A Novel Deep Learning-Based Model for Classification of Wheat Gene Expression

Deep learning(DL)plays a critical role in processing and converting data into knowledge and decisions.DL technologies have been applied in a variety of applications,including image,video,and genome sequence analysis.In deep learning the most widely utilized architecture is Convolutional Neural Networks(CNN)are taught discriminatory traits in a supervised environment.In comparison to other classic neural networks,CNN makes use of a limited number of artificial neurons,therefore it is ideal for the recognition and processing of wheat gene sequences.Wheat is an essential crop of cereals for people around the world.Wheat Genotypes identification has an impact on the possible development of many countries in the agricultural sector.In quantitative genetics prediction of genetic values is a central issue.Wheat is an allohexaploid(AABBDD)with three distinct genomes.The sizes of the wheat genome are quite large compared to many other kinds and the availability of a diversity of genetic knowledge and normal structure at breeding lines of wheat,Therefore,genome sequence approaches based on techniques of Artificial Intelligence(AI)are necessary.This paper focuses on using the Wheat genome sequence will assist wheat producers in making better use of their genetic resources and managing genetic variation in their breeding program,as well as propose a novel model based on deep learning for offering a fundamental overview of genomic prediction theory and current constraints.In this paper,the hyperparameters of the network are optimized in the CNN to decrease the requirement for manual search and enhance network performance using a new proposed model built on an optimization algorithm and Convolutional Neural Networks(CNN).

Intelligent Deep Learning Enabled Human Activity Recognition for Improved Medical Services

Human Activity Recognition(HAR)has been made simple in recent years,thanks to recent advancements made in Artificial Intelligence(AI)techni-ques.These techniques are applied in several areas like security,surveillance,healthcare,human-robot interaction,and entertainment.Since wearable sensor-based HAR system includes in-built sensors,human activities can be categorized based on sensor values.Further,it can also be employed in other applications such as gait diagnosis,observation of children/adult’s cognitive nature,stroke-patient hospital direction,Epilepsy and Parkinson’s disease examination,etc.Recently-developed Artificial Intelligence(AI)techniques,especially Deep Learning(DL)models can be deployed to accomplish effective outcomes on HAR process.With this motivation,the current research paper focuses on designing Intelligent Hyperparameter Tuned Deep Learning-based HAR(IHPTDL-HAR)technique in healthcare environment.The proposed IHPTDL-HAR technique aims at recogniz-ing the human actions in healthcare environment and helps the patients in mana-ging their healthcare service.In addition,the presented model makes use of Hierarchical Clustering(HC)-based outlier detection technique to remove the out-liers.IHPTDL-HAR technique incorporates DL-based Deep Belief Network(DBN)model to recognize the activities of users.Moreover,Harris Hawks Opti-mization(HHO)algorithm is used for hyperparameter tuning of DBN model.Finally,a comprehensive experimental analysis was conducted upon benchmark dataset and the results were examined under different aspects.The experimental results demonstrate that the proposed IHPTDL-HAR technique is a superior per-former compared to other recent techniques under different measures.

A Healthcare System for COVID19 Classification Using Multi-Type Classical Features Selection

The coronavirus(COVID19),also known as the novel coronavirus,first appeared in December 2019 in Wuhan,China.After that,it quickly spread throughout the world and became a disease.It has significantly impacted our everyday lives,the national and international economies,and public health.However,early diagnosis is critical for prompt treatment and reducing trauma in the healthcare system.Clinical radiologists primarily use chest X-rays,and computerized tomography(CT)scans to test for pneumonia infection.We used Chest CT scans to predict COVID19 pneumonia and healthy scans in this study.We proposed a joint framework for prediction based on classical feature fusion and PSO-based optimization.We begin by extracting standard features such as discrete wavelet transforms(DWT),discrete cosine transforms(DCT),and dominant rotated local binary patterns(DRLBP).In addition,we extracted Shanon Entropy and Kurtosis features.In the following step,a Max-Covariance-based maximization approach for feature fusion is proposed.The fused features are optimized in the preliminary phase using Particle Swarm Optimization(PSO)and the ELM fitness function.For final prediction,PSO is used to obtain robust features,which are then implanted in a Support Vector Data Description(SVDD)classifier.The experiment is carried out using available COVID19 Chest CT Scans and scans from healthy patients.These images are from the Radiopaedia website.For the proposed scheme,the fusion and selection process accuracy is 88.6%and 93.1%,respectively.A detailed analysis is conducted,which supports the proposed system efficiency.

Oppositional Harris Hawks Optimization with Deep Learning-Based Image Captioning

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.

Impulsive Noise Cancellation in OFDM System Using Low Density Parity Check

An effective communication application necessitates the cancellation of Impulsive Noise(IN)from Orthogonal Frequency Division Multiplexing(OFDM),which is widely used for wireless applications due to its higher data rate and greater spectral efficiency.The OFDM system is typically corrupted by Impulsive Noise,which is an unwanted short-duration pulse with random amplitude and duration.Impulsive noise is created by humans and has non-Gaussian characteristics,causing problems in communication systems such as high capacity loss and poor error rate performance.Several techniques have been introduced in the literature to solve this type of problem,but they still have many issues that affect the performance of the presented methods.As a result,developing a new hybridization-based method is critical for accurate method performance.In this paper,we present a hybrid of a state space adaptive filter and an information coding technique for cancelling impulsive noise from OFDM.The proposed method is also compared to Least Mean Square(LMS),Normalized Least Mean Square(NLMS),and Recursive Least Square(RLS)adaptive filters.It has also been tested using the binary phase-shift keyed(BPSK),four quadrature amplitude modulation(QAM),sixteen QAM,and thirty-two QAM modulation techniques.Bit error Rate(BER)simulations are used to evaluate system performance,and improved performance is obtained.Furthermore,the proposed method is more effective than recent methods.

Recognition and Tracking of Objects in a Clustered Remote Scene Environment

Object recognition and tracking are two of the most dynamic research sub-areas that belong to the field of Computer Vision.Computer vision is one of the most active research fields that lies at the intersection of deep learning and machine vision.This paper presents an efficient ensemble algorithm for the recognition and tracking of fixed shapemoving objects while accommodating the shift and scale invariances that the object may encounter.The first part uses the Maximum Average Correlation Height(MACH)filter for object recognition and determines the bounding box coordinates.In case the correlation based MACH filter fails,the algorithms switches to a much reliable but computationally complex feature based object recognition technique i.e.,affine scale invariant feature transform(ASIFT).ASIFT is used to accommodate object shift and scale object variations.ASIFT extracts certain features from the object of interest,providing invariance in up to six affine parameters,namely translation(two parameters),zoom,rotation and two camera axis orientations.However,in this paper,only the shift and scale invariances are used.The second part of the algorithm demonstrates the use of particle filters based Approximate Proximal Gradient(APG)technique to periodically update the coordinates of the object encapsulated in the bounding box.At the end,a comparison of the proposed algorithm with other stateof-the-art tracking algorithms has been presented,which demonstrates the effectiveness of the proposed algorithm with respect to the minimization of tracking errors.

Three Dimensional Optimum Node Localization in Dynamic Wireless Sensor Networks

Location information plays an important role in most of the applications in Wireless Sensor Network(WSN).Recently,many localization techniques have been proposed,while most of these deals with two Dimensional applications.Whereas,in Three Dimensional applications the task is complex and there are large variations in the altitude levels.In these 3D environments,the sensors are placed in mountains for tracking and deployed in air for monitoring pollution level.For such applications,2D localization models are not reliable.Due to this,the design of 3D localization systems in WSNs faces new challenges.In this paper,in order to find unknown nodes in Three-Dimensional environment,only single anchor node is used.In the simulation-based environment,the nodes with unknown locations are moving at middle&lower layers whereas the top layer is equipped with single anchor node.A novel soft computing technique namely Adaptive Plant Propagation Algorithm(APPA)is introduced to obtain the optimized locations of these mobile nodes.Thesemobile target nodes are heterogeneous and deployed in an anisotropic environment having an Irregularity(Degree of Irregularity(DOI))value set to 0.01.The simulation results present that proposed APPAalgorithm outperforms as tested among other meta-heuristic optimization techniques in terms of localization error,computational time,and the located sensor nodes.

Energy Aware Metaheuristic Optimization with Location Aided Routing Protocol for MANET

A mobile ad hoc network(MANET)involves a group of wireless mobile nodes which create an impermanent network with no central authority and infrastructure.The nodes in the MANET are highly mobile and it results in adequate network topology,link loss,and increase the re-initialization of the route discovery process.Route planning in MANET is a multi-hop communication process due to the restricted transmission range of the nodes.Location aided routing(LAR)is one of the effective routing protocols in MANET which suffers from the issue of high energy consumption.Though few research works have focused on resolving energy consumption problem in LAR,energy efficiency still remains a major design issue.In this aspect,this study introduces an energy aware metaheuristic optimization with LAR(EAMO-LAR)protocol for MANETs.The EAMO-LAR protocol makes use of manta ray foraging optimization algorithm(MRFO)to help the searching process for the individual solution to be passed to the LAR protocol.The fitness value of the created solutions is determined next to pass the solutions to the objective function.The MRFO algorithm is incorporated into the LAR protocol in the EAMO-LAR protocol to reduce the desired energy utilization.To ensure the improved routing efficiency of the proposed EAMO-LAR protocol,a series of simulations take place.The resultant experimental values pointed out the supreme outcome of the EAMO-LAR protocol over the recently compared methods.The resultant values demonstrated that the EAMO-LAR protocol has accomplished effectual results over the other existing techniques.

Skin Lesion Segmentation and Classification Using Conventional and Deep Learning Based Framework

Background:In medical image analysis,the diagnosis of skin lesions remains a challenging task.Skin lesion is a common type of skin cancer that exists worldwide.Dermoscopy is one of the latest technologies used for the diagnosis of skin cancer.Challenges:Many computerized methods have been introduced in the literature to classify skin cancers.However,challenges remain such as imbalanced datasets,low contrast lesions,and the extraction of irrelevant or redundant features.Proposed Work:In this study,a new technique is proposed based on the conventional and deep learning framework.The proposed framework consists of two major tasks:lesion segmentation and classification.In the lesion segmentation task,contrast is initially improved by the fusion of two filtering techniques and then performed a color transformation to color lesion area color discrimination.Subsequently,the best channel is selected and the lesion map is computed,which is further converted into a binary form using a thresholding function.In the lesion classification task,two pre-trained CNN models were modified and trained using transfer learning.Deep features were extracted from both models and fused using canonical correlation analysis.During the fusion process,a few redundant features were also added,lowering classification accuracy.A new technique called maximum entropy score-based selection(MESbS)is proposed as a solution to this issue.The features selected through this approach are fed into a cubic support vector machine(C-SVM)for the final classification.Results:The experimental process was conducted on two datasets:ISIC 2017 and HAM10000.The ISIC 2017 dataset was used for the lesion segmentation task,whereas the HAM10000 dataset was used for the classification task.The achieved accuracy for both datasets was 95.6% and 96.7%, respectively, which was higher thanthe existing techniques.

Cross-Layer Hidden Markov Analysis for Intrusion Detection

Ad hoc mobile cloud computing networks are affected by various issues,like delay,energy consumption,flexibility,infrastructure,network lifetime,security,stability,data transition,and link accomplishment.Given the issues above,route failure is prevalent in ad hoc mobile cloud computing networks,which increases energy consumption and delay and reduces stability.These issues may affect several interconnected nodes in an ad hoc mobile cloud computing network.To address these weaknesses,which raise many concerns about privacy and security,this study formulated clustering-based storage and search optimization approaches using cross-layer analysis.The proposed approaches were formed by cross-layer analysis based on intrusion detection methods.First,the clustering process based on storage and search optimization was formulated for clustering and route maintenance in ad hoc mobile cloud computing networks.Moreover,delay,energy consumption,network lifetime,and link accomplishment are highly addressed by the proposed algorithm.The hidden Markov model is used to maintain the data transition and distributions in the network.Every data communication network,like ad hoc mobile cloud computing,faces security and confidentiality issues.However,the main security issues in this article are addressed using the storage and search optimization approach.Hence,the new algorithm developed helps detect intruders through intelligent cross layer analysis with theMarkov model.The proposed model was simulated in Network Simulator 3,and the outcomes were compared with those of prevailing methods for evaluating parameters,like accuracy,end-to-end delay,energy consumption,network lifetime,packet delivery ratio,and throughput.

Non-Negative Minimum Volume Factorization (NMVF) for Hyperspectral Images (HSI) Unmixing: A Hybrid Approach

Spectral unmixing is essential for exploitation of remotely senseddata of Hyperspectral Images (HSI). It amounts to the identification of a position of spectral signatures that are pure and therefore called end members andtheir matching fractional, draft rules abundances for every pixel in HSI. Thispaper aims to unmix hyperspectral data using the minimal volume methodof elementary scrutiny. Moreover, the problem of optimization is solved bythe implementation of the sequence of small problems that are constrainedquadratically. The hard constraint in the final step for the abundance fractionis then replaced with a loss function of hinge type that accounts for outlinersand noise. Existing algorithms focus on estimating the endmembers (Ems)enumeration in a sight, discerning of spectral signs of EMs, besides assessmentof fractional profusion for every EM in every pixel of a sight. Nevertheless, allthe stages are performed by only a few algorithms in the process of hyperspectral unmixing. Therefore, the Non-negative Minimum Volume Factorization(NMVF) algorithm is further extended by fusing it with the nonnegativematrix of robust collaborative factorization that aims to perform all the threeunmixing chain steps for hyperspectral images. The major contributions ofthis article are in this manner: (A) it performs Simplex analysis of minimum volume for hyperspectral images with unsupervised linear unmixing isemployed. (B) The simplex analysis method is configured with an exaggeratedform of the elementary which is delivered by vertical component analysis(VCA). (C) The inflating factor is chosen carefully inactivating the constraintsin a large majority for relating to the source fractions abundance that speedsup the algorithm. (D) The final step is making simplex analysis method robustto outliners as well as noise that replaces the profusion element positivity hardrestraint by a hinge kind soft restraint, preserving the local minima havinggood quality. (E) The matrix factorization method is applied that is capable ofperforming the three major phases of the hyperspectral separation sequence.The anticipated approach can find application in a scenario where the endmembers are known in advance, however, it assumes that the endmemberscount is corresponding to an overestimated value. The proposed method isdifferent from other conventional methods as it begins with the overestimationof the count of endmembers wherein removing the endmembers that areredundant by the means of collaborative regularization. As demonstrated bythe experimental results, proposed approach yields competitive performancecomparable with widely used methods.

Malaria Blood Smear Classification Using Deep Learning and Best Features Selection

Malaria is a critical health condition that affects both sultry and frigid region worldwide,giving rise to millions of cases of disease and thousands of deaths over the years.Malaria is caused by parasites that enter the human red blood cells,grow there,and damage them over time.Therefore,it is diagnosed by a detailed examination of blood cells under the microscope.This is the most extensively used malaria diagnosis technique,but it yields limited and unreliable results due to the manual human involvement.In this work,an automated malaria blood smear classification model is proposed,which takes images of both infected and healthy cells and preprocesses themin the L^(*)a^(*)b^(*)color space by employing several contrast enhancement methods.Feature extraction is performed using two pretrained deep convolutional neural networks,DarkNet-53 and DenseNet-201.The features are subsequently agglutinated to be optimized through a nature-based feature reduction method called the whale optimization algorithm.Several classifiers are effectuated on the reduced features,and the achieved results excel in both accuracy and time compared to previously proposed methods.

Safest Route Detection via Danger Index Calculation and K-Means Clustering

The study aims to formulate a solution for identifying the safest route between any two inputted Geographical locations.Using the New York City dataset,which provides us with location tagged crime statistics;we are implementing different clustering algorithms and analysed the results comparatively to discover the best-suited one.The results unveil the fact that the K-Means algorithm best suits for our needs and delivered the best results.Moreover,a comparative analysis has been performed among various clustering techniques to obtain best results.we compared all the achieved results and using the conclusions we have developed a user-friendly application to provide safe route to users.The successful implementation would hopefully aid us to curb the ever-increasing crime rates;as it aims to provide the user with a beforehand knowledge of the route they are about to take.A warning that the path is marked high on danger index would convey the basic hint for the user to decide which path to prefer.Thus,addressing a social problem which needs to be eradicated from our modern era.