Research on Image Recognition Using Deep Learning Techniques

This study delves into the applications,challenges,and future directions of deep learning techniques in the field of image recognition.Deep learning,particularly Convolutional Neural Networks(CNNs),Recurrent Neural Networks(RNNs),and Generative Adversarial Networks(GANs),has become key to enhancing the precision and efficiency of image recognition.These models are capable of processing complex visual data,facilitating efficient feature extraction and image classification.However,acquiring and annotating high-quality,diverse datasets,addressing imbalances in datasets,and model training and optimization remain significant challenges in this domain.The paper proposes strategies for improving data augmentation,optimizing model architectures,and employing automated model optimization tools to address these challenges,while also emphasizing the importance of considering ethical issues in technological advancements.As technology continues to evolve,the application of deep learning in image recognition will further demonstrate its potent capability to solve complex problems,driving society towards more inclusive and diverse development.

A Comparison of Machine Learning Techniques in the Carpooling Problem

Urban traffic congestion is a severe and widely studied problem over the decade because of the negative impacts. However, in recent years some approaches emerge as proper and suitable solutions. The Carpooling initiative is one of the most representative efforts to propitiate a responsible use of particular vehicles. Thus, the paper introduces a carpooling model considering the users’ preference to reach an appropriate match among drivers and passengers. In particular, the paper conducts a study of 6 of the most avid classified techniques in machine learning to create a model for the selection of travel companions. The experimental results show the models’ precision and assess the best cases using Friedman’s test. Finally, the conclusions emphasize the relevance of the proposed study and suggest that it is necessary to extend the proposal with more drives and passengers’ data.

Optimal Placement and Sizing of Distributed Generations for Power Losses Minimization Using PSO-Based Deep Learning Techniques

The integration of distributed generations (DGs) into distribution systems (DSs) is increasingly becoming a solution for compensating for isolated local energy systems (ILESs). Additionally, distributed generations are used for self-consumption with excess energy injected into centralized grids (CGs). However, the improper sizing of renewable energy systems (RESs) exposes the entire system to power losses. This work presents an optimization of a system consisting of distributed generations. Firstly, PSO algorithms evaluate the size of the entire system on the IEEE bus 14 test standard. Secondly, the size of the system is allocated using improved Particles Swarm Optimization (IPSO). The convergence speed of the objective function enables a conjecture to be made about the robustness of the proposed system. The power and voltage profile on the IEEE 14-bus standard displays a decrease in power losses and an appropriate response to energy demands (EDs), validating the proposed method.

Complementary testing and machine learning techniques for the characterization and prediction of middle Permian tight gas sandstone reservoir quality in the northeastern Ordos Basin, China

In this study, an integrated approach for diagenetic facies classification, reservoir quality analysis and quantitative wireline log prediction of tight gas sandstones(TGSs) is introduced utilizing a combination of fit-for-purpose complementary testing and machine learning techniques. The integrated approach is specialized for the middle Permian Shihezi Formation TGSs in the northeastern Ordos Basin, where operators often face significant drilling uncertainty and increased exploration risks due to low porosities and micro-Darcy range permeabilities. In this study, detrital compositions and diagenetic minerals and their pore type assemblages were analyzed using optical light microscopy, cathodoluminescence, standard scanning electron microscopy, and X-ray diffraction. Different types of diagenetic facies were delineated on this basis to capture the characteristic rock properties of the TGSs in the target formation.A combination of He porosity and permeability measurements, mercury intrusion capillary pressure and nuclear magnetic resonance data was used to analyze the mechanism of heterogeneous TGS reservoirs.We found that the type, size and proportion of pores considerably varied between diagenetic facies due to differences in the initial depositional attributes and subsequent diagenetic alterations;these differences affected the size, distribution and connectivity of the pore network and varied the reservoir quality. Five types of diagenetic facies were classified:(i) grain-coating facies, which have minimal ductile grains, chlorite coatings that inhibit quartz overgrowths, large intergranular pores that dominate the pore network, the best pore structure and the greatest reservoir quality;(ii) quartz-cemented facies,which exhibit strong quartz overgrowths, intergranular porosity and a pore size decrease, resulting in the deterioration of the pore structure and reservoir quality;(iii) mixed-cemented facies, in which the cementation of various authigenic minerals increases the micropores, resulting in a poor pore structure and reservoir quality;(iv) carbonate-cemented facies and(v) tightly compacted facies, in which the intergranular pores are filled with carbonate cement and ductile grains;thus, the pore network mainly consists of micropores with small pore throat sizes, and the pore structure and reservoir quality are the worst. The grain-coating facies with the best reservoir properties are more likely to have high gas productivity and are the primary targets for exploration and development. The diagenetic facies were then translated into wireline log expressions(conventional and NMR logging). Finally, a wireline log quantitative prediction model of TGSs using convolutional neural network machine learning algorithms was established to successfully classify the different diagenetic facies.

Assessment of different machine learning techniques in predicting the compressive strength of self-compacting concrete

The compressive strength of self-compacting concrete(SCC)needs to be determined during the construction design process.This paper shows that the compressive strength of SCC(CS of SCC)can be successfully predicted from mix design and curing age by a machine learning(ML)technique named the Extreme Gradient Boosting(XGB)algorithm,including non-hybrid and hybrid models.Nine ML techniques,such as Linear regression(LR),K-Nearest Neighbors(KNN),Support Vector Machine(SVM),Decision Trees(DTR),Random Forest(RF),Gradient Boosting(GB),and Artificial Neural Network using two training algorithms LBFGS and SGD(denoted as ANN_LBFGS and ANN_SGD),are also compared with the XGB model.Moreover,the hybrid models of eight ML techniques and Particle Swarm Optimization(PSO)are constructed to highlight the reliability and accuracy of SCC compressive strength prediction by the XGB_PSO hybrid model.The highest number of SCC samples available in the literature is collected for building the ML techniques.Compared with previously published works’performance,the proposed XGB method,both hybrid and non-hybrid models,is the most reliable and robust of the examined techniques,and is more accurate than existing ML methods(R2=0.9644,RMSE=4.7801,and MAE=3.4832).Therefore,the XGB model can be used as a practical tool for engineers in predicting the CS of SCC.

Machine Learning Techniques for Software Maintainability Prediction:Accuracy Analysis

Maintaining software once implemented on the end-user side is laborious and,over its lifetime,is most often considerably more expensive than the initial software development.The prediction of software maintainability lias emerged as an important research topic to address industry expectations for reducing costs,in particular,maintenance costs.Researchers and practitioners have been working on proposing and identifying a variety of techniques ranging from statistical to machine learning(ML)for better prediction of software maintainability.This review has been carried out to analyze the empirical evidence on the accuracy of software product maintainability prediction(SPMP)using ML techniques.This paper analyzes and discusses the findings of 77 selected studies published from 2000 to 2018 according to the following criteria:maintainability prediction techniques,validation methods,accuracy criteria,overall accuracy of ML techniques,and the techniques offering the best performance.The review process followed the well-known syslematic review process.The results show that ML techniques are frequently used in predicting maintainability.In particular,artificial neural network(ANN),support vector machine/regression(SVM/R).regression&decision trees(DT),and fuzzy neuro fuzzy(FNF)techniques are more accurate in terms of PRED and MMRE.The N-fold and leave-one-out cross-validation methods,and the MMRE and PRED accuracy criteria are frequently used in empirical studies.In general,ML techniques outperformed non-machine learning techniques,e.g.,regression analysis(RA)techniques,while FNF outperformed SVM/R.DT.and ANN in most experiments.However,while many techniques were reported superior,no specific one can be identified as the best.

A Critical Analysis of Machine Learning and Deep Learning Methods for Cervical Cancer Screening

Cervical cancer is a serious public health issue worldwide, and early identification is crucial for better patient outcomes. Recent study has investigated how ML and DL approaches may be used to increase the accuracy of vagina tests. In this piece, we conducted a thorough review of 50 research studies that applied these techniques. Our investigation compared the outcomes to well-known screening techniques and concentrated on the datasets used and performance measurements reported. According to the research, convolutional neural networks and other deep learning approaches have potential for lowering false positives and boosting screening precision. Although several research used small sample sizes or constrained datasets, this raises questions about how applicable the findings are. This paper discusses the advantages and disadvantages of the articles that were chosen, as well as prospective topics for future research, to further the application of ml and dl in cervical cancer screening. The development of cervical cancer screening technologies that are more precise, accessible, and can lead to better public health outcomes is significantly affected by these findings.

Applying deep learning and benchmark machine learning algorithms for landslide susceptibility modelling in Rorachu river basin of Sikkim Himalaya, India

Landslide is considered as one of the most severe threats to human life and property in the hilly areas of the world.The number of landslides and the level of damage across the globe has been increasing over time.Therefore,landslide management is essential to maintain the natural and socio-economic dynamics of the hilly region.Rorachu river basin is one of the most landslide-prone areas of the Sikkim selected for the present study.The prime goal of the study is to prepare landslide susceptibility maps(LSMs)using computer-based advanced machine learning techniques and compare the performance of the models.To properly understand the existing spatial relation with the landslide,twenty factors,including triggering and causative factors,were selected.A deep learning algorithm viz.convolutional neural network model(CNN)and three popular machine learning techniques,i.e.,random forest model(RF),artificial neural network model(ANN),and bagging model,were employed to prepare the LSMs.Two separate datasets including training and validation were designed by randomly taken landslide and nonlandslide points.A ratio of 70:30 was considered for the selection of both training and validation points.Multicollinearity was assessed by tolerance and variance inflation factor,and the role of individual conditioning factors was estimated using information gain ratio.The result reveals that there is no severe multicollinearity among the landslide conditioning factors,and the triggering factor rainfall appeared as the leading cause of the landslide.Based on the final prediction values of each model,LSM was constructed and successfully portioned into five distinct classes,like very low,low,moderate,high,and very high susceptibility.The susceptibility class-wise distribution of landslides shows that more than 90%of the landslide area falls under higher landslide susceptibility grades.The precision of models was examined using the area under the curve(AUC)of the receiver operating characteristics(ROC)curve and statistical methods like root mean square error(RMSE)and mean absolute error(MAE).In both datasets(training and validation),the CNN model achieved the maximum AUC value of 0.903 and 0.939,respectively.The lowest value of RMSE and MAE also reveals the better performance of the CNN model.So,it can be concluded that all the models have performed well,but the CNN model has outperformed the other models in terms of precision.

Rock Strength Estimation Using Several Tree-Based ML Techniques

The uniaxial compressive strength(UCS)of rock is an essential property of rock material in different relevant applications,such as rock slope,tunnel construction,and foundation.It takes enormous time and effort to obtain the UCS values directly in the laboratory.Accordingly,an indirect determination of UCS through conducting several rock index tests that are easy and fast to carry out is of interest and importance.This study presents powerful boosting trees evaluation framework,i.e.,adaptive boosting machine,extreme gradient boosting machine(XGBoost),and category gradient boosting machine,for estimating the UCS of sandstone.Schmidt hammer rebound number,P-wave velocity,and point load index were chosen as considered factors to forecast UCS values of sandstone samples.Taylor diagrams and five regression metrics,including coefficient of determination(R2),root mean square error,mean absolute error,variance account for,and A-20 index,were used to evaluate and compare the performance of these boosting trees.The results showed that the proposed boosting trees are able to provide a high level of prediction capacity for the prepared database.In particular,itwas worth noting that XGBoost is the best model to predict sandstone strength and it achieved 0.999 training R^(2) and 0.958 testing R^(2).The proposed model had more outstanding capability than neural network with optimization techniques during training and testing phases.The performed variable importance analysis reveals that the point load index has a significant influence on predicting UCS of sandstone.

Machine learning approach to drivers of bank lending:evidence from an emerging economy

The study analyzes the performance of bank-specific characteristics,macroeconomic indicators,and global factors to predict the bank lending in Turkey for the period 2002Q4–2019Q2.The objective of this study is first,to clarify the possible nonlinear and nonparametric relationships between outstanding bank loans and bank-specific,macroeconomic,and global factors.Second,it aims to propose various machine learning algorithms that determine drivers of bank lending and benefits from the advantages of these techniques.The empirical findings indicate favorable evidence that the drivers of bank lending exhibit some nonlinearities.Additionally,partial dependence plots depict that numerous bank-specific characteristics and macroeconomic indicators tend to be important variables that influence bank lending behavior.The study’s findings have some policy implications for bank managers,regulatory authorities,and policymakers.

AI-Based Intelligent Model to Predict Epidemics Using Machine Learning Technique

The immediate international spread of severe acute respiratory syn-drome revealed the potential threat of infectious diseases in a closely integrated and interdependent world.When an outbreak occurs,each country must have a well-coordinated and preventative plan to address the situation.Information and Communication Technologies have provided innovative approaches to dealing with numerous facets of daily living.Although intelligent devices and applica-tions have become a vital part of our everyday lives,smart gadgets have also led to several physical and psychological health problems in modern society.Here,we used an artificial intelligence AI-based system for disease prediction using an Artificial Neural Network(ANN).The ANN improved the regularization of the classification model,hence increasing its accuracy.The unconstrained opti-mization model reduced the classifier’s cost function to obtain the lowest possible cost.To verify the performance of the intelligent system,we compared the out-comes of the suggested scheme with the results of previously proposed models.The proposed intelligent system achieved an accuracy of 0.89,and the miss rate 0.11 was higher than in previously proposed models.

Optimized Deep Learning-Inspired Model for the Diagnosis and Prediction of COVID-19

Detecting COVID-19 cases as early as possible became a critical issue that must be addressed to avoid the pandemic’s additional spread and early provide the appropriate treatment to the affected patients.This study aimed to develop a COVID-19 diagnosis and prediction(AIMDP)model that could identify patients with COVID-19 and distinguish it from other viral pneumonia signs detected in chest computed tomography(CT)scans.The proposed system uses convolutional neural networks(CNNs)as a deep learning technology to process hundreds of CT chest scan images and speeds up COVID-19 case prediction to facilitate its containment.We employed the whale optimization algorithm(WOA)to select the most relevant patient signs.A set of experiments validated AIMDP performance.It demonstrated the superiority of AIMDP in terms of the area under the curve-receiver operating characteristic(AUC-ROC)curve,positive predictive value(PPV),negative predictive rate(NPR)and negative predictive value(NPV).AIMDP was applied to a dataset of hundreds of real data and CT images,and it was found to achieve 96%AUC for diagnosing COVID-19 and 98%for overall accuracy.The results showed the promising performance of AIMDP for diagnosing COVID-19 when compared to other recent diagnosing and predicting models.

Solar cycle prediction using a long short-term memory deep learning model

In this paper,we propose a long short-term memory(LSTM)deep learning model to deal with the smoothed monthly sunspot number(SSN),aiming to address the problem whereby the prediction results of the existing sunspot prediction methods are not uniform and have large deviations.Our method optimizes the number of hidden nodes and batch sizes of the LSTM network structures to 19 and 20,respectively.The best length of time series and the value of the timesteps were then determined for the network training,and one-step and multi-step predictions for Cycle 22 to Cycle 24 were made using the well-established network.The results showed that the maximum root-mean-square error(RMSE)of the one-step prediction model was6.12 and the minimum was only 2.45.The maximum amplitude prediction error of the multi-step prediction was 17.2%and the minimum was only 3.0%.Finally,the next solar cycles(Cycle 25)peak amplitude was predicted to occur around 2023,with a peak value of about 114.3.The accuracy of this prediction method is better than that of the other commonly used methods,and the method has high applicability.

Machine learning of synaptic structure with neurons to promote tumor growth

In this paper,we use machine learning techniques to form a cancer cell model that displays the growth and promotion of synaptic and electrical signals.Here,such a technique can be applied directly to the spiking neural network of cancer cell synapses.The results show that machine learning techniques for the spiked network of cancer cell synapses have the powerful function of neuron models and potential supervisors for different implementations.The changes in the neural activity of tumor microenvironment caused by synaptic and electrical signals are described.It can be used to cancer cells and tumor training processes of neural networks to reproduce complex spatiotemporal dynamics and to mechanize the association of excitatory synaptic structures which are between tumors and neurons in the brain with complex human health behaviors.

Autism Spectrum Disorder Diagnosis Using Ensemble ML and Max Voting Techniques

Difficulty in communicating and interacting with other people are mainly due to the neurological disorder called autism spectrum disorder(ASD)diseases.These diseases can affect the nerves at any stage of the human being in childhood,adolescence,and adulthood.ASD is known as a behavioral disease due to the appearances of symptoms over thefirst two years that continue until adulthood.Most of the studies prove that the early detection of ASD helps improve the behavioral characteristics of patients with ASD.The detection of ASD is a very challenging task among various researchers.Machine learning(ML)algorithms still act very intelligent by learning the complex data and pre-dicting quality results.In this paper,ensemble ML techniques for the early detec-tion of ASD are proposed.In this detection,the dataset isfirst processed using three ML algorithms such as sequential minimal optimization with support vector machine,Kohonen self-organizing neural network,and random forest algorithm.The prediction results of these ML algorithms(ensemble)further use the bagging concept called max voting to predict thefinal result.The accuracy,sensitivity,and specificity of the proposed system are calculated using confusion matrix.The pro-posed ensemble technique performs better than state-of-the art ML algorithms.

Grey Wolf Optimizer Based Deep Learning for Pancreatic Nodule Detection

At an early point,the diagnosis of pancreatic cancer is mediocre,since the radiologist is skill deficient.Serious threats have been posed due to the above reasons,hence became mandatory for the need of skilled technicians.However,it also became a time-consuming process.Hence the need for automated diagnosis became mandatory.In order to identify the tumor accurately,this research pro-poses a novel Convolution Neural Network(CNN)based superior image classi-fication technique.The proposed deep learning classification strategy has a precision of 97.7%,allowing for more effective usage of the automatically exe-cuted feature extraction technique to diagnose cancer cells.Comparative analysis with CNN-Grey Wolf Optimization(GWO)is carried based on varied testing and training outcomes.The suggested study is carried out at a rate of 90%–10%,80%–20%,and 70%–30%,indicating the robustness of the proposed research work.Outcomes show that the suggested method is effective.GWO-CNN is reli-able and accurate relative to other detection methods available in the literatures.

Progressive Transfer Learning-based Deep Q Network for DDOS Defence in WSN

In The Wireless Multimedia Sensor Network(WNSMs)have achieved popularity among diverse communities as a result of technological breakthroughs in sensor and current gadgets.By utilising portable technologies,it achieves solid and significant results in wireless communication,media transfer,and digital transmission.Sensor nodes have been used in agriculture and industry to detect characteristics such as temperature,moisture content,and other environmental conditions in recent decades.WNSMs have also made apps easier to use by giving devices self-governing access to send and process data connected with appro-priate audio and video information.Many video sensor network studies focus on lowering power consumption and increasing transmission capacity,but the main demand is data reliability.Because of the obstacles in the sensor nodes,WMSN is subjected to a variety of attacks,including Denial of Service(DoS)attacks.Deep Convolutional Neural Network is designed with the stateaction relationship mapping which is used to identify the DDOS Attackers present in the Wireless Sensor Networks for Smart Agriculture.The Proposed work it performs the data collection about the traffic conditions and identifies the deviation between the network conditions such as packet loss due to network congestion and the presence of attackers in the network.It reduces the attacker detection delay and improves the detection accuracy.In order to protect the network against DoS assaults,an improved machine learning technique must be offered.An efficient Deep Neural Network approach is provided for detecting DoS in WMSN.The required parameters are selected using an adaptive particle swarm optimization technique.The ratio of packet transmission,energy consumption,latency,network length,and throughput will be used to evaluate the approach’s efficiency.

Challenge-Response Emotion Authentication Algorithm Using Modified Horizontal Deep Learning

Face authentication is an important biometric authentication method commonly used in security applications.It is vulnerable to different types of attacks that use authorized users’facial images and videos captured from social media to perform spoofing attacks and dynamic movements for penetrating secur-ity applications.This paper presents an innovative challenge-response emotions authentication model based on the horizontal ensemble technique.The proposed model provides high accurate face authentication process by challenging the authorized user using a random sequence of emotions to provide a specific response for every authentication trial with a different sequence of emotions.The proposed model is applied to the KDEF dataset using 10-fold cross-valida-tions.Several improvements are made to the proposed model.First,the VGG16 model is applied to the seven common emotions.Second,the system usability is enhanced by analyzing and selecting only the four common and easy-to-use emotions.Third,the horizontal ensemble technique is applied to enhance the emotion recognition accuracy and minimize the error during authen-tication processes.Finally,the Horizontal Ensemble Best N-Losses(HEBNL)is applied using challenge-response emotion to improve the authentication effi-ciency and minimize the computational power.The successive improvements implemented on the proposed model led to an improvement in the accuracy from 92.1%to 99.27%.

Digital Generative Multimedia Tool Theory (DGMTT): A Theoretical Postulation

The development of digital technology has brought about a substantial evolution in the multimedia field.The use of generative technologies to produce digital multimedia material is one of the newer developments in this field.The“Digital Generative Multimedia Tool Theory”(DGMTT)is therefore presented in this theoretical postulation by Timothy Ekeledirichukwu Onyejelem and Eric Msughter Aondover.It discusses and describes the principles behind the development and deployment of generative tools in multimedia creation.The DGMTT offers an all-encompassing structure for comprehending and evaluating the fundamentals and consequences of generative tools in the production of multimedia content.It provides information about the creation and use of these instruments,thereby promoting developments in the digital media industry.These tools create dynamic and interactive multimedia content by utilizing machine learning,artificial intelligence,and algorithms.This theory emphasizes how crucial it is to comprehend the fundamental ideas and principles of generative tools in order to use them efficiently when creating digital media content.A wide range of industries,including journalism,advertising,entertainment,education,and the arts,can benefit from the practical use of DGMTT.It gives artists the ability to use generative technologies to create unique and customized multimedia content for its viewers.

Assessment of groundwater quantity, quality, and associated health risk of the Tano river basin, Ghana

In the Tano River Basin,groundwater serves as a crucial resource;however,its quantity and quality with regard to trace elements and microbiological loadings remain poorly understood due to the lack of groundwater logs and limited water research.This study presents a comprehensive analysis of the Tano River Basin,focusing on three key objectives.First,it investigated the aquifer hydraulic parameters and the results showed significant spatial variations in borehole depths,yields,transmissivity,hydraulic conductivity,and specific capacity.Deeper boreholes were concentrated in the northeastern and southeastern zones,while geological formations,particu-larly the Apollonian Formation,exhibit a strong influence on borehole yields.The study identified areas with high transmissivity and hydraulic conductivity in the southern and eastern regions,suggesting good groundwater avail-ability and suitability for sustainable water supply.Sec-ondly,the research investigated the groundwater quality and observed that the majority of borehole samples fall within WHO(Guidelines for Drinking-water Quality,Environmental Health Criteria,Geneva,2011,2017.http://www.who.int)limit.However,some samples have pH levels below the standards,although the groundwater generally qualifies as freshwater.The study further explores hydrochemical facies and health risk assessment,highlighting the dominance of Ca–HCO3 water type.Trace element analysis reveals minimal health risks from most elements,with chromium(Cr)as the primary contributor to chronic health risk.Overall,this study has provided a key insights into the Tano River Basin’s hydrogeology and associated health risks.The outcome of this research has contributed to the broader understanding of hydrogeologi-cal dynamics and the importance of managing groundwater resources sustainably in complex geological environments.