Facial Image-Based Autism Detection:A Comparative Study of Deep Neural Network Classifiers

Autism Spectrum Disorder(ASD)is a neurodevelopmental condition characterized by significant challenges in social interaction,communication,and repetitive behaviors.Timely and precise ASD detection is crucial,particularly in regions with limited diagnostic resources like Pakistan.This study aims to conduct an extensive comparative analysis of various machine learning classifiers for ASD detection using facial images to identify an accurate and cost-effective solution tailored to the local context.The research involves experimentation with VGG16 and MobileNet models,exploring different batch sizes,optimizers,and learning rate schedulers.In addition,the“Orange”machine learning tool is employed to evaluate classifier performance and automated image processing capabilities are utilized within the tool.The findings unequivocally establish VGG16 as the most effective classifier with a 5-fold cross-validation approach.Specifically,VGG16,with a batch size of 2 and the Adam optimizer,trained for 100 epochs,achieves a remarkable validation accuracy of 99% and a testing accuracy of 87%.Furthermore,the model achieves an F1 score of 88%,precision of 85%,and recall of 90% on test images.To validate the practical applicability of the VGG16 model with 5-fold cross-validation,the study conducts further testing on a dataset sourced fromautism centers in Pakistan,resulting in an accuracy rate of 85%.This reaffirms the model’s suitability for real-world ASD detection.This research offers valuable insights into classifier performance,emphasizing the potential of machine learning to deliver precise and accessible ASD diagnoses via facial image analysis.

Natural Convection and Irreversibility of Nanofluid Due to Inclined Magnetohydrodynamics(MHD)Filled in a Cavity with Y-Shape Heated Fin:FEM Computational

This study explains the entropy process of natural convective heating in the nanofluid-saturated cavity in a heated fin andmagnetic field.The temperature is constant on the Y-shaped fin,insulating the topwall while the remaining walls remain cold.All walls are subject to impermeability and non-slip conditions.The mathematical modeling of the problem is demonstrated by the continuity,momentum,and energy equations incorporating the inclined magnetic field.For elucidating the flow characteristics Finite ElementMethod(FEM)is implemented using stable FE pair.A hybrid fine mesh is used for discretizing the domain.Velocity and thermal plots concerning parameters are drawn.In addition,a detailed discussion regarding generation energy by monitoring changes in magnetic,viscous,total,and thermal irreversibility is provided.In addition,line graphs are created for the u and v components of the velocity profile to predict the flow behavior.Current simulations assume the dimensionless representative of magnetic field Hartmann number Ha between 0 and 100 and a magnetic field inclination between 0 and 90 degrees.A constant 4% volume proportion of nanoparticles is employed throughout all scenarios.

Nodule Detection Using Local Binary Pattern Features to Enhance Diagnostic Decisions

Pulmonary nodules are small, round, or oval-shaped growths on the lungs. They can be benign (noncancerous) or malignant (cancerous). The size of a nodule can range from a few millimeters to a few centimeters in diameter. Nodules may be found during a chest X-ray or other imaging test for an unrelated health problem. In the proposed methodology pulmonary nodules can be classified into three stages. Firstly, a 2D histogram thresholding technique is used to identify volume segmentation. An ant colony optimization algorithm is used to determine the optimal threshold value. Secondly, geometrical features such as lines, arcs, extended arcs, and ellipses are used to detect oval shapes. Thirdly, Histogram Oriented Surface Normal Vector (HOSNV) feature descriptors can be used to identify nodules of different sizes and shapes by using a scaled and rotation-invariant texture description. Smart nodule classification was performed with the XGBoost classifier. The results are tested and validated using the Lung Image Consortium Database (LICD). The proposed method has a sensitivity of 98.49% for nodules sized 3–30 mm.

Brain Tumor Segmentation in Multimodal MRI Using U-Net Layered Structure

The brain tumour is the mass where some tissues become old or damaged,but they do not die or not leave their space.Mainly brain tumour masses occur due to malignant masses.These tissues must die so that new tissues are allowed to be born and take their place.Tumour segmentation is a complex and time-taking problem due to the tumour’s size,shape,and appearance variation.Manually finding such masses in the brain by analyzing Magnetic Resonance Images(MRI)is a crucial task for experts and radiologists.Radiologists could not work for large volume images simultaneously,and many errors occurred due to overwhelming image analysis.The main objective of this research study is the segmentation of tumors in brain MRI images with the help of digital image processing and deep learning approaches.This research study proposed an automatic model for tumor segmentation in MRI images.The proposed model has a few significant steps,which first apply the pre-processing method for the whole dataset to convert Neuroimaging Informatics Technology Initiative(NIFTI)volumes into the 3D NumPy array.In the second step,the proposed model adopts U-Net deep learning segmentation algorithm with an improved layered structure and sets the updated parameters.In the third step,the proposed model uses state-of-the-art Medical Image Computing and Computer-Assisted Intervention(MICCAI)BRATS 2018 dataset withMRI modalities such as T1,T1Gd,T2,and Fluidattenuated inversion recovery(FLAIR).Tumour types in MRI images are classified according to the tumour masses.Labelling of these masses carried by state-of-the-art approaches such that the first is enhancing tumour(label 4),edema(label 2),necrotic and non-enhancing tumour core(label 1),and the remaining region is label 0 such that edema(whole tumour),necrosis and active.The proposed model is evaluated and gets the Dice Coefficient(DSC)value for High-grade glioma(HGG)volumes for their test set-a,test set-b,and test set-c 0.9795, 0.9855 and 0.9793, respectively. DSC value for the Low-gradeglioma (LGG) volumes for the test set is 0.9950, which shows the proposedmodel has achieved significant results in segmenting the tumour in MRI usingdeep learning approaches. The proposed model is fully automatic that canimplement in clinics where human experts consumemaximumtime to identifythe tumorous region of the brain MRI. The proposed model can help in a wayit can proceed rapidly by treating the tumor segmentation in MRI.

A Multi-Modal Deep Learning Approach for Emotion Recognition

In recent years,research on facial expression recognition(FER)under mask is trending.Wearing a mask for protection from Covid 19 has become a compulsion and it hides the facial expressions that is why FER under the mask is a difficult task.The prevailing unimodal techniques for facial recognition are not up to the mark in terms of good results for the masked face,however,a multi-modal technique can be employed to generate better results.We proposed a multi-modal methodology based on deep learning for facial recognition under a masked face using facial and vocal expressions.The multimodal has been trained on a facial and vocal dataset.We have used two standard datasets,M-LFW for the masked dataset and CREMA-D and TESS dataset for vocal expressions.The vocal expressions are in the form of audio while the faces data is in image form that is why the data is heterogenous.In order to make the data homogeneous,the voice data is converted into images by taking spectrogram.A spectrogram embeds important features of the voice and it converts the audio format into the images.Later,the dataset is passed to the multimodal for training.neural network and the experimental results demonstrate that the proposed multimodal algorithm outsets unimodal methods and other state-of-the-art deep neural network models.

Lung Cancer Detection Using Modified AlexNet Architecture and Support Vector Machine

Lung cancer is the most dangerous and death-causing disease indicated by the presence of pulmonary nodules in the lung.It is mostly caused by the instinctive growth of cells in the lung.Lung nodule detection has a significant role in detecting and screening lung cancer in Computed tomography(CT)scan images.Early detection plays an important role in the survival rate and treatment of lung cancer patients.Moreover,pulmonary nodule classification techniques based on the convolutional neural network can be used for the accurate and efficient detection of lung cancer.This work proposed an automatic nodule detection method in CT images based on modified AlexNet architecture and Support vector machine(SVM)algorithm namely LungNet-SVM.The proposed model consists of seven convolutional layers,three pooling layers,and two fully connected layers used to extract features.Support vector machine classifier is applied for the binary classification of nodules into benign andmalignant.The experimental analysis is performed by using the publicly available benchmark dataset Lung nodule analysis 2016(LUNA16).The proposed model has achieved 97.64%of accuracy,96.37%of sensitivity,and 99.08%of specificity.A comparative analysis has been carried out between the proposed LungNet-SVM model and existing stateof-the-art approaches for the classification of lung cancer.The experimental results indicate that the proposed LungNet-SVM model achieved remarkable performance on a LUNA16 dataset in terms of accuracy.

Flexible Global Aggregation and Dynamic Client Selection for Federated Learning in Internet of Vehicles

Federated Learning(FL)enables collaborative and privacy-preserving training of machine learning models within the Internet of Vehicles(IoV)realm.While FL effectively tackles privacy concerns,it also imposes significant resource requirements.In traditional FL,trained models are transmitted to a central server for global aggregation,typically in the cloud.This approach often leads to network congestion and bandwidth limitations when numerous devices communicate with the same server.The need for Flexible Global Aggregation and Dynamic Client Selection in FL for the IoV arises from the inherent characteristics of IoV environments.These include diverse and distributed data sources,varying data quality,and limited communication resources.By employing dynamic client selection,we can prioritize relevant and high-quality data sources,enhancing model accuracy.To address this issue,we propose an FL framework that selects global aggregation nodes dynamically rather than a single fixed aggregator.Flexible global aggregation ensures efficient utilization of limited network resources while accommodating the dynamic nature of IoV data sources.This approach optimizes both model performance and resource allocation,making FL in IoV more effective and adaptable.The selection of the global aggregation node is based on workload and communication speed considerations.Additionally,our framework overcomes the constraints associated with network,computational,and energy resources in the IoV environment by implementing a client selection algorithm that dynamically adjusts participants according to predefined parameters.Our approach surpasses Federated Averaging(FedAvg)and Hierarchical FL(HFL)regarding energy consumption,delay,and accuracy,yielding superior results.

A Deep Learning Model of Traffic Signs in Panoramic Images Detection

To pursue the ideal of a safe high-tech society in a time when traffic accidents are frequent,the traffic signs detection system has become one of the necessary topics in recent years and in the future.The ultimate goal of this research is to identify and classify the types of traffic signs in a panoramic image.To accomplish this goal,the paper proposes a new model for traffic sign detection based on the Convolutional Neural Network for com-prehensive traffic sign classification and Mask Region-based Convolutional Neural Networks(R-CNN)implementation for identifying and extracting signs in panoramic images.Data augmentation and normalization of the images are also applied to assist in classifying better even if old traffic signs are degraded,and considerably minimize the rates of discovering the extra boxes.The proposed model is tested on both the testing dataset and the actual images and gets 94.5%of the correct signs recognition rate,the classification rate of those signs discovered was 99.41%and the rate of false signs was only around 0.11.

Resource Based Automatic Calibration System (RBACS) Using Kubernetes Framework

Kubernetes,a container orchestrator for cloud-deployed applications,allows the application provider to scale automatically to match thefluctuating intensity of processing demand.Container cluster technology is used to encapsulate,isolate,and deploy applications,addressing the issue of low system reliability due to interlocking failures.Cloud-based platforms usually entail users define application resource supplies for eco container virtualization.There is a constant problem of over-service in data centers for cloud service providers.Higher operating costs and incompetent resource utilization can occur in a waste of resources.Kubernetes revolutionized the orchestration of the container in the cloud-native age.It can adaptively manage resources and schedule containers,which provide real-time status of the cluster at runtime without the user’s contribution.Kubernetes clusters face unpredictable traffic,and the cluster performs manual expansion configuration by the controller.Due to operational delays,the system will become unstable,and the service will be unavailable.This work proposed an RBACS that vigorously amended the distribution of containers operating in the entire Kubernetes cluster.RBACS allocation pattern is analyzed with the Kubernetes VPA.To estimate the overall cost of RBACS,we use several scientific benchmarks comparing the accomplishment of container to remote node migration and on-site relocation.The experiments ran on the simulations to show the method’s effectiveness yielded high precision in the real-time deployment of resources in eco containers.Compared to the default baseline,Kubernetes results in much fewer dropped requests with only slightly more supplied resources.

An Intelligent Forwarding Strategy in SDN-Enabled Named-Data IoV

Internet of Vehicles(IoV),a rapidly growing technology for efficient vehicular communication and it is shifting the trend of traditional Vehicular Ad Hoc Networking(VANET)towards itself.The centralized management of IoV endorses its uniqueness and suitability for the Intelligent Transportation System(ITS)safety applications.Named Data Networking(NDN)is an emerging internet paradigm that fulfills most of the expectations of IoV.Limitations of the current IP internet architecture are the main motivation behind NDN.Software-Defined Networking(SDN)is another emerging networking paradigm of technology that is highly capable of efficient management of overall networks and transforming complex networking architectures into simple and manageable ones.The combination of the SDN controller,NDN,and IoV can be revolutionary in the overall performance of the network.Broadcast storm,due to the broadcasting nature of NDN,is a critical issue in NDN based on IoV.High speed and rapidly changing topology of vehicles in IoV creates disconnected link problem and add unnecessary transmission delay.In order to cop-up with the above-discussed problems,we proposed an efficient SDN-enabled forwarding mechanism in NDN-based IoV,which supports the mobility of the vehicle and explores the cellular network for the low latency control messages.In IoV environment,the concept of Edge Controller(EC)to maintain and manage the in-time and real-time vehicular topology is being introduced.A mathematical estimation model is also proposed in our work that assists the centralized EC and SDN to find not only the shortest and best path but also the most reliable and durable path.The naming scheme and in-network caching property of the NDN nodes reduce the delay.We used ndnSIM and NS-3 for the simulation experiment along with SUMO for the environment generation.The results of NDSDoV illustrate significant performance in terms of availability with limited routing overhead,minimized delay,retransmissions,and increased packet satisfaction ratio.Besides,we explored the properties of EC that contribute mainly in path failure minimization in the network.

Fuzzy Based Hybrid Focus Value Estimation for Multi Focus Image Fusion

Due to limited depth-of-field of digital single-lens reflex cameras,the scene content within a limited distance from the imaging plane remains in focus while other objects closer to or further away from the point of focus appear as blurred(out-of-focus)in the image.Multi-Focus Image Fusion can be used to reconstruct a fully focused image from two or more partially focused images of the same scene.In this paper,a new Fuzzy Based Hybrid Focus Measure(FBHFM)for multi-focus image fusion has been proposed.Optimal block size is very critical step for multi-focus image fusion.Particle Swarm Optimization(PSO)algorithm has been used to find optimal size of the block of the images for extraction of focus measure features.After finding optimal blocks,three focus measures Sum of Modified Laplacian,Gray Level Variance and Contrast Visibility has been extracted and combined these focus measures by using intelligent fuzzy technique.Fuzzy based hybrid intelligent focus values were estimated using contrast visibility measure to generate focused image.Different sets of multi-focus images have been used in detailed experimentation and compared the results with state-of-the-art existing techniques such as Genetic Algorithm(GA),Principal Component Analysis(PCA),Laplacian Pyramid discrete wavelet transform(DWT),and aDWT for image fusion.It has been found that proposed method performs well as compare to existing methods.

Mobile Devices Interface Adaptivity Using Ontologies

Currently,many mobile devices provide various interaction styles and modes which create complexity in the usage of interfaces.The context offers the information base for the development of Adaptive user interface(AUI)frameworks to overcome the heterogeneity.For this purpose,the ontological modeling has been made for specific context and environment.This type of philosophy states to the relationship among elements(e.g.,classes,relations,or capacities etc.)with understandable satisfied representation.The contextmechanisms can be examined and understood by anymachine or computational framework with these formal definitions expressed in Web ontology language(WOL)/Resource description frame work(RDF).The Protégéis used to create taxonomy in which system is framed based on four contexts such as user,device,task and environment.Some competency questions and use-cases are utilized for knowledge obtaining while the information is refined through the instances of concerned parts of context tree.The consistency of the model has been verified through the reasoning software while SPARQL querying ensured the data availability in the models for defined use-cases.The semantic context model is focused to bring in the usage of adaptive environment.This exploration has finished up with a versatile,scalable and semantically verified context learning system.This model can be mapped to individual User interface(UI)display through smart calculations for versatile UIs.

Multi Layered Rule-Based Technique for Explicit Aspect Extraction from Online Reviews

In the field of sentiment analysis,extracting aspects or opinion targets fromuser reviews about a product is a key task.Extracting the polarity of an opinion is much more useful if we also know the targeted Aspect or Feature.Rule based approaches,like dependency-based rules,are quite popular and effective for this purpose.However,they are heavily dependent on the authenticity of the employed parts-of-speech(POS)tagger and dependency parser.Another popular rule based approach is to use sequential rules,wherein the rules formulated by learning from the user’s behavior.However,in general,the sequential rule-based approaches have poor generalization capability.Moreover,existing approaches mostly consider an aspect as a noun or noun phrase,so these approaches are unable to extract verb aspects.In this article,we have proposed a multi-layered rule-based(ML-RB)technique using the syntactic dependency parser based rules along with some selective sequential rules in separate layers to extract noun aspects.Additionally,after rigorous analysis,we have also constructed rules for the extraction of verb aspects.These verb rules primarily based on the association between verb and opinion words.The proposed multi-layer technique compensates for the weaknesses of individual layers and yields improved results on two publicly available customer review datasets.The F1 score for both the datasets are 0.90 and 0.88,respectively,which are better than existing approaches.These improved results can be attributed to the application of sequential/syntactic rules in a layered manner as well as the capability to extract both noun and verb aspects.