Paper Title

ADAPTIVE HIERARCHICAL CYBER ATTACK DETECTION AND LOCALIZATION IN ACTIVE DISTRIBUTION SYSTEM

Abstract

Since dispersed renewable energy sources are increasingly being integrated into the grid, developing a cyber security plan for active distribution systems has become more difficult. This article describes an approach to using electrical waveform analysis to identify and localise cyberattacks in distributed active distribution systems. The cornerstone for cyber-attack detection is a sequential deep learning model, which allows the identification of even the slightest intrusions. The targeted cyberattack is initially localised inside the estimated cyberattack sub-region in a two-stage process. We present a network splitting approach based on a modified form of spectral clustering for \"coarse\" localisation of hierarchical cyber-attacks. To further localise the origin of a cyber assault, it is advised to define a number of waveform parameters and apply a normalised effect score based on statistical metrics of the waves themselves.Finally, a thorough quantitative assessment based on two case studies demonstrates that the proposed framework yields accurate estimations in contrast to both classic and state-of-the-art methods. Search Term Suggestions: Support Vector Machine; Random Forest; Gradient Boosting; Logistic Regression; Cyber Attack Detection.
KEYWORDS :

Paper Title

AN EFFICIENT AND SECURE G-CLOUD-BASED FRAMEWORK FOR GOVERNMENT HEALTHCARE SERVICES

Abstract

With the advancement of technology and the confinements of the good old medical services framework, an unplanned structure for social insurance is needed.. We\'ve witnessed a growing interest in and preference for cloud-based software development in the human services sector to manage and meet existing and future demands in social insurance administrations. We propose a cloud-based framework for medical services that is adaptable, safe, efficient, practical, and protected. For the administration EHR framework, we\'ve presented a safe and effective structure in which fine-grained access control is commonly controlled by multi-authority ciphertext property based encryption (CP-ABE), close by many levels of information structure to permit access control arrangements. E-government distributed computing is a major advantage for Saudi Arabia\'s top officials, who will be able to grow up their social insurance sector through the proposed framework.
KEYWORDS : Cloud Computing, Electronic Health Record, Security, Attribute-based Encryption, Ciphertext policy, Identity Proofing, Authentication, Authorization

Paper Title

BLOCK CHAIN BASED CERTIFICATE VALIDATION

Abstract

In the digital world, each and everything is digitalized in which the certificate of SSLC, HSC, and academic certificate are digitalized in the educational institution and provided to the students. Students are difficult to maintain their degree certificates. For the organization and institution, verification and validation of certificates are tedious and cumbersome. Our project will help to store the certificate in the blockchain system and provide security. First, the paper certificates are converted into digital certificates. The chaotic algorithm is used to generate the hash code value for the certificate. Then the certificates are store in blockchain. And these certificates are validated by using the mobile application. By using blockchain technology we can provide a more secure and efficient digital certificate validation.
KEYWORDS :

Paper Title

QR BASED ATTENDANCE SYSTEM

Abstract

In higher education institutions, student participation in the classroom is directly related to their academic performance. However, the majority of student attendance registration is still conventionally done, which is tedious and time-consuming, especially for those courses that involve large numbers of students. Over the years, attendance management has been conducted manually at most of the universities. To overcome the manual attendance issues, we proposed and implemented a smart attendance system with the aim to encourage the potential use of the Quick Response (QR) code as a future attendance management system, to track and record student attendance in lectures and exercises for all relevant courses, as an aim of this paper.
KEYWORDS : QR Code, attendance, system, professor, student.

Paper Title

IDENTIFYING BRAIN TUMOUR USING MRI IMAGES

Abstract

The detection, segmentation, and extraction from Magnetic Resonance Imaging (MRI) images of contaminated tumor areas are significant concerns; however, a repetitive and extensive task executed by radiologists or clinical experts relies on their expertise. Image processing concepts can imagine the various anatomical structure of the human organ. Detection of human brain abnormal structures by basic imaging techniques is challenging. In this paper, a Fully Automatic Heterogeneous Segmentation using Support Vector Machine (FAHS-SVM) has been proposed for brain tumor segmentation based on deep learning techniques. The present work proposes the separation of the whole cerebral venous system into MRI imaging with the addition of a new, fully automatic algorithm based on structural, morphological, and relaxometry details. The segmenting function is distinguished by a high level of uniformity between anatomy and the neighboring brain tissue. ELM is a type of learning algorithm consisting of one or more layers of hidden nodes. Such networks are used in various areas, including regression and classification. In brain MRI images, the probabilistic neural network classification system has been utilized for training and checking the accuracy of tumor detection in images. The numerical results show almost 98.51% accuracy in detecting abnormal and normal tissue from brain Magnetic Resonance images that demonstrate the efficiency of the system suggested.
KEYWORDS : Brain Tumor Detection, Classification, Segmentation, Deep learning, ELM.

Paper Title

MACHINE LEARNING FOR PLANT DISEASE IDENTIFICATION, TRACKING AND FORECASTING FOR FARMERS

Abstract

Plant diseases are a major problem that threaten farmers, consumers, the environment, and the global economy. In India, field crop failure due to pathogens and pests alone costs farmers 35% of their harvest. Pesticides represent a serious threat to human health since many of them are highly toxic and can be amplified by living organisms. Avoiding these consequences is possible with proper disease detection, crop monitoring, and individualized treatment plans. Typically, agricultural experts would first seek for visible symptoms of a disease. Meanwhile, farmers have little access to experts. When it comes to automatically diagnosing, tracking, and forecasting illnesses, our effort is the first collaborative, all-encompassing platform of its kind. Farmers may use a smartphone app to rapidly and accurately diagnose diseases by taking pictures of affected plant parts. Real-time diagnosis is now possible using cutting-edge AI algorithms for cloud-based image processing. The AI model continuously refines its performance based on data from user-uploaded images and expert critiques. Farmers can also talk to local experts using the platform. Using a database of geo-tagged pictures and micro-climate variables stored in the cloud, disease density maps with projections of spread are generated for preventative measures. Using a web interface, specialists may do geographically-based illness assessments. In our research, a convolutional neural network (CNN) artificial intelligence model was trained using large disease datasets derived from images of plants collected in a decentralised fashion over the course of 7 months from a variety of farms. After using the automated CNN model to diagnose test photographs, plant pathologists validated the results and gave their stamp of approval. Over 95% accuracy was achieved in the diagnosis of illnesses. To help farmers and agricultural experts manage illnesses in a wide range of crop plants in order to sustainably harvest their crops, we have developed a novel, flexible, and easily accessible tool.
KEYWORDS : CNN, Machine learning, Neural Network. Artificial Intelligence

Paper Title

HUMAN ACTIVITY RECOGNITION USINGDEEPLEARNING

Abstract

Human activity recognition using deep learning techniques has become increasing popular because of its high effectivity with recognizing complex tasks, as well as being relatively low in costs compared to more traditional machine learning techniques. This paper surveys some state-of-the-art human activity recognition models that are based on deep learning architecture and has layers containing Convolution Neural Networks (CNN), Long Short-Term Memory (LSTM), or a mix of more than one type for a hybrid system. The analysis outlines how the models are implemented to maximize its effectivity and some of the potential limitations it faces
KEYWORDS : Human Activity Recognition, Deep Learning

Paper Title

EMBEDDED NIGHT- VISION SYSTEM FOR PEDESTRIAN DETECTION

Abstract

The paper describes the use of thermal camera and IR night vision system for the detection of Pedestrians and objects that may cause accident at night time. As per the survey most of the accidents cause is due to low vision ability of human at night time, which leads to most dangerous and higher number of accidents at night with respect to day time. This system include the IR night vision camera which detects the object with the help of IR LED and photodiode pair, this camera have capability to detect the object up to 100m. The thermal camera detects the heat generated by any of the object like cars, Human animals etc. which gives us the facility to detect the object for higher range and with low reflective surface where IR night vision may fails. With the use of these two cameras mounted on car which helps the driver to drive safely. In this system, HOG (Histogram of orientated gradients) algorithm and support vector machine (SVM) is performed with the help of OpenCV in Matlab and EmguCV in Visual Basic 2012. The system is tested on the video recorded using these cameras, and got good and efficient result. And this system is cost efficient and easy to implement.
KEYWORDS : Thermal and IR Night vision, OpenCV, Video Processing, Object and Human Detection, Automobile Safty.

Paper Title

DEEP LEARNING APPROACH FOR SUSPICIOUS ACTIVITY DETECTION FROM SURVEILLANCE VIDEO

Abstract

The importance of video surveillance in modern society cannot be overstated. Once AI, ML, and DL were introduced, the technologies were already too far forward. Utilizing the aforementioned permutations, several methods have been developed to discern between different types of suspicious behaviour based on the live monitoring of film. Human conduct is the most erratic, and it\'s sometimes hard to tell whether an unusual pattern of behaviour is really typical. An alarm message is sent to the appropriate authority if the system predicts suspect behaviour in a school setting, and if the activity is normal, no alert is sent. In many monitoring applications, a series of frames taken from a video are used in rapid succession to conduct checks. The whole structure may be broken down into two halves. First, a classifier uses video frame computations to acquire features; next, using those characteristics, a prediction of whether a frame is suspicious or not may be made.
KEYWORDS : Video Surveillance, deep learning,

Paper Title

AN EXPERIMENTAL INVESTIGATION ON HIGH STRENGTH CONCRETE WITH PARTIALLY REPLACEMENT OF CEMENT BY FLY ASH AND SAND BY STONE DUST

Abstract

When the cement, sand, and aggregate are properly bound together, the compressive strength of the concrete is enhanced as well. Stone dust is a by-product of stone crushing operations that is used as a filler. Stone dust is used in the construction of the W.B.M. road to ensure good bonding of the coarse aggregate. Fly ash is a waste product produced by thermal power plants that is produced in huge quantities. When fly ash is combined with cement, the resulting mixture has the same properties as cement. The majority of the study was carried out using fly ash as a substitute for cement. To investigate the behaviour of concrete, stone dust and fly ash are mixed together and placed in a concrete mix. The main goal of using stone dust and fly ash in construction is to create a cost-effective building with a defined strength. In this experiment, stone dust is used to partly replace sand and fly ash is used to partially replace cement in the mix. It is estimated that stone dust will replace 50 percent of the sand used in the project, and that fly ash would replace 0, 5, and 10% of the cement used. The slump test of concrete is used to determine the workability of the concrete. It is determined how strong the concrete is in compressive strength, flexural strength, split tensile strength, modulus of elasticity, and other properties, and then compared to ordinary concrete of grade M40. All tests on concrete are carried out in accordance with the IS code requirements.
KEYWORDS :

Paper Title

AN EXPERIMENTAL STUDY CONCERNING THE USE OF BITUMEN EMULSION AND SOIL IN GRAVEL ROAD WITH THE GOAL OF IMPROVING THE ROAD\'S STABILITY

Abstract

The tensile strength and abrasion resistance of the subgrade soils have a direct and significant influence on the long-term performance of pavement constructions. In-situ subgrades usually are unable to offer the necessary support to attain and acceptably perform under the traffic loads that is being demanded by an ever-increasing number of environmental regulations. In this instance, we are using bitumen emulsion in conjunction with soil in order to boost the durability of pavements as well as their lifespan. The vast majority of emulsions are put to use in surface treatments. The low viscosity of the emulsion, in comparison to that of hot-applied bitumen, gives the emulsion superior penetrating and spreading capacities. The kind of emulsifying agent that is used in the production of the bituminous emulsion is what decides whether the emulsion will be anionic or cationic. The most common use of bitumen in modern times may be found in the paving business, both for new construction and routine maintenance. The specific gravity of the soil is 2.68, the liquid limit is 33.75%, and the plastic limit is 21.56%. Other physical features of bitumen emulsion include the compaction test using the modified proctor test and the California bearing test at the value of 2.5mm,5mm,7.5mm,10mm with the loads.
KEYWORDS :

Paper Title

FINITE ELEMENT ANALYSIS OF ALUMINA-MILD STEEL WELDED TUBE OF INTERNAL STRESSES

Abstract

In this paper to Evaluation of mechanical and interfacial properties of friction welded alumina-mild steel rods with the use of Al6061 sheet are presented in this work. The bonds were attained through interfacial interlocking and intermetallic phase formation with average bending strengths in the range of 40 to 200 MPa and insignificant hardness change in the parent alumina and mild steel. A preliminary simulation was made to predict the deformation, stress, strain and temperature distribution during the joining operation using a fully coupled thermo-mechanical FE model. The aluminum alloy metal being rubbed was simulated using a phenomenological Johnson-Cook viscoelasticity material model, which suited for materials subjected to large strains, high strain rates and high temperatures. The highest stress, strain and deformation are found to be within the heat affected zone of the weld close to the periphery rubbing surface region and correspond to the highest temperature profiles observed.
KEYWORDS : Friction welding, intermetallic, FE model, interface, bending strength

Paper Title

AN IN-DEPTH ANALYSIS OF THE EFFECTS OF EXHAUST GAS RECIRCULATION ON THE EFFICIENCY AND EMISSIONS OF A COMMON-IGNITION ENGINE OPERATED ON DIESEL AND BLENDS OF JATROPHA OIL BIODIESEL

Abstract

Start of injection, also known as injection timing, refers to the point in time when the process of injecting fuel into the combustion chamber really starts. Crank angle degrees (CAD) relative to top dead centre (TDC) of the compression stroke is the standard way that it is stated. The diesel engine has been favoured for a significant amount of time in the areas of the military, as well as in power plants, transportation, engineering equipment, and agricultural machinery. This is due to the diesel engine\'s great thermal efficiency, strong dependability, adequate and steady power, and other attributes. For a very long time, using diesel engines to power commercial transportation on land or water has shown to be the most efficient use of resources. However, the reduction of emissions generated by diesel engines is a primary issue, which has led to the search for alternative fuels and the development of one-of-a-kind in-cylinder platforms that are compatible with treatment equipment. These efforts are being made in an attempt to ease emission problems to the maximum degree that is practically possible. In recent years, the use of biodiesel in the automotive sector has seen a major increase. This may be attributed to the depletion of fossil fuels as well as the pollution that comes along with its use. The production of biodiesel takes place regionally, and its energy content is low, but it has a significantly positive impact on the emissions of greenhouse gases. You need to do more research into this particular aspect. The majority of biodiesels come from rice bran, rapeseed, palm, and canola oils, in addition to other regularly used culinary oils. According to the findings of the vast majority of earlier studies, the utilisation of bio-diesel results in the production of lower levels of carbon monoxide, particulate matter, and hydrocarbons as compared to clean diesel (D). The only potential drawback is that NOx emissions might potentially rise. Recirculating the exhaust gas, often known as EGR, is an efficient method for cutting down on NOx emissions. In the current study, 5%, 15%, and 25% of EGR flow rates are being used by the diesel engine when it is operating at half load. The engine is being fed diesel PD100 as well as blends of Jatropha biodiesel JOBD15 and JOBD30 in an effort to minimise NOx emissions while maintaining an injection pressure of 240 bar and an injection timing of 23°bTDC. Emission characteristics such as exhaust gas temperature (EGT), smoke parameters, and combustion parameters such as ignition delay, combustion duration and Start of combustion, end of combustion are to be evaluated, and engine performance parameters such as brake power (BP), brake specific fuel consumption (BSFC), and brake thermal efficiency (BTE) are to be recorded and compared with diesel and blends of biodiesel. Diesel, sustainability, alternative fuels, emissions, exhaust gas recirculation, and other related terms also feature prominently here.
KEYWORDS :

Paper Title

EXPERIMENTAL STUDY ON SELF CURING CONCRETE USING NATURAL AND RECYCLED COARSE AGGREGATE

Abstract

A self-curing concrete is provided to absorb water from atmosphere to achieve better hydration of cement in concrete which solves the problem of lowered cement hydration because of improper curing and thus unsatisfactory properties of concrete. The present investigation involves the use of self-curing agent viz., polyethylene glycol (PEG) of molecular weight 6000 (PEG 6000) for dosages ranging between 0.5 to 2% by weight of cement added to mixing water. The experimental program was planned as the following. Total 120 cubes, 120 cylinders, 120 prisms were cast which involves different dosages (0%, 0.5%, 1% and 2%) of self-curing agent PEG-6000 for four different mixes (Mix 30 and Mix 40), under different curing conditions (indoor, conventional) with different aggregates (normal coarse aggregate and recycled coarse aggregate). Comparative studies were carried out for self curing of recycled coarse aggregate and self curing of normal coarse aggregate. Comparative studies were carried out for water retentivity, compressive strength, split tensile strength, flexural strength for 7 days and 28 days for conventional cured and self-cured concrete. The properties of self-cured concrete are at least comparable and some time better than those of concrete with traditional curing. The comparative studies for strength were carried out at different dosages for different coarse aggregate. The results indicate that selfcuring concrete has shown greater strength compared to conventional curing concrete. The maximum strength for normal coarse aggregate concrete is at dosage of 2% SCA and for recycled coarse aggregate concrete is at dosage of 1% SCA and then decreases. For concrete using normal coarse aggregate in place of Recycled coarse aggregate the compressive strength was found to be 7.5% more at 28 days. The compressive strength of self curing concrete is 3% more then that of the concrete with conventional curing curing 28 days. Similarly the spilt tensile strength with normal coarse aggregate was found to be 7% more then with recycled coarse aggregate at same 28 days testing. Again the split tensile strength was found to be 3.1% more then the concrete with conventional curing at 28 days testing. The flexural strength 5% is more for natural coarse aggregate concrete compared to recycled coarse aggregate concrete 28 days. The flexural strength 2% more for selfcuring concrete compared to the conventional curing concrete for 28 days. The maximum weight loss in the concrete occurs at 0% of SCA and increases with increases in percentage of SCA.
KEYWORDS : Self Curing Agent, PEG 6000, Recycled Coarse Aggregate, OPC, Curing.

Paper Title

ENHANCEMENT OF POWER QUALITY USING MULTILEVEL INVERTERS BY ACTIVE FAULT TOLERANT CONTROL SYSTEM

Abstract

The integration of renewable energy sources and the increasing complexity of power systems demand advanced control strategies for inverters to ensure reliable and high-quality power supply. This research focuses on the design of an active fault-tolerant control system for multilevel inverters, aiming to enhance systems power quality. The proposed system combines fault detection, isolation, and compensation mechanisms to mitigate the impact of faults and disturbances, providing a robust and resilient solution for modern power system. Multilevel inverters have gained prominence in power electronics due to their ability to generate high-quality output voltage with reduced harmonic distortion. The growing emphasis on renewable energy integration and the increasing complexity of power grids necessitate the development of fault-tolerant control systems for multilevel inverters. This research aims to address this need by proposing an active fault-tolerant control strategy.
KEYWORDS :