International Journal of Future Generation Communication and Networking

IoT Based Smart Parking System using Laser Range Sensor

Punam Mahalle, Prof. A. R. Welekar, Dr A. N. Thakare — Sat, 02 Apr 2022 00:00:00 +0000

This paper introduces the concept of “Smart Parking System” using Laser Range Sensor. In car parking services in cities, the increasing number of vehicles on the road along with the mismanagement of available parking space; Leads to parking related problem as well as increase traffic congestion in smart parking management system that would help the driver very quickly. Although ample amount of research work on the development of smart parking system exit in the literature but most of they have not addressed the problem of real time detection of improper parking and automated collection of parking charges. In this paper, a prototype of Internet-of- Things based smart parking system is proposed. The smart parking system will uses on laser range sensor for detection of parked cars and send the data to microcontroller, ESP8266 microcontrollar with Wi-Fi module will send the data to server and to the Interface and manage the parking throughout parking area.

Segmentation And Feature Extraction Of H-Alpha Solar Images Observed From Kodaikanal Solar Observatory

Dr. Hemamalini G E, Dr. J Prakash — Sat, 02 Apr 2022 00:00:00 +0000

The main aim of our project is to use the Hα telescope facility and obtain the images of the Sun in strong Hα line whose wavelength is 6563Å. Hα telescope consists of Lyot filter which can be tuned to any location on the strong Hα absorption line in steps of 0.4Å and images at these locations on the line profile will be obtained. On the images obtained Image Processing techniques such as enhancement and segmentation are applied in order to detect and extract the features for which intensity v/s time graph is plotted. The time series analysis was developed on Hα images which were observed for two hours with the time resolution of two minute cadence and derived the intensity at the centre, 0.4Å and 0.8Å of the solar disk and time series graph is plotted. In addition, the evolution of the dark filaments has been examined which leads to the occurrence of the solar flare, which has high impact on earth’s climate, space weather and satellite communication.

Regression Analysis for Evaluation of Evopotranspiration for Agriculture Water Requirement

Sarika Patil, Dr. Radhakrishana Naik — Tue, 26 Apr 2022 00:00:00 +0000

India Grapes Farming is very important sector of agriculture. Due to volatile weather condions and scare water resources irrigation management becomes challenging aspect for grapes farmers. The proposed system considers all challenges of Grapes Farming and developed automated irrigation system. The water resource management is the challanging task in agriculture. To Achieve water management in agriculture field many new technology has been proposed in recent research work, however very few work focused on productivity of crop while optimizing water resources. Proposed model considers all aspect of Irrigation like weather, crop growth stages and canopy coverage. Morever system also considers landscape information like slope of the farm area, soil type, elevation level etc.

Proposed system predicting most enflucing parameter for evaluation of Evopotranspiration(ET0) using Machine Learning Regression analysis Algorithm. ET0 evaluation requires many parametrs like day Light hours, Vappour pressure, Longwave Radiation, Soil Heat Flux etc those are not readily available or one can not record it direcly. These parametrs are claculated using web scraped data then used in ET0 evaluation process in addition to crop growth data and landscape information. This predictive model provides optimised parameter for evaluation of ET0. Proposed model showing very less error deviation in Actaul and precited values of ET0.

To Develop Robust Algorithm for Security in Black box Using Explainable Artificial Intelligence (XAI)

Shruti Ajaykumar Yelne, Dr. A. N. Thakare — Sun, 01 May 2022 00:00:00 +0000

Artificial Intelligence based systems is that they often lack transparency. Indeed, the black-box nature of these systems allows powerful predictions, but it cannot be directly explained. This issue has triggered a new debate on explainable AI (XAI). AI to continue making steady progress without disruption.

Explainable Artificial Intelligence (XAI) is a branch of AI that advocates a set of tools, strategies, and algorithms for generating high-quality interpretable, intuitive, and human-understandable explanations of AI judgments. This paper gives mathematical summaries of seminal work in addition to offering a holistic assessment of the present XAI landscape in deep learning. We begin by establishing a taxonomy and categorising XAI strategies based on the scope of explanations, algorithmic methodology, and level of explanation or application, all of which aid in the development of reliable, interpretable, and self-explanatory deep learning models. The key ideas employed in XAI research are then described, and a timeline of significant XAI studies from 2007 to 2020 is shown. We evaluate the explanation maps created by XAI algorithms using image data, highlight the limitations of this methodology, and suggest potential future routes to improve XAI assessment after thoroughly discussing each category of methods and methodologies.

Skin Tumor Segmentation Using Artificial Neural Network in Ultrasonic Images

Md. Ejaz Ahamed, Ziaul Haque — Wed, 18 May 2022 00:00:00 +0000

One of the world's most popular and rising health conditions is the skin. The human skin tumour, because of the nuances in texture, colour, hair appearance and other attributes, is the most volatile and one of the toughest organisms to immediately identify and determine. In this project we have proposed a device that uses Artificial Neural Network to identify skin tumours. Different forms of dermatological tumours are effectively identified. It primarily comprises of three steps of picture preparation, teaching and identification. We add algorithms including a transition from grey to HSV to the input picture during the image processing step. The input image is observed with artificial neural network algorithms after HSV values are collected. The percentage of contamination is often identified as an exception to the identification.

BIEIDS: Bio-Inspired Ensemble Method for Intrusion Detection System

Arshad Hashmi — Sun, 01 May 2022 00:00:00 +0000

Intrusion detection systems (IDSs) take part in information protection by detecting and preventing malevolent computer network actions. For many years, intrusion detection has been a prominent subject of study, and various intrusion detection systems have been cited in the literature. In this research work, a bio-inspired ensemble method is proposed for the intrusion detection system. IDS usually manages large quantities of data traffic containing redundant and inappropriate features that have an unhelpful effect on the IDS's performance. Using various dimensionality reduction techniques, unnecessary and improper features in the network traffic data are first eliminated using bio-inspired ensemble feature selection. Particle swarm optimization, Binary cuckoo search, and Fish swarm optimization algorithm are used to remove irrelevant features and select optimized features. The bagging and boosting ensemble classification model are built on the features chosen to detect the intrusion. The model and algorithms were simulated and tested using the available real-time datasets. The experimental results indicate that the proposed model can increase the detection rate and reduce the false alarm rate efficiently.

A Multi-Stage Cloud Security for Cloud Data using Amalgamate Data Security

E. Ravi Kumar, S. Sai Satyanarayana Reddy, M. Babu Reddy — Wed, 25 May 2022 00:00:00 +0000

Every organization is planning to deploy their projects and data into the cloud storage based on availability of the cloud services. From the past many years security plays the major role in cloud storage for the data availability. Various Encryption and decryption algorithms are that are utilized to provide the better security for the cloud data. Recently another challenge that is identified in cloud storage is uploading large files within the cloud server. To overcome this issue, the multi cloud security is required to store the files in cloud server. Splitting of files in equal chunks and upload the files into multiple clouds, generating the keys for every files and merging the file when the user required for access. Previously various algorithms, techniques are discussed such as dual encryption technique; Compound Encryption based Algorithm (CEBA) for rapid encryption, Compound Secure Storage (CSS) of data with Ensemble Access of Data (EAD) are the integrated methods to provide the security, improving the encryption and decryption time. A few drawbacks are identified in the above techniques such as limited file size and more time for encryption and decryption. In this paper, An Amalgamate Data Security (ADS) is developed to split the large files into the equal shares and stored into the cloud. Generating the private keys for every chunk of the file is also a tedious task. To overcome this, an efficient file merger (EFM) is developed to merge the requested file by the user by matching the private keys. Result shows the performance in terms of encryption and decryption time based on the size of the file.

Gateway Placement Optimization using Multihop Traffic Approach in IoT Network

Suvarna Patil, Dr. Prasad Gokhale — Wed, 01 Jun 2022 00:00:00 +0000

The Internet of Things (IoT) is a promising advanced technology that links large wireless communications machines and devices in the future. In effective wireless communication, Gateway plays a significant tile. The performance of IoT networks is affected by various network parameters such as the position in the network gateways and heterogenous coordinating devices. To increase the performance of the network, the placement of the gateways should be optimal, which reduces the deployment cost and increases throughput. Furthermore, more than one gateway reduces congestion within the IoT network, resulting in noise and cost increases. Most researchers focused on the placement of internet gateway or mesh routers in the Wireless Mesh Network (WMN). However, the gateway placement problem needs to focus on IoT networks where heterogeneous wireless technologies are involved for machine-to-machine communication(M2M). In this article, a revolutionary IoT network gateway positioning is proposed. It defines the locality of a gateway based on the new Multi-hop Traffic Metric (Mh_TM). The Mh_TM computing includes many factors affecting the throughput of IoT networks: the set of coordinating devices, the set of gateways, the demand for traffic from coordinating devices, locality of gateways, and potential interference between gateways. The projected gateway position strategy offers a mechanism in which IoT networks improve their performance substantially by correctly placing gateways. A non-asymptotic throughput of the IoT network is driven by using link scheduling to assess the efficiency of the current gateway placement system. The experimental results of the proposed gateway placement system are outperforming the other systems with improved margins.

Enhanced Neural Network Based Combined Classification for Intrusion Detection System

Nusrath Unnisa A, Dr.Manjula Yerva, Dr. M. Z. Kurian — Wed, 01 Jun 2022 00:00:00 +0000

Communication is a method of conveying information between end users. In this digital era data communication plays a vital role where the information is transmitted through internet. All over the world, web applications are used to store sensitive and personal data. These issues make them an attractive target for malware that exploits vulnerabilities in order to acquire unauthorized access. In order to access a particular resource a unique address is used called URL (Uniform Resource locator). These URL’s can be attacked by an intruder to access the information stored on the client side or server by redirecting them. This paper proposes a model for intrusion detection system which is a combination of K-Nearest neighbour, Support vector machine and neural network in which the final output class is decided as Malicious or Benign based on the majority voting scheme. The work is carried out by using Cross Site scripting (XSS) attacks database and an alert is given to the end user that URL is malicious or benign.

Detection Of Cooperative Black Hole Attack In Mobile Ad Hoc Network (Manet) For Next Generation Network (Ipv6) Routing Protocol

Mr. Ganesh D. Dangat, Dr.S. Murugan — Thu, 10 Nov 2022 00:00:00 +0000

In some settings, mobile ad-hoc networks (MANET) can be set up quickly and without much effort. Routing with sufficient powerful performance is one of the main issues in installing MANET, which is characterised by a dynamic change in topology. In cooperative black hole attacks, each node falsely claims to control a dependable path between the starting point and the final resting place. The proposed unique solution takes into consideration the IPV6, IEEE 802.11e protocol, and aims for findings connected to the exchange of MANETs-Reactive routing protocols. The enriched routing protocol has a positive impact on performance and efficiency, resulting in significant enhancements to the protocol's features. Proactive routing protocols such as Asymmetric Outer-Distance Vector (AODV), Distance-Sequential Vector (DSDV), and Destination-Sequenced Distance Vector (DSDV) were tested in both IPv4 and IPv6 networks and compared using the cooperative black hole attack with respect to a variety of performance indicators (RO). The outcome demonstrates the effectiveness of the novel strategy as a whole, with throughput increasing and end-to-end latency decreasing.

Face Recognition System Using CNN Algorithm and Computer Vision

Poojitha Chennuru, Dr. P. Nageswararao, P. Ramesh — Thu, 08 Dec 2022 00:00:00 +0000

The human face is a key factor in identifying a person. Even identical twins have distinctive faces. In order to identify one another, facial recognition and identification are necessary. As a result, we are putting forth a technique that can identify CNN models that are based on deep learning. Here, we're compiling a dataset of various faces. We train the data with the CNN method after preprocessing it. After training, we'll use OpenCV to evaluate the findings and upload the image for face recognition.

Android Application for Disease Prediction and Medical Prescription

TD Lakshmi Prasanna , Dr. K. Venkataramana, P. Ramesh — Thu, 08 Dec 2022 00:00:00 +0000

Android Application for Disease Prediction and Medical Prescription contains different health diseases based on their appropriate symptoms and related prescriptions (Medicines) to be taken in order to prevent those diseases. This Application is helpful in urgent / emergency cases if the hospitals are far from their residence and if doctors are not available in right time and area. The patient scan easily identifies the disease by just providing their issues/symptoms and the Application generates what disease he/she may be infected from. It also guides them to be safe and what are the steps to be followed to be away from those diseases. This is most useful to the middle and lower class people in terms of the doctor’s fee, here they can know about the diseases and related medicines to be taken. Due to large amount of data grow thin biomedical and healthcare field providing accurate analysis of medical data that has benefits from early detection, patient care, and community services. Users can post their queries in order to seek information regarding diseases so that user get the proper answer to any kind of question and solving any problem related to the disease. This project allows not only disease prediction but also searching nearby hospitals, ordering medicines, nearest medical shops, vitamins/supplements and feedback of ordered medicines from v the customers.

A Study on the Performance Analysis of MIMO Based OFDM System Under Fading Channel

Musinada Harikrishna, Vijay Prakash Singh — Thu, 22 Dec 2022 00:00:00 +0000

MIMO-OFDM (Multiple Input Multiple Output Orthogonal Frequency Division Multiplexing) is currently perceived as perhaps of the most famous and serious wireless procedure. MIMO-OFDM innovation is a blend of multiple-input multiple-output (MIMO) wireless innovation and orthogonal frequency division multiplexing (OFDM), and it has been distinguished as one of the most encouraging procedures for supporting high information rates and execution in an assortment of channel conditions. MIMO innovation is significant in wireless communication frameworks since it gives critical expansions in information rate and connection range without requiring extra sends power. The proposed study centers around strategies for working on the exhibition of Multiple Input Multiple Output - Orthogonal frequency division multiplexing (MIMO-OFDM) in Fading Channels.

In communication frameworks, the most encouraging blend of advances for high information rate administrations in cutting edge wireless organizations is Multiple input Multiple output (MIMO) radio wire frameworks with orthogonal frequency division multiple entrance (OFDMA). Multiple recieving wires are utilized in both the transmitter and collector in MIMO frameworks to further develop communication execution, though orthogonal frequency division multiple entrance (OFDMA) is a multicarrier multiple entrance strategy. Due to its high transmission rates and protection from multipath fading, MIMO-OFDMA is broadly utilized in communication frameworks. This paper gives a top to bottom assessment of latest things and advancements in Orthogonal Frequency Division Multiple Accesses (OFDMA). In this paper, we will go over the basics of OFDM methods, their job in this day and age, their benefits and impediments, and a portion of their applications. In this paper, we present an investigation of different obstruction impacts and remuneration procedures in a MIMO-OFDMA framework. We present an exhaustive report on MIMO OFDMA for wireless communications in this paper.

Impact of MIMO-OFDM Communication System

Shubham Kailash Durge, Vijay Prakash Singh — Thu, 22 Dec 2022 00:00:00 +0000

The de facto method for a broadband data transfer is now remote communication frameworks based on multi-receiving wire multi-transporter tweak techniques, for instance, symmetrical recurrence division multiplexing (MIMO) (OFDM). However, it still falls short of meeting the steadily rising demand for high information rate transmission when used alone. Third Generation Partnership Project (3GPP) has proposed new features like transporter collection (CA) and advanced multi-recieving wire methods in Long Term Evolution-Advanced to meet this demand (LTE-A). The efficiency of the cell organisations can be fully advanced by utilising the benefits of OFDM with CA and advanced multi-recieving wire strategies. However, the high top to average power ratio (PAPR) problem in OFDM signals causes nonlinear signal bending when high power enhancers (HPAs) are used. Additionally, equipment degradation, or stage commotion brought on by subpar oscillators, completely degrades the framework's productivity and performance. When compared to straight frameworks, these flaws severely restrict the gains made by OFDM-based frameworks.

The effects of oscillator stage disturbances (PNs) on symmetrical recurrence division multiplexing (OFDM) MIMO frameworks are taken into consideration. It is demonstrated that while PNs of regular oscillators at the beneficiary and transmitter have different effects on spatial multiplexing MIMO-OFDM frameworks with SVD-based precoding/unraveling, they have similar effects on the demonstration of (single-stream) bar shaping MIMO-OFDM frameworks. The PNs at the transmitter and the recipient have different effects on shaft shaping MIMO-OFDM frameworks and spatial multiplexing MIMO-OFDM frameworks when each receiving wire is equipped with a free oscillator.

XGBOOST as A Classifier for Security Level Detection of Cryptosystem

Anyam Mohan, Dr. S. Raj Anand — Thu, 29 Dec 2022 00:00:00 +0000

By now, we have most likely heard of, or used, Zoom, the video conferencing service. Due to the coronavirus pandemic, Zoom has experienced an enormous spike in use over the past few months.Unfortunately, that same ease of use seems to have led to a variety of security and privacy issues.In short, Zoom’s meeting encryption exhibited less than “end-to-end” fortitude. In line with their privacy practices, the image, video and audio content during a Zoom meeting would remain private from any outsider (i.e., hackers). On this note, we can clearly tell that, though, several proposed encryption algorithms proven failed by allowing major vulnerabilities against important data. To reduce such vulnerabilities, it’s very important that which encryption algorithm is being used to protect the data. And we’ve to know which algorithm is suitable for that specific image, video or audio encryption along with the accuracy of encryption. Here for to full fill this need, we propose as security level detection approach for finding “strong, medium and weak” image encryption algorithms by incorporating a XGBoost Classifier Machine learning technique to reduce the effort of time complexity on detecting the appropriate encryption method.

A Cloud Secure Storage Mechanism Based On Data Dispersion And Encryption

S. Vishnu Priya , Dr. C. Siva Balaji Yadhav, P. Ramesh — Thu, 29 Dec 2022 00:00:00 +0000

Cloud storage service has shown its great power and wide popularity which provides fundamental support for rapid development of cloud computing. However, due to management negligence and malicious attack, there still lie enormous security incidents that lead to quantities of sensitive data leakage at cloud storage layer. From the perspective of protecting cloud data confidentiality, this paper proposed a Cloud Secure Storage Mechanism named CSSM. To avoid data breach at the storage layer, CSSM integrated data dispersion and distributed storage to realize encrypted, chucked and distributed storage. In addition, CSSM adopted a hierarchical management approach and combined user password with secret sharing to prevent cryptographic materials leakage. The experimental results indicate that proposed mechanism is not only suitable for ensuring the data security at storage layer from leakage, but also can store huge amount of cloud data effectively without imposing too much time overhead. For example, when users upload/download 5G sized file with CSSM, it only takes

646seconds/269seconds, which is acceptable for users.

Language And Meaning with Some Philosophical Context

Fatema Khatun — Tue, 05 Apr 2022 00:00:00 +0000

Language is a means of communication, the meaningful signs, understanding through which communication is possible. Language is not like the logical constants; it evolves. In course of development of human society, the words acquire meaning because of human effort to give words the meaning. Language is a system of conventional signs and we have to learn the meanings of those signs in order to know language. In this paper I would like to focus what is the main function of language in Indian and Western Context?