Search

Bipolar fuzzy graph is more precise than a fuzzy graph when dealing with imprecision as it is focusing on the positive and negative information of each vertex and edge. Nowadays, researchers have utilized bipolar fuzzy graphs in decision-making problems. Bipolar fuzzy competition graphs aid to compute the competition between the vertices in bipolar fuzzy graphs. To depict the best competitions among the competitions of bipolar fuzzy graphs, the best bipolar fuzzy competition graph can be defined using bipolar fuzzy α-cut and the strength of the competition between the vertices can also be determined. Fuzzy graphs are used well to frame modelling in real-time problems. In particular, when the real-time scenario is modelled using the bipolar fuzzy graph, it gives more precision and flexibility. At present, researchers have focused on decision-making techniques with bipolar fuzzy graphs. The DEMATEL method is one of the powerful decision-making tools. It effectively analyses the complicated digraphs and matrices. The fuzzy DEMATEL technique can convert the interrelations between factors into an intelligible structural model of the system and divide them into cause and effect groups. Therefore, this study attempts to design the DEMATEL method under the bipolar fuzzy environment. To illustrate this proposed technique, the problem of identifying the best mobile network is taken. With this method, the benefits and drawbacks of networks are measured and a complicated bipolar fuzzy directed graph can be transformed into a viewed structure.

Pattern mining from graph transactional data (GTD) is an active area of research with applications in the domains of bioinformatics, chemical informatics and social networks. Existing works address the problem of mining frequent subgraphs from GTD. However, the knowledge concerning the coverage aspect of a set of subgraphs is also valuable for improving the performance of several applications. In this regard, we introduce the notion of subgraph coverage patterns (SCPs). Given a GTD, a subgraph coverage pattern is a set of subgraphs subject to relative frequency, coverage and overlap constraints provided by the user. We propose the Subgraph ID-based Flat Transactional (SIFT) framework for the efficient extraction of SCPs from a given GTD. Our performance evaluation using three real datasets demonstrates that our proposed SIFT framework is indeed capable of efficiently extracting SCPs from GTD. Furthermore, we demonstrate the effectiveness of SIFT through a case study in computer-aided drug design.

COVID-19 has affected every individual physically or physiologically, leading to substantial impacts on how they perceive and respond to the pandemic’s danger. Due to the lack of vaccines or effective medicines to cure the infection, an urgent control measure is required to prevent the continued spread of COVID-19. This can be achieved using advanced computing, such as artificial intelligence (AI), machine learning (ML), deep learning (DL), cloud computing, and edge computing. To control the exponential spread of the novel virus, it is crucial for countries to contain and mitigate interventions. To prevent exponential growth, several control measures have been applied in the Kingdom of Saudi Arabia to mitigate the COVID-19 epidemic. As the pandemic has been spreading globally for more than a year, an ample amount of data is available for researchers to predict and forecast the effect of the pandemic in the near future. This article interprets the effects of COVID-19 using the Susceptible-Infected-Recovered (SIR-F) while F-stands for ‘Fatal with confirmation,’ age-structured SEIR (Susceptible Exposed Infectious Removed) and machine learning for smart health care and the well-being of citizens of Saudi Arabia. Additionally, it examines the different control measure scenarios produced by the modified SEIR model. The evolution of the simulation results shows that the interventions are vital to flatten the virus spread curve, which can delay the peak and decrease the fatality rate.

Application of deep learning techniques for de novo generation of molecules, termed as inverse molecular design, has been gaining enormous traction in drug design. The representation of molecules in SMILES notation as a string of characters enables the usage of state of the art models in natural language processing, such as Transformers, for molecular design in general. Inspired by generative pre-training (GPT) models that have been shown to be successful in generating meaningful text, we train a transformer-decoder on the next token prediction task using masked self-attention for the generation of druglike molecules in this study. We show that our model, MolGPT, performs on par with other previously proposed modern machine learning frameworks for molecular generation in terms of generating valid, unique, and novel molecules. Furthermore, we demonstrate that the model can be trained conditionally to control multiple properties of the generated molecules. We also show that the model can be used to generate molecules with desired scaffolds as well as desired molecular properties by conditioning the generation on scaffold SMILES strings of desired scaffolds and property values. Using saliency maps, we highlight the interpretability of the generative process of the model.

Coverage path planning methodology for an autonomous underwater vehicle to search multiple non-overlapping regions has been proposed in the paper. The proposed methodology is based on the genetic algorithm (GA). The GA used in the proposed methodology has been tuned for the specific problem, using design of experiment on an equivalent travelling salesman problem benchmark instance. Optimality of the generated paths was analysed through simulation studies. Results indicated that the proposed methodology generated shorter paths in comparison to conventional methods.

The Almost 1.3 million casualties are reported round a calendar year due to road accidents. Advanced collision avoidance systems play major role in predicting the collision risk to avoid accidents. The existing deep learning algorithms are unable to predict the crash risk efficiently. In the existing system, Long Short Term Memory algorithm is used to predict the crash risk where weights are not optimized. The objective is to predict the rear end collision risk with optimized weight by combining Long Short Term Memory(LSTM) with Levenberg–Marquardt (LM) algorithms. The proposed algorithm predicts the collision risk considering vehicle, driver related factors, and temporal dependencies. Next Generation Simulation Project (NGSIM) dataset is used to evaluate the proposed model. The performance of the proposed system is compared with the performance of Long Short Term Memory and Back Propagation Neural Network. 95.6% of accuracy is achieved by LM-LSTM based Time series Deep Network Model. The prediction accuracy has been improved considerably than the existing algorithms. There is the drastic improvement in minimization of false alarm and missed alarm rate. The main advantage of the proposed system is that it will present warning at the time of high collision risk and it helps drivers to prevent from accident.

Objective Monitoring fetal cardiac activity during pregnancy is a critical part of assessing the fetus's health. Non-invasive fetal electrocardiogram (NIFECG) is a safe emerging fetal cardiac monitoring approach receiving considerable interest. This paper proposes an effective way to separate the fetal ECG signal from the single-channel abdominal ECG signals. Methods The paper proposes a novel algorithm based on time–frequency analysis combining fractional Fourier transform (FrFT) and wavelet analysis to extract fetal ECG from abdominal signals at higher accuracy. The abdominal signals acquired from pregnant women are preprocessed and subjected to suppressing maternal ECG using fractional Fourier transform and maximum likelihood estimate. The estimated maternal signal is removed from the abdominal ECG. The residue is processed using wavelet decomposition to obtain a clean fetal ECG and calculate fetal heart rate. Results The proposed algorithm's performance is validated using signals from the Daisy database and Physionet challenge 2013 set-a dataset. Real-time signals acquired using Powerlab data acquisition hardware are also included for validation. The obtained results show that the proposed algorithm can effectively extract the fetal ECG and accurately estimate the fetal heart rate. Conclusion The proposed method is a promising and straightforward algorithm for FECG extraction. Fractional Fourier transform maps the time domain abdominal signal into the fractional frequency domain, distinguishing the fetal and maternal ECG. The Wavelet transform can efficiently denoise the residue abdominal signal and provides a clean fetal ECG. The proposed approach achieves 98.12% of accuracy, 98.85% of sensitivity, 99.16% of positive predictive value, and 99.42% of F1 measure.

Background: Coral reefs are one of the most oldest and dynamic ecosystems of the world. Manual annotation of coral reef is not possible due to lacking consistency and objectivity in human labeling. Objective: Manual annotation consumes an enormous number of hours to annotate every coral image and video frames as well as human resource. An emblematic survey states that more than 400 person hours are required to annotate 1000 images. Incidentally, some coral species have different shapes, sizes and colors, most of the corals seem indistinguishable to the human eye. In order to avoid the contradictory classifications, an expert system that can automatically annotate the corals is essential to improve the accuracy of classification. Method: The proposed improved WLD extract texture features from six combinations of color channels like (1) R Channel, (2) G Channel (3) B Channel (4) RG Channel (5) GB Channel and (6) BR Channel of an image in a holistic way while preserving their relations. The extracted features are analyzed, and classified using CNN Classifier. Results: Experiments are carried out with EILAT, RSMAS, EILAT 2 and MLC2008 datasets and the proposed improved WLD based coral reef classification is found to be appropriate. From the accuracy point of view, the improved WLD demonstrate higher accuracy compared to other state-of-the-art techniques. Conclusion: This paper analyzes the role of Improved WLD for feature extraction to classify coral reefs. For this purpose EILAT, RSMAS, EILAT 2 and MLC2008 datasets have been used. It is observed that the proposed IWLD based classifier gives promising results for coral reef classification.

Generally, radar echo is analysed in the assumptions that echo comes from stationary processes. Signal processing algorithms of atmospheric radar echoes are based on stationarity assumptions. In this paper, we propose a technique for processing the radar echoes by still preserving their non-stationary nature. The proposed algorithm is based on the complex empirical mode decomposition (CEMD) of non-stationary complex atmospheric radar signals. The well-established technique Hilbert Huang transform has been applied for the practical radar echoes collected from the Mesosphere-Stratosphere-Troposphere radar located at Gadanki Andhra Pradesh. The data is subjected to proposed CEMD algorithm and results are obtained and Stationarity is tested using the wavelet transform. The inference from the obtained results is of two-fold: Hilbert spectrum is very well localized and can be used for stationarity test like Wavelet spectrum, the frequency components in Hilbert spectrum lies in the signal region of Fourier spectrum thereby resembling it. For better interpretation, the algorithm is also applied for simulated signals under both stationary and non-stationary environments. The results motivate us for better exploitation of HHT for the spectral analysis of atmospheric radar echoes.

Mining online reviews to extract opinion targets and words are substantial tasks in fine-grained opinion mining. The main aim is to mine sensible multi-grain aspects and opinion words from unlabeled reviews. In this paper, Combined Aspect based Sentiment Model (CASM) is propounded to cooperatively mine multi-grain features and opinions. CASM deals with aspects, opinions, sentiment polarity and granularity concurrently. Support Vector Machine-Radial Basis Function kernel (SVM-RBF) classifier is applied to improve CASM by splitting aspects and opinion words. CASM-SVM-RBF deals with two different kinds of aspects and opinions: general and particular aspects, overall opinions and aspect-precise opinions. Candidates with improved confidence are mined as opinion targets or words. Index Terms:Aspects, Opinions, Sentiment, Support Vector Machine, Radial Basis Function, Support Vector Machine (SVM), Radial Basis Function (RBF)

Non-invasive extraction of fetal electrocardiogram (FECG) by processing the abdominal signals is emerging as a promising approach in the areas of obstetrics and gynecology. This paper presents a two-stage improved non-linear adaptive filter for FECG extraction. The reference input to the adaptive noise canceler (ANC) is first processed using an adaptive neuro-fuzzy inference system (ANFIS) to estimate the non-linear maternal component in abdominal signals. A parallel sub-filter (PSF) ANC is proposed to assess the fetal ECG from the abdominal signal. The PSF-ANC decomposes a single adaptive filter into multiple sub-filters to improve the convergence performance. The filter coefficients of PSF-ANC adaptively obtained using normalised least mean square algorithm by minimizing the mean square error. Different error and common error algorithms are proposed based on the computation of the error signal. A synthetic data from the FECG synthetic database is used to evaluate the convergence performance. Two real-time data from the Daisy database and the Non-invasive FECG database from Physionet are used to evaluate the proposed ANFIS-PSF’s performance qualitative and quantitatively. The results justify the performance improvement of proposed ANFIS-PSF ANC compared to the state of art techniques. The proposed scheme achieves a sensitivity of 97.92%, 94.52% accuracy, a positive predictive value of 94.66%, and an F1 score of 96.12%.

Mobile IPv6 (MIPv6) is considered inefficient to support mobility due to larger handover delay and signaling overhead. Therefore, Hierarchical MIPv6 (HMIPv6) is designed by introducing a Mobile Anchor Point (MAP) in the MIPv6 architecture. The MAP considerably drops the handoff delay and signaling load for mobility management in IPv6. The Three Layered MIPv6 (TLMIPv6), the focus of this paper, is influenced by the benefits of placing MAPs for efficient mobility management. In this model, three MAPs are placed in the architecture to reduce signaling cost and handoff latency. These MAPs are placed hierarchically in a tree like architecture, and the movement of nodes is coordinated by different MAP based on nodes’ movement patterns. The behavior of the proposed model is simulated under various traffic scenarios and mobility conditions and compared with MIPv6 and HMIPv6 and Flow Based Distributed Mobility Management (FBDM) protocols. The results depict that when users are less mobile or confined their movements to a small geographical area, the proposed TLMIPv6 outperforms MIPv6, HMIPv6, and FBDM in handoff latency and signaling costs. Some suitable application scenarios for adopting TLMIPv6 are also mentioned at the end of the paper. The future scopes of the work are outlined.

Reliable communication in ad hoc networks necessitates mobile nodes to synchronize among themselves for cooperation. The cooperation in ad hoc networks is enforced through the implementation of encryption algorithms and intrusion detection systems. Most of the intrusion detection and encryption algorithms are not effective enough to address the extent to which a participative mobile node may trust other interacting mobile nodes for data forwarding. The existing mitigation frameworks consider packet forwarding capability as the single parameter for calculating trust values which cannot be appropriate for computing the accurate trust factor as reliable nodes are highly impacted by data rate, throughput, delay and energy consumption. An Integrated Context-based Mitigation Framework (ICMF) is proposed for facilitating effective mitigation of rendezvous point misbehavior and for enhancing the performance of the network. This proposed ICMF framework facilitates rendezvous point misbehavior detection by determining Grey theory Inspired Discriminating Factor (GTIDF) that is contextually derived from multiple factors including data rate, throughput, delay and energy consumptions using the benefits of the Grey theory. From the simulation results of the proposed ICMF framework, improved root node attackers survivability rate and root node attackers categorization rate are inferred when compared to the benchmarked baseline mitigation frameworks.

Cornea is the outmost layer of an eye helps to focuses the light rays towards the retinal layer of the eye. The irregular thickness of the corneal layer results in poor focus of light rays over the retinal layer and hence it results in blur vision. Lasik is a surgical procedure made for correcting the irregular thickness of the cornea to certain extent for making the light rays to fall exactly on the retinal layer. In order to undergo with a lasik procedure, an eye must have sufficient thickness of corneal layer to tolerate the medical procedure. Similarly, the corneal layers are can't be operated after certain extent. Therefore there is a need for pre-surgical planning by measuring the thickness availability of the corneal layer. The proposed work is engaged to identify the three major boundaries of the corneal layer using a capsule network based algorithm. The proposed work is segregated as preprocessing, classification and segmentation. A hybrid speckle noise reduction filter was employed in the preprocessing stage to minimize the noise presence in the corneal images. Then the images are moved further to train the ClassCaps algorithm to classify a better noiseless image from the group of test images. The modified SegCaps algorithm was utilized in this work to detect the three major boundaries of the cornea from the noiseless image output from the ClassCaps algorithm. The performance of the proposed algorithm was verified with the several classification and segmentation algorithm to prove its accuracy.

Purpose The purpose of this paper is to design an Internet-of-Things (IoT) architecture-based Diabetic Retinopathy Detection Scheme (DRDS) proposed for identifying Type-I or Type-II diabetes and to specifically advise the Type-II diabetic patients about the possibility of vision loss. Design/methodology/approach The proposed DRDS includes the benefits of automatic calculation of clip limit parameters and sub-window for making the detection process completely adaptive. It uses the advantages of extended 5 × 5 Sobels operator for estimating the maximum edges determined through the convolution of 24 pixels with eight templates to achieve 24 outputs corresponding to individual pixels for finding the maximum magnitude. It enhances the probability of connecting pixels in the vascular map with its closely located neighbourhood points in the fundus images. Then, the spatial information and kernel of the neighbourhood pixels are integrated through the Robust Semi-supervised Kernelized Fuzzy Local information C-Means Clustering (RSKFL-CMC) method to attain significant clustering process. Findings The results of the proposed DRDS architecture confirm the predominance in terms of accuracy, specificity and sensitivity. The proposed DRDS technique facilitates superior performance at an average of 99.64% accuracy, 76.84% sensitivity and 99.93% specificity. Research limitations/implications DRDS is proposed as a comfortable, pain-free and harmless diagnosis system using the merits of Dexcom G4 Plantinum sensors for estimating blood glucose level in diabetic patients. It uses the merits of RSKFL-CMC method to estimate the spatial information and kernel of the neighborhood pixels for attaining significant clustering process. Practical implications The IoT architecture comprises of the application layer that inherits the DR application enabled Graphical User Interface (GUI) which is combined for processing of fundus images by using MATLAB applications. This layer aids the patients in storing the capture fundus images in the database for future diagnosis. Social implications This proposed DRDS method plays a vital role in the detection of DR and categorization based on the intensity of disease into severe, moderate and mild grades. The proposed DRDS is responsible for preventing vision loss of diabetic Type-II patients by accurate and potential detection achieved through the utilization of IoT architecture. Originality/value The performance of the proposed scheme with the benchmarked approaches of the literature is implemented using MATLAB R2010a. The complete evaluations of the proposed scheme are conducted using HRF, REVIEW, STARE and DRIVE data sets with subjective quantification provided by the experts for the purpose of potential retinal blood vessel segmentation.

In facelift surgeries, tracking the exact position of the patient’s facial nerves, blood vessels and other tissues can help the surgeons make the right decisions during surgery. Using Augmented Reality technologies that display the mapping of soft tissues beneath the skin, surgeons will be able to detect and locate the regions of cutting correctly prior to making the first cut. The study of Augmented Reality-assisted surgeries has not been found in facelift surgeries involving facial soft tissues, thus this journal can provide with invaluable first steps into the more concentrated studies involving this area. The current available systems in the oral and maxillofacial areas has shown limitation in supporting the elastic nature of facial soft tissues, which shape shifts and changes due to patient’s movement, or movement caused by surgeon during surgery. This paper aims to increase overlay accuracy by reducing elastic deformation error for Augmented Reality in facelift surgeries. The proposed system consists of a Gaussian Distribution and Tukey Weight (GDaTW) algorithm to reduce the deformation error after the geometric error algorithm had been performed. The test results confirm that the new algorithm improves the video accuracy by ~0.10 mm by reducing the overlay error caused by elastic deformation with the display framerate of 5–10 frames per second compared to 10–13 frames per second in existing system. The improvement proposed in this system increases the overlay accuracy by reducing elastic deformation error. The correct display of soft tissues in the mandibular region using Augmented Reality aims to aid plastic surgeons perform facelift surgeries with confidence, to avoid making the wrong cuts of vital areas occluded by the patient’s skin.

Cloud MANET is a latest technique in which individual smart devices joins the Cloud MANET and can communicate in a distributed fashion. This is advantageous, as the Smart device does not need any infrastructural establishments. These nodes communicate together. Several MANETS formed in manner can be connected to cloud and can avail cloud services in real time. In this paper we attempt to establish a virtual backbone of Cloud MANET nodes using the concept Connected Dominating Sets, we also introduced a lightweight security scheme in order to avoid blackhole and greyhole attacks. The algorithm uses Q learning technique for learning about the capacity of nodes and establishes the CDS in Cloud MANET. The entire set up is established with public key infrastructure to emulate block chain based security. The concept of smart contract is used to ensure that every transaction is recorded and any compromised nodes in the CDS is discovered and eliminated.

In emergency situations, cooperative positioning of vehicular nodes is essential for facilitating precise and stable information for achieving reliable data dissemination in Vehicular Ad hoc NETworks (VANETs). However, the existence of Non-Line-Of-Sight (NLOS) nodes degrades the accuracy in estimating ranging measurements introduced by the blockages from tall vehicles and buildings. In this paper, Raccoon Optimization Algorithm-based Accurate Positioning Scheme (ROA-APS) is proposed for improving the accuracy in the estimation of ranging measurements in order to determine the exact position of NLOS nodes. It is proposed for ensuring maximized reliability and reduced latency in the event of warning message exchange. It inherits the food rummaging style of real raccoons for speeding and strengthening the local and global search process involved in the estimation of NLOS node positions. It utilizes maximum probability of acquiring higher adaptability through active learning to attain better localization of NLOS nodes. It inherits the distance information for calculating the position accuracy associated with vehicle trajectory, distance information error and the number of vehicles. It also uses the method of weighted average to enforce more confidence to the distance information provided by neighboring nodes. The simulation experiments of the proposed ROA-APS using EstiNet simulators are conducted to determine its significance with respect to positioning accuracy, emergency message dissemination rate, positioning error, neighbor vehicles awareness rate and positioning time. The results confirm an increased mean emergency message dissemination rate, positioning accuracy and neighbor vehicles awareness rate by 16.21%, 14.38% and 15.16% when compared to the benchmarked schemes.

With an increasing number of web users, the data traffic generated by these users generates tremendous network traffic which takes a long time to connect with the web server. The main reason is, the distance between the client making requests and the servers responding to those requests. The use of the CDN (content delivery network) is one of the strategies for minimizing latency. But, it incurs additional cost. Alternatively, web caching and preloading are the most viable approaches to this issue. It is therefore decided to introduce a novel web caching strategy called optimized popularity-aware modified least frequently used (PMLFU) policy for information retrieval based on users' past access history and their trends analysis. It helps to enhance the proxy-driven web caching system by analyzing user access requests and caching the most popular web pages driven on their preferences. Experimental results show that the proposed systems can significantly reduce the user delay in accessing the web page. The performance of the proposed system is measured using IRCACHE data sets in real time.

Human adaptive mechatronics (HAM) device is operated using neuromuscular interface controller. The muscle activity is monitored with the help of electromyogram (EMG) signals. The change in signal strength due to the volunteering movement of body parts is detected by placing few electrodes on the skin surface. EMG signal is used as the control signal and it gives the movement coordination. The amplitude of the signal changes with respect to the muscle activity. The HAM device is made to operate depending upon the amplitude changes in the generated EMG signal. The option of using cybernetic loop facilitates the balance of the control error and the delayed response time of the system. This paper elaborates the working of human adaptive neuromuscular interface controller in mechatronics device and the simulation is carried out in real time approach for the different muscle activity mainly between the two actions: volunteer motion and intended motion.

This work addresses the automatic classification of arrhythmia beats into four generalized classes as described by the Association for the Advancement of Medical Instrumentation (AAMI) standard. We propose a method that includes time-series, statistical and frequency features of RR-interval, DWT, and EMD analysis of QRS morphology. Also, a data filtration technique using support vector selection and under-sampling is applied to find those features as well as data points having significant prediction capabilities. While testing the above combination on MIT-BIH arrhythmia database, adopting the inter-patient paradigm, we achieved 70%, 99.79%, 64.5%, and 80.55% Se and 61.76%, 94.64%, 83.22%, and 77.48% PPV for F, N, SVEB, and VEB classes respectively. Further, the proposed method reduced the classifier’s complexity through feature selection and computation time by data reduction while maintaining the generalization capability of the model. Another finding includes the significant contribution that RR-interval, 180–360 Hz and 0–45 Hz band power, and non-linear statistical characteristics have in distinguishing the arrhythmia classes. The feature and data selection criterion used is F -score and one-class classification by RBF-SVM respectively. The classifier used for building the final model is SVM with the cubic kernel.

Our day-to-day activity is highly influenced by development of Internet. One of the rapid growing area in Internet is E-commerce. People are eager to buy products from online sites like Amazon, embay, Flipkart etc. Customers can write reviews about the products purchased online. The purchasing of good through online has been increasing exponentially since last few years. As there is no physical contact with goods before purchasing through online, people totally rely on reviews about the product before purchasing it. Hence review plays an important role in deciding the quality of the product. There are many customers who give online reviews about the product after using it. Hence the quality of the product is decided by the reviews of the customers. Thus, detection of fake reviews has become one of the important task. The proposed system will help in finding such fake reviews about the product, so that the fake reviews can be eliminated. Therefore, the purchasing of the products will be totally based on the genuine reviews. The proposed system uses Deep Recurrent Neural Network (DRNN) to predict the fake reviews and the performance of the proposed method has compared with Naïve Bayes Algorithm. The proposed model shows good accuracy and can handle huge amount of data over the existing system.

Most of today’s every power system networks deals with a serious scenario of Power quality. This problem had ever more observed with the advent of practical hardware, in which it will carry out serious impact in the eminence of power supply in to the micro-grid networks. Matter by reason of power quality, it is produced and critical to a non-common normal current and voltage re-emergence. It takes with reference to the distress of sophisticated electronic gadgets and renewable vigor sources. The predominant matter is centers to the voltage enlargements and dips. In this paper the instigator introduces a precise method for the bulge of voltages and dips. In the direction of revise the topic pointed out above for modified power types of electronic cog is embraces. Solitary, dynamic voltage restorer (DVR), is a leading progressed control hardware that can be utilized in micro-grids. If any uncertainty produced in the micro-grid DVR act as most favorably to ease the power quality problems. This job clarifies the MATLAB consequences of a dynamic voltage restorer (DVR) demonstrating with investigation. Particular form of controller’s similar to PI and NN controller like (proportional integral and neural network) is utilized in this DVR system. In this system procedure, DVR NN controller actualizes modified through the conventional PID-controller can be used examine a builded Composite micro grid system with Renewable sources. The newly developed controller is faster than traditional process initiated controller. By the use of MATLAB replication tools, presentation of the system shall be considered. To find the performance of the suggested NN based DVR which is simulated for the power loss reduction, power factor correction, and active and reactive power flow control. From the simulation results, NN based DVR is better compared to PI based DVR.

There has been intense debate about lockdown policies in the context of Covid-19 for limiting damage both to health and to the economy. We present an AI-driven approach for generating optimal lockdown policies that control the spread of the disease while balancing both health and economic costs. Furthermore, the proposed reinforcement learning approach automatically learns those policies, as a function of disease and population parameters. The approach accounts for imperfect lockdowns, can be used to explore a range of policies using tunable parameters, and can be easily extended to fine-grained lockdown strictness. The control approach can be used with any compatible disease and network simulation models.

Computer screen images such as wallpaper, web pages and powerpoint images are compound images. As these images contain a mixture of textual, graphical, pictorial and smooth regions, compression of computer screen images necessitates accurate classification and segmentation of these regions. In this study, an improved compound image segmentation using automatic block classification with support vector machine (SVM) is presented. First, the input compound image is divided into several non-overlapping blocks, and then the statistical features embedded in each block are mined after applying discrete wavelet transform. Then, the SVM model is trained effectively by using the informative samples of fuzzy c-means clustering, which takes block-level edge features and block neighbourhood information as input. Finally, the compound image is classified into two classes such as text/graphics and picture/background with the trained SVM model. Experimental results show that the proposed method performs automatic block classification with high accuracy. As the proposed classifier uses both structural and contextual information as features, block classification accuracy has been improved to a great extent. Hence, the proposed method has made ∼6.2% improvement in block classification accuracy while comparing with existing approaches.

The Wireless Sensor Networks (WSN) comprises of countless transfer hubs that gather the ecological data from the sensor hub and send them to a sink or (cluster head) CH. The improvement of communication advancements has propelled the utilization of WSNs and the remote communication. Since WSNs turned out to be progressively mainstream, the nature of service extend by the WSN in the part of information collection, maintaining accuracy and transmission in a convenient way has caused more to notice the research framework of network system designers. However, the hubs are inclined to failure because of the vitality limitation, device failure, communication link error and malicious attack. The node insufficiency is the one of the most vital issue in the WSN. The proposed TIC calculation using fuzzy logic discovers the trust score for reinforcement hand-off hub task to defeat the issue in establishing the network.

This letter investigates the physical layer security of the data from the weak user (WU) against interception by the strong user (SU) in non-orthogonal multiple access (NOMA) systems. The proposed NOMA using directional modulation (NOMAD) allows access of the intended symbols at the WU while giving access to a different but valid lower order symbol alphabet to the SU for performing successive interference cancellation. The optimal lower order symbol alphabet and directional modulation vectors are designed in a multiple-input single-output framework. The sum and secrecy rate results show that NOMAD provides non-zero secrecy rates against the zero secrecy rate of NOMA and also delivers spectral efficiency benefit of NOMA. Further, NOMAD performs better than an orthogonal multiple access, such as a zero-forcing beamformer. A combined NOMA/NOMAD can present trade-offs between sum and secrecy rates. Bit error results are also presented confirming the advantages of the proposed NOMAD.

Classifying a particular image from a data set is a complex work for any image analyst. Generally, the output of medical image scan gives numerous images for analysis. In that, the image analyst has to manually predict a better noiseless image for computer-assisted image process program. Manual verification of all the output images from the scan device consumes a lot of time in predicting the abnormality of a patient. The proposed capsule network for noiseless image algorithm assists the image analyst by classifying the noiseless image from the data set for further computer-assisted image enhancement or segmentation program. The proposed algorithm performance is evaluated and compared with the existing algorithms in terms of accuracy, sensitivity, specificity, positive predictive value, and negative predictive value.

Solubility of drug molecules is related to pharmacokinetic properties such as absorption and distribution, which affects the amount of drug that is available in the body for its action. Computational or experimental evaluation of solvation free energies of drug-like molecules/solute that quantify solubilities is an arduous task and hence development of reliable computationally tractable models is sought after in drug discovery tasks in pharmaceutical industry. Here, we report a novel method based on graph neural network to predict solvation free energies. Previous studies considered only the solute for solvation free energy prediction and ignored the nature of the solvent, limiting their practical applicability. The proposed model is an end-to-end framework comprising three phases namely, message passing, interaction and prediction phases. In the first phase, message passing neural network was used to compute inter-atomic interaction within both solute and solvent molecules represented as molecular graphs. In the interaction phase, features from the preceding step is used to calculate a solute-solvent interaction map, since the solvation free energy depends on how (un)favorable the solute and solvent molecules interact with each other. The calculated interaction map that captures the solute-solvent interactions along with the features from the message passing phase is used to predict the solvation free energies in the final phase. The model predicts solvation free energies involving a large number of solvents within the limits of chemical accuracy. We also show that the interaction map captures the electronic and steric factors that govern the solubility of drug-like molecules and hence is chemically interpretable.

Over speeding is an important factor for occurring accidents. Road accident statistics shows two wheelers account for 25% of total road crash deaths and also one third of accidents are due to over speeding. But there is lagging of research in preventing the accidents for two wheeler. An effective prevention mechanism is to provide safety mechanism to the drivers with the advancement of wireless communication. The Objective of this paper is to develop a automatic speed control system to avoid accidents by controlling the speed of a motor bike using intelligent based automatic speed control. Intelligent based automatic speed control system consist of electronic acceleration system, Ultrasonicsensor, MQ3 alcohol sensors eye blink sensors. The existing system of acceleration in two wheelers can be replaced by electronic acceleration system. The signal from ultrasonic sensor will be sent continuously and monitors other obstacles that are in front of motor bike. The distance coverage of ultrasonic sensor is upto 4 m. When it detects obstacle, Vehicle is controlled automatically without any manual operation. This system detects the driver if he is under the influence of alcohol. MQ3 alcohol sensor is used to analyze breath to determine alcohol consumption in the body The eye blink sensor detects the eye blink of driver and if eye is closed more than 30 sec, vehicle will be stopped automatically, and gives alarm to driver alert. Speed Information will be sent to the server and from the server authorized user can view the speed information and control the speed. This system will be more efficient to control the speed of two wheelers so that the accidents can be prevented.

Human eye always reveals a non –linear understanding, for the disturbances caused by the lossy image and video coding. This is mainly because of the masking capability of the human eye to conceal the attributes such as contrast, luminous, spatial and temporal frequencies. To have a distortion less and efficient video encoding for the high dynamic video range content by eluding the invisible messages in the video that causes disturbances the paper puts forth the quantization with perception utilizing the luminous masking. The methodology utilized, computes the tone mapping to scale every frames in the HDR and later quantizes on unit basis with perception tuning. For this purpose the mechanism put forth incorporates the reference model of the HEVC with the extension range of the HEVC. The proposed model was validated by evaluating the reduction incurred in each rate of bit compared to the HDR range extension. The results acquired proved to have an enhancement in terms of the savings endured in the bit rate compared to the High efficient video coding that relied on the high dynamic range visible difference predictor-II

Background: Measuring cornea thickness is an essential parameter for patients undergoing refractive Laser-Assisted in SItu Keratomileusis (LASIK) surgeries. Discussion: This paper describes about the various available imaging and non-imaging methods for identifying cornea thickness and explores the most optimal method for measuring it. Along with the thickness measurement, layer segmentation in the cornea is also an essential parameter for diagnosing and treating eye-related disease and problems. The evaluation supports surgical planning and estimation of the corneal health. After surgery, the thickness estimation and layer segmentation are also necessary for identifying the layer surface disorders. Conclusion: Hence the paper reviews the available image processing techniques for processing the corneal image for thickness measurement and layer segmentation.

Security during surgical telepresence has not yet been sufficiently considered. This paper aims to propose a solution to enhance security during surgery between the site of surgery (local site) and the site that hosts the expert surgeon (remote site). The proposed system consists of an Enhanced Advanced Encryption Standard, which enhances the confusion and diffusion of the encrypted video. Two-factor authentication have been used biometrics and a one-time password complemented by archiving that are also considered for pre and post-surgery respectively. In the proposed system the substitution box and shift rows are eliminated and replaced with mix row step, this leads to increase the complexity of the proposed system. Also the Henon chaiotic map was used in the key generation process, and this is provided more randomness. The results demonstrate that the proposed encryption method increases the entropy of the encrypted video by 0.25% compared to the Advanced Encryption Standard algorithm. In addition, a reduction in processing time have been achieved, for encryption and decryption by 24% and 38% respectively. For testing the strength of security, we measure the plain-text sensitivity by using the information entropy, Peak Signal-to-Noise Ratio (PSNR) and Mean Square Error (MSE). Also, the encryption/decryption time is measured for the proposed algorithm and state of the art algorithm. The decreasing in PSNR means the stronger encryption algorithm, and while the PSNR of the proposed system was decreased then this leads to better encryption method. The proposed system aims to enhance surgical network security to make it viable for implementation during surgery where data is exchanged under conditions of telepresence. The proposed system eliminates the limitation of the traditional AES algorithm. The proposed EAES provides high security by increasing the entropy while decreasing the encryption and decryption time.

Geographical Information System (GIS) and remote sensing have become necessary tools in finding out land use land cover (LULC) change integrated with their associated driving factors. The utilization of satellite imagery made it easy to interpret the highly urbanized Warangal City that has experienced a lot of change in LULC during the last few decades. This paper discusses the ability of the integration of cellular automata (CA) and Markov chain–based 2D land use simulation module conjunction with GIS techniques. Markov chain algorithm is used for calibration and optimization by considering LULC of appropriate set of images for the years 2004, 2006, and 2018. Transitional change in LULC from one class to another is simulated using an artificial neural network (ANN) while cellular automata simulation is carried out to predict the plausible future LULC for the year 2052 after validating the model using the LULC of the year 2018. Analysis of the multi-temporal LULC maps indicated that the biophysical and socio-economic factors have greatly influenced the rise in built up while a decrease in agriculture in the year 2052. In conclusion, this technique is a powerful tool for monitoring and modeling change in land cover. Further suggestions for government officials are provided for an effective policymaking and to protect the land resource.

The accurate classification of the histopathological images of breast cancer diagnosis may face a huge challenge due to the complexity of the pathologist images. Currently, computer-aided diagnosis is implemented to get sound and error-less diagnosis of this lethal disease. However, the classification accuracy and processing time can be further improved. This study was designed to control diagnosis error via enhancing image accuracy and reducing processing time by applying several algorithms such as deep learning, K-means, autoencoder in clustering and enhanced loss function (ELF) in classification. Histopathological images were obtained from five datasets and pre-processed by using stain normalisation and linear transformation filter. These images were patched in sizes of 512 × 512 and 128 × 128 and extracted to preserve the tissue and cell levels to have important information of these images. The patches were further pre-trained by ResNet50-128 and ResNet512. Meanwhile, the 128 × 128 were clustered and autoencoder was employed with K-means which used latent feature of image to obtain better clustering result. Classification algorithm is used in current proposed system to ELF. This was achieved by combining SVM loss function and optimisation problem. The current study has shown that the deep learning algorithm has increased the accuracy of breast cancer classification up to 97% compared to state-of-the-art model which gave a percentage of 95%, and the time was decreased to vary from 30 to 40 s. Also, this work has enhanced system performance via improving clustering by employing K-means with autoencoder for the nonlinear transformation of histopathological image.

This paper presents a study on how body material properties affects the electrical characteristics of a Junctionless field effect transistor (JLFET). The study is performed by simulating a symmetric double gate JLFET on TCAD simulator for the materials- Silicon (Si), Germanium (Ge), Gallium Arsenide (GaAs) and Gallium Nitride (GaN). Simulations show that the use of compound materials (GaAs, GaN) in the body of JLFET results in better electrical characteristics compared to other element semiconductor (Si, Ge).

Several novel applications and services of networking for the IoT are supported by the Social Internet of Things (SIoT) in a more productive and powerful way. SIoTs are the recent hot topics rather than other extensions of IoTs. In this research, the authors have extracted the Big Data SIoT using the well-known model named MapReduce framework. Moreover, the unwanted data and noise from the database are reduced using the Gabor filter, and the big databases are mapped and reduced using the Hadoop MapReduce (HMR) technique for improving the efficiency of the proposed GA-EHO. Furthermore, the feature selection using GA-EHO is processed on the filtered dataset. The implementation of the proposed system is done by using some machine learning classifiers for classifying the data and the efficiency is predicted for the proposed work. From the simulation results, the specificity, maximum accuracy, and sensitivity of the proposed GA-EHO are produced about 87.88%, 99.1%, and 81%. Also, the results are compared with other existing techniques.

Protein-drug interactions play important roles in many biological processes and therapeutics. Prediction of the active binding site of a protein helps discover and optimise these interactions leading to the design of better ligand molecules. The tertiary structure of a protein determines the binding sites available to the drug molecule. A quick and accurate prediction of the binding site from sequence alone without utilising the three-dimensional structure is challenging. Deep Learning has been used in a variety of biochemical tasks and has been hugely successful. In this paper, a Residual Neural Network (leveraging skip connections) is implemented to predict a protein's most active binding site. An Annotated Database of Druggable Binding Sites from the Protein DataBank, sc-PDB, is used for training the network. Features extracted from the Multiple Sequence Alignments (MSAs) of the protein generated using DeepMSA, such as Position-Specific Scoring Matrix (PSSM), Secondary Structure (SS3), and Relative Solvent Accessibility (RSA), are provided as input to the network. A weighted binary cross-entropy loss function is used to counter the substantial imbalance in the two classes of binding and non-binding residues. The network performs very well on single-chain proteins, providing a pocket that has good interactions with a ligand.

Software-defined networking is a network paradigm which has shifted the intelligence of the underlying network interface to an independent control plane. The controller acts independently from the data plane. This isolation of the plane brings about greater opportunities but with a challenge of attaining higher reliability and optimum energy consumption in packet delivery. This paper aims at identifying approaches that improve the performance of the software-defined networking (SDN) with increase in reliability, specially required for real-time data delivery.

Genomic research has been highly prominent in recent times. Society has witnessed huge progress in genomic research in the last decade. The amount of data generated due activities like genome sequencing is huge. It is important to analyse such huge amount of data for acquiring meaningful insight so that such knowledge finds application in real-life scenarios. However, analysing such huge volume of data is extremely difficult because of the unique characteristics and complexities of these data. Big data analytic approaches are possible to explore for analytic purpose, and there have been researching efforts in that direction. In this paper, the relationship between genomic data and big data analytics has been explored. Challenges in processing of genomic data are analysed. The issue like how big data analytics concepts can be applied in genomic data processing is addressed. Future trends in combined research direction in the area of genomics and big data analytics are outlined.

The main purpose of the proposed system is to design a low-cost universal PV battery charger for electric vehicle application. The proposed system is integrated with a slope-compensated current controller which controls the charging current that corresponds to maximum power point of the PV module. As an interface converter, the proposed system consists of a buck converter to control the flow of the charging current and to find out the reference current Iref from the PV array at MPP. The battery control circuit is implemented by measuring the state of charge (SOC) of the battery, and an LCD display has been used to monitor the battery parameters. This proposed system acts as a smart and efficient PV battery charger for e-vehicles.

Forecasting infection case counts and estimating accurate epidemiological parameters are critical components of managing the response to a pandemic. This paper describes a modular, extensible framework for a COVID-19 forecasting system, primarily deployed during the first Covid wave in Mumbai and Jharkhand, India. We employ a variant of the SEIR compartmental model motivated by the nature of the available data and operational constraints. We estimate best fit parameters using Sequential Model-Based Optimization (SMBO), and describe the use of a novel, fast and approximate Bayesian model averaging method (ABMA) for parameter uncertainty estimation that compares well with a more rigorous Markov Chain Monte Carlo (MCMC) approach in practice. We address on-the-ground deployment challenges such as spikes in the reported input data using a novel weighted smoothing method. We describe extensive empirical analyses to evaluate the accuracy of our method on ground truth as well as against other state-of-the-art approaches. Finally, we outline deployment lessons and describe how inferred model parameters were used by government partners to interpret the state of the epidemic and how model forecasts were used to estimate staffing and planning needs essential for addressing COVID-19 hospital burden.CCS CONCEPTSApplied computing → Health care information systems; Forecasting;Computing methodologies → Modeling methodologies.

CCybersecurity primarily deals with a clear interpretation of various issues related to attacks that occur on digital resources and subsequent remedies therein. While discussing the safety against attacks or crimes against digital resources, the confidentiality, integrity, and availability of such information must be preserved. The COVID-19 pandemic showed us that most human activities such as education, work in various fields, shopping, and communication shifted to online quickly. Therefore, the cybersecurity of computers, networks, and communication systems is critical. Cybersecurity is a challenging and rapidly evolving domain, and it is essential to stay up to date and use the latest protection technologies. This chapter introduces the basic cybersecurity concepts and terminology. The domains and the threats and actors are characterized extensively. Also, this chapter tries to explain the need for cybersecurity in the context of digitalization and increasing Internet usage. A short book outline is also presented. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Adversaries use many nefarious techniques to stay hidden and anonymous during their online activities. But there are still loopholes in the identity hiding services that can be exploited at a granular level to deanonymize the user. The Internet has gone through significant advancement in the last few decades. This technology change provides useful data and information via websites and blogs, but it gives add-on services that help users while on a route. For the last few years, such third-party services were continuously grabbing and capturing our personal information for their own benefits, such as advertisement or providing more recommendations without the consent of users. Furthermore, there is a possibility of sharing data with traders of the black market, where personal information such as mail, phone, or physical address can be sold and used for illegal access to various systems. Such information may also be used for any atrocious act. Many anonymous services are rendered over the Internet to provide low-level anonymity and privacy to communicated data. However, those services still have flaws that can be easily exploited. Such systems are susceptible to various attacks, including exploiting hardware devices, traffic analysis, footprinting, and many more. Proxy servers that help alter IP addresses and location details are also receptive in nature to collect data by authorities. Virtual private network (VPN), which uses the same features as proxy servers, adds an extra encryption layer. This functionality makes VPN a more secure technology compared to proxy servers. Though it has security, VPN has another serious issue of untrustworthy of VPN servers located around the globe. These VPN servers can collect users’ data, or they can be used as network security monitoring (NSM) media. This chapter focuses on anonymous systems like Invisible Internet Project (I2P), Freenet, and JonDonym, services that hide the user identity from the surface Internet. It also includes an introduction to The Onion Router (TOR) without going into details. Moreover, the chapter demonstrates the configure of each system and its crucial elements to make the users’ identity safe from different nemesis.