Search

The Tracking System, which is built on the Internet of Things (IoT), enables solar panels to track the sun's movement, enhancing the effectiveness of solar energy harvesting. Two axis solar trackers in this system employ IoT technology to continuously modify the angle of the solar panels in accordance with the location of the sun. The system can gather data from various sensors thanks to IoT technology, and it can then use that data to position the solar panels as efficiently as possible. The system can be utilised in a range of applications, including residential, commercial, and industrial ones, and it is made to be scalable. This technology has the potential to lower energy costs and lessen our reliance on fossil fuels by boosting solar energy collecting efficiency. [ABSTRACT FROM AUTHOR]

Pothole detection is a challenging task as it involves inhomogeneity in intensity, complex topologies, contrast less, and noise rich background. Still, it's a very important task concerning the maintenance of roads. Potholes are being detected using computer vision which generally involves analysis of a two-dimensional image of the road or modeling of the road surface. Provided both these methods are independently used. The accuracy of this method of pothole detection is far from the top point. These bring the usage of digital image processing which develops the detection of potholes with at most accuracy. Digital Image processing provides strong receptivity, usage of huge actions, and broad benefits. In this paper, we propose a system that supports digital image processing techniques of high efficiency to result in consistent and accurate detection of potholes. This project studies an intelligent digital industrial pothole detection mechanism to increase human safety, detection capability and decrease the factor of risk. Firstly, the sources of images from the road are pre-processed to remove noise and other irrelevant features. Then a training model was developed to train the system to classify between path holes and normal cracks using convolution neural networks and MATLAB. Also, an IoT device is used in this system which updates the detected potholes on the road to the respective web server along with the location coordinates, as a part to notify a complaint to check. This system works on providing a better pothole detection technique and also updating the same to the concerned. [ABSTRACT FROM AUTHOR]

There have been a wide variety of methods utilized for automatic event detection in recent years. The highlights of a soccer game are what make up a clip that sums up the action. Sports events are now annotated by hand by human operators to provide such highlights. Inevitably, these events will need to be annotated, but doing so manually would require too much time and effort to be practical. Recent studies have demonstrated that these occurrences can be found automatically using deep-learning methods. An improved deep-learning method for automating human annotators' work on sports videos is presented in this thesis. With the SoccerNet-v2 dataset, test out both precomputed features derived in a model using deep learning and precomputed characteristics taken from various other models. Proposed system evaluate our findings against the best existing models for action recognition using the SoccerNet-v2 dataset. In addition, investigate how carefully adjusting the hyper parameters of the chosen deep-learning methods affects the final product. [ABSTRACT FROM AUTHOR]

One of nature's most catastrophic natural disasters is flooding, which can happen at any time. It's really difficult to forecast them. Primary prevention, policy recommendations, reducing human losses, and water property damage reduction are all on the table as a result of the advancement of flood forecasts. It is important to anticipate disasters in order to take the appropriate precautions and lessen harm to people and property. As a result, numerous sorts of research are carried out to anticipate such disasters caused by climate change utilizing hydrological, mathematical, and AI-based methods. This has led to improved performance and affordable solutions. To avoid this difficulty, researchers investing heavily on neural network-based algorithms to forecast whether or not a flood would occur depends on rainfall amount. Machine learning algorithm will be used for collecting variety data on the entire dataset, including variable identification, missing value treatments, validation of data, and data cleanup. To improve the efficiency of the programming languages structure flask-based app in predicting is utilized. whether or not such a flood will take place using accuracy arithmetic and assessment classification findings, to recognize the confusion matrix, and to show that the programming languages structure flask-based application is effective in predicting whether or not a flood will occur. [ABSTRACT FROM AUTHOR]

Computed Tomography (CT) is far and wide utilized to make a diagnosis and access thoracic diseases. The enhanced resolution of CT examination has resulted in a considerable investigation of statistics for analysis. Computerizing the scrutiny of such facts is consequently necessitate and fashioned a hastily emergent research region in medical imaging. The finding of thoracic diseases by means of image processing directs to a pre-processing step identified as "Lung segmentation" which portrays a wide range of techniques starts with simple Thresholding and numerous image processing elements are incorporated to progress segmentation, precision and heftiness. In image processing, techniques like image pre-processing, segmentation and feature extraction have been thrashed out in detail. This paper suggestions investigation of literature on computer examination of the lungs in CT scans and statements the Preprocessing ideas, segmentation of a choice of pulmonary arrangements, and Feature Extraction intended at recognition and categorization of chest abnormalities. As well as, research developments and disputes are recognized and instructions for further examinations are discussed. [ABSTRACT FROM AUTHOR]

In this work, it is propose a novel data hiding algorithm for high dynamic range (HDR) images encoded by the Open EXR file format. The proposed algorithm exploits each of three 10 bit mantissa fields as an embedding unit in order to conceal k bits of a secret message using an optimal base which produces the least pixel variation. An aggressive bit encoding and decomposition scheme is recommended, which offers a high probability to convey (k+1) bits without increasing the pixel variation caused by message concealment. In addition, we present a bit inversion embedding strategy to further increase the capacities when the probability of appearance of secret bit "1" is greater than 0.5. Furthermore, An adaptive data hiding approach for concealing more secret messages in pixels with low luminance, exploiting the features of the human visual system to achieve luminance-aware adaptive data hiding. The stego HDR images produced by our algorithm coincide with the HDR image file format, causing no suspicion from malicious eavesdroppers. The generated stego HDR images and their tone mapped low dynamic range (LDR) images reveal no perceptual differences when subjected to quantitative testing by visual difference predictor. Our algorithm can resist steganalytic attacks from the HDR and LDR RS and SPAM steg analyzers. We present the first data hiding algorithm for Open EXR HDR images offering a high embedding rate and producing high visual quality of the stego images. Our algorithm outperforms the current state-of-the-art works. [ABSTRACT FROM AUTHOR]

An authentication method that combines various systems is called an iris recognition strategy. used to increase the iris recognition method's accuracy. Iris recognition has built-in flaws that put system security at risk. Among them are parody attacks. Compared to standard iris recognition techniques, enhanced iris recognition is more susceptible to parody assaults. The biometric sensor receives duplicate input during parodying. To determine whether a given input is unique or a copy, parody detection is utilised. Overcoming parody attacks on the iris recognition process is the goal. Using mean, median, variance, and local trinary pattern (LTP) approaches, the suggested methodology extracts a set of features from the iris. The retrieved biometric characteristics are then merged and used in deep learning. In order to identify mocked features, it is fed into a convolutional neural network. original purpose. The suggested method for iris recognition performs better than current liveness detection methods. [ABSTRACT FROM AUTHOR]

In Wireless sensor networks (WSN) tiny sensor nodes are deployed in remote locations to collect information like temperature, moisture level, water level etc in the selected area. Information collected by sensor nodes is highly sensitive and vulnerable to different security attacks including Denial of Service (DoS) attack. Due to resource constraints providing security to the WSN is a difficult task. Successful authentication schemes used in wired networks are not suitable for WSN. Most of the available authentication schemes use more computations for encryption and decryption. This paper proposes a novel token-based authentication algorithm to provide security against Denial of Service attacks. The proposed algorithm has three different phases namely Registration phase, Authentication phase and New token creation phase to preserve user anonymity and provide secure authentication against DoS attacks. A simple private key based cryptography algorithm with minimal computation has been used for encryption and decryption which makes this algorithm more suitable for WSN. [ABSTRACT FROM AUTHOR]

Machine Learning is widely used technology in today's market, It plays an important role in healthcare industry. It is impossible to process thousands of medical reports manually but with machine learning algorithms millions of data can processed in no time. Using machine learning algorithms, it is possible to predict a disease within hours even before their onset, which is not possible in the real time. Sepsis is one among fatal disease brought by the body's reaction to an infection which in turn causes Systematic Inflammation Response Syndrome leading to a progressive organ dysfunction. With help of Ensemble approach, sepsis is predicted with improved accuracy (97.7%) using improved random forest. Our Proposed System is helpful for doctors to diagnose the sepsis very quickly compared to traditional way. [ABSTRACT FROM AUTHOR]

Cloud data centers experience an important testing issue in which the segment should be considered in addition to the migration of reconfigurable virtual machines. Further, one should also consider the integrated characteristics of facilitating physical machines during the relocation of VMs. In this study, a Dynamic Resource Assignment Framework (DRAM) is presented for cloud data centers. In traditional stack balance arranging calculations, only one factor is considered, for instance CPU stack in physical servers. However, the proposed strategy takes multiple factors into account such as CPU, memory and framework information for both virtual machines as well as physical machines. The authors created a joint estimate on irregularity dimensions of a cloud data center. In addition to this, every server's ordinary disproportion dimension was also considered in this study. The results inferred that DRAM is excellent in terms of execution which can be understood via its abnormality level, heavy dimension of every server and its general running time. [ABSTRACT FROM AUTHOR]