For the robustness analysis of the security mechanism, the time complexity and asymptotic security of the algorithm are analysed and used. Therefore, this work examines the resilience of the zero-knowledge proofs (ZKP) technique utilising the RSA (Rivest, Shamir, and Adleman) problem. The result of this research is a better option for Internet of Things (IoT) devices to address key security challenges (attacks on confidentiality, authentication, integrity, and availability). The zero-knowledge proofs technique has been used with the RSA problem. It is analysed and compared with Elliptic Curve Cryptography (ECC) to see how they are correlated with each other and whether ZKP using the RSA problem can address the security issues of IoT devices in a better way or not. The final correlation result shows that both ZKP using RSA for Pollard's rho algorithm and ECC are highly correlated with one another. Asymptotic time complexity and the graph of ZKP using RSA for Pollard's rho algorithm and ECC clearly show that RSA for Pollard's rho algorithm has better time complexity than ECC. So, it can address the security issues required by IoT devices.
Brain tumor is a group of unfamiliar cells present in the cerebrum that may lead to cancer. Brain tumor can be diagnosed by several easy ways but among them MRI imaging is the best way to discover a tumor in the brain. To form images of a brain it uses radio waves and magnetic field so that the information regarding the abnormal tissue growth in the brain can be identified. The detection of brain tumor is done by using deep learning algorithm which somewhat a branch or a subset of machine learning and in this proposed system we will use the CNN(Convolution neural network) model to determine whether the brain has a tumor or not and all of this can only be done by using MRI(Magnetic resonance imaging) scans. CNN is a kind of network architecture for deep learning algorithms and is used specifically for image recognition and processing the pixel data. Brain tumor detection is done quickly with higher accuracy when these algorithms were used on the MRI scans Images which also helps in providing treatment to the diagnosed person. These predictions also help the radiologists in making the decisions quickly. The steps for creating this project is as follows: A collection of data containing images from MRI scans from various sources. In addition to that the data will be pre- processed and augmented. Next, a neural network model for tumor detection will be developed and in the end model training and testing will be performed. In generally, CNN offers a fairly high training accuracy and the error rate is also very low as compared to other techniques
In order to measure the aspects of employee-tourist interactions that have an effect on tourist experiences, text analytics is used in this article. Rather than the conventional, constrained research method, a big data analytics technique is used to create a methodological evaluation of aspects of employee-tourist interactions. We assess the concept and the significance of the components for optimizing opinions of fulfilment, service, and value. The findings show how crucial the various experience value components are in fostering favourable visitor views during employee-tourist interactions. This contributes a knowledge base to destination management organizations to encourage the implementation of official tourism statistics systems using big data.
One of the primary structural materials in the development business is concrete. Compressive strength is the most frequently utilized metric when assessing the strength and nature of cement. This paper clarifies how to make use of technical regression (RT) methodology to decide the legitimate dose of the concrete mixture. Water, Cement, Fly Ash, Blast Furnace, Superplasticizer, Coarse, and Fine Aggregate, were used as input parameters, on the other hand, compressive strength was used as an output parameter. The produced models were evaluated using statistical parameters: Linear Regression, Decision Tree Regression, and Random Forest Regression. In contrast with other applicable models, it was found that the Gaussian process regression model based on the function of the nucleus of radial bases delivered relatively better results. The recommended models should get a good deal on saving money on materials, labor, and time while also improving accuracy. The proposed concrete should be more durable and accordingly more cost-effective.
The procedure of detecting dyslexia is difficult and needs a multidisciplinary approach. Early dyslexia detection is essential for providing people with this learning disability with adequate assistance and intervention. This study categorizes most relevant and recently published approaches proposed for dyslexia detection on the basis of physiological traits used as dataset and the algorithms used for the same. The analysis showed application of various traits such as handwriting, neurological scans and eye-based movements. A detailed analysis has been presented in terms of accuracy as well. The study has successfully condensed a multitude of the state of the arts methods for dyslexia detection leading towards possibly more physiological traits based study.
Weld cladding can be termed as a surface modification technique used on the components which are serving under highly corrosive environments such as seashore applications, petrochemicals, and nuclear industries. Computers play a key role in optimizing and controlling the welding process parameters as per the desired output. Weld cladding by Gas Tungsten Arc Welding (GTAW) process has been proved to be static and capable of easy arc control, all position capability and spatter free deposits. This paper presents a review of addition of filler wire in preheated condition during welding and cladding processes with computer assistance. It highlights the exploration of preheating of the filler wire used in arc welding process, close to its melting point before it is fed into molten pool by additional power source. The main power source controls viz. automation of the wire feed, shielding gas flow and welding current requirements help to optimize the deposition and surface quality. Hot filler wire addition results in lower heat input going into the base metal which improves the clad deposition, reduces the base metal dilution, and narrows heat affected zone (HAZ) thereby reducing the requirement of multilayered weld deposits to achieve the filler chemistry. The issues of adding hot filler wire to cladding and welding processes are discussed in this review paper along with their advancements.
A well-known and most suitable method to address real-life situations is the Assignment problem. In this paper, an optimum distribution of duty of paddocks to the crops is in the Intuitionistic fuzzy (IF) assignment problem with the cost function as an Intuitionistic triangular undefined number. The assignment costs are fuzzified into crisp numbers, and a multistage decision-making method known as Dynamic Mathematical Programming is used to find the best solution to the inverse problem. This study uses an AI-based dynamic programming approach in the field of agriculture. This study tries to solve the IF assignment problems.
The separation of the data and control planes and an integrated software-based administration strategy grounded on a central controller are two considerations put forth by the software-defined networking (SDN) paradigm to make it easier to deploy new applications and services. Those architectural concepts set the stage for a software-controlled network that is more flexible, efficient, and dynamic. With SDN networks, the network can be managed by software that uses minimal network hardware components and enables easy interconnection and installation. It provides the easiest mechanism for network administrators to deploy modern applications and security services. As a result, most network services will be more adaptable, programmable, and unrestricted by platforms. However, there are several difficulties and security-related problems with these centralized and programmable approaches. Security problems in the high- speed network are growing as network traffic grows as well. However, there are a variety of security weaknesses in the SDN architecture's components that might be used by intruders to execute malicious deeds and disrupt the infrastructure and its operations. This research proposes a deep learning-based attack classification method to classify the malicious and legitimate hosts and to block unwanted traffic in the SDN networks. This work mainly focuses on the detection and prevention of TCP-based assaults of the control plane in the SDN networks. The experimental results show better classification accuracy with minimum overhead in terms of efficiency.
Ribes nigrum L., commonly known as blackcurrant berries, is a species of the family Grossulariaceae. The extract of blackcurrant berries is abundant in polyphenols and can promote apoptosis in a variety of cancer cells, thus can act as a potential anticancer agent and shows promising results to treat various cancers. The various compounds present in the blackcurrant berries have already been identified as having anticancer properties in breast cancer and gastric cancer. In order to explore its potential further, we have performed a comprehensive In Silico analysis to study its effect on cervical cancer. A validated epigenetics-related enzyme, protein arginine methyltransferase 5 (PRMT5), has been studied recently as a promising therapeutic target for Cervical cancer. Also, caspase-3 and caspase-9, apoptotic signaling proteins, can also act as potential target proteins for cervical cancer. With an endeavor to study the effect of blackcurrant berries, we have targeted the PRMT5, caspase-3, and caspase-9 for in silico for interaction study. We have used 12 volatile compounds of Ribes nigrum L. for the current study. Molecular docking and further free energy of binding calculations were performed falling in the range of (-5 to -9Kcal/mol) and (-40 to -70Kcal/mol) respectively which suggested strong interactions of selected compounds with the target proteins. The results showed a promising profile of the associated compounds which can be further investigated and evaluated for cervical cancer treatment and management studies.
Internet of Things (IoT) connects individual devices, software, and sensors over a network without misnomers of a public domain. It is a very common scenario in designing better low-cost enterprise solutions for smarter homes, cities, and healthcare. One key issue smart cities are dealing nowadays is car parking. It directly affects traffic congestion, costing people time and fuel. In this work, we solve the current problem by the implementation of an android application with the on-site deployment of an IoT module, where users can search for nearby parking spaces, reserve multiple slots according to their preference, and navigate to the selected location. Also, the application is capable of automatically notifying users of nearby parking locations in real time. Additionally, for efficient parking management, users will get an alert until the parking of a car is not done within the allotted boundaries.
We have always been concerned about outsiders breaking into our homes, offices, and, in particular, hospital blood banks. Blood samples from people with uncommon blood types are stored in a blood bank. Any adjustments or modifications can possibly endanger people's lives. As a result, security is critical. The Internet of Things (loT) paradigm seeks to solve this security issue as cheaply as possible. This research proposes a low-cost fingerprint door lock system that can store 137 fingerprints at once. The loT model includes two phases: the enrolment phase, in which fingerprints are enrolled, and the verification phase, in which the person accessing the blood bank must authenticate their fingerprint. This is one of the cheapest and finest ways to safeguard blood banks against intruders, and it may be simply implemented by various government entities and non-profit groups that serve society. It has a 98% accuracy rate. The system uses lights and a buzzer to approve or disapprove people.
Carbon Dioxide and Greenhouse Gases are the main cause of the change in the climate. It is recognized worldwide that need to reduce the emissions of greenhouse gases to avoid their worst impact on the change of the climate. Greenhouse effect is the effect in which the greenhouse gases in our environment traps the heat which leads to the rise in the temperature of earth. Greenhouse gases include carbon dioxide, methane, nitrous oxides, and water vapor. In coming years this will harm agriculture, biosphere, and many living organisms. In this research, we have analyzed different countries and their level of emission of harmful gases. And want to tell countries to take steps towards the reduction in the production of these gases. In this Analysis, we worked on “Who is responsible for climate change?” “What are the main sources?”, “Who is producing it at a very high rate? We have used the dashboard for analyzing it in all possible ways.
Parkinson's disease which is a neurodegenerative disease tends to deteriorate muscle control steadily. Although Parkinson's disease primarily affects elderly people, but adults can also be affected by this disease. The symptoms are caused by the gradual nerve cell loss in the area of the brain that regulates movement. Patients' quality of life is greatly reduced because it shows motor, cognitive, and other sorts of symptoms. Parkinson's disease is usually diagnosed based on a patient's medical history and physical symptoms. However, it has a subjective nature and a poor prognosis. In the diagnosis of Parkinson's disease, artificial intelligence (AI) has shown promising results. Yet because of the small sample size, poor validation and lack of big data design, it introduces bias. This paper outlines the state-of-the-art methods that have been used to detect Parkinson's disease. The findings of the literature, as well as frequent methodological flaws that may skew results, are identified. The question is can AI alone be successful in clinical settings for Parkinson's disease identification? By incorporating AI algorithms with Internet of Things (IoT) treatment can be improved effectively while reducing related healthcare expenditures.
Every single Internet of Things (IoT) device needs an antenna. IoT applications, especially those where wired connectivity is practically non-existent, largely rely on wireless access for communication between IoT gateways and other communication-based devices. Wireless technology is significantly impacted by the antenna's improved technical improvement. Due to the rapid growth of Internet of Things (IoT) applications in existing communication systems, there is an increasing requirement for small-sized antennas. Micro-strip patch antennas are frequently used in IoT applications because to their compatibility. The micro-strip antenna's key benefit is how simple it is to integrate into Internet of Things (IoT) devices. Wideband and multiband antennas are used to avoid using various antennas for different tasks on different frequencies. In this study, single band to multiband conversion strategies for microstrip patch antennas are covered. Different micro-strip antennas used for Internet of Things applications are compared with regard to their performance metrics, such as size, gain, and bandwidth. A single band antenna may be transformed into a multiband antenna using fractal and proximity coupled methodologies, which have been demonstrated to be significantly better than all previous methods. In order to achieve the multiband property of a patch antenna with high bandwidth, gain, and efficiency, several designs and methodologies have been examined in the literature.
At present, healthcare is one of the biggest concerns in the world. Brain Stroke is the leading cause of death worldwide. Prediction and detection of the occurrences of a brain stroke at the early stages is a valuable work in the medical field. There are several factors which are responsible for the brain stroke such as BMI (Body Mass Index); Age; Sex; Family Background; Gender; smoking status; hypertension, etc. In healthcare, a lot of research work has been done on the prediction of heart disease, but relatively little attention is paid on predicting a brain stroke. The main aim of this study is to review different research articles published earlier and to choose the best machine learning techniques for the prediction of brain stroke for our future work. After reviewing the different machine learning methods utilized for stroke predictions and after taking into account the previously published studies, it has been discovered that death rate and functional results are the expected outcomes for the majority of the research work done. Support Vector Machine, Stacking, Decision Tree, Weighted Voting, Random Forest, Neural Networks and Naive Bayes were the most frequently employed methods.
In recent era, the use of software systems is growing rapidly. Hence, reliability and customer satisfaction are the most important objectives for software development organizations. Software reliability growth models are essential for checking software reliability. In this paper, we first present an investigative review of testing-effort dependent software-reliability growth models. We discuss the different software reliability growth models with testing-effort behaviors. We then integrate the exponentiated-Weibull testing effort function into a delayed S-shaped software reliability growth model. To validate the proposed model, we present the analysis and estimate of the parameters with authentic data and compare the experimental outcome with the findings of previous models from the articles. Finally, we wrap up the paper by presenting the contributions and by indicating the probable research scope.
The sensor data points that exhibit unexpected behaviour that considerably deviates from the norm are considered anomalies in the time-series sensor data. We can model univariate time series data using a number of traditional methods, including ARIMA, GARCH, SARIMA and VAR. Modern deep learning algorithms have lately been used to study time series analysis and prediction. This study contrasts three autoregressive models, which project future events based on past observations. Three different sets of temperature, vibration, and pressure sensor data are used to compare the performance of the Bidirectional Long Short-Term Memory (Bi-LSTM), Convolutional Long Short-Term Memory (C-LSTM), and Stacked Long Short-Term Memory (S-LSTM) architectures. The models performance and training time are reported for healthy, unhealthy and noisy time-series data. Experimental results shows that, Model trained and build using Bi-LSTM can consistently detect point anomaly for healthy, unhealthy and noisy time-series data with minimum error rate across three sensor datasets.
Malicious URLs (Uniform Resource Locator) are known for hosting unsolicited content that can deceive common users and lead to scams resulting in significant financial losses, private information theft, and malware installation. Despite the development of prevention strategies, it remains a significant risk, even with measures such as receptive blacklisting of URLs. Unfortunately, this approach falls short due to the short lifespan of phishing websites. To address this problem, a real-time malicious URL detection method is required, which can effectively detect and prevent such attacks. Typically, phishing URLs have certain connections between the registered domain level and the URL's path. The approach presented in this paper uses these connections to characterize the URLs by inter-relatedness, and various attributes were mined from them to make estimations. These attributes were then used in several machine learning techniques to detect malicious URLs from a real dataset. Maximum accuracy of 90% was achieved using K-N earest Neighbors Algorithm. The patterns for a URL being Malicious or Benign were also visualized using graphs.
This paper attempts at the development of an OCR of the handwritten Telugu text comprising the words made up of only the basic characters without matras for simplicity. There are 3 steps in this OCR. The first step is concerned with the segmentation of the basic characters from the handwritten Telugu words. The second step involves placing the characters into anyone of 6 groups. The first four groups are those that satisfy one of the four types of openness criteria (top, bottom, left and right). The 5th group satisfies more than one type of openness and 6 th group the closedness criterion. The third step deals with the recognition of the character in each group for which a deep learning network called Convolutional Neural Network (CNN) is employed. The procedure to be applied on each test character involves finding its group first and then identifying the character. The contributions include the development of the segmentation approach, proposition of openness and closedness criteria, and the use of CNN for the recognition of characters. Out of several network architectures tried, the best performance of 98% accuracy is obtained on the created database of the handwritten basic Telugu characters using the modified CNN model that results from changing different parameters such as Adam optimizer of the original CNN. Similarly changing AlexNet parameters, an accuracy of 90.5%is achieved, and by removing some dense layers in it the accuracy is improved to 95.5% whereas LeNet-S provides the accuracy of 89.5% %. As another study for the sake of comparison, we have extracted the Histogram of Gradients (HOG) features from the same dataset and used Support Vector Machine (SVM) as the classifier and the overall accuracy has come out to be 94.13%.
In the last few decades, Deep Learning has experienced remarkable growth, which has improved computer vision tasks. Deep fake is a technology that uses deep learning algorithms that manipulates the features of original content digitally to produce fake realistic-looking content that can be audio, video, photos, etc. There are various methods available in literature for creating deep fake such as GAN (General Adversarial Network), Auto Encoders, pix2pixGAN, Cycle GAN, Style GAN, Wave Net etc. and some of the open source digitally available tools are Deep Face Lab, Face Swap, etc. In the video game and film sectors, the adoption of the aforementioned techniques has expanded significantly. This study elaborates on a survey that was performed by several research organisations and focused on the feasibility gaps that need to be recovered for deep fakes. In this work, many contemporary strategies for creating false images are explained, along with the various dataset types that authors used. Finally, numerous research gaps and potential future directions are highligh ted.
