IJCST Logo










 

International Journal of Computer Science and Technology
IJCST Vol 14 Issue 3 (July-Sept 2023)

S.No. Research Topic Paper ID Download
01

Dual Access Control For Cloud-Based Data Storage and Sharing Using ABE Method

Yanala Veera Lakshmi, D.S. Ram Kiran

Abstract

Cloud storage offerings have come to be increasingly across the board. In light of the fact that of the estimation of privations, many cloud storage encryption plans have been proposed to shield information from people who don’t have section. Every such plan expected that cloud storage merchants are riskless and can’t be hacked; in any case, in take after, a few specialists (i.e., coercers) may drive cloud storage suppliers to unveil individual insider facts or private information on the cloud, hence through and through dodging storage encryption plans. In this paper, we exhibit our outline for a fresh out of the box new cloud storage encryption conspire that grants cloud storage suppliers to make persuading counterfeit client privileged insights to take care of client privatives. For the reason that coercers can’t reveal if procured mysteries are appropriate or not, the cloud storage provider be sure that client privateers keeps on being safely secured.
Full Paper

IJCST/143/1/A-1009
02

Smart Crypt-Secure Storage and Sharing of Time Series Data Stream in Iot

Kadali Joshna Seshasai, S.Srinivas

Abstract

A growing number of Industrial Internet of Things (IIoT) devices and services collect massive time-series data related to production, monitoring and maintenance. To provide ubiquitous access, scalability and sharing possibilities, the IIoT applications utilize the cloud to store collected data streams. However, secure storing of the massive and continuously generated data poses significant privacy risks, including data breaches for IIoT applications. Alongside, we need to protect the utility of the data streams by allowing benign services to access and run analytics securely and selectively.
To address this, we propose SmartCrypt, a data storing and sharing system that supports scalable analytics over the encrypted time-series data. SmartCrypt enables users to secure and fine-grain sharing of their encrypted data. Additionally, SmartCrypt guarantees data confidentiality in the presence of unauthorized parties by allowing end-to-end encryption using a novel symmetric homomorphic encryption scheme. We perform extensive experiments on a real-world dataset primarily to assess the feasibility of SmartCrypt for secure storing and sharing of IIoT data streams. The results show that SmartCrypt reduces query time by 17%, reduces range query time by 32%, improves throughput by 9% and scalability by 20% over the best performed scheme in the state-of-the-art.
Full Paper

IJCST/143/1/A-1010
03

A Secure Backup System Using Multi Cloud and Fog Computing

Kothakota Satya Supriy, D.S.Ramkiran

Abstract

Data backup is essential for disaster recovery. Current cloud-based solutions offer a secure infrastructure. However, there is no guarantee of data privacy while hosting the data on a single cloud. Another solution is using multi-Cloud technologies. Although using multiple clouds to save smaller pieces of the data can enhance data privacy, it comes at the cost of the need for the edge device to manage different accounts and manage communication with different clouds.
These drawbacks made this technology rare to use technology. In this paper, we propose DropStore to provide an easy-to-use, highly secure, and reliable backup system using state-of-the-art multi-Cloud and encryption techniques. DropStore adds an abstraction layer for the end-user to hide all system complexities using a locally hosted device,„„the Droplet‟‟, that is fully managed by the user. Hence, the user does not rely on any untrusted third party. This was achieved using Fog Computing technology. The uniqueness of DropStore comes from the convergence of MultiCloud and Fog Computing principles. The system implementation is open-source and available online. Performance results show that the proposed system improves data protection in terms of reliability, security, and privacy preservation while maintaining a simple and easy interface with edge devices.
Full Paper

IJCST/143/1/A-1011
04

A Quality Representation Intended for Data Sharing and Privacy Preserving Application for Cloud Data

Nethala Chandra Kiran, S. Srinivas

Abstract

A standout amongst the most critical current examinations in the Cloud Computing provisioning is the Service Level Agreement and its application in guaranteeing the supplied distributed computing administrations. The method for giving dispersed administrations has been re-imagined as an outcome of utilizing distributed computing which as a part of turn has acquainted new difficulties with both suppliers and shoppers. Measuring the nature of distributed computing procurement from the customer’s perspective is imperative so as to guarantee that the administration fits in with the level determined in the understanding; this is generally alluded to as Quality of Experience. There has been some exertion in measuring the Quality of Service as a strategy for guaranteeing the administration level in distributed computing. One of the difficulties with measuring the Quality of Experience parameters is that huge numbers of the parameters are subjective, and consequently makes it hard to characterize a measured metric to be utilized for instrumenting the supplied administration. This paper portrays a workin-advancement explore that endeavors to characterize an evaluated metric that can be utilized as an execution measure to benchmark SaaS applications in distributed computing. Such a metric will be valuable to cloud suppliers and also purchasers for guaranteeing that the conveyed administrations meet the client needs.
Full Paper

IJCST/143/1/A-1012
05

The Secure and Expressive Data Access Control for Cloud Storage

Kona Vanitha, S Surya Godha Devi

Abstract

Secure cloud storage, which is an emerging cloud service, is designed to protect the confidentiality of outsourced data but also to provide flexible data access for cloud users whose data is out of physical control. Ciphertext-Policy Attribute-Based Encryption (CP-ABE) is regarded as one of the most promising techniques that may be leveraged to secure the guarantee of the service. However, the use of CP-ABE may yield an inevitable security breach which is known as the misuse of access credential (i.e. decryption rights), due to the intrinsic “all-or-nothing” decryption feature of CP-ABE. In this paper, we investigate the two main cases of access credential misuse: one is on the semi-trusted authority side, and the other is on the side of cloud user. To mitigate the misuse, we propose the first accountable authority and revocable CP-ABE based cloud storage system with white-box traceability and auditing, referred to as CryptCloud+. We also present the security analysis and further demonstrate the utility of our system via experiments.
Full Paper

IJCST/143/1/A-1013
06

Secure Data Sharing for Cloud Computing Based Cloud Storage System

Bhupathiraju Shivani, D. Srinivas

Abstract

Cloud computing has been considered an enterprise for IT infrastructure, which can organize huge resource of computing, storage and applications, and enable users to enjoy ubiquitous, convenient on-demand network access to a configurable computing resources with great efficiency and minimal economic overhead for shared pool. Attracted by these appealing features, both individuals and enterprises are motivated to contract out their data to the cloud, instead of purchasing software and hardware to manage the data themselves. So far, most of the works have been proposed under different threat models to achieve various search functions, such as single keyword search, similarity search, multi- keyword Boolean search, ranked search, multi-keyword ranked search, etc. Among them, multikeyword ranked search achieves more attention for its practical applicability. propose a secure and ranked multikeyword search protocol in a multi-owner cloud model over encrypted cloud data.
Full Paper

IJCST/143/1/A-1014
07

The Data Sharing and Personalized Analysis Model for 5G-Smart Diabetes

Rongala Lavanya, D. Srinivas

Abstract

The healthcare business is being refined at an exponential rate as a result of the speed with which digital innovation and technology disruption are occurring. The massive amount of healthcare data continues to grow by the minute, making it increasingly impossible to find any sort of useful information. Big data analytics is currently transforming traditional information distribution into actionable insights. Big data analytics has a lot of benefits in the healthcare industry, such as detecting critical diseases early on and delivering better healthcare services to the appropriate patient at the right time to improve the quality of life care. Existing health data analytics platforms that provide procedural mechanisms for data collection, gathering, processing, analysis, visualisation, and interpretation have a number of difficulties to address. We hope to design a long-term, commercially viable, and intellectual diabetes diagnosis solution with tailored therapy in this study. Due to a lack of comprehensive research in the prior literature, this paper examines the promising topic of huge data analytics in big data analytical tools, as well as the various phases followed by the healthcare economy from data collection to information distribution. The investigational results demonstrate that our system can efficiently deliver adapted diagnosis and treatment suggestions to patients, and the focus here is on information exchange technique and adapted data analysis model for Smart Diabetes system.
Full Paper

IJCST/143/1/A-1015
08

The Integrity Auditing for Multi-Copy in Cloud Storage Based on Red-Black Tree

Damera Sai Lalitha Keerthana, K. V. Durga Devi

Abstract

With the rapid development of cloud storage, cloud users are willing to store data in the cloud storage system, and at the same time, the requirements for the security, integrity, and availability of data storage are getting higher and higher. Although many cloud audit schemes have been proposed, the data storage overhead is too large and the data cannot be dynamically updated efficiently when most of the schemes are in use. In order to solve these problems, a cloud audit scheme for multi-copy dynamic data integrity based on red-black tree full nodes is proposed. This scheme uses ID-based key authentication, and improves the classic Merkel hash tree MHT to achieve multi-copy storage and dynamic data manipulation, which improves the efficiency of real-time dynamic data update (insertion, deletion, modification). The thirdparty audit organization replaces users to verify the integrity of data stored on remote cloud servers, which reduces the computing overhead and system communication overhead. The security analysis proves that the security model based on the CDH problem and the DL problem is safe. Judging from the results of the simulation experiment, the scheme is safe and efficient.
Full Paper

IJCST/143/1/A-1016
09

Securing Government Research Content with QR Code Using Cryptography

V V Sita Prasanna K, S Surya Godha Devi

Abstract

Government division may be a crucial portion of the nation’s economy. Security of government inquire about substance from all sorts of dangers is basic not as it were for trade coherence but too for supporting the economy of the country as a entirety. With the digitization of conventional records, government substances experience troublesome issues, such as government capacity and access. Research office spend significant time questioning the specified information when getting to Government investigate substance subtle elements, but they gotten information are not fundamentally rectify, and get to is some of the time limited. On this premise, this think about proposes a investigate substance which utilize ciphertext-based encryption to guarantee information privacy and get to control of record subtle elements. The investigate head may scramble the put away data for accomplishing get to control and keeping information secure. In this manner AES Rijndael calculation is utilized for encryption. This guarantees security for the data and empowers Protection.
Full Paper

IJCST/143/1/A-1017
10

REGISTRA Cyber Threat Analysis based on ANN using Event Profiles

Bondada Naveen Kumar, D.S.Ramkiran

Abstract

Cyber Supply Chain (CSC) system is complex which involves different sub-systems performing various tasks. Security in supply chain is challenging due to the inherent vulnerabilities and threats from any part of the system which can be exploited at any point within the supply chain. This can cause a severe disruption on the overall business continuity. Therefore, it is paramount important to understand and predicate the threats so that organization can undertake necessary control measures for the supply chain security. Cyber Threat Intelligence (CTI) provides an intelligence analysis to discover unknown to known threats using various properties including threat actor skill and motivation, Tactics, Techniques, and Procedure (TT and P), and Indicator of Compromise (IoC). This paper aims to analyse and predicate threats to improve cyber supply chain security. We have applied Cyber Threat Intelligence (CTI) with Machine Learning (ML) techniques to analyse and predict the threats based on the CTI properties. That allows to identify the inherent CSC vulnerabilities so that appropriate control actions can be undertaken for the overall cybersecurity improvement. To demonstrate the applicability of our approach, CTI data is gathered and a number of ML algorithms, i.e., Logistic Regression (LG), Support Vector Machine (SVM), Random Forest (RF), and Decision Tree (DT), are used to develop predictive analytics using the Microsoft Malware Prediction dataset.
Parameters and vulnerabilities and Indicators of compromise (IoC) as output parameters. The results relating to the prediction reveal that Spyware/Ransomware and spear phishing are the most predictable threats in CSC. We have also recommended relevant controls to tackle these threats. We advocate using CTI data for the ML predicate model for the overall CSC cyber security improvement.
Full Paper

IJCST/143/1/A-1018
11

The Secure and Expressive Data Access Control for Cloud Storage

Konda Sindhuja, S Surya Godha Devi

Abstract

Secure cloud storage, which is an emerging cloud service, is designed to protect the confidentiality of outsourced data but also to provide flexible data access for cloud users whose data is out of physical control. Ciphertext-Policy Attribute-Based Encryption (CP-ABE) is regarded as one of the most promising techniques that may be leveraged to secure the guarantee of the service. However, the use of CP-ABE may yield an inevitable security breach which is known as the misuse of access credential (i.e. decryption rights), due to the intrinsic “all-or-nothing” decryption feature of CP-ABE. In this paper, we investigate the two main cases of access credential misuse: one is on the semi-trusted authority side, and the other is on the side of cloud user. To mitigate the misuse, we propose the first accountable authority and revocable CP-ABE based cloud storage system with white-box traceability and auditing, referred to as CryptCloud+. We also present the security analysis and further demonstrate the utility of our system via experiments.

Full Paper

IJCST/143/1/A-1019
12

The Automatic Song Recommendation System Based on Human Facial Expressions

Surisetti Maha Lakshmi, S Surya Godha Devi

Abstract

The human face is an important organ of an individual‘s body and it especially plays an important role in extraction of an individual‘s behaviour and emotional state. Manually segregating the list of songs and generating an appropriate playlist based on an individual‘s emotional features is a very tedious, time consuming, labour intensive and upheld task. Various algorithms have been proposed and developed for automating the playlist generation process. However, the proposed existing algorithms in use are computationally slow, less accurate. This proposed system based on facial expression extracted will generate a playlist automatically thereby reducing the effort and time involved in rendering the process manually. Thus, the proposed system tends to reduce the computational time involved in obtaining the results and the overall cost of the designed system, thereby increasing the overall accuracy of the system. Facial expressions are captured using an inbuilt camera. The accuracy of the emotion detection algorithm used in the system for real time images is around 85-90%, while for static images it is around 98- 100%. Thus, it yields better accuracy in terms of performance and computational time and reduces the designing cost, compared to the algorithms used in the literature survey. Based on the obtained emotion, playlist is created.

Full Paper

IJCST/143/1/A-1020
13

Identification of Fraud Detection from Credit Card Transactions Using Machine Learning

Nargana Satya, D Srinivas

Abstract

This Project is focused on credit card fraud detection in real world scenarios. Nowadays credit card frauds are drastically increasing in number as compared to earlier times. Criminals are using fake identity and various technologies to trap the users and get the money out of them. Therefore, it is very essential to find a solution to these types of frauds. In this proposed project we designed a model to detect the fraud activity in credit card transactions. This system can provide most of the important features required to detect illegal and illicit transactions. As technology changes constantly, it is becoming difficult to track the behavior and pattern of criminal transactions. To come up with the solution one can make use of technologies with the increase of machine learning, artificial intelligence and other relevant fields of information technology; it becomes feasible to automate this process and to save some of the intensive amounts of labor that is put into detecting credit card fraud. Initially, we will collect the credit card usage data-set by users and classify it as trained and testing dataset using a random forest algorithm and decision trees. Using this feasible algorithm, we can analyze the larger data-set and user provided current data-set. Then augment the accuracy of the result data. Proceeded with the application of processing of some of the attributes provided which can find affected fraud detection in viewing the graphical model of data visualization. The performance of the techniques is gauged based on accuracy, sensitivity, and specificity, precision. The results is indicated concerning the best accuracy for Random Forest are unit 98.6% respectively.

Full Paper

IJCST/143/1/A-1021
14

The Heart Disease Prediction Using Bio Inspired Algorithms

Pidimarla Prathyusha, K.Durga Devi

Abstract

As we all know that heart is the major organ when compared to the brain which plays an important role in the human body. It pumps blood, supplies blood to all parts of the body, and purifies the blood. Nowadays, heart diseases have become common irrespective of age. A large number of death cases all over the world are related to heart diseases. Prediction of occurrence of heart diseases is an urge nowadays the cases are increasing and heart disease does not occur all of a sudden. To deal with this problem, we need to bring about awareness about the diseases to the world. Heart diseases can be predicted with the help of Machine Learning Algorithms. A huge number of patients details will be collected and interpreted to predict the occurrence of disease. In this paper, we calculate the accuracy of machine learning algorithms for predicting heart disease. The algorithms which are used is Logistic Regression (LR), K Nearest Neighbor (KNN), Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), and Naïve Bayes (NB) by using a sample dataset from Kaggle website. For implementation of Python programming, Jupyter notebook is used.

Full Paper

IJCST/143/1/A-1022
15

DNN Based Fake News Identification and Analysis

Nagumalla Lalitha Naga Lakshmi Alekya, S Surya Godha Devi

Abstract

As the world is growing towards Internet-based digitalization over the social media, millions of articles are uploaded every second, and the Internet users are more keep on social media applications such as WhatsApp, Meta, Instagram, Twitter and other online applications. The aim of the project is to detect the Fake or Real News in online available articles. There are many news channels online, who are publishing the daily news and more people read online media as it has many benefits such as paperless, fingertip availability of news, Attractive headlines and colorful titles. The recent advancement of the online social media platforms has impacted the daily life of civilization. The people who are using the above online news platform should not get the fake news regarding, we need to identify the challenging solution that can detect the fake news. The application of the Project is detecting the fake news using Machine Learning (ML) and Deep learning (DL). The project uses two major algorithms namely Passive Aggressive Classifier and Adaptive Boosting Classifier (ABC) and Long Short Term Memory (LSTM). We have made the strong analysis and visualization on the dataset supplied. Our models are providing 95% & above accuracy. Finally we have developed the Web Application for the prediction of Forged and Actual news.

Full Paper

IJCST/143/1/A-1023
16

Stress Detection In IT Professionals Using Deep Learning

Manda Mahalakshmi, D Srinivas

Abstract

The main motive of our project is to detect stress in the IT professionals using Deep learning, vivid Machine learning and Image processing techniques.Our system is an upgraded version of the old stress detection systems which excluded the live detection and the personalcounselling but this system comprises of live detection and periodic analysis of employees and detecting physical as well as mental stress levels in his/her by providing them with proper remedies for managing stress by providing survey forms periodically. Our project mainly focuses on managing stress and making the working environment healthy and spontaneous for the employees and to get the best out of them during working hours.

Full Paper

IJCST/143/1/A-1024
17

Random Forest Based Chronic Kidney Disease Prediction and Analysis

Nuvvula Nikhitha, K.Durga Devi

Abstract

Chronic Kidney Disease (CKD) need to be diagnosed earlier before kidneys fail to work.In order to help doctors or medical experts in prediction of CKD among patients easily, this paper has developed an intelligent system named Chronic Kidney Disease Prediction System (CKDPS) that can predict CKD among patients. The proposed system predict the CKD with minimal feature input instead of dumping all the features which may not relevant to predict the disease.To achieve this we have planned to approach by three feature selection algorithm with combination of two feature Extraction algorithm.After performing feature selection and Feature Extraction, those features will be trained with different Machine Learning algorithm. The accuracy of best combination algorithm will be implemented for predicting the CKD.Finally, Random Forest algorithm is chosen to implement CKDPS as it gives 95% accuracy, precision and recall results.

Full Paper

IJCST/143/1/A-1025
18

A Child Tracking System Based on Real Time Vehicle Tracking System

Kadimi Sowjanya, D Srinivas

Abstract

When it comes to student transportation, every school has two major problems – student school bus safety and efficient fleet management. The reports from international crime bureau that a child goes missing for every three minutes in the world. This is a big issue which has to roll in parents mind. They always worried about the child when they send their children to a place behind their eyes the places like school or private classes. To lessen the parent’s anxiety about their children, a vehicle positioning system is prepared by merging radio frequency identification, global positioning system, web server, web tracking, and android technology. The system consists of RFID tags and reader which is designed to scrutinize the entry and exit of a person in the particular vehicle where child boarded each person is assigned the tag which holds the precise identification details when children enters the vehicle, the readers read the person tag and stores the details of entry, exit, and vehicle identification code. This information is notified to the concerned authority like school admin and parents via the android app and website as entering, exit, pickup, drop, vehicle emergency and wrong route of the vehicle. The proposed system facilitates to know about the area where the vehicle has crossed the path using RFID. The GPS technology connected with this system helps in acquiring location updates in the school server database. This proficient tracking structure with the enriched feature is designed and implemented for the purpose of protection in various stream. It is up and coming technology in the field of communication and network. The tag on the road model is an evolving and just able technique in the future world. The projected system here is planned to be implemented in schools for the safety of the students and it can also be installed in the professional security system.

Full Paper

IJCST/143/1/A-1026
19

An Efficient Cyber Hacking Breaches Analysis Using Machine Learning

Chennapragada Madhava Rao, V.Veerndra Subash

Abstract

Analyzing cyber incident information units is an essential approach for deepening our expertise in the evolution of the chance situation. This is an especially new study topic, and lots of research continue to be done. In this paper, we record a statistical evaluation of a breach incident records set similar to 12 years (2005–2017) of cyber hacking sports that encompass malware attacks. We display that, an evaluation of the findings stated withinside the literature, each hacking breach incident inter-arrival instances and breach sizes must be modeled through stochastic processes, instead of through distributions due to the fact they show off autocorrelations. Then, we recommend specific stochastic procedure fashions to, respectively, shape the inter-arrival instances and the breach sizes. We additionally display that those fashions can expect the inter-arrival instances and the breach sizes. In order to get deeper insights into the evolution of hacking breach incidents, we behaviour each qualitative and quantitative fashion analysis at the records set. We draw a fixed of cyber safety insights, together with that the chance of cyber hacks is certainly getting worse in phrases in their frequency, however now no longer in phrases of the value in their damage.

Full Paper

IJCST/143/1/A-1027
20

Classification of Online Toxic Comments Using Machine Learning

Rayudu Hinduja, P.Rama Krishna

Abstract

Conversational toxicity is a problem that might drive people to cease truly expressing themselves and seeking out other people’s opinions out of fear of being attacked or harassed. The purpose of this research is to employ natural language processing (NLP) techniques to detect toxicity in writing, which might be used to alert people before transmitting potentially toxic informational messages. Natural language processing (NLP) is a part of machine learning that enables computers to comprehend natural language. Understanding, analysing, manipulating, and maybe producing human data language with the help of a machine are all possibilities. Natural Language Processing (NLP) is a type of artificial intelligence that allows machines to understand and interpret human language instead of simply reading it. Machines can understand written or spoken text and execute tasks such as speech recognition, sentiment analysis, text classification, and automatic text summarization using natural language processing (NLP).

Full Paper

IJCST/143/1/A-1028
21

Analysis of Efficient Cyber Hacking Breaches Using Machine Learning

Achanta Ayyappa, P.Rama Krishna

Abstract

Contrasted with the past, improvements in PC and correspondence innovations have given broad and propelled changes. The use of new innovations give incredible advantages to people, organizations, and governments, be that as it may, messes some up against them. For instance, the protection of significant data, security of put away information stages, accessibility of information and so forth. Contingent upon these issues, digital fear based oppression is one of the most significant issues in this day and age. Digital fear, which made a great deal of issues people and establishments, has arrived at a level that could undermine open and nation security by different gatherings, for example, criminal association, proficient people and digital activists. Along these lines, Intrusion Detection Systems (IDS) has been created to maintain a strategic distance from digital assaults.

Full Paper

IJCST/143/1/A-1029
22

Cyber Fraud: Detection and Analysis of Crypto Ransomware

Tolum Srihari, S Srinivas

Abstract

The internet users are increasing day by day causing internet traffic. Fraud detection is one of the main challenges in e-commerce transactions. As transactions are increasing, the quantity of fraud on online transaction also may increase. Huge amount transactions are often done on e-commerce websites. When large amounts of money are moved, there is a high risk that users will engage in fraudulent activities. Fraud prevention in e-commerce shall be developed using machine learning, this work to analyze the suitable machine learning algorithm such as Random Forest and Decision Tree algorithms. Machine learning is really great at detecting fraudulent activity. The goal of this challenge is to create a machine learning model that predicts the probability that a new user’s first transaction will be fraudulent. Our proposed system can be applied on Kaggle dataset.

Full Paper

IJCST/143/1/A-1030
23

Cyber Detail Analysis and Prediction Using Machine Learning

S N S Rama Somesh N, G Aruna Rekha

Abstract

Crime is one of the biggest and dominating problem in our society and its prevention is an important. task. Daily there are huge numbers of crimes committed frequently. This require keeping track of all the crimes and maintaining a database for same which may be used for future reference. The current problem faced are maintaining of proper dataset of crime and analyzing this data to help in predicting and solving crimes in future. The objective of this project is to analyze dataset which consist of numerous crimes and predicting the type of crime which may happen in future depending upon various conditions. In this project, we will be using the technique of machine learning and data science for crime prediction of Chicago crime data set. The crime data is extracted from the official portal of Chicago police. It consists of crime information like location description, type of crime, date, time, latitude, longitude. Before training of the model data preprocessing will be done following this feature selection and scaling will be done so that accuracy obtain will be high. The K-Nearest Neighbor (KNN) classification and various other algorithms will be tested for crime prediction and one with better accuracy will be used for training. Visualization of dataset will be done in terms of graphical representation of many cases for example at which time the criminal rates are high or at which month the criminal activities are high. The soul purpose of this project is to give a jest idea of how machine learning can be used by the law enforcement agencies to detect, predict and solve crimes at a much faster rate and thus reduces the crime rate. It not restricted to Chicago, this can be used in other states or countries depending upon the availability of the dataset.

Full Paper

IJCST/143/1/A-1031
24

Traffic Sign Recognition Using Deep Learning for Autonomous Driverless Vehicles

Javvadi Usha Naga Sri Lakshmi, B.Maha Lakshmi Rao

Abstract

Traffic sign acknowledgment (TSR) is one of the most significant foundation examine themes for empowering independent vehicle driving frameworks. Independent driving frameworks require extraordinary treatment of info information: there is no time for complex changes or refined picture handling procedures, they need a strong and ongoing investigation of a circumstance. This test get more difficult to meet in a city like condition where various traffic signs, advertisements, leaving vehicles, walkers, and other moving or foundation objects make the acknowledgment considerably more difficult. While various arrangements have been distributed, arrangements are tried on auto ways, open country, or at an extremely low speed. As per measurements, most street mishaps happen because of absence of reaction time to moment traffic occasions. With oneself driving autos, this issue can be tended to by actualizing mechanized frameworks to distinguish these traffic occasions. To plan such acknowledgment framework in self-driving this includes effectively recognizing the traffic signs that can be looked by a computerized vehicle, characterizing them, and reacting to them. Traffic sign acknowledgment and discovery is a significant piece of any self-sufficient vehicle. Be that as it may, the genuine test lies in the location and acknowledgment of these traffic sign from the characteristic picture progressively and with exactness. This paper gives an outline of the traffic street sign location and acknowledgment framework, we created and executed utilizing a fake neural system which is prepared utilizing genuine datasets. The use of convolution neural system alongside of our venture to achieve constant outcome with precision. The framework created dependent on this approach can be actualized in broad daylight transports, individual autos, and different vehicles so as to keep drivers caution and lessen human blunders that lead to mishaps. The undertaking has a wide usage of self-driving vehicles.

Full Paper

IJCST/143/1/A-1032
25

Smart Traffic Detection and Control Using Canny Edge Detection Algorithm

Bayyana Haritha, S Srinivas

Abstract

The frequent traffic jams at major junctions call for an efficient traffic management system in place [1,2].The resulting wastage of time and increase in pollution levels can be eliminated on a city-wide scale by these systems [2]. The paper proposes to implement a smart traffic controller using real time image processing. The image sequences from a camera are analyzed using various edge detection Algorithms and object counting methods. Subsequently, the number of vehicles at the intersection is evaluated and traffic is efficiently managed [7]. The paper also proposes to implement a real- time emergency vehicle detection system. In case an emergency vehicle is detected, the lane is given priority over all the others [5].

Full Paper

IJCST/143/1/A-1033
26

Generic Model to Analyze and Predict Brain Tumor from MRI and CT Images using Deep Learning

Neerukonda Sravani, S Srinivas

Abstract

Medical imaging is gaining importance with an increase in the demand for automated, reliable, fast and efficient diagnosis which can provide insight into the image better than human eyes. The brain tumor is the second leading cause for cancer-related deaths in men age 20 to 39 and leading cause cancer among women in the same age group. Brain tumors are painful and should end in various diseases if not cured properly. The diagnosis of the tumor is a very important part of its treatment. Identification plays an important part in the diagnosis of benign and malignant tumors. A prime reason behind a rise in the number of cancer patients worldwide is the ignorance towards the treatment of a tumor in its early stages. This paper discusses such a machine learning algorithm that can write the user about the details of the tumor using brain MRI. These methods include noise removal and sharpening of the image along with basic morphological functions, erosion, and dilation, to obtain the background. Subtractions of background and its negative from different sets of images result in extracted in age. Plotting contour and c-label of the tumor and its boundary provides us with information related to the tumor that can help in a better visualization in diagnosing cases. This process helps in identifying the size, shape, and position of the tumor. It helps the medical staff as well the patient to understand the seriousness of the tumor with the help of different color-labeling for different levels of elevation. A GUI for the contour of the tumor and its boundary can provide information to the medical staff on the click of user choice buttons.

Full Paper

IJCST/143/1/A-1034
27

Machine Learning Techniques For Cyber -Attacks Detection

GudlaAasrita, D S Ramkiran

Abstract

Cloud computing is an evolving technology thatprovides reliable and scalable on-demand resources and different services to users with less infrastructure cost. Even though the cloud has many advantages it faces many drawbacks like vulnerability to attacks, network connectivity dependency, downtime, vendor lock-in, limited control. From the above-mentioned disadvantages, a security attack is the main drawback in the cloud. There are various security attacks like Denial-of-service (DOS) attack, Malware injection attack, Side channel attack, Man-in-the-middle attack, Authentication attack. To detect this attack in the cloud the machine learning algorithm like Support vector machine (SVM), Naive Bayes, Decision tree, Logistic regression, Ensemble methods can be used. In this paper, we have mainly focused on various security attacks in the cloud and the machine learning algorithms used for detecting the attacks.

Full Paper

IJCST/143/1/A-1035
28

Multi-Traffic Scene Perception Based on Supervised Learning

Nethi V VKrishna Saran Kumar, G Aruna Rekha

Abstract

Accidents affecting road travel add significant casualties to the lives and properties of individuals. Advanced driver helpers (ADAS) perform a significant part in rising road collisions. Valuable knowledge for relief agencies is a multi-traffic view of dynamic weather conditions. Unique methods focused on various environmental factors may be used to boost visibility. This would continue to extend the ADAS. So far no research has been conducted on weather-related problems for automotive cameras. Classification by marginal quality of interior and exterior pictures. Concentration curves across a neural network to create four layers of fog. To have a novel basis for the identification of various climates. Milford, plus a number more. Localization and visualization dependent on existing vision of modifying local environments. Seeking essential improvements Operating is a big challenge when running Support Systems. Say a sight-based skyline Detection algorithms under the variations of camera brightness Fu and Al Automatic processing of traffic data vary with Lighting conditions. Freatch, plus even more. Groups for use Detecting section of road in certain traffic scenes.

Full Paper

IJCST/143/1/A-1036
29

An Application for Plant Disease Prediction Using Machine Learning

Peddireddi Lalitha Rajeswari, S Surya Godha Devi

Abstract

Brown spot, Mosaic, Grey spot, and Rust all significantly reduce apple yield. Rust is a sign of Foliar illness in this instance. The primary factor influencing apple output is the occurrence of apple leaf diseases, which results in significant yearly economic losses. Therefore, it is very important to research apple leaf disease identification. Plants are frequently attacked by pests, bacterial diseases, and other microorganisms. Inspection of the leaves, stem, or fruit usually identifies the attack’s signs. Powdery Mildew and Leaf Blight are two common plant diseases that can cause severe harm if not treated quickly. In the realm of agriculture, image processing is frequently utilized for classification, detection, grading, and quality control. Finding and identifying plant diseases is crucial, especially when trying to produce fruit of the highest caliber. The real-time identification of apple leaf diseases is addressed in this research using a deep learning strategy that is based on enhanced convolutional neural networks (CNNs). This study uses data augmentation and image annotation tools to create the foliar disease dataset, which is made up of complex images captured in the field and laboratories.
Overall, we can identify the illness present in plants on a massive scale by utilizing machine learning to train the vast data sets that are publically available. The project explains how to identify plant leaf diseases, how they affect plant yield, and which pesticides should be used to treat them. in agriculture. To monitor huge plant fields and automatically identify disease symptoms as soon as they develop on plant leaves, research on automatic plant disease is crucial. In this essay, we’ll demonstrate how to identify plant illnesses by obtaining photos of their leaves.

Full Paper

IJCST/143/1/A-1037
30

Detection of all Diseases in Human Body Using RF Algorithm In Machine Learning

Juvvala Mercy, D Srinivas

Abstract

A Harvard study by Prof Jha shows that 5.2 million medical errors are happening in India annually. We can prevent this wrong diagnosis with the help of advanced technology of Machine Learning, Deep Leaning and mobile Applications. This application provides users the facility to predict the disease on the basis of their X-Ray and MRI Scan along with the precautionary measures. Even if user is not satisfied with the result, He/ She can do a live chat or Video call to the Experienced Doctors. The ambition of this paper is to evaluate the previous effort of disease prediction, exploratory evaluation of disease and implementation of technology in Medical. Correct Disease prediction at the starting stage is demanding challenge. There are numerous experiments done on disease prediction on the basis of complex datasets but due to the shortage of automation and technology in medical they aren’t available directly to the public use.

Full Paper

IJCST/143/1/A-1038
31

Prediction of all Types of Cancers using Machine Learning Model

Velugula Bhanu Teja, S. Surya Goda Devi

Abstract

The main objective of this project to build the model for predicting cancer using a support vector machine classifier algorithm and compare the accuracies on different kernels and apply the various parameters on the efficient one kernel. The cancer dataset will be imported from the scikit-learn library. Cancer has been characterized as a heterogeneous disease consisting of many various subtypes. The soon diagnosis and prognosis of a cancer type have becomes a need in cancer research, as it can facilitate the subsequent clinical management of patients. these technique include Artificial Neural Network, Bayesian Networks, Support Vector Machines and Decision Trees have been widely apply in cancer research for the development of predictive prototype, results in effective and accurate decision making. Even though it is obvious that the use of ML methods can improve our understanding of cancer progression, an appropriate level of validations is needed in order for these methods to be Consider in the everyday clinical practice. In this work, we present a review of Machine learning approaches employed in the modeling of cancer progression. The predictive models discussed here are based on various supervised Machine learning techniques as well as on different input features and data samples. The using Algorithm KNN (K Nearest Neighbors), SVM(Support Vector Machine), LR(Logistic Regression), NB(Naïve Bayes) and also evaluate and compare that the classification of accuracy, precision, recall, f1-score.the UCI machine learning dataset will be partitioned as 75% for training phase and 25% for the testing phase and then apply all algorithm is best performance of All parameter.

Full Paper

IJCST/143/1/A-1039
32

White Blood Cell Disease Prediction Using Neural Network Classifier

Rakesh, Aarti

Abstract

White Blood Cells (WBCs) are an important part of the immune system and help our body to fight infections and other disease. As medical technology advances, the need for faster and more accurate diagnostic tools will become more important. In this study the image recognition problem of blood cells was investigated. Classification of five types of white blood cell (leukocytes) using a feed forward back propagation neural network. In this study, a neural network was used as a good decision maker to make microscopic images of blood cells to accurately identify white blood cells. Neural networks are powerful at analyzing complex data, and the wide and diverse applications of neural networks include analysis andcontrol, image recognition and decision making.

Full Paper

IJCST/143/1/A-1040