An Improved Lung Cancer Segmentation Based on Nature-Inspired Optimization Approaches

The distinction and precise identification of tumor nodules are crucial for timely lung cancer diagnosis andplanning intervention. This research work addresses the major issues pertaining to the field of medical imageprocessing while focusing on lung cancer Computed Tomography (CT) images. In this context, the paper proposesan improved lung cancer segmentation technique based on the strengths of nature-inspired approaches. Thebetter resolution of CT is exploited to distinguish healthy subjects from those who have lung cancer. In thisprocess, the visual challenges of the K-means are addressed with the integration of four nature-inspired swarmintelligent techniques. The techniques experimented in this paper are K-means with Artificial Bee Colony (ABC),K-means with Cuckoo Search Algorithm (CSA), K-means with Particle Swarm Optimization (PSO), and Kmeanswith Firefly Algorithm (FFA). The testing and evaluation are performed on Early Lung Cancer ActionProgram (ELCAP) database. The simulation analysis is performed using lung cancer images set against metrics:precision, sensitivity, specificity, f-measure, accuracy,Matthews Correlation Coefficient (MCC), Jaccard, and Dice.The detailed evaluation shows that the K-means with Cuckoo Search Algorithm (CSA) significantly improved thequality of lung cancer segmentation in comparison to the other optimization approaches utilized for lung cancerimages. The results exhibit that the proposed approach (K-means with CSA) achieves precision, sensitivity, and Fmeasureof 0.942, 0.964, and 0.953, respectively, and an average accuracy of 93%. The experimental results prove thatK-meanswithABC,K-meanswith PSO,K-meanswith FFA, andK-meanswithCSAhave achieved an improvementof 10.8%, 13.38%, 13.93%, and 15.7%, respectively, for accuracy measure in comparison to K-means segmentationfor lung cancer images. Further, it is highlighted that the proposed K-means with CSA have achieved a significantimprovement in accuracy, hence can be utilized by researchers for improved segmentation processes of medicalimage datasets for identifying the targeted region of interest.

Computing Challenges of UAV Networks: A Comprehensive Survey

Devices and networks constantly upgrade,leading to rapid technological evolution.Three-dimensional(3D)point cloud transmission plays a crucial role in aerial computing terminology,facilitating information exchange.Various network types,including sensor networks and 5G mobile networks,support this transmission.Notably,Flying Ad hoc Networks(FANETs)utilize Unmanned Aerial Vehicles(UAVs)as nodes,operating in a 3D environment with Six Degrees of Freedom(6DoF).This study comprehensively surveys UAV networks,focusing on models for Light Detection and Ranging(LiDAR)3D point cloud compression/transmission.Key topics covered include autonomous navigation,challenges in video streaming infrastructure,motivations for Quality of Experience(QoE)enhancement,and avenues for future research.Additionally,the paper conducts an extensive review of UAVs,encompassing current wireless technologies,applications across various sectors,routing protocols,design considerations,security measures,blockchain applications in UAVs,contributions to healthcare systems,and integration with the Internet of Things(IoT),Artificial Intelligence(AI),Machine Learning(ML),and Deep Learning(DL).Furthermore,the paper thoroughly discusses the core contributions of LiDAR 3D point clouds in UAV systems and their future prediction along with mobility models.It also explores the prospects of UAV systems and presents state-of-the-art solutions.

Machine Learning with Dimensionality Reduction for DDoS Attack Detection

With the advancement of internet,there is also a rise in cybercrimes and digital attacks.DDoS(Distributed Denial of Service)attack is the most dominant weapon to breach the vulnerabilities of internet and pose a significant threat in the digital environment.These cyber-attacks are generated deliberately and consciously by the hacker to overwhelm the target with heavy traffic that genuine users are unable to use the target resources.As a result,targeted services are inaccessible by the legitimate user.To prevent these attacks,researchers are making use of advanced Machine Learning classifiers which can accurately detect the DDoS attacks.However,the challenge in using these techniques is the limitations on capacity for the volume of data and the required processing time.In this research work,we propose the framework of reducing the dimensions of the data by selecting the most important features which contribute to the predictive accuracy.We show that the‘lite’model trained on reduced dataset not only saves the computational power,but also improves the predictive performance.We show that dimensionality reduction can improve both effectiveness(recall)and efficiency(precision)of the model as compared to the model trained on‘full’dataset.

Human-Computer Interaction Using Deep Fusion Model-Based Facial Expression Recognition System

A deep fusion model is proposed for facial expression-based human-computer Interaction system.Initially,image preprocessing,i.e.,the extraction of the facial region from the input image is utilized.Thereafter,the extraction of more discriminative and distinctive deep learning features is achieved using extracted facial regions.To prevent overfitting,in-depth features of facial images are extracted and assigned to the proposed convolutional neural network(CNN)models.Various CNN models are then trained.Finally,the performance of each CNN model is fused to obtain the final decision for the seven basic classes of facial expressions,i.e.,fear,disgust,anger,surprise,sadness,happiness,neutral.For experimental purposes,three benchmark datasets,i.e.,SFEW,CK+,and KDEF are utilized.The performance of the proposed systemis compared with some state-of-the-artmethods concerning each dataset.Extensive performance analysis reveals that the proposed system outperforms the competitive methods in terms of various performance metrics.Finally,the proposed deep fusion model is being utilized to control a music player using the recognized emotions of the users.

EBAKE-SE: A novel ECC-based authenticated key exchange between industrial IoT devices using secure element

Industrial IoT(IIoT)aims to enhance services provided by various industries,such as manufacturing and product processing.IIoT suffers from various challenges,and security is one of the key challenge among those challenges.Authentication and access control are two notable challenges for any IIoT based industrial deployment.Any IoT based Industry 4.0 enterprise designs networks between hundreds of tiny devices such as sensors,actuators,fog devices and gateways.Thus,articulating a secure authentication protocol between sensing devices or a sensing device and user devices is an essential step in IoT security.In this paper,first,we present cryptanalysis for the certificate-based scheme proposed for a similar environment by Das et al.and prove that their scheme is vulnerable to various traditional attacks such as device anonymity,MITM,and DoS.We then put forward an interdevice authentication scheme using an ECC(Elliptic Curve Cryptography)that is highly secure and lightweight compared to other existing schemes for a similar environment.Furthermore,we set forth a formal security analysis using the random oracle-based ROR model and informal security analysis over the Doleve-Yao channel.In this paper,we present comparison of the proposed scheme with existing schemes based on communication cost,computation cost and security index to prove that the proposed EBAKE-SE is highly efficient,reliable,and trustworthy compared to other existing schemes for an inter-device authentication.At long last,we present an implementation for the proposed EBAKE-SE using MQTT protocol.

An Optimal Algorithm for Secure Transactions in Bitcoin Based on Blockchain

Technological advancement has made a significant contribution to the change of the economy and the advancement of humanity.Because it is changing how economic transactions are carried out,the blockchain is one of the technical developments that has a lot of promise for this progress.The public record of the Bitcoin blockchain provides dispersed users with evidence of transaction owner-ship by publishing all transaction data from block reward transactions to unspent transaction outputs.Attacks on the public ledger,on the other hand,are a result of the fact that all transaction information are exposed.De-anonymization attacks allow users to link transaction entities and acquire user privacy through specified transaction amounts.As a result,in light of the Bitcoin blockchain system’s priv-acy issues,this scheme combines the concept of coin mixing with encrypted trans-action technology to create a truly anonymous blockchain system that preserves the payer identity and transaction amount privacy.The one-way aggregated sig-nature technique of Boneh,Gentry,and Lynn systematically embeds the notion of mixing into the whole block.The homomorphic encryption approach of Boneh,Goh,and Nissim allows miners to check the legality of encrypted transactions.Miners will validate transactions,conceal transactions,and package transactions as entities in the scheme.Finally,this technique was chosen after a comparison of several privacy-preserving blockchain schemes.It not only ensures complete anonymity,but also keeps transaction storage overhead to a minimum.

An Optimized Method for Accounting Information in Logistic Systems

In the era of rapid information development,with the popularity of computers,the advancement of science and technology,and the ongoing expansion of IT technology and business,the enterprise resource planning(ERP)system has evolved into a platform and a guarantee for the fulfilment of company management procedures after long-term operations.Because of developments in information technology,most manual accounting procedures are being replaced by computerized Accounting Information Systems(AIS),which are quicker and more accurate.The primary factors influencing the decisions of logistics firm trading parties are investigated in order to enhance the design of decision-supporting modules and to improve the performance of logistics enterprises through AIS.This paper proposed a novel approach to calculate the weights of each information element in order to establish their important degree.The main purpose of this research is to present a quantitative analytic approach for determining the important information of logistics business collaboration response.Furthermore,the idea of total orders and the significant degrees stated above are used to identify the optimal order of all information elements.Using the three ways of marginal revenue,marginal cost,and business matching degree,the information with cumulative weights is which is deployed to form the data from the intersection of the best order.It has the ability to drastically reduce the time and effort required to create a logistics business control/decision-making system.

An Optimized Method for Information System Transactions Based on Blockchain

Accounting Information System(AIS),which is the foundation of any enterprise resource planning(ERP)system,is often built as centralized system.The technologies that allow the Internet-of-Value,which is built onfive aspects that are network,algorithms,distributed ledger,transfers,and assets,are based on blockchain.Cryptography and consensus protocols boost the blockchain plat-form implementation,acting as a deterrent to cyber-attacks and hacks.Blockchain platforms foster innovation among supply chain participants,resulting in ecosys-tem development.Traditional business processes have been severely disrupted by blockchains since apps and transactions that previously required centralized struc-tures or trusted third-parties to authenticate them may now function in a decentra-lized manner with the same level of assurance.Because a blockchain split in AIS may easily lead to double-spending attacks,reducing the likelihood of a split has become a very important and difficult research subject.Reduced block relay time between the nodes can minimize the block propagation time of all nodes,resulting in better Bitcoin performance.In this paper,three problems were addressed on transaction and block propagation mechanisms in order to reduce the likelihood of a split.A novel algorithm for blockchain is proposed to reduce the total pro-pagation delay in AIS transactions.Numerical results reveal that,the proposed algorithm performs better and reduce the transaction delay in AIS as compared with existing methods.

An Optimized Technique for RNA Prediction Based on Neural Network

Pathway reconstruction, which remains a primary goal for many investigations, requires accurate inference of gene interactions and causality. Non-coding RNA (ncRNA) is studied because it has a significant regulatory role in manyplant and animal life activities, but interacting micro-RNA (miRNA) and longnon-coding RNA (lncRNA) are more important. Their interactions not only aidin the in-depth research of genes’ biological roles, but also bring new ideas forillness detection and therapy, as well as plant genetic breeding. Biological investigations and classical machine learning methods are now used to predict miRNAlncRNA interactions. Because biological identification is expensive and time-consuming, machine learning requires too much manual intervention, and the featureextraction process is difficult. This research presents a deep learning model thatcombines the advantages of convolutional neural networks (CNN) and bidirectional long short-term memory networks (Bi-LSTM). It not only takes intoaccount the connection of information between sequences and incorporates contextual data, but it also thoroughly extracts the sequence data’s features. On thecorn data set, cross-checking is used to evaluate the model’s performance, andit is compared to classical machine learning. To acquire a superior classificationeffect, the proposed strategy was compared to a single model. Additionally, thepotato and wheat data sets were utilized to evaluate the model, with accuracy ratesof 95% and 93%, respectively, indicating that the model had strong generalization capacity.

RFID Adaption in Healthcare Organizations:An Integrative Framework

Radio frequency identification(RFID),also known as electronic label technology,is a non-contact automated identification technology that recognizes the target object and extracts relevant data and critical characteristics using radio frequency signals.Medical equipment information management is an important part of the construction of a modern hospital,as it is linked to the degree of diagnosis and care,as well as the hospital’s benefits and growth.The aim of this study is to create an integrated view of a theoretical framework to identify factors that influence RFID adoption in healthcare,as well as to conduct an empirical review of the impact of organizational,environmental,and individual factors on RFID adoption in the healthcare industry.In contrast to previous research,the current study focuses on individual factors as well as organizational and technological factors in order to better understand the phenomenon of RFID adoption in healthcare,which is characterized as a dynamic and challenging work environment.This research fills a gap in the current literature by describing how user factors can influence RFID adoption in healthcare and how such factors can lead to a deeper understanding of the advantages,uses,and impacts of RFID in healthcare.The proposed study has superior performance and effective results.

A Comprehensive Review on Medical Diagnosis Using Machine Learning

The unavailability of sufficient information for proper diagnosis,incomplete or miscommunication between patient and the clinician,or among the healthcare professionals,delay or incorrect diagnosis,the fatigue of clinician,or even the high diagnostic complexity in limited time can lead to diagnostic errors.Diagnostic errors have adverse effects on the treatment of a patient.Unnecessary treatments increase the medical bills and deteriorate the health of a patient.Such diagnostic errors that harm the patient in various ways could be minimized using machine learning.Machine learning algorithms could be used to diagnose various diseases with high accuracy.The use of machine learning could assist the doctors in making decisions on time,and could also be used as a second opinion or supporting tool.This study aims to provide a comprehensive review of research articles published from the year 2015 to mid of the year 2020 that have used machine learning for diagnosis of various diseases.We present the various machine learning algorithms used over the years to diagnose various diseases.The results of this study show the distribution of machine learning methods by medical disciplines.Based on our review,we present future research directions that could be used to conduct further research.

An Optimal Scheme for WSN Based on Compressed Sensing

Wireless sensor networks(WSNs)is one of the renowned ad hoc network technology that has vast varieties of applications such as in computer networks,bio-medical engineering,agriculture,industry and many more.It has been used in the internet-of-things(IoTs)applications.A method for data collecting utilizing hybrid compressive sensing(CS)is developed in order to reduce the quantity of data transmission in the clustered sensor network and balance the network load.Candidate cluster head nodes are chosen first from each temporary cluster that is closest to the cluster centroid of the nodes,and then the cluster heads are selected in order based on the distance between the determined cluster head node and the undetermined candidate cluster head node.Then,each ordinary node joins the cluster that is nearest to it.The greedy CS is used to compress data transmission for nodes whose data transmission volume is greater than the threshold in a data transmission tree with the Sink node as the root node and linking all cluster head nodes.The simulation results demonstrate that when the compression ratio is set to ten,the data transfer volume is reduced by a factor of ten.When compared to clustering and SPT without CS,it is reduced by 75%and 65%,respectively.When compared to SPT with Hybrid CS and Clustering with hybrid CS,it is reduced by 35%and 20%,respectively.Clustering and SPT without CS are compared in terms of node data transfer volume standard deviation.SPT with Hybrid CS and clustering with Hybrid CS were both reduced by 62%and 80%,respectively.When compared to SPT with hybrid CS and clustering with hybrid CS,the latter two were reduced by 41%and 19%,respectively.

Intelligent Approach for Traffic Orchestration in SDVN Based on CMPR

The vehicle ad hoc network that has emerged in recent years was originally a branch of the mobile ad hoc network.With the drafting and gradual establishment of standards such as IEEE802.11p and IEEE1609,the vehicle ad hoc network has gradually become independent of the mobile ad hoc network.The Internet of Vehicles(Vehicular Ad Hoc Network,VANET)is a vehicle-mounted network that comprises vehicles and roadside basic units.This multi-hop hybrid wireless network is based on a vehicle-mounted self-organizing network.As compared to other wireless networks,such as mobile ad hoc networks,wireless sensor networks,wireless mesh networks,etc.,the Internet of Vehicles offers benefits such as a large network scale,limited network topology,and predictability of node movement.The paper elaborates on the Traffic Orchestration(TO)problems in the Software-Defined Vehicular Networks(SDVN).A succinct examination of the Software-defined networks(SDN)is provided along with the growing relevance of TO in SDVN.Considering the technology features of SDN,a modified TO method is proposed,which makes it possible to reduce time complexity in terms of a group of path creation while simultaneously reducing the time needed for path reconfiguration.A criterion for path choosing is proposed and justified,which makes it possible to optimize the load of transport network channels.Summing up,this paper justifies using multipath routing for TO.