Minimum Time Complexity Research Articles

Deep Learning-Based Network Security Situation Prediction for Sensor-Enabled Networks

Aims and background: Network security detection has become increasingly complex due to the proliferation of Internet nodes and the ever-changing nature of network architecture. To address this, a multi-layer feedforward neural-network has been employed to construct a model for security threat detection, which has enhanced network security protection. Objectives and Methods: Improving prediction accuracy and real-time performance, this research suggests an optimal strategy based on Clockwork Recurrent-Neural-Networks(CW-RNNs) to handle nonlinearity and temporal dynamics in network security circumstances. We get the model to pick up on both the short-term and long-term temporal aspects of network-security situations by using the clock-cycle RNN. To further improve the network security scenario prediction model, we tune the network hyperparameters using the Grey-Wolf-Optimization(GWO) technique. By incorporating a clock-cycle for hidden units, the model can improve its pattern recognition capabilities by learning short-term knowledge from high-frequency update modules and preserving long-term memory from low-frequency update modules. Results: The optimized clock-cycle RNN achieves better prediction accuracy than competing network models when it comes to extracting nonlinear and temporal characteristics of network security scenarios, according to the experimental data. Conclusions: In addition, our method is perfect for tracking massive amounts of data transmitted by sensor networks because of its minimal time complexity and outstanding real-time performance.

Efficient Intrusion Detection in Patient Health Records Based on LSTM-Based RNN

Advancements in Information and Communication Technology applications play an important role in the field of healthcare and bio-medical engineering. The process of image processing and analysis starts from receiving visual information to giving out the description of the scene for improving the visual appearance of the human viewer and extract the features of the data. Moreover, IDS can be deployed along with other security mechanisms as a line of defence to ensure security of system and network resources. There have been various efforts in designing IDS using Machine Learning (ML) techniques. Additionally, by developing a hybrid strategy for intrusion detection and classification and using feature engineering approaches to extract significant features for learning, among other things, efforts have been made to improve the classification performance of ML-based IDS. However, as networking technology have advanced, attack types have evolved as well. For this reason, an efficient and successful intrusion detection and classification system must be created. To address the issue and achieve good generalization ability for intrusion detection and classification, the paper presents empirical analysis of LSTM based RNN classifiers. The suggested methods' effectiveness is assessed using a range of performance metrics, such as recall, f-score, accuracy, precision, and False Positive Rate (FPR). The LSTM based RNN method recognize attacks with 99.2% accuracy with minimum time complexity (5 s).

STUDY OF IMAGE SEGMENTATION METHODS WITH MRI IMAGES

Digital image processing is the use of a digital computer to process digital images. Image processing transforms input images into digital form for certain operations to obtain useful information. Segmentation is a well-known process used in image processing that partitions input images into different regions. Image segmentation is a sub-area of computer vision and digital image processing for grouping similar segments of an image under respective class labels. Several methods were performed with neutrosophic sets on dissimilar image-processing domains. However, the denoising and segmentation were not carried out accurately with minimal time complexity. To address these issues, many image segmentation methods are reviewed.

A new efficient decoder of linear block codes based on ensemble learning models: case of boosting

<p>Error-correcting codes are used to partially or completely correct errors as much as possible, while ensuring high transmission speeds. Several Machine Learning (ML) models such as Logistic Regression and Decision tree have been applied to correct transmission errors. Among the most powerful ML techniques are aggregation methods which have yielded to excellent results in many areas of research. It is this excellence that has prompted us to consider their application for the hard decoding problem. In this sense, we have successfully designed, tested and validated our proposed EL-BoostDec decoder (hard decision decoder based on Ensemble Learning - Boosting technique) which is based on computing of the syndrome of the received word and on using Ensemble Learning techniques to find the corresponding corrigible error. The obtained results with EL-BoostDec are very encouraging in terms of the binary error rate (BER) that it offers. Practically EL-BoostDec has succeed to correct 100% of errors that have weights less than or equal to the correction capacity of studied codes. The comparison of EL-BoostDec with many competitors proves its power. A study of parameters which impact on EL-BoostDec performances has been established to obtain a good BER with minimum run time complexity.</p>

Ridge Regressive Data Preprocessed Quantum Deep Belief Neural Network for Effective Trajectory Planning in Autonomous Vehicles

Trajectory planning is a new research topic in the field of automated vehicles (AVs). It is the process of identifying a trajectory for the vehicle to traverse its environment without obstacle collision. Trajectories are computed fast in real time as the environment constantly changes with time. To address these problems, the Ridge Regressive Data Preprocessed Quantum Deep Belief Neural Network (RRDPQDBNN) model is developed. The RRDPQDBNN model intends to carry out effective trajectory planning in autonomous vehicles through enhanced accuracy and minimum time complexity. Initially, in the RRDPQDBNN model, vehicle data are extracted and transmitted to the input layer. Secondly, Ridge Regressive Data Preprocessing is performed to eliminate noisy data from collected vehicle data. Finally, quantum data clustering is carried out in the RRDPQDBNN model to identify the severity of the risk without collision during the trajectory. This, in turn, is effective trajectory planning performed in autonomous vehicles. Experimental results are computed in terms of clustering accuracy, clustering time, error rate, precision, and recall. From experimental results, the RRDPQDBNN model increases clustering accuracy by 11%, precision by 13%, and recall by 5%, as well as reduces clustering time by 31% and error rate by 58% compared to existing methods.

Efficient and Secure Data Deduplication in Distributed Cloud Storage: A Fault-Tolerant Model Using Active Learning for Big Data Management

As the big data era advances, more and more redundant data are being expressed in various ways. Data deduplication knowledge has never been more important than it is now for lowering redundant data storage and enhancing data quality. Connecting several data tables and identifying distinct entries that point to the same item is typically required, particularly when multi-source data deduplication is involved. Active learning minimises the amount of data that needs to be annotated and trains the classical by choosing the data pieces with the greatest evidence divergence. This approach offers special benefits when handling massive data annotations. Unfortunately, the majority of existing active learning techniques are rarely used for data deduplication jobs and only use classical entity matching. The research effort suggests a model, a distributed cloud storage method that ensures effectiveness, security, and high availability, to close this research gap. By intelligently distributing data subsets among servers, the suggested approach achieves fault tolerance while preserving redundancy for high availability. This suggested model reduces the amount of storage space and upkeep required for the data while eliminating duplicate copies. Additionally, the data is kept in a highly secure and effective manner. The suggested model's efficacy in fault tolerance, cost reduction, batch auditing, and block- and file-level deduplication is demonstrated by the experimental findings. It performs better than current systems thanks to its robust fault tolerance, minimal time complexity, and excellent deduplication capabilities.

An efficient Cucconi based feature extraction with random decision forest classification for improved sentiment analysis

Sentiment analysis is a form of opinion mining technique that identifies the polarity of extracted opinions. Nowadays, opinion mining has become an important research area in recent decades to identify the polarity of the statements. Various research works have been carried out on sentiment analysis. However, the existing sentimental analysis techniques, such as time and space complexity, still have considerable limitations. To deal with these issues, this paper proposed the Cucconi Feature Extracted Random Decision Forest Classification (CFDFC) Approach. The main objective of the CFDFC approach is to provide effective sentiment analysis with improved accuracy and reduced time complexity. The proposed CFDFC framework comprises pre-processing, feature extraction, and classification. The pre-processing step eliminates stop words and stem words from user reviews. After the pre-processing step, the feature extraction process is carried out to minimize the dimensionality and time consumption for opinion classification. Cucconi's projective feature extraction process is used in this work to reduce dimensionality. Finally, the classification process is formulated using a random decision forest classifier. The random decision forest classifier uses the ID3 DT (decision tree) as a weak learner to classify the review statements. The performance evaluation of the proposed approach is carried out using performance metrics such as accuracy, error rates, recall values, and time and space complexities concerning the number of review statements gathered from the dataset. The results show that the proposed CFDFC model achieves remarkable accuracy, recall, and minimal time complexity compared to existing methods.

Cucconi Feature Extracted Random Decision Forest Classification for Efficient Sentiment Analysis

Sentiment is the method of conveying the opinion by the customer for particular product e-commerce website. Sentiment analysis is otherwise termed as opinion mining that identifies the polarity of extracted opinions. Nowadays, opinion mining concept received large interest by many researchers to identify the polarity of the statements. A number of scholars have conducted their research on efficient sentiment analysis with better accuracy. But the space complexity and time complexity performance did not reduced using existing classification techniques. To deal with these issues, CFDFC (Cucconi Feature Extracted Random Decision Forest Classification) Approach is presented. The primary aim of CFDFC Approach is to perform effective sentiment analysis with improved accuracy and reduced time complexity. The number of user review statement is collected from the input dataset. The proposed CFDFC Technique comprises of pre-processes, feature extractions, and classifications. Pre-processes eliminate stop words and stem words from user reviews. After pre-processing, the features (i.e. keywords) extraction process is performed to minimize the dimensionality and time consumption for opinion classification. This work uses cucconi projective feature extractions in CFDFC to squeeze out opinion words from reviews where cucconi projective feature extraction is generally a dimensionality reduction technique used for identifying the projections in multidimensional data. Finally, the classification process is carried out using random decision forest classifier. The random decision forest classifier uses the ID3 DT (decision tree) as a weak learner to classify the review statements with the extracted features. By using the voting scheme, random decision forest classifications finally classify instances with higher accuracy. This again is useful to boost the performance of sentiment analysis. The comprehensive experimental assessment is carried out using various parameters including accuracy, error rates, recall values , time and space complexities with regard to the number of review statements gathered from the dataset.The statistical results obtained show that the proposed CFDFC Technique achieves remarkable accuracy, recall, and minimal time complexity than the current methods.

Network Identification for Diffusively Coupled Networks With Minimal Time Complexity

The theory of network identification, namely identifying the (weighted) interaction topology among a known number of agents, has been widely developed for linear agents. However, the theory for nonlinear agents using probing inputs is far less developed, relying on dynamics linearization, and thus cannot be applied to networks with non-smooth or discontinuous dynamics. We use global convergence properties of the network, which can be assured using passivity theory, to present a network identification method for nonlinear agents. We do so by linearizing the steady-state equations rather than the dynamics, achieving a sub-cubic time algorithm for network identification. We also study the problem of network identification from a complexity theory standpoint, showing that the presented algorithms are optimal in terms of time complexity. We demonstrate the presented algorithm in two case studies with discontinuous dynamics.

An effective cryptanalysis of DES for secure communication using hybrid cryptanalysis and deep neural network

SummaryIn today's world, information security plays a key role in data storage and communication owing to the modern evolution of digitized data interchange in electronic mode. Cryptography is a widely preferred technique for securing transmitted information by transforming the original text into cipher text. A few cryptographic techniques have the inability to protect the data which are vulnerable to a distinct class of attacks. Therefore, a reliable cryptographic technique is necessitated for enlarging information security. In this paper, a new hybrid cryptanalysis (HCA) model has been proposed to acquire optimal cryptanalysis of data encryption standard (DES). It combines linear cryptanalysis (LCA) and neural cryptanalysis (NCA) for enhancing the performance of the cryptographic system with minimal time complexity. Primarily, the HCA model employs LCA to break cryptographic codes by analyzing linear approximations of the cryptographic algorithm. NCA is then applied with the aid of a deep neural network for identifying patterns in larger datasets. These patterns can be further utilized to break encryption. The efficacy of the proposed HCA model will be assessed through the assessment of three different datasets. The results manifest that the accuracy of the proposed model is increased up to 97.66% and the time needed to break encryption can be reduced.

A novel COVID diagnosis and feature extraction based on discrete wavelet model and classification using X-ray and CT images.

Recently, the Covid-19 pandemic has affected several lives of people globally, and there is a need for a massive number of screening tests to diagnose the existence of coronavirus. For the medical specialist, detecting COVID-19 cases is a difficult task. There is a need for fast, cheap and accurate diagnostic tools. The chest X-ray and the computerized tomography (CT) play a significant role in the COVID-19 diagnosis. The advancement of deep learning (DL) approaches helps to introduce a COVID diagnosis system to achieve maximum detection rate with minimum time complexity. This research proposed a discrete wavelet optimized network model for COVID-19 diagnosis and feature extraction to overcome these problems. It consists of three stages pre-processing, feature extraction and classification. The raw images are filtered in the pre-processing phase to eliminate unnecessary noises and improve the image quality using the MMG hybrid filtering technique. The next phase is feature extraction, in this stage, the features are extracted, and the dimensionality of the features is diminished with the aid of a modified discrete wavelet based Mobile Net model. The third stage is the classification here, the convolutional Aquila COVID detection network model is developed to classify normal and COVID-19 positive cases from the collected images of the COVID-CT and chest X-ray dataset. Finally, the performance of the proposed model is compared with some of the existing models in terms of accuracy, specificity, sensitivity, precision, f-score, negative predictive value (NPV) and positive predictive value (PPV), respectively. The proposed model achieves the performance of 99%, 100%, 98.5%, and 99.5% for the CT dataset, and the accomplished accuracy, specificity, sensitivity, and precision values of the proposed model for the X-ray dataset are 98%, 99%, 98% and 97% respectively. In addition, the statistical and cross validation analysis is conducted to validate the effectiveness of the proposed model.

RGSO-UAV: Reverse Glowworm Swarm Optimization inspired UAV path-planning in a 3D dynamic environment

Three-dimensional path planning for UAVs is a very complex, NP-hard optimization problem. It is an effort to resolve the best feasible trajectory between the source and the destination while prohibiting collision in a dynamic environment. Many researchers have proposed different deterministic and non-deterministic solutions to the path-planning problem. However, it is still open to new promising methods to acquire better quality solutions with minimum time complexity. This article presents a novel methodology inspired by the Reverse Glowworm Swarm Optimization (RGSO) algorithm to resolve this problem for the UAV without colliding with any dynamic and static obstructions appearing in its path. A tuned path is generated after the initial one to optimize further and smoothen the trajectory. The proposed method has been extensively experimented with, and the outcomes show it outperforms the other algorithm in a three-dimensional dynamic environment in a path-planning strategy. The result shows that our proposed scheme reduces the value of the cost function by approximately 49% - 107% less than other existing approaches, and the execution time of this mechanism reduces by 2% - 61% compared with other existing methods. Thus, the proposed technique RGSO-UAV is an optimal and energy-efficient path-planning model in flying ad-hoc networks that enhance UAV's lifetime.

A Secure Medical Image Transmission System Based On 2D Logistic Map and Diffie-Hellman Key Exchange Mechanisms

With the tremendous growth of searchable visual media, the content-based medical image retrieval and computer-aided diagnosis systems have become popular in recent years to improve knowledge and provide facilities for radiologists. Medical images transferred throughout public networks demand a mechanism that guarantees image privacy, ownership and source of origin reliability, and image integrity verification. For this reason, secure image retrieval and diagnosis scheme have been given considerable interest due to users’ security concerns. This work proposed a secure framework based on a two-dimensional (2D) chaotic map with Diffie–Hellman key exchange protocols to ensure patient information privacy and security. Consequently, from a security and protection perspective, the objective is to provide a privacy procedure for medical image retrieval systems through image encryption technique combined with a secure key exchange procedure to minimize the possibility of secret key interception by an unauthorized person. Simulation results and security analysis show that the suggested technique could protect images with minimal time complexity and a high level of security while also resisting numerous attacks.

Survival study on cyclone prediction methods with remote sensing images

Image classification has large interest for many decades in the remote sensing communities to reduce injure caused by cyclones. A cyclone is the leading rotating storm that includes the strong wind and rain. It included the number of interrelated features like eye, cyclone pathway, wind speed, generated storm surges, rainfall intensity and so on. Among the features, it is essential one to find in which direction cyclone travels and it influence the areas increasing the damage to life and assets. The cyclone prediction is a key issue where image intensity described the pattern characteristics at various stages. Many existing works have been designed in cyclone prediction for attaining better prediction accuracy. But, it is difficult to enhance the cyclone prediction accuracy with minimum time complexity. In order to address these issues, cyclone prediction can be carried out using deep leaning methods.

Articulation Point Based Quasi Identifier Detection for Privacy Preserving in Distributed Environment

These days, huge data size requires high-end resources to be stored in IT organizations premises. They depend on cloud for additional resource necessities. Since cloud is a third-party, we cannot guarantee high security for our information as it might be misused. This necessitates the need of privacy in data before sharing to the cloud. Numerous specialists proposed several methods, wherein they attempt to discover explicit identifiers and sensitive data before distributing it. But, quasi-identifiers are attributes which can spill data of explicit identifiers utilizing background knowledge. Analysts proposed strategies to find quasi- identifiers with the goal that these properties can likewise be considered for implementing privacy. But, these techniques suffer from many drawbacks like higher time consumption and extract more quasi identifiers which decreases data utility. The proposed work overcomes this drawback by extracting minimum required quasi attributes with minimum time complexity.

Aging Facial Recognition for Feature Extraction Using Adaptive Fully Recurrent Deep Neural Learning

Abstract The face recognition (FR) process identifies or confirms a person with the help of images and videos. The traditional aging FR (AFR) method encounters numerous issues as a result of age-related biological transformation. An adaptive fully recurrent deep neural learning (AFRDNL) technique is presented in this research to improve FR accuracy (FRA) with minimal time complexity (TC). Feature extraction and classification are two processes included in the proposed technique. The AFRDNL technique gathers facial images from the database and trains the face images with three layers. To learn the facial features, three hidden layers are employed in the AFRDNL technique. Finally, the AFRDNL technique utilizes the Gaussian activation function for matching extracted testing features with earlier saved training features. This process is repeated until a minimal training error with a higher FRA is achieved. Experimental evaluation is carried out with three image datasets like Face and Gesture Recognition Research Network, MORPH and Cross-Age Labeled faces in the Wild (CALFW) datasets using different metrics, such as FRA, false-positive rate (FPR), TC and F1score. The experimental results confirm that the AFRDNL technique effectively increases the FRA and F1score and minimizes the FPR and TC more effectively than the state-of-the-art methods.

Machine Learning Technique to Detect Radiations in the Brain

The brain of humans and other organisms is affected in various ways through the electromagnetic field (EMF) radiations generated by mobile phones and cell phone towers. Morphological variations in the brain are caused by the neurological changes due to the revelation of EMF. Cellular level analysis is used to measure and detect the effect of mobile radiations, but its utilization seems very expensive, and it is a tedious process, where its analysis requires the preparation of cell suspension. In this regard, this research article proposes optimal broadcasting learning to detect changes in brain morphology due to the revelation of EMF. Here, Drosophila melanogaster acts as a specimen under the revelation of EMF. Automatic segmentation is performed for the brain to attain the microscopic images from the prejudicial geometrical characteristics that are removed to detect the effect of revelation of EMF. The geometrical characteristics of the brain image of that is microscopic segmented are analyzed. Analysis results reveal the occurrence of several prejudicial characteristics that can be processed by machine learning techniques. The important prejudicial characteristics are given to four varieties of classifiers such as naïve Bayes, artificial neural network, support vector machine, and unsystematic forest for the classification of open or nonopen microscopic image of D. melanogaster brain. The results are attained through various experimental evaluations, and the said classifiers perform well by achieving 96.44% using the prejudicial characteristics chosen by the feature selection method. The proposed system is an optimal approach that automatically identifies the effect of revelation of EMF with minimal time complexity, where the machine learning techniques produce an effective framework for image processing.

Proxy-Based Deep Learning Framework for Spectral–Spatial Hyperspectral Image Classification: Efficient and Robust

Deep convolutional networks have been extensively deployed in hyperspectral image (HSI) classification. Reaching for high accuracy, the existing deep-learning-based methods commonly deepen or widen their networks for better performance, which brings higher computational complexity and the risk of overfitting. Although the introduction of the residual module and batch-normalization reduces the generalization degradation in complex networks, the mainstream methods still suffer from low robustness to the noise. To tackle these issues, a compact proxy-based deep learning framework is proposed to perform highly accurate HSI classification with superb efficiency and robustness. In this article: 1) novel deep proxies are integrated to replace the dense classifier layers in conventional networks, which represents specific classes in deep embedding space and enables fast and reliable convergence; 2) the proxy-based feature embedding is studied in distance metric and similarity metric, and compatible dual-metric loss functions are designed for further optimized embedding distribution, which leads to more robust generalization; and 3) state-of-the-art performance and robustness are demonstrated by the proposed framework on mainstream HSI data sets with the minimal network scale and time complexity.

Performance evaluation of outlier detection techniques in production timeseries: A systematic review and meta-analysis

Time-series data have been extensively collected and analyzed in many disciplines, such as stock market, medical diagnosis, meteorology, and oil and gas industry. Numerous data in these disciplines are sequence of observations measured as functions of time, which can be further used for different applications via analytical or data analytics techniques (e.g., to forecast future price, climate change, etc.). However, presence of outliers can cause significant uncertainties to interpretation results; hence, it is essential to remove the outliers accurately and efficiently before conducting any further analysis. A total of 17 techniques that belong to statistical, regression-based, and machine learning (ML) based categories for outlier detection in timeseries are applied to the oil and gas production data analysis. 15 of these methods are utilized for production data analysis for the first time. Two state-of-the-art and high-performance techniques are then selected for data cleaning which require minimum control and time complexity. Moreover, performances of these techniques are evaluated based on several metrics including the accuracy, precision, recall, F1 score, and Cohen’s Kappa to rank the techniques. Results show that eight unsupervised algorithms outperform the rest of the methods based on the synthetic case study with known outliers. For example, accuracies of the eight shortlisted methods are in the range of 0.83–0.99 with a precision between 0.83 and 0.98, compared to 0.65–0.82 and 0.07–0.77 for the others. In addition, ML-based techniques perform better than statistical techniques. Our experimental results on real field data further indicate that the k-nearest neighbor (KNN) and Fulford-Blasingame methods are superior to other outlier detection frameworks for outlier detection in production data, followed by four others including density-based spatial clustering of applications with noise (DBSCAN), and angle-based outlier detection (ABOD). Even though the techniques are examined with oil and gas production data, but the same data cleaning workflow can be used to detect timeseries’ outliers in other disciplines.

The exponential-time hypothesis and the relative complexity of optimization and logical reasoning problems

Obtaining lower bounds for NP-hard problems has for a long time been an active area of research. Algebraic techniques introduced by Jonsson et al. (2017) [4] show that the fine-grained time complexity of the parameterized ▪ problem correlates to the lattice of strong partial clones. With this ordering they isolated a relation R such that ▪ can be solved at least as fast as any other NP-hard ▪ problem. In this paper we extend this method and show that such languages also exist for the surjective SAT problem, the max ones problem, the propositional abduction problem, and the Boolean valued constraint satisfaction problem over finite-valued constraint languages. These languages may be interesting when investigating the borderline between polynomial time, subexponential time and exponential-time algorithms since they in a precise sense can be regarded as NP-hard problems with minimum time complexity. Indeed, with the help of these languages we relate all of the above problems to the exponential time hypothesis (ETH) in several different ways.