Sentence classification is the process of categorizing a sentence based on the context of the sentence.Sentence categorization requires more semantic highlights than other tasks,such as dependence parsing,which requir...Sentence classification is the process of categorizing a sentence based on the context of the sentence.Sentence categorization requires more semantic highlights than other tasks,such as dependence parsing,which requires more syntactic elements.Most existing strategies focus on the general semantics of a conversation without involving the context of the sentence,recognizing the progress and comparing impacts.An ensemble pre-trained language model was taken up here to classify the conversation sentences from the conversation corpus.The conversational sentences are classified into four categories:information,question,directive,and commission.These classification label sequences are for analyzing the conversation progress and predicting the pecking order of the conversation.Ensemble of Bidirectional Encoder for Representation of Transformer(BERT),Robustly Optimized BERT pretraining Approach(RoBERTa),Generative Pre-Trained Transformer(GPT),DistilBERT and Generalized Autoregressive Pretraining for Language Understanding(XLNet)models are trained on conversation corpus with hyperparameters.Hyperparameter tuning approach is carried out for better performance on sentence classification.This Ensemble of Pre-trained Language Models with a Hyperparameter Tuning(EPLM-HT)system is trained on an annotated conversation dataset.The proposed approach outperformed compared to the base BERT,GPT,DistilBERT and XLNet transformer models.The proposed ensemble model with the fine-tuned parameters achieved an F1_score of 0.88.展开更多
Social media outlets deliver customers a medium for communication,exchange,and expression of their thoughts with others.The advent of social networks and the fast escalation of the quantity of data have created opport...Social media outlets deliver customers a medium for communication,exchange,and expression of their thoughts with others.The advent of social networks and the fast escalation of the quantity of data have created opportunities for textual evaluation.Utilising the user corpus,characteristics of social platform users,and other data,academic research may accurately discern the personality traits of users.This research examines the traits of consumer personalities.Usually,personality tests administered by psychological experts via interviews or self-report questionnaires are costly,time-consuming,complex,and labour-intensive.Currently,academics in computational linguistics are increasingly focused on predicting personality traits from social media data.An individual’s personality comprises their traits and behavioral habits.To address this distinction,we propose a novel LSTMapproach(BERT-LIWC-LSTM)that simultaneously incorporates users’enduring and immediate personality characteristics for textual personality recognition.Long-termPersonality Encoding in the proposed paradigmcaptures and represents persisting personality traits.Short-termPersonality Capturing records changing personality states.Experimental results demonstrate that the designed BERT-LIWC-LSTM model achieves an average improvement in accuracy of 3.41% on the Big Five dataset compared to current methods,thereby justifying the efficacy of encoding both stable and dynamic personality traits simultaneously through long-and short-term feature interaction.展开更多
Traffic signs are basic security workplaces making the rounds,which expects a huge part in coordinating busy time gridlock direct,ensuring the pros-perity of the road and dealing with the smooth segment of vehicles and...Traffic signs are basic security workplaces making the rounds,which expects a huge part in coordinating busy time gridlock direct,ensuring the pros-perity of the road and dealing with the smooth segment of vehicles and indivi-duals by walking,etc.As a segment of the clever transportation structure,the acknowledgment of traffic signs is basic for the driving assistance system,traffic sign upkeep,self-administering driving,and various spaces.There are different assessments turns out achieved for traffic sign acknowledgment in the world.However,most of the works are only for explicit arrangements of traffic signs,for example,beyond what many would consider a possible sign.Traffic sign recognizable proof is generally seen as trying on account of various complexities,for example,extended establishments of traffic sign pictures.Two critical issues exist during the time spent identification(ID)and affirmation of traffic signals.Road signs are occasionally blocked not entirely by various vehicles and various articles are accessible in busy time gridlock scenes which make the signed acknowledgment hard and walkers,various vehicles,constructions,and loads up may frustrate the ID structure by plans like that of road signs.Also concealing information from traffic scene pictures is affected by moving light achieved by environment conditions,time(day-night),and shadowing.Traffic sign revelation and affirmation structure has two guideline sorts out:The essential stage incorpo-rates the traffic sign limitation and the resulting stage portrays the perceived traffic signs into a particular class.展开更多
Energy efficiency is the prime concern in Wireless Sensor Networks(WSNs) as maximized energy consumption without essentially limits the energy stability and network lifetime. Clustering is the significant approach ess...Energy efficiency is the prime concern in Wireless Sensor Networks(WSNs) as maximized energy consumption without essentially limits the energy stability and network lifetime. Clustering is the significant approach essential for minimizing unnecessary transmission energy consumption with sustained network lifetime. This clustering process is identified as the Non-deterministic Polynomial(NP)-hard optimization problems which has the maximized probability of being solved through metaheuristic algorithms.This adoption of hybrid metaheuristic algorithm concentrates on the identification of the optimal or nearoptimal solutions which aids in better energy stability during Cluster Head(CH) selection. In this paper,Hybrid Seagull and Whale Optimization Algorithmbased Dynamic Clustering Protocol(HSWOA-DCP)is proposed with the exploitation benefits of WOA and exploration merits of SEOA to optimal CH selection for maintaining energy stability with prolonged network lifetime. This HSWOA-DCP adopted the modified version of SEagull Optimization Algorithm(SEOA) to handle the problem of premature convergence and computational accuracy which is maximally possible during CH selection. The inclusion of SEOA into WOA improved the global searching capability during the selection of CH and prevents worst fitness nodes from being selected as CH, since the spiral attacking behavior of SEOA is similar to the bubble-net characteristics of WOA. This CH selection integrates the spiral attacking principles of SEOA and contraction surrounding mechanism of WOA for improving computation accuracy to prevent frequent election process. It also included the strategy of levy flight strategy into SEOA for potentially avoiding premature convergence to attain better trade-off between the rate of exploration and exploitation in a more effective manner. The simulation results of the proposed HSWOADCP confirmed better network survivability rate, network residual energy and network overall throughput on par with the competitive CH selection schemes under different number of data transmission rounds.The statistical analysis of the proposed HSWOA-DCP scheme also confirmed its energy stability with respect to ANOVA test.展开更多
Due to its complexity and involvement of numerous stakeholders,the pharmaceutical supply chain presents many challenges that companies must overcome to deliver necessary medications to patients efficiently.The pharmac...Due to its complexity and involvement of numerous stakeholders,the pharmaceutical supply chain presents many challenges that companies must overcome to deliver necessary medications to patients efficiently.The pharmaceutical supply chain poses different challenging issues,encompasses supply chain visibility,cold-chain shipping,drug counterfeiting,and rising prescription drug prices,which can considerably surge out-of-pocket patient costs.Blockchain(BC)offers the technical base for such a scheme,as it could track legitimate drugs and avoid fake circulation.The designers presented the procedure of BC with fabric for creating a secured drug supplychain management(DSCM)method.With this motivation,the study presents a new blockchain with optimal deep learning-enabled DSCM and recommendation scheme(BCODL-DSCMRS)for Pharmaceutical Industries.Firstly,Hyperledger fabric is used for DSC management,enabling effective tracking processes in the smart pharmaceutical industry.In addition,a hybrid deep belief network(HDBN)model is used to suggest the best or top-rated medicines to healthcare providers and consumers.The spotted hyena optimizer(SHO)algorithm is used to optimize the performance of the HDBN model.The design of the HSO algorithm for tuning the HDBN model demonstrates the novelty of the work.The presented model is tested on the UCI repository’s open-access drug reviews database.展开更多
The term Epilepsy refers to a most commonly occurring brain disorder after a migraine.Early identification of incoming seizures significantly impacts the lives of people with Epilepsy.Automated detection of epileptic ...The term Epilepsy refers to a most commonly occurring brain disorder after a migraine.Early identification of incoming seizures significantly impacts the lives of people with Epilepsy.Automated detection of epileptic seizures(ES)has dramatically improved the life quality of the patients.Recent Electroencephalogram(EEG)related seizure detection mechanisms encountered several difficulties in real-time.The EEGs are the non-stationary signal,and seizure patternswould changewith patients and recording sessions.Further,EEG data were disposed to wide noise varieties that adversely moved the recognition accuracy of ESs.Artificial intelligence(AI)methods in the domain of ES analysis use traditional deep learning(DL),and machine learning(ML)approaches.This article introduces an Oppositional Aquila Optimizer-based Feature Selection with Deep Belief Network for Epileptic Seizure Detection(OAOFS-DBNECD)technique using EEG signals.The primary aim of the presented OAOFS-DBNECD system is to categorize and classify the presence of ESs.The suggested OAOFS-DBNECD technique transforms the EEG signals into.csv format at the initial stage.Next,the OAOFS technique selects an optimal subset of features using the preprocessed data.For seizure classification,the presented OAOFS-DBNECD technique applies Artificial Ecosystem Optimizer(AEO)with a deep belief network(DBN)model.An extensive range of simulations was performed on the benchmark dataset to ensure the enhanced performance of the presented OAOFS-DBNECD algorithm.The comparison study shows the significant outcomes of the OAOFS-DBNECD approach over other methodologies.In addition,the result of the suggested approach has been evaluated using the CHB-MIT database,and the findings demonstrate accuracy of 97.81%.These findings confirmed the best seizure categorization accuracy on the EEG data considered.展开更多
In healthcare systems,the Internet of Things(IoT)innovation and development approached new ways to evaluate patient data.A cloud-based platform tends to process data generated by IoT medical devices instead of high st...In healthcare systems,the Internet of Things(IoT)innovation and development approached new ways to evaluate patient data.A cloud-based platform tends to process data generated by IoT medical devices instead of high storage,and computational hardware.In this paper,an intelligent healthcare system has been proposed for the prediction and severity analysis of lung disease from chest computer tomography(CT)images of patients with pneumonia,Covid-19,tuberculosis(TB),and cancer.Firstly,the CT images are captured and transmitted to the fog node through IoT devices.In the fog node,the image gets modified into a convenient and efficient format for further processing.advanced encryption Standard(AES)algorithm serves a substantial role in IoT and fog nodes for preventing data from being accessed by other operating systems.Finally,the preprocessed image can be classified automatically in the cloud by using various transfer and ensemble learning models.Herein different pre-trained deep learning architectures(Inception-ResNet-v2,VGG-19,ResNet-50)used transfer learning is adopted for feature extraction.The softmax of heterogeneous base classifiers assists to make individual predictions.As a meta-classifier,the ensemble approach is employed to obtain final optimal results.Disease predicted image is consigned to the recurrent neural network with long short-term memory(RNN-LSTM)for severity analysis,and the patient is directed to seek therapy based on the outcome.The proposed method achieved 98.6%accuracy,0.978 precision,0.982 recalls,and 0.974 F1-score on five class classifications.The experimental findings reveal that the proposed framework assists medical experts with lung disease screening and provides a valuable second perspective.展开更多
Attacks on the cyber space is getting exponential in recent times.Illegal penetrations and breaches are real threats to the individuals and organizations.Conventional security systems are good enough to detect the kno...Attacks on the cyber space is getting exponential in recent times.Illegal penetrations and breaches are real threats to the individuals and organizations.Conventional security systems are good enough to detect the known threats but when it comes to Advanced Persistent Threats(APTs)they fails.These APTs are targeted,more sophisticated and very persistent and incorporates lot of evasive techniques to bypass the existing defenses.Hence,there is a need for an effective defense system that can achieve a complete reliance of security.To address the above-mentioned issues,this paper proposes a novel honeypot system that tracks the anonymous behavior of the APT threats.The key idea of honeypot leverages the concepts of graph theory to detect such targeted attacks.The proposed honey-pot is self-realizing,strategic assisted which withholds the APTs actionable tech-niques and observes the behavior for analysis and modelling.The proposed graph theory based self learning honeypot using the resultsγ(C(n,1)),γc(C(n,1)),γsc(C(n,1))outperforms traditional techniques by detecting APTs behavioral with detection rate of 96%.展开更多
The detection of cyber threats has recently been a crucial research domain as the internet and data drive people’s livelihood.Several cyber-attacks lead to the compromise of data security.The proposed system offers c...The detection of cyber threats has recently been a crucial research domain as the internet and data drive people’s livelihood.Several cyber-attacks lead to the compromise of data security.The proposed system offers complete data protection from Advanced Persistent Threat(APT)attacks with attack detection and defence mechanisms.The modified lateral movement detection algorithm detects the APT attacks,while the defence is achieved by the Dynamic Deception system that makes use of the belief update algorithm.Before termination,every cyber-attack undergoes multiple stages,with the most prominent stage being Lateral Movement(LM).The LM uses a Remote Desktop protocol(RDP)technique to authenticate the unauthorised host leaving footprints on the network and host logs.An anomaly-based approach leveraging the RDP event logs on Windows is used for detecting the evidence of LM.After extracting various feature sets from the logs,the RDP sessions are classified using machine-learning techniques with high recall and precision.It is found that the AdaBoost classifier offers better accuracy,precision,F1 score and recall recording 99.9%,99.9%,0.99 and 0.98%.Further,a dynamic deception process is used as a defence mechanism to mitigateAPTattacks.A hybrid encryption communication,dynamic(Internet Protocol)IP address generation,timing selection and policy allocation are established based on mathematical models.A belief update algorithm controls the defender’s action.The performance of the proposed system is compared with the state-of-the-art models.展开更多
Deep Learning is one of the most popular computer science techniques,with applications in natural language processing,image processing,pattern iden-tification,and various otherfields.Despite the success of these deep ...Deep Learning is one of the most popular computer science techniques,with applications in natural language processing,image processing,pattern iden-tification,and various otherfields.Despite the success of these deep learning algorithms in multiple scenarios,such as spam detection,malware detection,object detection and tracking,face recognition,and automatic driving,these algo-rithms and their associated training data are rather vulnerable to numerous security threats.These threats ultimately result in significant performance degradation.Moreover,the supervised based learning models are affected by manipulated data known as adversarial examples,which are images with a particular level of noise that is invisible to humans.Adversarial inputs are introduced to purposefully confuse a neural network,restricting its use in sensitive application areas such as bio-metrics applications.In this paper,an optimized defending approach is proposed to recognize the adversarial iris examples efficiently.The Curvelet Transform Denoising method is used in this defense strategy,which examines every sub-band of the adversarial images and reproduces the image that has been changed by the attacker.The salient iris features are retrieved from the reconstructed iris image by using a pretrained Convolutional Neural Network model(VGG 16)followed by Multiclass classification.The classification is performed by using Support Vector Machine(SVM)which uses Particle Swarm Optimization method(PSO-SVM).The proposed system is tested when classifying the adversarial iris images affected by various adversarial attacks such as FGSM,iGSM,and Deep-fool methods.An experimental result on benchmark iris dataset,namely IITD,produces excellent outcomes with the highest accuracy of 95.8%on average.展开更多
Data fusion generates fused data by combining multiple sources,resulting in information that is more consistent,accurate,and useful than any individual source and more reliable and consistent than the raw original dat...Data fusion generates fused data by combining multiple sources,resulting in information that is more consistent,accurate,and useful than any individual source and more reliable and consistent than the raw original data,which are often imperfect,inconsistent,complex,and uncertain.Traditional data fusion methods like probabilistic fusion,set-based fusion,and evidential belief reasoning fusion methods are computationally complex and require accurate classification and proper handling of raw data.Data fusion is the process of integrating multiple data sources.Data filtering means examining a dataset to exclude,rearrange,or apportion data according to the criteria.Different sensors generate a large amount of data,requiring the development of machine learning(ML)algorithms to overcome the challenges of traditional methods.The advancement in hardware acceleration and the abundance of data from various sensors have led to the development of machine learning(ML)algorithms,expected to address the limitations of traditional methods.However,many open issues still exist as machine learning algorithms are used for data fusion.From the literature,nine issues have been identified irrespective of any application.The decision-makers should pay attention to these issues as data fusion becomes more applicable and successful.A fuzzy analytical hierarchical process(FAHP)enables us to handle these issues.It helps to get the weights for each corresponding issue and rank issues based on these calculated weights.The most significant issue identified is the lack of deep learning models used for data fusion that improve accuracy and learning quality weighted 0.141.The least significant one is the cross-domain multimodal data fusion weighted 0.076 because the whole semantic knowledge for multimodal data cannot be captured.展开更多
An ad-hoc sensor network(ASN)is a group of sensing nodes that transmit data over a wireless link to a target node,direct or indirect,through a series of nodes.ASN becomes a high-risk group for several security exploit...An ad-hoc sensor network(ASN)is a group of sensing nodes that transmit data over a wireless link to a target node,direct or indirect,through a series of nodes.ASN becomes a high-risk group for several security exploits due to the sensor node’s limited resources.Internal threats are more challenging to protect against than external attacks.The nodes are grouped,and calculate each node’s trust level.The trust level is the result of combining internal and external trust degrees.Cluster heads(CH)are chosen based on the anticipated trust levels.The communications are then digitally signed by the source,encoded using a key pair given by a trustworthy CH,decoded by the recipient,and supervised by verifications.It authenticates the technique by identifying the presence of both the transmitter and the recipient.Our approach looks for a trustworthy neighboring node that meets the trust threshold condition to authenticate the key produced.The companion node reaffirms the node’s reliability by getting the public-key certification.The seeking sensor node and the certification issuer node must have a close and trusting relationship.The results of the proposed hybrid authentication using a node trustworthy(HANT)system are modeled and tested,and the suggested approach outperforms conventional trust-based approaches in throughput,latency,lifetime,and vulnerability methods.展开更多
Energy conservation has become a significant consideration in wireless sensor networks(WSN).In the sensor network,the sensor nodes have internal batteries,and as a result,they expire after a certain period.As a result,...Energy conservation has become a significant consideration in wireless sensor networks(WSN).In the sensor network,the sensor nodes have internal batteries,and as a result,they expire after a certain period.As a result,expanding the life duration of sensing devices by improving data depletion in an effective and sustainable energy-efficient way remains a challenge.Also,the clustering strategy employs to enhance or extend the life cycle of WSNs.We identify the supervisory head node(SH)or cluster head(CH)in every grouping considered the feasible strategy for power-saving route discovery in the clustering model,which diminishes the communication overhead in the WSN.However,the critical issue was determining the best SH for ensuring timely communication services.Our secure and energy concise route revamp technology(SECRET)protocol involves selecting an energy-concise cluster head(ECH)and route revamping to optimize navigation.The sensors transmit information over the ECH,which delivers the information to the base station via the determined optimal path using our strategy for effective data transmission.We modeled our methods to accom-plish power-efficient multi-hop routing.Furthermore,protected navigation helps to preserve energy when routing.The suggested solution improves energy savings,packet delivery ratio(PDR),route latency(RL),network lifetime(NL),and scalability.展开更多
Forested areas are extremely vulnerable to disasters leading to environmental destruction.Forest Fire is one among them which requires immediate attention.There are lot of works done by authors where Wireless Sensors ...Forested areas are extremely vulnerable to disasters leading to environmental destruction.Forest Fire is one among them which requires immediate attention.There are lot of works done by authors where Wireless Sensors and IoT have been used for forest fire monitoring.So,towards monitoring the forest fire and managing the energy efficiently in IoT,Energy Efficient Routing Protocol for Low power lossy networks(E-RPL)was developed.There were challenges about the scalability of the network resulting in a large end-to-end delay and less packet delivery which led to the development of Aggregator-based Energy Efficient RPL with Data Compression(CAAERPL).Though CAA-ERPL proved effective in terms of reduced packet delivery,less energy consumption,and increased packet delivery ratio for varying number of nodes,there is still challenge in the selection of aggregator which is based purely on probability percentage of nodes.There has been research work where fuzzy logic been employed for Mobile Ad-hoc Routing,RPL routing and cluster head selection in Wireless Sensor.There has been no work where fuzzy logic is employed for aggregator selection in Energy Efficient RPL.So accordingly,we here have proposed Fuzzy Based Aggregator selection in Energy-efficient RPL for region thereby forming DODAG for communicating to Fog/Edge.We here have developed fuzzy inference rules for selecting the aggregator based on strength which takes residual power,Node degree,and Expected Transmission Count(ETX)as input metrics.The Fuzzy Aggregator Energy Efficient RPL(FA-ERPL)based on fuzzy inference rules were analysed against E-RPL in terms of scalability(First and Half Node die),Energy Consumption,and aggregator node energy deviation.From the analysis,it was found that FA-ERPL performed better than E-RPL.These were simulated using MATLAB and results.展开更多
Due to latest advancements in the field of remote sensing,it becomes easier to acquire high quality images by the use of various satellites along with the sensing components.But the massive quantity of data poses a ch...Due to latest advancements in the field of remote sensing,it becomes easier to acquire high quality images by the use of various satellites along with the sensing components.But the massive quantity of data poses a challenging issue to store and effectively transmit the remote sensing images.Therefore,image compression techniques can be utilized to process remote sensing images.In this aspect,vector quantization(VQ)can be employed for image compression and the widely applied VQ approach is Linde–Buzo–Gray(LBG)which creates a local optimum codebook for image construction.The process of constructing the codebook can be treated as the optimization issue and the metaheuristic algorithms can be utilized for resolving it.With this motivation,this article presents an intelligent satin bowerbird optimizer based compression technique(ISBO-CT)for remote sensing images.The goal of the ISBO-CT technique is to proficiently compress the remote sensing images by the effective design of codebook.Besides,the ISBO-CT technique makes use of satin bowerbird optimizer(SBO)with LBG approach is employed.The design of SBO algorithm for remote sensing image compression depicts the novelty of the work.To showcase the enhanced efficiency of ISBO-CT approach,an extensive range of simulations were applied and the outcomes reported the optimum performance of ISBO-CT technique related to the recent state of art image compression approaches.展开更多
In recent times,Internet of Things(IoT)has become a hot research topic and it aims at interlinking several sensor-enabled devices mainly for data gathering and tracking applications.Wireless Sensor Network(WSN)is an i...In recent times,Internet of Things(IoT)has become a hot research topic and it aims at interlinking several sensor-enabled devices mainly for data gathering and tracking applications.Wireless Sensor Network(WSN)is an important component in IoT paradigm since its inception and has become the most preferred platform to deploy several smart city application areas like home automation,smart buildings,intelligent transportation,disaster management,and other such IoT-based applications.Clustering methods are widely-employed energy efficient techniques with a primary purpose i.e.,to balance the energy among sensor nodes.Clustering and routing processes are considered as Non-Polynomial(NP)hard problems whereas bio-inspired techniques have been employed for a known time to resolve such problems.The current research paper designs an Energy Efficient Two-Tier Clustering with Multi-hop Routing Protocol(EETTC-MRP)for IoT networks.The presented EETTC-MRP technique operates on different stages namely,tentative Cluster Head(CH)selection,final CH selection,and routing.In first stage of the proposed EETTC-MRP technique,a type II fuzzy logic-based tentative CH(T2FL-TCH)selection is used.Subsequently,Quantum Group Teaching Optimization Algorithm-based Final CH selection(QGTOA-FCH)technique is deployed to derive an optimum group of CHs in the network.Besides,Political Optimizer based Multihop Routing(PO-MHR)technique is also employed to derive an optimal selection of routes between CHs in the network.In order to validate the efficacy of EETTC-MRP method,a series of experiments was conducted and the outcomes were examined under distinct measures.The experimental analysis infers that the proposed EETTC-MRP technique is superior to other methods under different measures.展开更多
The exponential growth of data necessitates an effective data storage scheme,which helps to effectively manage the large quantity of data.To accomplish this,Deoxyribonucleic Acid(DNA)digital data storage process can b...The exponential growth of data necessitates an effective data storage scheme,which helps to effectively manage the large quantity of data.To accomplish this,Deoxyribonucleic Acid(DNA)digital data storage process can be employed,which encodes and decodes binary data to and from synthesized strands of DNA.Vector quantization(VQ)is a commonly employed scheme for image compression and the optimal codebook generation is an effective process to reach maximum compression efficiency.This article introduces a newDNAComputingwithWater StriderAlgorithm based Vector Quantization(DNAC-WSAVQ)technique for Data Storage Systems.The proposed DNAC-WSAVQ technique enables encoding data using DNA computing and then compresses it for effective data storage.Besides,the DNAC-WSAVQ model initially performsDNA encoding on the input images to generate a binary encoded form.In addition,aWater Strider algorithm with Linde-Buzo-Gray(WSA-LBG)model is applied for the compression process and thereby storage area can be considerably minimized.In order to generate optimal codebook for LBG,the WSA is applied to it.The performance validation of the DNAC-WSAVQ model is carried out and the results are inspected under several measures.The comparative study highlighted the improved outcomes of the DNAC-WSAVQ model over the existing methods.展开更多
Image Captioning is an emergent topic of research in the domain of artificial intelligence(AI).It utilizes an integration of Computer Vision(CV)and Natural Language Processing(NLP)for generating the image descriptions...Image Captioning is an emergent topic of research in the domain of artificial intelligence(AI).It utilizes an integration of Computer Vision(CV)and Natural Language Processing(NLP)for generating the image descriptions.Itfinds use in several application areas namely recommendation in editing applications,utilization in virtual assistance,etc.The development of NLP and deep learning(DL)modelsfind useful to derive a bridge among the visual details and textual semantics.In this view,this paper introduces an Oppositional Harris Hawks Optimization with Deep Learning based Image Captioning(OHHO-DLIC)technique.The OHHO-DLIC technique involves the design of distinct levels of pre-processing.Moreover,the feature extraction of the images is carried out by the use of EfficientNet model.Furthermore,the image captioning is performed by bidirectional long short term memory(BiLSTM)model,comprising encoder as well as decoder.At last,the oppositional Harris Hawks optimization(OHHO)based hyperparameter tuning process is performed for effectively adjusting the hyperparameter of the EfficientNet and BiLSTM models.The experimental analysis of the OHHO-DLIC technique is carried out on the Flickr 8k Dataset and a comprehensive comparative analysis highlighted the better performance over the recent approaches.展开更多
文摘Sentence classification is the process of categorizing a sentence based on the context of the sentence.Sentence categorization requires more semantic highlights than other tasks,such as dependence parsing,which requires more syntactic elements.Most existing strategies focus on the general semantics of a conversation without involving the context of the sentence,recognizing the progress and comparing impacts.An ensemble pre-trained language model was taken up here to classify the conversation sentences from the conversation corpus.The conversational sentences are classified into four categories:information,question,directive,and commission.These classification label sequences are for analyzing the conversation progress and predicting the pecking order of the conversation.Ensemble of Bidirectional Encoder for Representation of Transformer(BERT),Robustly Optimized BERT pretraining Approach(RoBERTa),Generative Pre-Trained Transformer(GPT),DistilBERT and Generalized Autoregressive Pretraining for Language Understanding(XLNet)models are trained on conversation corpus with hyperparameters.Hyperparameter tuning approach is carried out for better performance on sentence classification.This Ensemble of Pre-trained Language Models with a Hyperparameter Tuning(EPLM-HT)system is trained on an annotated conversation dataset.The proposed approach outperformed compared to the base BERT,GPT,DistilBERT and XLNet transformer models.The proposed ensemble model with the fine-tuned parameters achieved an F1_score of 0.88.
文摘Social media outlets deliver customers a medium for communication,exchange,and expression of their thoughts with others.The advent of social networks and the fast escalation of the quantity of data have created opportunities for textual evaluation.Utilising the user corpus,characteristics of social platform users,and other data,academic research may accurately discern the personality traits of users.This research examines the traits of consumer personalities.Usually,personality tests administered by psychological experts via interviews or self-report questionnaires are costly,time-consuming,complex,and labour-intensive.Currently,academics in computational linguistics are increasingly focused on predicting personality traits from social media data.An individual’s personality comprises their traits and behavioral habits.To address this distinction,we propose a novel LSTMapproach(BERT-LIWC-LSTM)that simultaneously incorporates users’enduring and immediate personality characteristics for textual personality recognition.Long-termPersonality Encoding in the proposed paradigmcaptures and represents persisting personality traits.Short-termPersonality Capturing records changing personality states.Experimental results demonstrate that the designed BERT-LIWC-LSTM model achieves an average improvement in accuracy of 3.41% on the Big Five dataset compared to current methods,thereby justifying the efficacy of encoding both stable and dynamic personality traits simultaneously through long-and short-term feature interaction.
文摘Traffic signs are basic security workplaces making the rounds,which expects a huge part in coordinating busy time gridlock direct,ensuring the pros-perity of the road and dealing with the smooth segment of vehicles and indivi-duals by walking,etc.As a segment of the clever transportation structure,the acknowledgment of traffic signs is basic for the driving assistance system,traffic sign upkeep,self-administering driving,and various spaces.There are different assessments turns out achieved for traffic sign acknowledgment in the world.However,most of the works are only for explicit arrangements of traffic signs,for example,beyond what many would consider a possible sign.Traffic sign recognizable proof is generally seen as trying on account of various complexities,for example,extended establishments of traffic sign pictures.Two critical issues exist during the time spent identification(ID)and affirmation of traffic signals.Road signs are occasionally blocked not entirely by various vehicles and various articles are accessible in busy time gridlock scenes which make the signed acknowledgment hard and walkers,various vehicles,constructions,and loads up may frustrate the ID structure by plans like that of road signs.Also concealing information from traffic scene pictures is affected by moving light achieved by environment conditions,time(day-night),and shadowing.Traffic sign revelation and affirmation structure has two guideline sorts out:The essential stage incorpo-rates the traffic sign limitation and the resulting stage portrays the perceived traffic signs into a particular class.
文摘Energy efficiency is the prime concern in Wireless Sensor Networks(WSNs) as maximized energy consumption without essentially limits the energy stability and network lifetime. Clustering is the significant approach essential for minimizing unnecessary transmission energy consumption with sustained network lifetime. This clustering process is identified as the Non-deterministic Polynomial(NP)-hard optimization problems which has the maximized probability of being solved through metaheuristic algorithms.This adoption of hybrid metaheuristic algorithm concentrates on the identification of the optimal or nearoptimal solutions which aids in better energy stability during Cluster Head(CH) selection. In this paper,Hybrid Seagull and Whale Optimization Algorithmbased Dynamic Clustering Protocol(HSWOA-DCP)is proposed with the exploitation benefits of WOA and exploration merits of SEOA to optimal CH selection for maintaining energy stability with prolonged network lifetime. This HSWOA-DCP adopted the modified version of SEagull Optimization Algorithm(SEOA) to handle the problem of premature convergence and computational accuracy which is maximally possible during CH selection. The inclusion of SEOA into WOA improved the global searching capability during the selection of CH and prevents worst fitness nodes from being selected as CH, since the spiral attacking behavior of SEOA is similar to the bubble-net characteristics of WOA. This CH selection integrates the spiral attacking principles of SEOA and contraction surrounding mechanism of WOA for improving computation accuracy to prevent frequent election process. It also included the strategy of levy flight strategy into SEOA for potentially avoiding premature convergence to attain better trade-off between the rate of exploration and exploitation in a more effective manner. The simulation results of the proposed HSWOADCP confirmed better network survivability rate, network residual energy and network overall throughput on par with the competitive CH selection schemes under different number of data transmission rounds.The statistical analysis of the proposed HSWOA-DCP scheme also confirmed its energy stability with respect to ANOVA test.
文摘Due to its complexity and involvement of numerous stakeholders,the pharmaceutical supply chain presents many challenges that companies must overcome to deliver necessary medications to patients efficiently.The pharmaceutical supply chain poses different challenging issues,encompasses supply chain visibility,cold-chain shipping,drug counterfeiting,and rising prescription drug prices,which can considerably surge out-of-pocket patient costs.Blockchain(BC)offers the technical base for such a scheme,as it could track legitimate drugs and avoid fake circulation.The designers presented the procedure of BC with fabric for creating a secured drug supplychain management(DSCM)method.With this motivation,the study presents a new blockchain with optimal deep learning-enabled DSCM and recommendation scheme(BCODL-DSCMRS)for Pharmaceutical Industries.Firstly,Hyperledger fabric is used for DSC management,enabling effective tracking processes in the smart pharmaceutical industry.In addition,a hybrid deep belief network(HDBN)model is used to suggest the best or top-rated medicines to healthcare providers and consumers.The spotted hyena optimizer(SHO)algorithm is used to optimize the performance of the HDBN model.The design of the HSO algorithm for tuning the HDBN model demonstrates the novelty of the work.The presented model is tested on the UCI repository’s open-access drug reviews database.
文摘The term Epilepsy refers to a most commonly occurring brain disorder after a migraine.Early identification of incoming seizures significantly impacts the lives of people with Epilepsy.Automated detection of epileptic seizures(ES)has dramatically improved the life quality of the patients.Recent Electroencephalogram(EEG)related seizure detection mechanisms encountered several difficulties in real-time.The EEGs are the non-stationary signal,and seizure patternswould changewith patients and recording sessions.Further,EEG data were disposed to wide noise varieties that adversely moved the recognition accuracy of ESs.Artificial intelligence(AI)methods in the domain of ES analysis use traditional deep learning(DL),and machine learning(ML)approaches.This article introduces an Oppositional Aquila Optimizer-based Feature Selection with Deep Belief Network for Epileptic Seizure Detection(OAOFS-DBNECD)technique using EEG signals.The primary aim of the presented OAOFS-DBNECD system is to categorize and classify the presence of ESs.The suggested OAOFS-DBNECD technique transforms the EEG signals into.csv format at the initial stage.Next,the OAOFS technique selects an optimal subset of features using the preprocessed data.For seizure classification,the presented OAOFS-DBNECD technique applies Artificial Ecosystem Optimizer(AEO)with a deep belief network(DBN)model.An extensive range of simulations was performed on the benchmark dataset to ensure the enhanced performance of the presented OAOFS-DBNECD algorithm.The comparison study shows the significant outcomes of the OAOFS-DBNECD approach over other methodologies.In addition,the result of the suggested approach has been evaluated using the CHB-MIT database,and the findings demonstrate accuracy of 97.81%.These findings confirmed the best seizure categorization accuracy on the EEG data considered.
文摘In healthcare systems,the Internet of Things(IoT)innovation and development approached new ways to evaluate patient data.A cloud-based platform tends to process data generated by IoT medical devices instead of high storage,and computational hardware.In this paper,an intelligent healthcare system has been proposed for the prediction and severity analysis of lung disease from chest computer tomography(CT)images of patients with pneumonia,Covid-19,tuberculosis(TB),and cancer.Firstly,the CT images are captured and transmitted to the fog node through IoT devices.In the fog node,the image gets modified into a convenient and efficient format for further processing.advanced encryption Standard(AES)algorithm serves a substantial role in IoT and fog nodes for preventing data from being accessed by other operating systems.Finally,the preprocessed image can be classified automatically in the cloud by using various transfer and ensemble learning models.Herein different pre-trained deep learning architectures(Inception-ResNet-v2,VGG-19,ResNet-50)used transfer learning is adopted for feature extraction.The softmax of heterogeneous base classifiers assists to make individual predictions.As a meta-classifier,the ensemble approach is employed to obtain final optimal results.Disease predicted image is consigned to the recurrent neural network with long short-term memory(RNN-LSTM)for severity analysis,and the patient is directed to seek therapy based on the outcome.The proposed method achieved 98.6%accuracy,0.978 precision,0.982 recalls,and 0.974 F1-score on five class classifications.The experimental findings reveal that the proposed framework assists medical experts with lung disease screening and provides a valuable second perspective.
文摘Attacks on the cyber space is getting exponential in recent times.Illegal penetrations and breaches are real threats to the individuals and organizations.Conventional security systems are good enough to detect the known threats but when it comes to Advanced Persistent Threats(APTs)they fails.These APTs are targeted,more sophisticated and very persistent and incorporates lot of evasive techniques to bypass the existing defenses.Hence,there is a need for an effective defense system that can achieve a complete reliance of security.To address the above-mentioned issues,this paper proposes a novel honeypot system that tracks the anonymous behavior of the APT threats.The key idea of honeypot leverages the concepts of graph theory to detect such targeted attacks.The proposed honey-pot is self-realizing,strategic assisted which withholds the APTs actionable tech-niques and observes the behavior for analysis and modelling.The proposed graph theory based self learning honeypot using the resultsγ(C(n,1)),γc(C(n,1)),γsc(C(n,1))outperforms traditional techniques by detecting APTs behavioral with detection rate of 96%.
文摘The detection of cyber threats has recently been a crucial research domain as the internet and data drive people’s livelihood.Several cyber-attacks lead to the compromise of data security.The proposed system offers complete data protection from Advanced Persistent Threat(APT)attacks with attack detection and defence mechanisms.The modified lateral movement detection algorithm detects the APT attacks,while the defence is achieved by the Dynamic Deception system that makes use of the belief update algorithm.Before termination,every cyber-attack undergoes multiple stages,with the most prominent stage being Lateral Movement(LM).The LM uses a Remote Desktop protocol(RDP)technique to authenticate the unauthorised host leaving footprints on the network and host logs.An anomaly-based approach leveraging the RDP event logs on Windows is used for detecting the evidence of LM.After extracting various feature sets from the logs,the RDP sessions are classified using machine-learning techniques with high recall and precision.It is found that the AdaBoost classifier offers better accuracy,precision,F1 score and recall recording 99.9%,99.9%,0.99 and 0.98%.Further,a dynamic deception process is used as a defence mechanism to mitigateAPTattacks.A hybrid encryption communication,dynamic(Internet Protocol)IP address generation,timing selection and policy allocation are established based on mathematical models.A belief update algorithm controls the defender’s action.The performance of the proposed system is compared with the state-of-the-art models.
文摘Deep Learning is one of the most popular computer science techniques,with applications in natural language processing,image processing,pattern iden-tification,and various otherfields.Despite the success of these deep learning algorithms in multiple scenarios,such as spam detection,malware detection,object detection and tracking,face recognition,and automatic driving,these algo-rithms and their associated training data are rather vulnerable to numerous security threats.These threats ultimately result in significant performance degradation.Moreover,the supervised based learning models are affected by manipulated data known as adversarial examples,which are images with a particular level of noise that is invisible to humans.Adversarial inputs are introduced to purposefully confuse a neural network,restricting its use in sensitive application areas such as bio-metrics applications.In this paper,an optimized defending approach is proposed to recognize the adversarial iris examples efficiently.The Curvelet Transform Denoising method is used in this defense strategy,which examines every sub-band of the adversarial images and reproduces the image that has been changed by the attacker.The salient iris features are retrieved from the reconstructed iris image by using a pretrained Convolutional Neural Network model(VGG 16)followed by Multiclass classification.The classification is performed by using Support Vector Machine(SVM)which uses Particle Swarm Optimization method(PSO-SVM).The proposed system is tested when classifying the adversarial iris images affected by various adversarial attacks such as FGSM,iGSM,and Deep-fool methods.An experimental result on benchmark iris dataset,namely IITD,produces excellent outcomes with the highest accuracy of 95.8%on average.
基金supported in part by the Higher Education Sprout Project from the Ministry of Education(MOE)and National Science and Technology Council,Taiwan(109-2628-E-224-001-MY3,112-2622-E-224-003)and in part by Isuzu Optics Corporation.Dr.Shih-Yu Chen is the corresponding author.
文摘Data fusion generates fused data by combining multiple sources,resulting in information that is more consistent,accurate,and useful than any individual source and more reliable and consistent than the raw original data,which are often imperfect,inconsistent,complex,and uncertain.Traditional data fusion methods like probabilistic fusion,set-based fusion,and evidential belief reasoning fusion methods are computationally complex and require accurate classification and proper handling of raw data.Data fusion is the process of integrating multiple data sources.Data filtering means examining a dataset to exclude,rearrange,or apportion data according to the criteria.Different sensors generate a large amount of data,requiring the development of machine learning(ML)algorithms to overcome the challenges of traditional methods.The advancement in hardware acceleration and the abundance of data from various sensors have led to the development of machine learning(ML)algorithms,expected to address the limitations of traditional methods.However,many open issues still exist as machine learning algorithms are used for data fusion.From the literature,nine issues have been identified irrespective of any application.The decision-makers should pay attention to these issues as data fusion becomes more applicable and successful.A fuzzy analytical hierarchical process(FAHP)enables us to handle these issues.It helps to get the weights for each corresponding issue and rank issues based on these calculated weights.The most significant issue identified is the lack of deep learning models used for data fusion that improve accuracy and learning quality weighted 0.141.The least significant one is the cross-domain multimodal data fusion weighted 0.076 because the whole semantic knowledge for multimodal data cannot be captured.
文摘An ad-hoc sensor network(ASN)is a group of sensing nodes that transmit data over a wireless link to a target node,direct or indirect,through a series of nodes.ASN becomes a high-risk group for several security exploits due to the sensor node’s limited resources.Internal threats are more challenging to protect against than external attacks.The nodes are grouped,and calculate each node’s trust level.The trust level is the result of combining internal and external trust degrees.Cluster heads(CH)are chosen based on the anticipated trust levels.The communications are then digitally signed by the source,encoded using a key pair given by a trustworthy CH,decoded by the recipient,and supervised by verifications.It authenticates the technique by identifying the presence of both the transmitter and the recipient.Our approach looks for a trustworthy neighboring node that meets the trust threshold condition to authenticate the key produced.The companion node reaffirms the node’s reliability by getting the public-key certification.The seeking sensor node and the certification issuer node must have a close and trusting relationship.The results of the proposed hybrid authentication using a node trustworthy(HANT)system are modeled and tested,and the suggested approach outperforms conventional trust-based approaches in throughput,latency,lifetime,and vulnerability methods.
文摘Energy conservation has become a significant consideration in wireless sensor networks(WSN).In the sensor network,the sensor nodes have internal batteries,and as a result,they expire after a certain period.As a result,expanding the life duration of sensing devices by improving data depletion in an effective and sustainable energy-efficient way remains a challenge.Also,the clustering strategy employs to enhance or extend the life cycle of WSNs.We identify the supervisory head node(SH)or cluster head(CH)in every grouping considered the feasible strategy for power-saving route discovery in the clustering model,which diminishes the communication overhead in the WSN.However,the critical issue was determining the best SH for ensuring timely communication services.Our secure and energy concise route revamp technology(SECRET)protocol involves selecting an energy-concise cluster head(ECH)and route revamping to optimize navigation.The sensors transmit information over the ECH,which delivers the information to the base station via the determined optimal path using our strategy for effective data transmission.We modeled our methods to accom-plish power-efficient multi-hop routing.Furthermore,protected navigation helps to preserve energy when routing.The suggested solution improves energy savings,packet delivery ratio(PDR),route latency(RL),network lifetime(NL),and scalability.
基金This work is partially funded by FCT/MCTES through national funds and,when applicable,co-funded EU funds under the Project UIDB/50008/2020Ministry of Science and Higher Education of the Russian Federation,Grant 08-08by the Brazilian National Council for Scientific and Technological Development-CNPq,via Grant No.313036/2020-9.
文摘Forested areas are extremely vulnerable to disasters leading to environmental destruction.Forest Fire is one among them which requires immediate attention.There are lot of works done by authors where Wireless Sensors and IoT have been used for forest fire monitoring.So,towards monitoring the forest fire and managing the energy efficiently in IoT,Energy Efficient Routing Protocol for Low power lossy networks(E-RPL)was developed.There were challenges about the scalability of the network resulting in a large end-to-end delay and less packet delivery which led to the development of Aggregator-based Energy Efficient RPL with Data Compression(CAAERPL).Though CAA-ERPL proved effective in terms of reduced packet delivery,less energy consumption,and increased packet delivery ratio for varying number of nodes,there is still challenge in the selection of aggregator which is based purely on probability percentage of nodes.There has been research work where fuzzy logic been employed for Mobile Ad-hoc Routing,RPL routing and cluster head selection in Wireless Sensor.There has been no work where fuzzy logic is employed for aggregator selection in Energy Efficient RPL.So accordingly,we here have proposed Fuzzy Based Aggregator selection in Energy-efficient RPL for region thereby forming DODAG for communicating to Fog/Edge.We here have developed fuzzy inference rules for selecting the aggregator based on strength which takes residual power,Node degree,and Expected Transmission Count(ETX)as input metrics.The Fuzzy Aggregator Energy Efficient RPL(FA-ERPL)based on fuzzy inference rules were analysed against E-RPL in terms of scalability(First and Half Node die),Energy Consumption,and aggregator node energy deviation.From the analysis,it was found that FA-ERPL performed better than E-RPL.These were simulated using MATLAB and results.
基金This work was supported by Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(2020R1A6A1A03038540)National Research Foundation of Korea(NRF)grant funded by the Korea government,Ministry of Science and ICT(MSIT)(2021R1F1A1046339).
文摘Due to latest advancements in the field of remote sensing,it becomes easier to acquire high quality images by the use of various satellites along with the sensing components.But the massive quantity of data poses a challenging issue to store and effectively transmit the remote sensing images.Therefore,image compression techniques can be utilized to process remote sensing images.In this aspect,vector quantization(VQ)can be employed for image compression and the widely applied VQ approach is Linde–Buzo–Gray(LBG)which creates a local optimum codebook for image construction.The process of constructing the codebook can be treated as the optimization issue and the metaheuristic algorithms can be utilized for resolving it.With this motivation,this article presents an intelligent satin bowerbird optimizer based compression technique(ISBO-CT)for remote sensing images.The goal of the ISBO-CT technique is to proficiently compress the remote sensing images by the effective design of codebook.Besides,the ISBO-CT technique makes use of satin bowerbird optimizer(SBO)with LBG approach is employed.The design of SBO algorithm for remote sensing image compression depicts the novelty of the work.To showcase the enhanced efficiency of ISBO-CT approach,an extensive range of simulations were applied and the outcomes reported the optimum performance of ISBO-CT technique related to the recent state of art image compression approaches.
基金Shabnam Mohamed Aslam would like to thank the Deanship of Scientific Research at Majmaah University for supporting this work under Project No.R-2021-242.
文摘In recent times,Internet of Things(IoT)has become a hot research topic and it aims at interlinking several sensor-enabled devices mainly for data gathering and tracking applications.Wireless Sensor Network(WSN)is an important component in IoT paradigm since its inception and has become the most preferred platform to deploy several smart city application areas like home automation,smart buildings,intelligent transportation,disaster management,and other such IoT-based applications.Clustering methods are widely-employed energy efficient techniques with a primary purpose i.e.,to balance the energy among sensor nodes.Clustering and routing processes are considered as Non-Polynomial(NP)hard problems whereas bio-inspired techniques have been employed for a known time to resolve such problems.The current research paper designs an Energy Efficient Two-Tier Clustering with Multi-hop Routing Protocol(EETTC-MRP)for IoT networks.The presented EETTC-MRP technique operates on different stages namely,tentative Cluster Head(CH)selection,final CH selection,and routing.In first stage of the proposed EETTC-MRP technique,a type II fuzzy logic-based tentative CH(T2FL-TCH)selection is used.Subsequently,Quantum Group Teaching Optimization Algorithm-based Final CH selection(QGTOA-FCH)technique is deployed to derive an optimum group of CHs in the network.Besides,Political Optimizer based Multihop Routing(PO-MHR)technique is also employed to derive an optimal selection of routes between CHs in the network.In order to validate the efficacy of EETTC-MRP method,a series of experiments was conducted and the outcomes were examined under distinct measures.The experimental analysis infers that the proposed EETTC-MRP technique is superior to other methods under different measures.
基金This research was supported in part by Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(NRF-2021R1A6A1A03039493)in part by the NRF grant funded by the Korea government(MSIT)(NRF-2022R1A2C1004401)in part by the 2022 Yeungnam University Research Grant.
文摘The exponential growth of data necessitates an effective data storage scheme,which helps to effectively manage the large quantity of data.To accomplish this,Deoxyribonucleic Acid(DNA)digital data storage process can be employed,which encodes and decodes binary data to and from synthesized strands of DNA.Vector quantization(VQ)is a commonly employed scheme for image compression and the optimal codebook generation is an effective process to reach maximum compression efficiency.This article introduces a newDNAComputingwithWater StriderAlgorithm based Vector Quantization(DNAC-WSAVQ)technique for Data Storage Systems.The proposed DNAC-WSAVQ technique enables encoding data using DNA computing and then compresses it for effective data storage.Besides,the DNAC-WSAVQ model initially performsDNA encoding on the input images to generate a binary encoded form.In addition,aWater Strider algorithm with Linde-Buzo-Gray(WSA-LBG)model is applied for the compression process and thereby storage area can be considerably minimized.In order to generate optimal codebook for LBG,the WSA is applied to it.The performance validation of the DNAC-WSAVQ model is carried out and the results are inspected under several measures.The comparative study highlighted the improved outcomes of the DNAC-WSAVQ model over the existing methods.
基金supported by the Soonchunhyang University Research Fund andUniversity Innovation Support Project.
文摘Image Captioning is an emergent topic of research in the domain of artificial intelligence(AI).It utilizes an integration of Computer Vision(CV)and Natural Language Processing(NLP)for generating the image descriptions.Itfinds use in several application areas namely recommendation in editing applications,utilization in virtual assistance,etc.The development of NLP and deep learning(DL)modelsfind useful to derive a bridge among the visual details and textual semantics.In this view,this paper introduces an Oppositional Harris Hawks Optimization with Deep Learning based Image Captioning(OHHO-DLIC)technique.The OHHO-DLIC technique involves the design of distinct levels of pre-processing.Moreover,the feature extraction of the images is carried out by the use of EfficientNet model.Furthermore,the image captioning is performed by bidirectional long short term memory(BiLSTM)model,comprising encoder as well as decoder.At last,the oppositional Harris Hawks optimization(OHHO)based hyperparameter tuning process is performed for effectively adjusting the hyperparameter of the EfficientNet and BiLSTM models.The experimental analysis of the OHHO-DLIC technique is carried out on the Flickr 8k Dataset and a comprehensive comparative analysis highlighted the better performance over the recent approaches.
