre-processing stage, outlier removal and missing data filling are the main techniques to enhance the quality of data. Further, the optimal feature selection is performed using Neighbour Count-based Dragonfly Electric Fish Optimization (NC-DEFO). These acquired features are subjected to the Optimized Ensemble Classifier (OEC), in which “Convolutional Neural Network, Artificial Neural Network, and Support Vector Machine” are used according to the high ranking. Once the dengue fever in a particular area is predicted, the proper medical recommendation is provided in that area in terms of precaution steps, immunity-boosting remedies, drug prescription, spreading avoidance, etc. The evaluated results of the developed model with different comparative algorithms have shown efficient and superior outcomes from the implemented model, which seems to be accurate for the earlier diagnosis of dengue fever.