An Online Algorithm for the Dynamic Maximal Dense Tree Problem

Abstract. The Online Maximal Dense Tree problem is as follows: given a weighted directed graph and a source node, users issue online requests for connection to the source node. A request can either be accepted or rejected (the admission control decision). If the connection request is accepted, it must be connected to the source or to a node previously connected to the source (the routing decision). The objective is to maximize the total number of connections while keeping the connection density , i.e. the ratio of accepted requests to the weight of the spanning tree, sufficiently high. The primary motivation for the Maximal Dense Tree problem is the Online Capacitated Multicast admission control and routing problem. In the Online Capacitated Multicast problem, we are given a communication network with limited link capacities and a set of signal source nodes. Users generate online requests for connection to the signal sources, and the network administrator has to make the admission control and routing decisions. The goal of the network administrator is to maximize the total number of users connected subject to the network capacity constraints. The Online Maximal Dense Tree problem is also faced by a cable TV operator who wishes to connect as many customers as possible while keeping down the amount of wiring per customer. Informally, the Online Maximal Dense Tree algorithm must ``gamble' on certain geographic areas, connecting nodes which are unprofitable to start with, in the hope that eventually enough requests will arrive in its vicinity to make the investment profitable. In this paper we present a randomized online algorithm for the Maximal Dense Tree problem that guarantees acceptance of a (1- ɛ) factor of the requests accepted by the optimum offline algorithm with the expectation of density being at most polylogarithmically lower than that of the offline algorithm. This yields an online capacitated multicast algorithm whose throughput is only poly-logarithmically lower than that of the optimum offline algorithm. Previous work on multicast routing and maximal dense tree problems either made probabilistic assumptions or resulted in linear performance gaps with the offline algorithm. Attempts to solve the Online Maximal Dense Tree problem have also lead to the development of the first polylogarithmic approximation algorithms for the k -MST and the Prize Collecting Salesman problems [AABV].     

A privacy-preserving model based on differential approach for sensitive data in cloud environment

A large amount of data and applications need to be shared with various parties and stakeholders in the cloud environment for storage, computation, and data utilization. Since a third party operates the cloud platform, owners cannot fully trust this environment. However, it has become a challenge to ensure privacy preservation when sharing data effectively among different parties. This paper proposes a novel model that partitions data into sensitive and non-sensitive parts, injects the noise into sensitive data, and performs classification tasks using k-anonymization, differential privacy, and machine learning approaches. It allows multiple owners to share their data in the cloud environment for various purposes. The model specifies communication protocol among involved multiple untrusted parties to process owners’ data. The proposed model preserves actual data by providing a robust mechanism. The experiments are performed over Heart Disease, Arrhythmia, Hepatitis, Indian-liver-patient, and Framingham datasets for Support Vector Machine, K-Nearest Neighbor, Random Forest, Naive Bayes, and Artificial Neural Network classifiers to compute the efficiency in terms of accuracy, precision, recall, and F1-score of the proposed model. The achieved results provide high accuracy, precision, recall, and F1-score up to 93.75%, 94.11%, 100%, and 87.99% and improvement up to 16%, 29%, 12%, and 11%, respectively, compared to previous works.

     

Hybrid neural network model for reconstruction of occluded regions in multi-gait scenario

In real-time situations such as airports, railway stations, and shopping complexes, etc. people walk in a group, and such a group of walking persons termed as multi-gait (MG). In these situations, occlusion is a serious issue that affects gait recognition performance. This issue of occlusion of body regions affects the extraction of gait features for the correct recognition of an object. The objective of this article is to reconstruct occluded regions at the preprocessing stage, which can be used for human recognition in the MG scenario. The article is divided into two folds. Firstly, we segment five regions of interest such as ankle, knee, wrist, elbow, and shoulder. We propose a particle swarm optimization (PSO) based neural network (NN) called hybrid NN to solve this problem. The performance of the proposed model is validated on our constructed dataset (SMVDU-MG), considering two view directions i.e. lateral (left to right) and oblique (left to right diagonal). Experimental results show that the proposed model gives better performance compared to an artificial neural network and alternating least square (ALS) method based on mean square error (MSE) and mean absolute percentage error (MAPE) as a performance measure function.

     

Change point detection for compositional multivariate data

Change point detection algorithms have numerous applications in areas of medical condition monitoring, fault detection in industrial processes, human activity analysis, climate change detection, and speech recognition. We consider the problem of change point detection on compositional multivariate data (each sample is a probability mass function), which is a practically important sub-class of general multivariate data. While the problem of change-point detection is well studied in univariate setting, and there are few viable implementations for a general multivariate data, the existing methods do not perform well on compositional data. In this paper, we propose a parametric approach for change point detection in compositional data. Moreover, using simple transformations on data, we extend our approach to handle any general multivariate data. Experimentally, we show that our method performs significantly better on compositional data and is competitive on general data compared to the available state of the art implementations.

     

Towards a super-resolution based approach for improved face recognition in low resolution environment

Multimedia Tools and Applications - The video surveillance activity generates a vast amount of data, which can be processed to detect miscreants. The task of identifying and recognizing an object...     

A data hiding technique for digital videos using entropy-based blocks selection

Microsystem Technologies - The technique of hiding knowledge in certain details is steganography. One of the main trends of computer infrastructure and connectivity following the advent of the...     

A computational method of forecasting based on high-order fuzzy time series

This paper presents a computational method of forecasting based on high-order fuzzy time series. The developed computational method provides a better approach to overcome the drawback of existing high-order fuzzy time series models. Its simplicity lies with the use of differences in consecutive values of various orders as forecasting parameter and a w-step fuzzy predictor in place of complicated computations of fuzzy logical relations. The objective of the present study is to examine the suitability of various high-order fuzzy time series models in forecasting. The general suitability of the developed method has been tested by implementing it in the forecasting of student enrollments of the University of Alabama and in the forecasting of crop (Lahi) production, a case of high uncertainty in time series data. The results obtained have been compared in terms of average error of forecast to show superiority of the proposed model.     

Performance Analysis of Machine Learning Algorithms for Classifying Hand Motion-Based EEG Brain Signals

Brain-computer interfaces (BCIs) records brain activity using electroencephalogram (EEG) headsets in the form of EEG signals; these signals can be recorded, processed and classified into different hand movements, which can be used to control other IoT devices. Classification of hand movements will be one step closer to applying these algorithms in real-life situations using EEG headsets. This paper uses different feature extraction techniques and sophisticated machine learning algorithms to classify hand movements from EEG brain signals to control prosthetic hands for amputated persons. To achieve good classification accuracy, denoising and feature extraction of EEG signals is a significant step. We saw a considerable increase in all the machine learning models when the moving average filter was applied to the raw EEG data. Feature extraction techniques like a fast fourier transform (FFT) and continuous wave transform (CWT) were used in this study; three types of features were extracted, i.e., FFT Features, CWT Coefficients and CWT scalogram images. We trained and compared different machine learning (ML) models like logistic regression, random forest, k-nearest neighbors (KNN), light gradient boosting machine (GBM) and XG boost on FFT and CWT features and deep learning (DL) models like VGG-16, DenseNet201 and ResNet50 trained on CWT scalogram images. XG Boost with FFT features gave the maximum accuracy of 88%.     

SVM based robust watermarking for enhanced medical image security

Medical images are more typical than any other ordinary images, since it stores patient’s information for diagnosis purpose. Such images need more security and confidentiality as total diagnosis depends on it. In telemedicine applications, transmission of medical image via open channel, demands strong security and copyright protection. In our proposed robust watermarking model, a double layer security is introduced to ensure the robustness of embedded data. The embedded data is scrambled using a unique key and then a transform domain based hybrid watermarking technique is used to embed the scrambled data into the transform coefficients of the host image. The data embedding in medical images involves more attention, so that the diagnosis part must not be affected by any modification. Therefore, Support Vector Machine (SVM) is used as a classifier, which classify a medical image into two regions i.e. Non Region of Interest (NROI) and Region of Interest (ROI) to embed watermark data into the NROI part of the medical image, using the proposed embedding algorithm. The objective of the proposed model is to avoid any quality degradation to the medical image. The simulation is performed to measure the Peak Signal to Noise Ratio (PSNR) for imperceptibility and Structural Similarity Index (SSIM) to test the robustness. The experimented result shows, robustness and imperceptibility with SSIM of more than 0.50 and PSNR of more than 35 dB for proposed watermarking model.

     

Analysis and optimization of noises of an analog circuit via PSO algorithms

Microsystem Technologies - The strategy for analysis of noise generated in the analog circuit is presented here. Further, methodology for optimization of noise to improve the performance of the...