Improving Generalization for Hyperspectral Image Classification:The Impact of Disjoint Sampling on Deep Models

Disjoint sampling is critical for rigorous and unbiased evaluation of state-of-the-art(SOTA)models e.g.,Attention Graph and Vision Transformer.When training,validation,and test sets overlap or share data,it introduces a bias that inflates performance metrics and prevents accurate assessment of a model’s true ability to generalize to new examples.This paper presents an innovative disjoint sampling approach for training SOTA models for the Hyperspectral Image Classification(HSIC).By separating training,validation,and test data without overlap,the proposed method facilitates a fairer evaluation of how well a model can classify pixels it was not exposed to during training or validation.Experiments demonstrate the approach significantly improves a model’s generalization compared to alternatives that include training and validation data in test data(A trivial approach involves testing the model on the entire Hyperspectral dataset to generate the ground truth maps.This approach produces higher accuracy but ultimately results in low generalization performance).Disjoint sampling eliminates data leakage between sets and provides reliable metrics for benchmarking progress in HSIC.Disjoint sampling is critical for advancing SOTA models and their real-world application to large-scale land mapping with Hyperspectral sensors.Overall,with the disjoint test set,the performance of the deep models achieves 96.36%accuracy on Indian Pines data,99.73%on Pavia University data,98.29%on University of Houston data,99.43%on Botswana data,and 99.88%on Salinas data.

Multimodal Medical Image Registration and Fusion for Quality Enhancement

For the last two decades,physicians and clinical experts have used a single imaging modality to identify the normal and abnormal structure of the human body.However,most of the time,medical experts are unable to accurately analyze and examine the information from a single imaging modality due to the limited information.To overcome this problem,a multimodal approach is adopted to increase the qualitative and quantitative medical information which helps the doctors to easily diagnose diseases in their early stages.In the proposed method,a Multi-resolution Rigid Registration(MRR)technique is used for multimodal image registration while Discrete Wavelet Transform(DWT)along with Principal Component Averaging(PCAv)is utilized for image fusion.The proposed MRR method provides more accurate results as compared with Single Rigid Registration(SRR),while the proposed DWT-PCAv fusion process adds-on more constructive information with less computational time.The proposed method is tested on CT and MRI brain imaging modalities of the HARVARD dataset.The fusion results of the proposed method are compared with the existing fusion techniques.The quality assessment metrics such as Mutual Information(MI),Normalize Crosscorrelation(NCC)and Feature Mutual Information(FMI)are computed for statistical comparison of the proposed method.The proposed methodology provides more accurate results,better image quality and valuable information for medical diagnoses.

Adversarial Attacks on Featureless Deep Learning Malicious URLs Detection

Detecting malicious Uniform Resource Locators(URLs)is crucially important to prevent attackers from committing cybercrimes.Recent researches have investigated the role of machine learning(ML)models to detect malicious URLs.By using ML algorithms,rst,the features of URLs are extracted,and then different ML models are trained.The limitation of this approach is that it requires manual feature engineering and it does not consider the sequential patterns in the URL.Therefore,deep learning(DL)models are used to solve these issues since they are able to perform featureless detection.Furthermore,DL models give better accuracy and generalization to newly designed URLs;however,the results of our study show that these models,such as any other DL models,can be susceptible to adversarial attacks.In this paper,we examine the robustness of these models and demonstrate the importance of considering this susceptibility before applying such detection systems in real-world solutions.We propose and demonstrate a black-box attack based on scoring functions with greedy search for the minimum number of perturbations leading to a misclassication.The attack is examined against different types of convolutional neural networks(CNN)-based URL classiers and it causes a tangible decrease in the accuracy with more than 56%reduction in the accuracy of the best classier(among the selected classiers for this work).Moreover,adversarial training shows promising results in reducing the inuence of the attack on the robustness of the model to less than 7%on average.

Multi Sensor-Based Implicit User Identification

Smartphones have ubiquitously integrated into our home and work environments,however,users normally rely on explicit but inefficient identification processes in a controlled environment.Therefore,when a device is stolen,a thief can have access to the owner’s personal information and services against the stored passwords.As a result of this potential scenario,this work proposes an automatic legitimate user identification system based on gait biometrics extracted from user walking patterns captured by smartphone sensors.A set of preprocessing schemes are applied to calibrate noisy and invalid samples and augment the gait-induced time and frequency domain features,then further optimized using a non-linear unsupervised feature selection method.The selected features create an underlying gait biometric representation able to discriminate among individuals and identify them uniquely.Different classifiers are adopted to achieve accurate legitimate user identification.Extensive experiments on a group of 16 individuals in an indoor environment show the effectiveness of the proposed solution:with 5 to 70 samples per window,KNN and bagging classifiers achieve 87–99%accuracy,82–98%for ELM,and 81–94%for SVM.The proposed pipeline achieves a 100%true positive and 0%false-negative rate for almost all classifiers.

On Determining the Optimal Lifting Law of the Walking Propulsion Device Foot of an Underwater Robot from the Bottom

The problem of lifting the foot of the walking propulsion device of an underwater mobile robot is considered,taking into account the additional"compression""force acting on it.A mathematical model has been developed for the detachment of a propulsion foot from the ground,based on Henry's laws establishing the concentration of dissolved air in a liquid,the law of gas expansion at a constant temperature,Darcy's law on fluid filtration,and the theorem on the motion of the center of mass of a solid body.The linearized model allows to obtain and analytical solutions.Based on the solution of the variat ional problem,optimal modes of lifting the foot of the walking propulsion of an underwater mobile robot are established.

The case of HyperLedger Fabric as a blockchain solution for healthcare applications

The healthcare industry deals with highly sensitive data which must be managed in a secure way.Electronic Health Records(EHRs)hold various kinds of personal and sensitive data which contain names,addresses,social security numbers,insurance numbers,and medical history.Such personal data is valuable to the patients,healthcare service providers,medical insurance companies,and research institutions.However,the public release of this highly sensitive personal data poses serious privacy and security threats to patients and healthcare service providers.Hence,we foresee the requirement of new technologies to address the privacy and security challenges for personal data in healthcare applications.Blockchain is one of the promising solutions,aimed to provide transparency,security,and privacy using consensus-driven decentralised data management on top of peer-to-peer distributed computing systems.Therefore,to solve the mentioned problems in healthcare applications,in this paper,we investigate the use of private blockchain technologies to assess their feasibility for healthcare applications.We create testing scenarios using HyperLedger Fabric to explore different criteria and use-cases for healthcare applications.Additionally,we thoroughly evaluate the representative test case scenarios to assess the blockchain-enabled security criteria in terms of data confidentiality,privacy and access control.The experimental evaluation reveals the promising benefits of private blockchain technologies in terms of security,regulation compliance,compatibility,flexibility,and scalability.

Sparse representation for machine learning the properties of defects in 2D materials

Two-dimensional materials offer a promising platform for the next generation of(opto-)electronic devices and other high technology applications.One of the most exciting characteristics of 2D crystals is the ability to tune their properties via controllable introduction of defects.However,the search space for such structures is enormous,and ab-initio computations prohibitively expensive.We propose a machine learning approach for rapid estimation of the properties of 2D material given the lattice structure and defect configuration.The method suggests a way to represent configuration of 2D materials with defects that allows a neural network to train quickly and accurately.We compare our methodology with the state-of-the-art approaches and demonstrate at least 3.7 times energy prediction error drop.Also,our approach is an order of magnitude more resource-efficient than its contenders both for the training and inference part.