International Journal of Communication Networks and Information Security (IJCNIS)
Not a member yet
1021 research outputs found
Sort by
Explainable Machine Learning Techniques in Medical Image Analysis Based on Classification with Feature Extraction
Get PDFAnimals are also afflicted by COVID-19, a virus that is quickly spreading and infects both humans and animals. This fatal viral disease has an impact on people's daily lives, health, and economy of a nation. Most effective machine learning method is deep learning, which offers insightful analysis for examining a significant number of chest x-ray pictures that have a significant bearing on COVID-19 screening. This research proposes novel technique in lung image analysis for detection of lung infection due to COVID using Explainable Machine learning techniques. Here the input has been collected as COVID patient’s lung image dataset and it has been processed for noise removal and smoothening. This processed image features have been extracted using spatio transfer neural network integrated with DenseNet+ architecture. Extracted features has been classified using stacked auto Boltzmann encoder machine with VGG-19Net+. With the transfer learning method integrated into the binary classification process, the suggested algorithm achieves good classification accuracy. The experimental analysis has been carried out for various COVID dataset in terms of accuracy, precision, Recall, F-1score, RMSE, MAP. The proposed technique attained accuracy of 95%, precision of 91%, recall of 85%, F_1 score of 80%, RMSE of 61% and MAP of 51%
Numerical Protection Analysis of Shen Xiu Intangible Cultural Heritage Based on Software Definition Technology
Get PDFThe role of numerical protection analysis in the digital protection of Shen Xiu's intangible culture has changed the numerical value of Shen Xiu's intangible culture and made the digital protection of Shen Xiu's intangible culture a hot spot. However, in the process of numerical protection of intangible culture in Shen Xiu, there are some problems, such as poor digital collection effect and small amount of digital processing data. The main reason is that the traditional way of oral transmission and heart-to-heart transmission limits the development of digital numerical protection of intangible culture in Shen Xiu. Therefore, this paper proposes a digital protection method for Shen Xiu's intangible culture based on software-defined technology and plans the characteristics of Shen Xiu's intangible culture with different values. First of all, the data of Shen Xiu intangible culture in Shen Xiu are collected by software-defined technology, and the data of different values are summarized by software-defined technology, and the numerical division of Shen Xiu intangible culture is carried out according to the characteristics of Suzhou embroidery, leaving common characteristics. Then, according to the software-defined technology, the protective communication of numerical protection is carried out to promote the integration of the characteristics of Shen Xiu's intangible culture. The results of numerical protection analysis show that software-defined technology can improve the numerical extraction level of Shen Xiu intangible culture, promote the development of digital numerical protection of Shen Xiu intangible culture by using software-defined technology, and meet the requirements of numerical protection of Shen Xiu intangible culture
Leveraging LSTM Network Reinforcement Learning to Enhance Vehicle Traffic Optimization in a Publicly Guarded Intelligent Transportation System
No full textIntelligent Transportation Systems (ITS) provide better outcomes when it comes to efficiently resolving difficult and unpleasant transportation problems. Modern transportation systems face crucial issues with traffic prediction, accident prediction, demand prediction, vehicle location prediction, vehicle communication prediction, and trip safety. Intelligent health aid for drivers, reroute suggestions to increase public transport use and car traffic optimization are all parts of the planned study. The current position of vehicles, the precise number of vehicles on each route, and the number of empty seats on board are just a few of the complicated transportation concerns that this study aims to resolve. In addition, the suggested method is more efficient because of vehicle communication, which prevents registered users and the cloud server from experiencing communication delays or losing traffic information. An innovative and smart approach for optimizing traffic in real-time transportation systems has been suggested as part of this study using Long Short-Term Memory (LSTM) and Reinforcement Learning (RL). In order to provide registered users with the best possible route recommendation, the vehicle detection method counts the number of cars on each route. The efficiency of the suggested system is enhanced by the successful implementation of a cluster-based vehicle communication and position estimation model
An Optimal Routing Protocol Using a Multiverse Optimizer Algorithm for Wireless Mesh Network
Get PDFWireless networks, particularly Wireless Mesh Networks (WMNs), are undergoing a significant change as a result of wireless technology advancements and the Internet's rapid expansion. Mesh routers, which have limited mobility and serve as the foundation of WMN, are made up of mesh clients and form the core of WMNs. Mesh clients can with mesh routers to create a client mesh network. Mesh clients can be either stationary or mobile. To properly utilise the network resources of WMNs, a topology must be designed that provides the best client coverage and network connectivity. Finding the ideal answer to the WMN mesh router placement dilemma will resolve this issue MRP-WMN. Since the MRP-WMN is known to be NP-hard, approximation methods are frequently used to solve it. This is another reason we are carrying out this task. Using the Multi-Verse Optimizer algorithm, we provide a quick technique for resolving the MRP-WMN (MVO). It is also proposed to create a new objective function for the MRP-WMN that accounts for the connected client ratio and connected router ratio, two crucial performance indicators. The connected client ratio rises by an average of 16.1%, 12.5%, and 6.9% according to experiment data, when the MVO method is employed to solve the MRP-WMN problem, the path loss falls by 1.3, 0.9, and 0.6 dB when compared to the Particle Swarm Optimization (PSO) and Whale Optimization Algorithm (WOA), correspondingly
Cyclostationary Algorithm for Signal Analysis in Cognitive 4G Networks with Spectral Sensing and Resource Allocation
Get PDFCognitive Radio (CR) effectively involved in the management of spectrum to perform improved data transmission. CR system actively engaged in the data sensing, learning and dynamic adjustment of radio spectrum parameters with management of unused spectrum in the signal. The spectrum sensing is indispensable in the CR for the management of Primary Users (PUs) and Secondary users (SUs) without any interference. Spectrum sensing is considered as the effective adaptive signal processing model to evaluate the computational complexity model for the signal transmission through Matched filtering, Waveform and Cyclostationary based Energy sensing model. Cyclostationary based model is effective for the energy based sensing model based on unique characteristics with estimation of available channel in the spectrum to extract the received signal in the PU signal. Cyclostationary based model uses the spectrum availability without any periodic property to extract the noise features. This paper developed a Adaptive Cross Score Cyclostationary (ACSCS) to evaluate the spectrum sensing in the CR network. The developed ACSCS model uses the computational complexity with estimation of Signal-to-Interference-and-Noise Ratio (SINR) elimination of cost function. ACSCS model uses the Adaptive Least square Spectral Self-Coherence Restoral (SCORE) with the Adaptive Cross Score (ACS) to overcome the issues in CR. With the derived ACSCS algorithm minimizes the computational complexity based on cost function compared with the ACS algorithm. To minimize the computational complexity pipeline triangular array based Gram-Schmidt Orthogonalization (GSO) structure for the optimization of network. The simulation performance analysis with the ACSCS scheme uses the Rician Multipath Fading channel to estimate detection probability to sense the Receiver Operating Characteristics, detection probability and probability of false alarm using Maximum Likelihood (ML) detector. The ACSC model uses the Square-law combining (SLC) with the moment generation function in the multipath fading channel for the channel sensing with reduced computational complexity. The simulation analysis expressed that ACSC scheme achieves the maximal detection probability value of 1. The analysis expressed that proposed ACSC scheme achieves the improved channel estimation in the 4G communication environment
Recommendation Model-Based 5G Network and Cognitive System of Cloud Data with AI Technique in IOMT Applications
Get PDFRecommender system provides the significant suggestion towards the effective service offers for the vast range of big data. The Internet of Things (IoT) environment exhibits the value added application services to the customer with the provision of the effective collection and processing of information. In the extension of the IoT, Internet of Medical Things (IoMT) is evolved for the patient healthcare monitoring and processing. The data collected from the IoMT are stored and processed with the cognitive system for the data transmission between the users. However, in the conventional system subjected to challenges of processing big data while transmission with the cognitive radio network. In this paper, developed a effective cognitive 5G communication model with the recommender model for the IoMT big data processing. The proposed model is termed as Ranking Strategy Internet of Medical Things (RSIoMT). The proposed RSIoMT model uses the distance vector estimation between the feature variables with the ranking. The proposed RSIoMT model perform the recommender model with the ranking those are matches with the communication devices for improved wireless communication quality. The proposed system recommender model uses the estimation of direct communication link between the IoMT variables in the cognitive radio system. The proposed RSIoMT model evaluates the collected IoMT model data with the consideration of the four different healthcare datasets for the data transmission through cognitive radio network. Through the developed model the performance of the system is evaluated based on the deep learning model with the consideration of the collaborative features. The simulation analysis is comparatively examined based on the consideration of the wireless performance. Simulation analysis expressed that the proposed RSIoMT model exhibits the superior performance than the conventional classifier. The comparative analysis expressed that the proposed mode exhibits ~3 – 4% performance improvement over the conventional classifiers. The accuracy of the developed model achieves 99% which is ~3 – 9% higher than the conventional classifier. In terms of the channel performance, the proposed RSIoMT model exhibits the reduced recommender relay selection count of 1 while the other technique achieves the relay value of 13 which implies that proposed model performance is ~4-6% higher than the other techniques
Application of Internet of Things to Ensure Improved Performance within the Internal Supply Chain Unit of an Organization
Get PDFWith the rapidly changing business world, technology adapted for doing business has also undergone rapid transformation leading to use Internet of Things as an advanced technological innovation required to connect production units to internet devices for smooth production and operation, with enhanced ICT systems and infrastructure. Internet of Things is considered to be an advanced information and communication technology, whose applicability is highly needed to ensure smart performance of organizations in Indonesia. Indonesia, being a developing country, adapting to new ways of doing things, including the use of IoT takes time, hence affecting studies regarding the use of IoT in business units, such as the internal supply chain sector. Thus, there is no much studies from a localized perspective, measuring the importance and using IoT as well as supply chain performance of the country. The present paper applied an organizational capacity theory to establish the Internet of Things impact on varying dimensions of Supply Chain, which included supply chain integration process, organizational performance of supply chain and the capacity to the influence production. The research applied a survey of cross-section on several companies within the Greater Jakarta area as the research approach. Data was obtained from over 161 companies from across Jakarta. Finally, the data was analyzed with the help of the structural equation modelling (SEM-AMOS) for the development of an empirical structural model
Performance Evaluation of an Intelligent and Optimized Machine Learning Framework for Attack Detection
Get PDFIn current decades, the size and complexity of network traffic data have risen significantly, which increases the likelihood of network penetration. One of today's largest advanced security concerns is the botnet. They are the mechanisms behind several online assaults, including Distribute Denial of Service (DDoS), spams, rebate fraudulence, phishing as well as malware attacks. Several methodologies have been created over time to address these issues. Existing intrusion detection techniques have trouble in processing data from speedy networks and are unable to identify recently launched assaults. Ineffective network traffic categorization has been slowed down by repetitive and pointless characteristics. By identifying the critical attributes and removing the unimportant ones using a feature selection approach could indeed reduce the feature space dimensionality and resolve the problem.Therefore, this articledevelops aninnovative network attack recognitionmodel combining an optimization strategy with machine learning framework namely, Grey Wolf with Artificial Bee Colony optimization-based Support Vector Machine (GWABC-SVM) model. The efficient selection of attributes is accomplished using a novel Grey wolf with artificial bee colony optimization approach and finally the Botnet DDoS attack detection is accomplished through Support Vector machine.This articleconducted an experimental assessment of the machine learning approachesfor UNBS-NB 15 and KDD99 databases for Botnet DDoS attack identification. The proposed optimized machine learning (ML) based network attack detection framework is evaluated in the last phase for its effectiveness in detecting the possible threats. The main advantage of employing SVM is that it offers a wide range of possibilities for intrusion detection program development for difficult complicated situations like cloud computing. In comparison to conventional ML-based models, the suggested technique has a better detection rate of 99.62% and is less time-consuming and robust
SMART: A Subspace based Malicious Peers Detection algorithm for P2P Systems
Get PDFIn recent years, reputation management schemes have been proposed as promising solutions to alleviate the blindness during peer selection in distributed P2P environment where malicious peers coexist with honest ones. They indeed provide incentives for peers to contribute more resources to the system and thus promote the whole system performance. But few of them have been implemented practically since they still suffer from various security threats, such as collusion, Sybil attack and so on. Therefore, how to detect malicious peers plays a critical role in the successful work of these mechanisms, and it will also be our focus in this paper. Firstly, we define malicious peers and show their influence on the system performance. Secondly, based on Multiscale Principal Component Analysis (MSPCA) and control chart, a Subspace based MAlicious peeRs deTecting algorithm (SMART) is brought forward. SMART first reconstructs the original reputation matrix based on subspace method, and then finds malicious peers out based on Shewhart control chart. Finally, simulation results indicate that SMART can detect malicious peers efficiently and accurately
Packet Resonance Strategy: A Spoof Attack Detection and Prevention Mechanism in Cloud Computing Environment
Get PDFDistributed Denial of Service (DDoS) is a major threat to server availability. The attackers hide from view by impersonating their IP addresses as the legitimate users. This Spoofed IP helps the attacker to pass through the authentication phase and to launch the attack. Surviving spoof detection techniques could not resolve different styles of attacks. Packet Resonance Strategy (PRS) armed to detect various types of spoof attacks that destruct the server resources or data theft at Datacenter. PRS ensembles to any Cloud Service Provider (CSP) as they are exclusively responsible for any data leakage and sensitive information hack. PRS uses two-level detection scheme, allows the clients to access Datacenter only when they surpass initial authentication at both levels. PRS provides faster data transmission and time sensitiveness of cloud computing tasks to the authenticated clients. Experimental results proved that the proposed methodology is a better light-weight solution and deployable at server-end