Minimum Error Rate Research Articles

Federated Learning and Autonomous UAVs for Hazardous Zone Detection and AQI Prediction in IoT Environment

Air pollution monitoring, finding the hazardous zone, and future air quality predictions have recently become a significant issue for many researchers. With the adverse effect of low air quality on human health, it has become necessary for predicting the air quality index (AQI) accurately and on time. The unmanned aerial vehicle (UAV) can collect air quality data with high spatial and temporal resolutions. Using a fleet of UAVs could be considered a good option. In the proposed work, we implement a distributed federated learning (FL) algorithm within a UAV swarm that collects air quality data using built-in sensors. A scheme for finding the area with the highest AQI value is proposed using swarm intelligence. The collected data are then fed to a CNN-LSTM model to predict the AQI. The trained local model is sent to the central server, and the server aggregates the received models from UAVs in the swarm. A global model is created and is transmitted to the UAV swarm again in the next iteration. The proposed architecture is compared with other time-series models. The results show that the proposed model predicts AQI daily with a minimal error rate on a real-time data set from Delhi.

Feature selection and classification in breast cancer prediction using IoT and machine learning

Breast cancer (BC) is the most commonly found disease among women all over the world. The early diagnosis of breast cancer can potentially reduce the mortality rate and increase the chances of a successful treatment. Paper focuses on proposing a methodology to conduct early diagnosis of breast cancer using the Internet of Things and Machine Learning. The main objective of the paper is to explore the machine learning techniques in predicting breast cancer with IoT devices.Proposed classifier resulted in 98%, 97%, 96% and 98% of precision, recall, F_Measure and accuracy, respectively. The minimum error rate for the classifier have also been determined and found to be 34.21%, 45.82%8, 64.47% of Mean Absolute Error (MAR), Root Mean Square Error (RMSE) and Relative Absolute Error (RAE), respectively. It was evident through the obtained results that the MLP classifier yields a higher accuracy with a minimum error rate when compared to LR and RF.

Molecular insights into a mechanism of resveratrol action using hybrid computational docking/CoMFA and machine learning approach

A phytoalexin, Resveratrol remains a legendary anticancer drug candidate in the archives of scientific literature. Although earlier wet-lab experiments rendering its multiple biological targets, for example, epidermal growth factors, Pro-apoptotic protein p53, sirtuins, and first apoptosis signal (Fas) receptor, Mouse double minute 2 (MDM2) ubiquitin-protein ligase, Estrogen receptor, Quinone reductase, etc. However, notwithstanding some notable successes, identification of an appropriate Resveratrol target(s) has remained a major challenge using physical methods, and hereby limiting its translation into an effective therapeutic(s). Thus, computational insights are much needed to establish proof-of-concept towards potential Resveratrol target(s) with minimum error rate, narrow down the search space, and to assess a more accurate Resveratrol signaling pathway/mechanism at the starting point. Herein, a brute-force technique combining computational receptor-, ligand-based virtual screening, and classification-based machine learning, reveals the precise mechanism of Resveratrol action. Overall, MDM2 ubiquitin-protein ligase (4OGN.pdb) and co-crystallized quinone reductases 2 (4QOH.pdb) were found two suitable drug targets in the case of Resveratrol derivatives. Indeed, carotenoid cleaving oxygenase together with later twos gave gigantic momentum in guiding the rational drug design of Resveratrol derivatives. These molecular modeling insights would be useful for Resveratrol lead optimization into a more precise science. Communicated by Ramaswamy H. Sarma

MADDPG-Based Security Situational Awareness for Smart Grid with Intelligent Edge

Advanced communication and information technologies enable smart grids to be more intelligent and automated, although many security issues are emerging. Security situational awareness (SSA) has been envisioned as a potential approach to provide safe services for power systems’ operation. However, in the power cloud master station mode, massive heterogeneous power terminals make SSA complicated, and failure information cannot be promptly delivered. Moreover, the dynamic and continuous situational space also increases the challenges of SSA. By taking advantages of edge intelligence, this paper introduces edge computing between terminals and the cloud to address the drawbacks of the traditional power cloud paradigm. Moreover, a deep reinforcement learning algorithm based on the edge computing paradigm of multiagent deep deterministic policy gradient (MADDPG) is proposed. The minimum processing cost under the premise of minimum detection error rate is taken to analyze the smart grids’ SSA. Performance evaluations show that the algorithm under this paradigm can achieve faster convergence and the optimal goal, namely the provision of real-time protection for smart grids.

Optimal Voting Rule and Minimization of Total Error Rate in Cooperative Spectrum Sensing for Cognitive Radio Networks

Optimal Voting Rule and Minimization of Total Error Rate in Cooperative Spectrum Sensing for Cognitive Radio Networks

Fractional sequential likelihood ascent search detector for interference cancelation in massive MIMO systems in 5G technology

ABSTRACT Interference is considered as the major problem in the next-generation wireless systems to attain higher throughput. The conventional interference cancelation techniques attain a theoretical breach in endorsing the wireless systems. However, the interference in the signals causes an error or imprecise estimation of the channel for future fifth-generation (5 G) transmissions. Thus, this paper proposes a technique, named Fractional Sequential Likelihood Ascent Search (Fractional-SLAS) for mitigating the interference in massive Multiple Input Multiple Output (MIMO) systems in 5 G technology. The proposed Fractional-SLAS is the integration of Fractional calculus (FC) and Sequential Likelihood Ascent Search Detector (SLAS). Initially, the signals are transmitted through the transmitter and undergo the encoding and modulation process. Then, the obtained modulated signals are fetched using the transmitting antenna that transmits the signals to the receiver. At the receiver side, interference is generated due to the number of cross antennas. Thus, the interference in the signals is eradicated by applying the proposed Fractional-SLAS at the receiver end. Hence, the proposed interference mitigation method is completely eradicated from the signals without any delay or loss in the quality of the transmitted signal. The proposed Fractional-SLAS provides superior performance with minimal Bit Error Rate (BER), Symbol Error Rate (SER), and throughput with values 0.00006 dB, 0.00006 dB, and 0.96 bps.

Adaptive Management of Multimodal Biometrics—A Deep Learning and Metaheuristic Approach

This paper introduces the framework for adaptive rank-level biometric fusion: a new approach towards personal authentication. In this work, a novel attempt has been made to identify the optimal design parameters and framework of a multibiometric system, where the chosen biometric traits are subjected to rank-level fusion. Optimal fusion parameters depend upon the security level demanded by a particular biometric application. The proposed framework makes use of a metaheuristic approach towards adaptive fusion in the pursuit of achieving optimal fusion results at varying levels of security. Rank-level fusion rules have been employed to provide optimum performance by making use of Ant Colony Optimization technique. The novelty of the reported work also lies in the fact that the proposed design engages three biometric traits simultaneously for the first time in the domain of adaptive fusion, so as to test the efficacy of the system in selecting the optimal set of biometric traits from a given set. Literature reveals the unique biometric characteristics of the fingernail plate, which have been exploited in this work for the rigorous experimentation conducted. Index, middle and ring fingernail plates have been taken into consideration, and deep learning feature-sets of the three nail plates have been extracted using three customized pre-trained models, AlexNet, ResNet-18 and DenseNet-201. The adaptive multimodal performance of the three nail plates has also been checked using the already existing methods of adaptive fusion designed for addressing fusion at the score-level and decision-level. Exhaustive experiments have been conducted on the MATLAB R2019a platform using the Deep Learning Toolbox. When the cost of false acceptance is 1.9, experimental results obtained from the proposed framework give values of the average of the minimum weighted error rate as low as 0.0115, 0.0097 and 0.0101 for the AlexNet, ResNet-18 and DenseNet-201 based experiments respectively. Results demonstrate that the proposed system is capable of computing the optimal parameters for rank-level fusion for varying security levels, thus contributing towards optimal performance accuracy.

Performance Analysis of RKHS Based Detectors for Nonlinear NLOS Ultraviolet Communications

Ultraviolet (UV) communication has emerged as a promising solution for providing non-line-of-sight (NLOS) wireless connectivity due to strong molecular and aerosol scattering at UV wavelength. However, performance of UV based communication systems is severely impaired due to nonlinear transfer-characteristics of light emitting diode (LED), which degrades the overall symbol error rate (SER) performance. In addition, UV based communication systems are also impaired by multiplicative distortion due to turbulence, that causes detrimental instantaneous outages. Hence, in this work, first an expression for the outage probability is derived for a nonlinear UV communication system via analytical characterization of the statistics of the additive distortion. Further, utilizing the proposed analytical model for additive distortion, the error rate of reproducing kernel Hilbert space (RKHS) based detectors is quantified for the nonlinear outdoor NLOS UV channel. Additionally, using the derived expression for error-rate, an RKHS based minimum symbol error rate (MSER) equalizer is formulated to mitigate the distortion due to LED nonlinearity, and to enhance the error-rate performance of the considered nonlinear NLOS UV link. Convergence of the proposed MSER equalizer is analyzed, and improvements in error-rate promised by the proposed equalizer are validated by computer simulations over typical NLOS UV channels.

Big data and artificial intelligence based early risk warning system of fire hazard for smart cities

Driven by information technology, big data provides new development opportunities for city construction. People use multiple scientific advancements such as the Internet of Things (IoT) for data acquisition and Artificial Intelligence (AI) for big data analytics to enhance the integration and sharing of data and optimize the basic standards of smart cities. Past few years, the concept behind the Internet of Things has been a major research topic in the development of smart cities, education, industry, and commerce. Services and applications of IoT are the major factors for creating a sustainable urban life that is employed by smart cities. The stakeholders of smart cities become more aware, efficient, and interactive using Information and Communication Technology (ICT) in IoT. The applications of smart cities based on IoT have been increased in number which leads to production and increase in the amount of data and its processing. Moreover, the city stakeholders and governments take prior actions/precautions for processing the collected data from the IoT devices and predicting the future consequences for securing a sustainable environment. Artificial Intelligence is one of the key research techniques which several researchers have analysed and proved to be the best in improving the performance of detecting fire hazard in smart cities. In this research, a Deep Belief Network (DBN) with Recurrent LSTM Neural Network (R-LSTM-NN) is proposed for prediction of big data that are collected from smart cities based on IoT. Moreover, the proposed model mainly concentrates in predicting the fire hazard values that gathered from smart cities using IoT devices. The simulation results show that the proposed technique proves to be better when compared with other existing techniques in terms of accuracy, precision, recall, and F-1 score. The proposed model detects the fire outbreak with a 98.4% of accuracy that having 0.14% of minimal error rate. Furthermore, the proposed model can be used for various prediction problems that are faced by smart cities.

WITHDRAWN: Cloud based Machine learning with advanced predictive Analytics using Google Colaboratory

Abstract With the exponential elevation in the velocity, variety and volume of the data the need of high performance applications and platforms are explored very frequently. To process the huge amount of data with the effective analysis patterns and predictions, the deep learning applications are used. Deep Learning enables to extract the feature points from the dataset automatically so that better predictions and knowledge discovery can be implemented with higher degree of accuracy and minimum error rate. Colab is an open, cloud-friendly notebook environment. It helps you and the members of your team to edit documents, and how you use Google Docs. Colab supports several common research libraries that can be loaded conveniently on your notebook. Colaboratory is a collaborative initiative developed by Google to encourage machine learning and research. The world of Jupyter's notebook doesn't need any configuration and runs in the cloud absolutely. This work is focusing on the integration of Google Colab for advanced applications of Machine Learning and Deep Learning on Cloud.

Wisdom of crowds benefits perceptual decision making across difficulty levels

Decades of research on collective decision making has claimed that aggregated judgment of multiple individuals is more accurate than expert individual judgement. A longstanding problem in this regard has been to determine how decisions of individuals can be combined to form intelligent group decisions. Our study consisted of a random target detection task in natural scenes, where human subjects (18 subjects, 7 female) detected the presence or absence of a random target as indicated by the cue word displayed prior to stimulus display. Concurrently the neural activities (EEG signals) were recorded. A separate behavioural experiment was performed by different subjects (20 subjects, 11 female) on the same set of images to categorize the tasks according to their difficulty levels. We demonstrate that the weighted average of individual decision confidence/neural decision variables produces significantly better performance than the frequently used majority pooling algorithm. Further, the classification error rates from individual judgement were found to increase with increasing task difficulty. This error could be significantly reduced upon combining the individual decisions using group aggregation rules. Using statistical tests, we show that combining all available participants is unnecessary to achieve minimum classification error rate. We also try to explore if group aggregation benefits depend on the correlation between the individual judgements of the group and our results seem to suggest that reduced inter-subject correlation can improve collective decision making for a fixed difficulty level.

A Self-Adaptive Deep Learning-Based Algorithm for Predictive Analysis of Bitcoin Price

Bitcoin generates a massive amount of data every day due to its innate transparency and capacity of operating completely decentralised. In this paper, we introduce on-chain metrics derived from data on the bitcoin network that enable us to describe the state and usage of the underlying network. Based on their characteristics, we classify them into user, miner, exchange activities and run a correlation analysis with the price to understand the dynamics of bitcoin’s price and its underlying mechanics. Using the correlated data, we develop a deep learning model. However, determining the best values of parameters in a deep learning model can be a very challenging and time-consuming task. Hence, we propose a self-adaptive technique using a jSO optimization algorithm to find the best values of these parameters to accurately predict the price of bitcoin. Compared to traditional LSTM model, our approach is highly accurate and optimised with a minimum error rate.

Comparison of Detection and Classification of Hard Exudates Using Artificial Neural System vs. SVM Radial Basis Function in Diabetic Retinopathy

Diabetic Retinopathy (DR) is a disease that occurs in the eye which results in blindness as it passes to proliferative stage. Diabetes can significantly result in symptoms like blurring of vision, kidney failure, nervous damage. Hence it has become necessary to identify retinal damage that occurs in diabetic eye due to raised glucose level in its initial stage itself. Hence automated detection of anamoly has become very essential. The appearance of crimson and yellow lesions is considered as the earliest symptoms of DR which are called as hemorrhages and exudates. If DR is analysed at initial stage, blindness does not occur. The damage in retina can hinder the light that passes through nerves of the eye leading to visual loss. The motivation behind this research is to reduce the number of false positives by accurate detection which is possible using proposed fuzzy system based on ANN. Though several classifiers are available to detect the exudates this paper makes analysis of support vector machine using radial basis kernel function with proposed ANN technique. Also, adaptive neuro fuzzy inference system segmentation is performed after feature extraction technique, which makes classifer to outperform. The evaluation results showed that proposed artificial neural network based on fuzzy approach attained significant results compared to other classifiers. Moreover, the proposed algorithm has significant accuracy of 94% and minimum error rate has been observed.

Brain Tumour Detection by Gamma DeNoised Wavelet Segmented Entropy Classifier

Magnetic resonance imaging (MRI) is an essential tool for detecting brain tumours. However, identification of brain tumours in the early stages is a very complex task since MRI images are susceptible to noise and other environmental obstructions. In order to overcome these problems, a Gamma MAP denoised Strömberg wavelet segmentation based on a maximum entropy classifier (GMDSWS-MEC) model is developed for efficient tumour detection with high accuracy and low time consumption. The GMDSWS-MEC model performs three steps, namely pre-processing, segmentation, and classification. Within the GMDSWS-MEC model, the Gamma MAP filter performs the pre-processing task and achieves a significant increase in the peak signal-to-noise ratio by removing noisy artefacts from the input brain image. After pre-processing, Strömberg wavelet transform segmentation is carried out to partition the pre-processed image into a number of blocks based on the features extracted from the image. Finally, the maximum entropy classifier identifies and locates the tumour from the input image based on extracted features with high accuracy and minimal error rate. Using a number of MRI images, experimental evaluation and comparison of the proposed model and existing methods is carried out on the basis of four metrics: peak signal-to-noise ratio, tumour detection accuracy, error rate, and tumour detection time with respect to MRI image size. The proposed model offers superior performance in terms of all four metrics.

Application of Distance Metric Learning to Automated Malware Detection

Distance metric learning aims to find the most appropriate distance metric parameters to improve similarity-based models such as k-Nearest Neighbors or k-Means. In this paper, we apply distance metric learning to the problem of malware detection. We focus on two tasks: (1) to classify malware and benign files with a minimal error rate, (2) to detect as much malware as possible while maintaining a low false positive rate. We propose a malware detection system using Particle Swarm Optimization that finds the feature weights to optimize the similarity measure. We compare the performance of the approach with three state-of-the-art distance metric learning techniques. We find that metrics trained in this way lead to significant improvements in the k-Nearest Neighbors classification. We conducted and evaluated experiments with more than 150,000 Windows-based malware and benign samples. Features consisted of metadata contained in the headers of executable files in the portable executable file format. Our experimental results show that our malware detection system based on distance metric learning achieves a 1.09 % error rate at 0.74 % false positive rate (FPR) and outperforms all machine learning algorithms considered in the experiment. Considering the second task related to keeping minimal FPR, we achieved a 1.15 % error rate at only 0.13 % FPR.

Gaussian bilateral filtered discrete Hartley feature transformation based infomax boosting for hyperspectral image classification

Hyperspectral Image (HSI) is a spatially sampled image collected from a lot of neighboring narrowed spectrum bands via hyperspectral sensor. The process of HSIs is a difficult obligation because of the high-dimensional image features. Conventional techniques mainly utilize hand-made characteristics that are not fit for classification. For the purpose of enhancing the correctness and reducing the overall time complexity, an efficient technique called Gaussian Bilateral Filtered Hartley Feature Transformation Based Infomax Boost Classification (GBFHFT-IBC) is introduced. The input hyperspectral image is divided into the number of spectral bands. The proposed GBFHFT-IBC method includes three fundamental procedures, which include preprocessing, characteristics classification and extraction. Preprocessing is carried out using a Gaussian kernelized bilateral filter that replaces the pixel intensity from the picture with the weighted to take the position of the intensity of every pixel from the picture with the prejudiced average of neighboring pixels resulting in it removes the noisy pixels and improve the image quality. After preprocessing, the different characteristics like texture, color and shape are extracted from the image using the Discrete Hartley transformation technique. With the extracted features, the Infomax Boost method is applicable when classifying different scenes from the spectrum band, which has to be grouped into various categories with the top categorization accuracy that consider the minimal error rates. The experiments are done using the hyperspectral picture dataset composed of various factors like categorization accuracy, PSNR, positive and negative rate, and timeline complexity considering the number of spectral bands. The observed result shows that the presented GBFHFT-IBC method improves the hyperspectral image classification correctness, PSNR and minimized negative and positive rates, which include timeline complexity compared to using the sophisticated techniques.

Symbol Error Rate Minimization Based Constructive Interference Precoding for Multi-User Systems

Symbol level precoding based on the concept of constructive interference has been recognized as an advanced version of conventional interference-avoidance precoding for multi-user transmission. With the full knowledge of channel state information (CSI) and symbol information, inter-user interference is adjusted to bring constructive effect to the desired signal. However, the existing schemes are limited within the concept of channel pre-equalization which could be further improved. In this paper, we propose a symbol error rate (SER) minimization based constructive interference precoding scheme for multi-user systems. The constructive interference region is firstly defined based on the analysis of the SER expression, which implies that the proposed scheme is essentially a symbol pre-detection scheme. Then, we prove that the optimal precoded signal for SER minimization shall be the linear combination of the channel vectors. Accordingly, a modified feasible direction algorithm is developed to handle the complex expression of SER, where an extra projection step is proposed to enhance the efficiency of the feasible direction. Finally, the proposed scheme is further extended for transmit power optimization and imperfect CSI cases. Simulation results highlight the efficiency of the modified feasible direction, and the superiority of the proposed scheme in terms of SER and transmit power.

A Robust Multi-Objective Feature Selection Model Based on Local Neighborhood Multi-Verse Optimization

Classification tasks often include, among the large number of features to be processed in the datasets, many irrelevant and redundant ones, which can even decrease the efficiency of classifiers. Feature Selection (FS) is the most common preprocessing technique utilized to overcome the drawbacks of the high dimensionality of datasets and often has two conflicting objectives: The first function aims to maximize the classification performance or reduce the error rate of the classifier. In contrast, the second function is designed to minimize the number of features. However, the majority of wrapper FS techniques are developed for single-objective scenarios. Multi-verse optimizer (MVO) is considered as one of the well-regarded optimization approaches in recent years. In this paper, the binary multi-objective variant of MVO (MOMVO) is proposed to deal with feature selection tasks. The standard MOMVO suffers from local optima stagnation, so we propose an improved binary MOMVO to deal with this issue using the memory concept and personal best of the universes. The experimental results and comparisons indicate that the proposed binary MOMVO approach can effectively eliminate irrelevant and/or redundant features and maintain a minimum classification error rate when dealing with different datasets compared with the most popular feature selection techniques. Furthermore, the 14 benchmark datasets showed that the proposed approach outperforms the stat-of-art multi-objective optimization algorithms for feature selection.

Sparse decision feedback equalization for underwater acoustic channel based on minimum symbol error rate

Abstract Underwater Acoustic Channels (UAC) have inherent sparse characteristics. The traditional adaptive equalization techniques do not utilize this feature to improve the performance. In this paper we consider the Variable Adaptive Subgradient Projection (V-ASPM) method to derive a new sparse equalization algorithm based on the Minimum Symbol Error Rate (MSER) criterion. Compared with the original MSER algorithm, our proposed scheme adds sparse matrix to the iterative formula, which can assign independent step-sizes to the equalizer taps. How to obtain such proper sparse matrix is also analyzed. On this basis, the selection scheme of the sparse matrix is obtained by combining the variable step-sizes and equalizer sparsity measure. We call the new algorithm Sparse-Control Proportional-MSER (SC-PMSER) equalizer. Finally, the proposed SC-PMSER equalizer is embedded into a turbo receiver, which perform turbo decoding, Digital Phase-Locked Loop (DPLL), time-reversal receiving and multi-reception diversity. Simulation and real-field experimental results show that the proposed algorithm has better performance in convergence speed and Bit Error Rate (BER).

Unified Authentication and Access Control for Future Mobile Communication‐Based Lightweight IoT Systems Using Blockchain

The Internet of Things (IoT) is a new revolution defined by heterogeneous devices made up of intelligent, omnipresent items that are all hooked up to The internet. These devices are frequently implemented in different areas to offer innovative programs in various industrial applications, including intelligent urban, medicine, and societies. Such Internet of Things (IoT) equipment generates a large volume of private and safety information. Because IoT systems are resource‐constrained in terms of operation, memory, and communication capability, safeguarding accessibility to them is a difficult task. In the blockchain concept, the majority, or even all network nodes, check the validity and accuracy of exchanged data before accepting and recording it, whether this data is related to financial transactions, measurements of a sensor, or an authentication message. In evaluating the validity of exchanged data, nodes must reach a consensus in order to perform a special action, in which case the opportunity to enter and record transactions and unreliable interactions with the system is significantly reduced. Recently, in order to share and access management of IoT devices’ information with a distributed attitude, a new authentication protocol based on blockchain has been proposed, and it is claimed that this protocol satisfies user privacy while preserving security. Today’s identification and authentication techniques have substantial shortcomings due to rapidly growing prevalence and implementation. As a result, the protection of such gadgets is critical to guarantee the program’s efficacy and safety. A decentralized authentication and access control method for lightweight IoT systems are proposed in this work and a blockchain‐based system that enables identification and secures messaging with IoT nodes. The technique is built on fog information systems and the idea of a blockchain system; when contrasted to something like a blockchain‐based verification system, the testing findings show that the suggested mechanism outperforms it. The authentication and verification system undergoes using the blockchain technique. Our method takes advantage of blockchain’s inherent advantages while also associated with development authentication systems. Our suggested blockchain‐based approach, structure, and layout, in particular, provide for transparency, consistency, and provenance while also providing tamper‐proof records. The article describes the general systems architectural style and the analysis and execution of a real scenario as just a prototype system. The authentication included give as protected prototype that can transmit data with secured protocol and achieves minimum error rate.