Search

The Extraction of data from videos is crucial and likely to be used in many fields for investigation and data collection purposes. Video analysis has been one of the topics for debate for a long time as much data can be extracted from a video. In this article, we have made a prototype of video analyzing software that extracts useful data from the video with the help of various techniques. Our project primarily focuses on the analysis of YouTube videos. To create a user- friendly graphical interface for our tool, we have utilized the Python Tkinter library. We also used the Matplotlib library for data visualization. Deep learning algorithms using TensorFlow, scikit-learn, pandas, CV tool, and imutils libraries for object and action analysis are utilized in our tools for data extraction from the videos. Our tool incorporates sentiment analysis as well, enabling us to analyze the emotional tone of a video and measure its impact on viewers. The data extracted from the video is stored in a database for further processing. This tool can be developed to be utilized in real-time video analysis. Overall, our goal with this project is to provide an automated video analysis for cyber-security by leveraging these powerful algorithms and technologies. [ABSTRACT FROM AUTHOR]

In this paper, a new method of decoding binary linear block codes using soft decision decoding is presented. The primary concept behind this strategy is to gradually improve error performance over time. When near-optimal error performance or a desirable level of error performance has been attained for each decoding step, the decoding process ends. It's possible to choose between performance and decoding difficulty with greater freedom now. In order to decode the signals, it is recommended that they be reordered depending on the dependability level of each individual symbol. We examine the statistics of ordered noise in this work. The reprocessing technique is based on two monotonic features obtained from these statistics. Reprocessing the hard-decision-decoded codeword in consecutive stages until the required performance is obtained is the second step in decoding each codeword. Using a cost function, reprocessing is predicated on the ordering's monotonic features. [ABSTRACT FROM AUTHOR]

It has been observed that disabled people like deaf and mute have hard time communicating and coping up with normal people due to their inability to speak. So, the only way in which they express their emotions or convey their thoughts is by using sign language, but in today's world very few people understand sign language. Approximately 10% of the world's population is mute or deaf, hence they use sign language as their primary language. Looking at their struggle to communicate led us to the idea of building this project. In this era of advancement, it is very essential to use our technology wisely and in a feasible way, such that it can help people of various stands in their daily life. This project involves a smart glove embedded with multiple flex sensors for precise figure bending or movement of fingers which will send data to microcontroller ARDUINO. The data thus obtained gets processed in microcontroller. Based on that, the hand sign language will be decoded using a predefined database. After this the output gets displayed in an on-board LCD display for the user to view and also gets transmitted in audio and text format to smartphone of the person user's talking to. [ABSTRACT FROM AUTHOR]

With the history of various virus-based contaminations and present-day tragedy of Covid-19 this fully featured virus spread control work provides a decentralized way to control and prevent such infections. The team did a deep dive into existing models which offer the desired functionality. It was noticed that most of the functions were available only in separate packages. Our work will be a fully featured virus spread control system ensuring safety and security of affected and vulnerable citizens during covid-19. [ABSTRACT FROM AUTHOR]

This paper proposes a Swarm Rover System with a cross platform mobile app which can be used in the Hotel Management industry where multiple rovers have been set up to deliver the package from the warehouse to the customers room. The server identifies the most efficient path that can be taken to reach the room and if there are any nearby rovers that are currently active and returning from a recent delivery, then the current rover carrying the package will transfer the package to the other rover and hence reduce the time taken for a normal delivery or done by a rover system which cannot calculate the path efficiently. The cross-platform mobile application can be used for ordering the required package, live tracking of the delivery time and keeps track and shows the cost of all orders at the end of the service. [ABSTRACT FROM AUTHOR]

The major goal is to boost accuracy by comparing the Novel Gradient Boosting Regressor algorithm and the K Nearest Neighbours Classifier approach for analysis and prediction of solar power generation. Materials and Methods: To evaluate, compare, and understand the effectiveness of recommended algorithms, a total of sixty samples were gathered for the two study groups' SPSS analysis. Thirty samples from group 2's K Nearest Neighbours Classifier method and thirty samples from group 1's Novel Gradient Boosting Regressor (GBR) algorithm underwent an 80% power G-power analysis. The accuracy rates observed were 78.6% for the K Nearest Neighbours (KNN) Classifier and 93.3% for the Novel Gradient Boosting Regressor. Consequently, it can be concluded that the GBR method outperforms the KNN Classifier algorithm significantly. [ABSTRACT FROM AUTHOR]

An automated face detection and recognition system use the Eigenface principle component analysis (PSA) algorithm to compare the accuracy of pictures obtained from PGC and stereo vision using the new Violas-Jones technique. The Eigenface (PSA) Algorithm and the Novel Violas Jones Algorithm are two of the groups that this study uses, with a sample size of N = 40. The sample sizes are further divided using the G power (power = 0.85 and α = 0.05 as the setup parameters) to form two groups of size n = 20. In terms of effective face detection, the study's findings indicate that the violas jones approach has an accuracy of 95% and the eigenface detection system has an accuracy of 89%. P=0.012 is the significant value of the independent sample t-test. When compared to the Eigenface Principal Component Analysis technique, the Violas Jones algorithm outperformed it in terms of recognition and detection accuracy rate for images acquired by pixel grayscale and stereo vision cameras. [ABSTRACT FROM AUTHOR]

This study aims to enhance image watermarking techniques by comparing the Peak Signal-to-Noise Ratio (PSNR) performance of a Fuzzy-based Algorithm against the established Discrete Cosine Transform (DCT). Two groups of 10 image samples each were analyzed, with sample size determined using G*Power (power = 0.80, α = 0.05, effect size = 0.85). Results demonstrate a statistically significant improvement in PSNR for the Fuzzy-based Algorithm (97.01 dB) compared to DCT (90.05 dB), with a two-tailed significance of 0.001 (p < 0.05). This indicates the Fuzzy-based Algorithm's superior effectiveness in denoising digital images during the watermarking process, offering potential advancements in image protection techniques. [ABSTRACT FROM AUTHOR]

The development of the cloud makes virtual machines a growing target for malware attacks. Virtual Environments are the legitimate target of Advanced Persistent Threats creating an undetected presence to gain access to sensitive data over a certain period. Rootkit is hidden in some arbitrary files accessed while opening and can modify or delete the data in the targeted system. In the proposed model the features are derived from the network attributes applied to the Artificial Neural Network of the private cloud. The classification is based on the anomaly detection of data in the cloud. Neural networks divide the network attributes and categorize them into two classes Benign and Root-Kit. Satisfactory results may be obtained from the mathematical models using security metrics due to their reliance on empirical data, qualitative methodologies, and compliance testing. The results show the high accuracy of detecting the rootkit malware using ANN with backward propagation. [ABSTRACT FROM AUTHOR]

There is developing proof that mental sicknesses because of work environment stress are more normal in clinical experts around the world (stress, misery, tension and a sleeping disorder) and sensations of enthusiastic fatigue, and it was discovered to be identified with deficiencies in system of wellbeing and health. Arising content on the side of reality that Indian medical care experts are presently working under tension because of the work environment condition, and the ebb and flow COVID-19 pandemic has likewise intensified and we need to explore the word related pressure among Indian specialists more than whatever other time, that can complete perceptions from the information accumulated during this survey, which will be significant in distinguishing the current issue and giving suitable information sponsored proposals to changing the norm. To dissect several aspects of stress at work among Indian experts throughout COVID19, which may need the feasibility of execution in silent treatment. In order to capture and measure mental reactions associated with Covid-19, a web-based test with the support of an overview was designed. It involves three components addressing themes relating to the accompanying key regions.: (1) socio demographic information (2) Pressure at the working environment during pandemic (3) data on people's functioning condition. Factors discovered to be identified with higher working environment stress in line staff medical care experts were as determined: Lengthy working hours, more patients, diminished degree of help from colleagues, and less opinions of execution during exercises in pandemic. Modest or gentle degree of stress was experienced by roughly 66% of the example. Wretchedness, nervousness or exhaustion is connected to diminished lavishness for entertainment only get-togethers, verbal or actual brutality in quiet/parental figure hands, discernments that partners don't show worry for patients and furthermore towards their companions. The most recent investigation shows an imperceptibly more prominent extent of Indian specialists who experience pressure, weakness and burnout encounters. A lengthy working hour and demoted patient related impacts, the transcendence of strain, nervousness despondency, and passionate depletion is related with hindering specialist patient encounters and awkward gathering elements among associates. Our investigations have tracked down the potential reasons that make working environment stress that should be considered while fighting a calamity that significantly affects human advancement internationally, to ensure the enthusiastic wellbeing of doctors. [ABSTRACT FROM AUTHOR]

This work aims to improve the accuracy of cholera disease prediction using water characteristics by utilizing a new technique called Ensemble Learning (EL) instead of Naive Bayes (NB). The Kaggle database management system provided the dataset for this study. A sample size of 3964 individuals (equally divided between Group 1 and Group 2) and a computation utilizing a G-power of 0.8, α=0.05, and β=0.2 were used to achieve improved prediction accuracy for cholera disease. The significance level of the test yielded a value of p=0.001 (p<0.05) with a 95% confidence interval using independent sample T-tests. Using the same number of data samples (N=1982), the Ensemble Learning (EL) and Naive Bayes (NB) algorithms were used to predict cholera cases; nevertheless, EL performed more accurately. The success rate of the suggested EL algorithm was 96.30%, higher than that of the NB classifier, which had an 89.50% success rate. At p=0.034, the statistical significance of this disagreement has been shown. The Ensemble Learning (EL) model performs better than the Naive Bayes model in the assessment of cholera infection performance. [ABSTRACT FROM AUTHOR]

The proposed research work anticipates the regular workout patterns of users by utilising the data collected from their smartphones. The study indicates that the Random Forest algorithm is more effective in predicting human exercise routines with higher precision than the Linear regression algorithm. A dataset of 3000 entry with the headings 'user','activity','Timestamp', and so on are used to compare, with two groups of 10 sample size for each being studied. Linear Regression recorded an accuracy of 73.67%, while the innovative Random Forest Algorithm gives an precision of 76.51. The difference between these groups is statistically significant at 0.033, which is smaller than 0.05 (p<0.05). It is obvious that these groups differ statistically significantly from one another. Compared to the results of the linear regression, the predictions made by the Random Forest algorithm model are more accurate. [ABSTRACT FROM AUTHOR]

The aim of this research is to enhance the accuracy of Blockchain based smart voting systems. Secure Hash Algorithm 384-bit (SHA-384) and Secure Hash Algorithm 256-bit (SHA-256) is executed for Blockchain based smart voting systems. The Gpower test used is about 80% (There are 20 samples total,10 for each group variables: alpha 0.05 and beta 0.2and power=0.85). Secure Hash Algorithm 384-bit (SHA-384) (99.45%) has the increased accuracy over Secure Hash Algorithm 256-bit (SHA-256) (99.01%) with a significance value of p=.03, (p<0.05). The accuracy of Secure Hash Algorithm 384-bit (SHA-384) is better when compared to accuracy of Secure Hash Algorithm 256-bit (SHA-256). [ABSTRACT FROM AUTHOR]

This study aims to compare logistic regression and the Naive Bayes approach's performance accuracy using readmission dataset samples to identify patients who are at risk of developing heart failure. Group 2 uses Naive Bayes, whereas Group 1 uses Logistic Regression. Groups 1 and 2 each have 38 iterations. An online statistical analysis tool with an alpha value of 0.05 and a pretest power of 80% with 95% confidence is used to determine the sample size. The dataset contains 25001 samples, of which 17500 are used for testing and 7500 for training. According to the simulation findings, the Naive Bayes method had an accuracy of 68.11% while the Logistic Regression approach had an accuracy of 98.8%. According to the independent sample test, there is a statistically significant difference in accuracy between the two algorithms, as indicated by the independent sample T-test significance value of p=0.000. The differences between the two groups are statistically significant as a result. Logistic regression performs significantly better than naive bayes in the prediction of readmission heart failure. [ABSTRACT FROM AUTHOR]

Since many decades ago, there has been a large increase in the use of neonatal hip ultrasound imaging, making it simpler to identify hip developmental anomalies (DDH). In this paper, a novel strategy for data enhancement is proposed. It entails the use of an improved Bayesian non-local median filtering to reduce speckle noise (OBNLM). After already being supplemented with information from the OBNLM, the intended CNN system's accuracy is improved from 92.29 percent to 97.70 percent. This novel method for automatically classifying DDH detects dysplastic newborn hips with a high accuracy rate, which may assist evaluators boost the success rate of their assessments. For a fully automated evaluation of the scan effectiveness of three-dimensional ultrasound volumes, we provide a deep learning approach. We trained a Convolutional Neural Network to determine whether or not 3D Ultrasound (3DUS) hip pictures are diagnostically adequate (CNN). 2187 3DUS images were included in Dataset 1 (DS1), and the quality of the scan was evaluated by a single reader using a scale from 1 (the lowest standard) to 5 (the highest quality) (optimal quality). Dataset 2 consists of 107 3DUS photos that were evaluated semi-quantitatively by four users using a 10-point scale (DS2). It was determined whether or not these datasets were suitable for testing the efficacy of this AI method. The majority of the Intraclass Correlation Coefficient (ICC) and Cohen's kappa coefficient showed that the AI method agreed well with expert readings, and the AI method's extremely accurate estimates on both datasets as a binary classifier (adequate/inadequate) (DS1 accuracy = 96% and DS2 accuracy = 91%) were consistent with those obtained by the experts (K). Our AI-powered technology can be used as a screening tool during ultrasound imaging or post-processing to ensure a higher quality scan and a more precise assessment of the baby's hip. Additionally, the characteristics that the convolutional layers gain show that FNet can concentrate on crucial characteristics, which is useful for accurately reconstructing the femoral head anatomy. In conclusion, the recommended approach is effective in appropriately segmenting the femoral head and providing recommendations for assessing hip development abnormalities. [ABSTRACT FROM AUTHOR]

CubeSats, nanosatellites, including microsatellites with a moisture content of up to 60 kg have all contributed to the fast expansion of the Earth Observation sector. This development has also been aided by the reduction in cost associated with reaching space. Image data that has been acquired serves as a vital source of information in a variety of fields. As more remote sensing data is collected, the available bandwidth capabilities for the data transfer, known as the downlink, will eventually be used up. Under this article, we explain six different methodologies, including Pruning, Quantization, Information Distillation, Present Sample, Tensor Decomposing, and Sub-quadratic Converter based approaches, for compaction of such modeling techniques to enable their implementations in real industry NLP projects. These methods include information extraction, present sample, tensor decomposition, and parametric sharing. We believe that this survey organises the vast amount of work that has been done in the field of "deep learning for natural language processing" over the past couple of years and introduces it as a coherent story. This is especially important in light of the important need to build implementations with effectual and small designs, as well as the huge portion of newly published work in this area. Examples are shown using three-channel remote sensing and pictures obtained using RS that are included in multispectral data. It has been proved that the quality of pictures compressed using Discrete Atomic Transform may be adjusted and controlled by adjusting the greatest absolute deviation. This parameter also has a direct and tight relationship with more conventional metrics such as root mean square error (RMSE) and peak transmission ratio (PSNR), all of which are within the control of the user. Nevertheless, the majority of attention is being paid to several antenna applications, including millimetre wave, body-centric, radiofrequency, satellite, unmanned aircraft systems, gps devices, and textiles. The objective of this study is to investigate the recent trends in research within this sphere. We look at a variety of optimization strategies that are presently used to cram resource-constrained embedded and mobile systems with computation- and memory-intensive algorithms and examine how these strategies may be improved. [ABSTRACT FROM AUTHOR]

Code parity-check matrix dimensions and a maximum distance restriction are generated by the Eigen structure of the Fourier number theoretic transform. Such codes may be deciphered using a given method. Error-correcting code Fourier codes are introduced. Shortened syndrome look-up tables are efficiently used in a manner that provides an improvement over conventional decoding methods for syndromes. One way to think about it is that it's an intriguing twist on the permutation decoding method that allows for permutations without maintaining the code. The functioning of non- binary LDPC codes is examined for various Galois Field orders and PCM topologies. Several potential code constructions aimed at the small block regime are discussed in this paper, alongside traditional error-correction coding systems and length performance limitations. Using an additive white Gaussian noise channel, this study investigates the application of binary and high-order modulation techniques over the noise. We will demonstrate how to use different performance vs. decoding complexity trade-offs to reach theoretical limits. Despite its decreased complexity, our revised decoder has a word error rate that is superior to current decoders. As the last step, we integrate our improved decoder with the traditional belief propagation method. Fast Fourier transforms (FFTs), regarded as the building blocks of all signal processing systems, may be accomplished utilizing the algorithm-based fault tolerance approach. In the best-case scenario, the suggested technique can detect numerous faults and correct multiple problems at the same time. The code may be used to encode two-dimensional data for usage in bar codes and data storage. The performance of non-binary LDPC codes is examined for various Galois Field orders and PCM topologies. The LDPC codes' robustness is defined by their parity check matrix (PCM). [ABSTRACT FROM AUTHOR]

The encryption strength and compression efficiency are sometimes two opposing concepts in simultaneous picture compression and encryption methods. In this research, we suggest a novel lossy JPEG-based combined picture compression and encryption strategy that strives to increase encryption capability while preserving JPEG's compression efficiency. A covert orthogonal transform encrypts an original picture as a collection of coefficients. Since the image has a sparse representation in the conventional transform domain, it can be reconstructed from a small number of measurements, and thus allows the encrypted picture data to be compressed into a collection of measurement data. A secondary encryption approach based on the Fourier transform is used to a series of photographs to further strengthen their security. In addition, a fractional-order chaotic system with more complex chaotic behavior is constructed for application in picture compression and encryption. From what we can tell from experiments, the algorithm is robust and secure. First, we employ content-adaptive interpolation to acquire missing bitplanes and rejected pixels in order to rebuild the original picture. The first three MSBs are recovered losslessly by a combination of LDPC decoding, decryption, and Markov random field (MRF) exploitation. [ABSTRACT FROM AUTHOR]

Predicting heart disease in advance could be a significant medical breakthrough because it is widespread. A reliable strategy that can be utilized to do this is machine learning. Decision tree classifiers, random forests, and multilayer perceptron have all been used in studies to predict heart disease. However, several of these techniques could be improved, like poor precision. In our research, we have taken the South African heart Disease dataset and implemented a few models, which include Support Vector Machine (SVM), K Neighbors (KNN), Artificial neural network and XG Boost Classifier. We have used different methods for measuring performance. SVM with 69.0 accuracy, KNN with 86.0 accuracy, and ANN with 80.0 accuracy. However, the XGB classifier has shown some promising results in predicting heart disease with an accuracy of 90%. Further, when the hyperparameters were tuned using the random search method, the accuracy increased to 92.8%. The benefit of this work is that it uses machine-learning approaches to enhance the performance of coronary heart disease prediction. [ABSTRACT FROM AUTHOR]