In this work girl child security system using a GPS tracker in lOT with Thingspeak (Group 1) is going to be designed and compared with the girl child security device using fuzzy classifier (Group 2).: This system ensures the safety and security of the girl child by continuous monitoring of the location details of the girl child. 10 samples were taken for each group. The P¡0.005 signifies the performance of the system. Girl child security system using a GPS tracker in lOT with Thingspeak (Group 1) having mean accuracy 0.4, Standard deviation 0.516 and standard error 0.1633 and the Girl child security device using fuzzy classifier (Group 2) mean accuracy 0.2, Standard deviation 0.422 and standard error 0.133. The significance P¡O.05 shows the goodness in the performance. The girl child security system using a GPS tracker in lOT with Thingspeak significantly performs better than the girl child security device using fuzzy classifier.
In today's fast-growing world, we all are bounded by time and need our things as fast as possible on our tables. So, is the case of tech-domain. The world is viewing a shift in the digital world. It is highly visible that various fields are extending their business from physical to virtual world. An instance for that is that fruits are now not only available in a physical market but can be bought through online platforms. And this shift of the digital world is making the business environment more competitive. Therefore, to be more rapid, effective the older technologies of integration need modification. Hence, the rapid change in older integration technologies are seen nowadays. SOA (service-oriented architecture) does provide theoretical instructions but it rarely meets the expectations when used practically. Therefore, today's companies have to be up to date to provide a smooth and hurdle-less experience to their users. Also, it's a known fact that this digital transformation is not a product of only one technology or applications. It requires multiple technologies and applications to go hand in hand to meet all the requirements of the user. In order to do so, they must bring data from disparate sources to multiple audiences, such as customers, suppliers, and employees, securely, and at scale. That is why now connectivity is seen as an executive concern. But still there are organizations who don't consider connectivity as an important part to lead their whole firm onto the path of success. Earlier approaches were made for fewer endpoints and slower delivery expectations. That's why we need new point to point integrations. IT leaders then must meet two seemingly contradictory goals: they must ensure stability and control over core systems of record, while enabling innovation and rapid iteration of the applications that access those systems of record. This is the challenge now variously referred to as bi - modal or two-speed IT. Existing connectivity approaches are not fit for these new challenges. And using SOAP-based web services technology to implement SOA proved to be a heavyweight approach that was ill-suited then and even more ill-suited now for today's mobile use cases. This research paper highly focuses on the new approaches towards connectivity of multiple technologies and their integration. API - led connectivity approach meets all today's connectivity needs. This research paper would be providing an outline of the core of this approach, implementation's challenges and discuss how IT leaders can realize this vision in their own organizations.
The smart devices intercommunication concept has gained an enormous increase in fame and use with the constant development and research in communication networking, especially in the lives of people who live in highly developed areas. In this concept, a huge number of daily used smart applications are users in exchange of data being collected by smart devices, this may lead to the security and privacy issues. Normal user might not take observation on weakness and threats that initiate by advance technologies. Main aim of the paper it to provide clear image of lOT, attacks that can happen on HAN and there possible solutions to overcome those attacks in future integrated on a single platform. The HAN devices provides the users with continent and comfortable life reducing their physical efforts, by determining the behavioral activities of the.
The article discusses the possibility of political organizations utilizing deepfake technologies. It is observed that deepfakes can affect all levels of public and political life and contribute to the development of several problems, including reputational risks for celebrities and ordinary citizens, the growth of organized crime, and social stability and national security concerns. The sophistication of deepfake technology (DT) has increased significantly. Cybercriminals can now modify sounds, images, and movies to scam individuals and organizations. This growing threat to international institutions and individuals demands our attention. This article discusses deepfakes, their societal benefits, and how deception technology works. The hazards deepfakes pose to enterprises, governments, and legal systems worldwide are highlighted. In addition, the paper will examine potential solutions for deepfakes and end with future research goals. The authors conclude by discussing potential threats, prospects, and key pathsfor state regulation of this content within the framework of broader political and legal instruments to combat the spread of disinformation and fake news.
The objective of the work is Car Loan Forecasting Using an Extreme Logistic Regression algorithm with novel credal sets and K-Nearest Neighbors algorithm. Machine Learning Techniques is an emerging research field that can be used for predictions. When compared to the Extreme Logistic Regression algorithm with novel credal sets, and the K-Nearest neighbors algorithm uses a framework for vehicle loan prediction to predict loan default from banks while clients are facing significant challenges. This research study considers two groups such as an Extreme Logistic Regression algorithm with novel credal sets and K-Nearest Neighbors algorithm. The sample size considered for each of the algorithms is 20. The accuracy, precision, and recall of Logistic Regression Algorithm with Novel Credal Set produce 73.86%, 17.75% and 24.73% respectively in Car Loan Forecasting on the dataset used whereas the Accuracy, Precision, and Recall of K-Nearest Neighbors algorithm produces 67.86%, 16.67%, and 21.86% respectively Car Loan Forecasting default. It shows the statistical significance of (p ¿ 0.001) from the independent sample T-test. When comparing with accuracy, precision, and recall, an Extreme Logistic Regression algorithm outperformed the K-Nearest Neighbors algorithm approach sub-stantially.
The pandemic has brought the digital world an indelible part of one's lifestyle. The rushed digitalisation in the education spectrum that was totally unprepared for, comes with its own challenges. With shift in the mode of education, the access to internet and the time spent by the students online has increased multifold. The study is intended to determine the youngster's financial knowledge, attitude and prudential behaviour. To collect data, a survey was conducted amongst 282 women pursuing their graduation. The interlinkage between financial knowledge, attitude and behaviour was studied thoroughly and the result has established a positive relationship between them. This study has enriched the existing research findings by identifying additional aspect of attitude towards digital finance and more specifically throwing light on the learner's choice of acquiring financial knowledge. This research establishes that it is necessary to incorporate financial literacy as a part of undergraduate curriculum for the long term financial safety and wellbeing.
Energy management is an important issue to restrict the crisis of global warming. Power utilities and consumers are looking at the energy management system to improve energy production, minimize energy costs and reduce greenhouse gas emissions. Internet of things (loT) can fulfill the pressing needs of energy management for resolving Pakistan's energy crisis. Numerous wireless technologies in home energy management systems (HEMS) i.e. ZigBee, Z- Wave, Bluetooth, and Wi-Fi can promote communication between appliances. Wireless personal area networks and wireless sensor networks have quickly become popular. This system unifies various home appliances and smart sensors by Wi-Fi. The paper elaborates home energy management system which comprises of micro controller and real-time WiFi Module (ESP8266) connectivity. Users can control the home appliances locally by using Wi-Fi or remotely by using Android App. Moreover, the temperature and humidity of the room are sensed with the help of a sensor. The system will help provide automation in smart city houses.
Visual learning is one of the most effective ways to grasp the knowledge of anything. Algorithm visualization demonstrates operation of logic in a pictorial manner, this enhances the knowledge and simplifies the understanding. In this paper, We address the need for a pictorial explanation of algorithms and suggest solution to visualize sorting algorithms by building a web application and explore probable future directions based on our own findings and observations using objective checklist of the web application.
With the rise of Bitcoin, blockchain technology has gained a lot of attention from the financial world. While the underlying distributed ledger technology has many potential applications, Bitcoin remains the most well-known and widely- adopted use case. As a result, Bitcoin is often seen as a bellwether for the wider blockchain industry. However, there is another side to blockchain that is often overlooked: dapps. Decentralized apps (dapps) are applications that run on a decentralized network, such as Ethereum. Unlike traditional apps, which are controlled by a central authority, dapps are open source and controlled by no one. This makes them incredibly appealing to developers who value decentralization and censorship-resistance. The readers will get an overview of blockchain and dApps research.
The current study aims to examine the mediating role of attitude on e-learning adoption and its impact on the students' performance in business faculties at Jordanian universities. The study population consists of students from Jordanian universities' business faculties, both public and private. A random sample of 427 students was solicited from these faculties at different educational levels. The results show a significant effect of e-learning adoption on students' performance, except for the electronic curriculum. Regression analysis revealed that organizational culture possesses the highest effect, while human resources secure the lowest. The results show a statistically significant effect of e-learning adoption dimensions on students'attitudes, except for human resources and the electronic curriculum. Again, regression analysis revealed that organizational culture possesses the highest effect, while human resources secure the lowest. Results show a partial mediation effect of students' attitudes in the relationship between e-learning and students' performance in business faculties in Jordanian universities.
To improve accuracy in automatic detection of Tuberculosis (TB) disease from Lung CT images. The dataset used is Chest CT scan images consisting of 1000 images. Detection of Tuberculosis is done by the Support Vector Machine Classifier (N=10) and KNN classifier. During testing, 10 iterations have been taken for each classification algorithm. The experimental results show that the Support Vector Machine algorithm with mean accuracy of 94.17% is compared with K Nearest Neigh-bour algorithm with mean accuracy of 89.84%. The statistical significance of two algorithms sig (2-tailed) p-value observed is 0.00 in the independent sample t test. Within the limitations of this study SVM has better accuracy than KNN.
The occurrence of kidney abnormalities (K.Abs) prevalence is elevating which have noxious and deleterious affects all over the world. An automated detection of K.Abs accurately detects and classify with labels by implementing latest DL method with transfer learning approaches. The prior methods were expensive, tedious, arduous and less efficient to detect K.Abs from noisy low frequency images with limited no. of classes and small size dataset. The proposed IA2SKAbs research introduced two effective automated model's 1st was Efficient-b0 and 2nd ResNet-18 which resolve all abovementioned problems expeditiously. Both models enhance the overall accuracy and classification accuracy with large dataset (12446) of CT images along with a greater number of classes which efficiently work in contrast to prior research. Both pre-trained models were trained by altering last three layers or using them from scratch like fully Connected, SoftMax and Classification output layers according to the size of classification problem. Before training of model's dataset was pre-processed with $224\times 224$ dimensions which are according to the used models. The training accuracy of Efficient-b0 and ResNet-18 99.92% and 99.97%; the overall classification accuracy of both models was 99.99% and 98.1% respectively. The implementation detail of system architecture is discussed below in section 3.
With the speedy advancement of the web, a consistently expanding number of people that utilize online social media. Subsequently, hate speech becomes uncontrolled in social media, and it is critical to group the hate speech and control it before it spread. With the presentation and the advancement of deep learning, hate speech recognition becomes practice. Many examinations use information from social platforms, for example, Twitter and Facebook along with machine learning or deep learning advances to identify and perceive hate speech. In any case, there are insufficient surveys about this area. After studying various article's and research papers, no such review is available to see assortment of feature extraction/engineering methods (FEM) and ML-Algorithms that assess, which feature extraction/engineering procedure and ML-Algorithms can perform better on open source or openly accessible dataset. Thus, the purpose of this research paper is to look at 3-FET or strategies and 8-ML-Algorithums to assess their performance on an openly accessible dataset and this dataset has 3 classes. The research outcomes exhibited that SVM-Algorithm with BIGRAM features performed better with almost 80% accuracy. This research paper shows viable ramifications what's more, can be used as a gauge concentrate on to identifying hate speech communications/messages. Also, the result of various correlations will be utilized as condition of- workmanship strategies to look at future explores for existing mechanized text classification procedures.
Terrorism is the evolving phenomenon which has been increased to a huge extent in the past few decades which threatens the stability of a country / region. Government Officials like FBI, CIA etc. could not depend upon only telecommunications, satellite activities etc. to capture activities of terrorists as they are prone to these technologies and can easily plan attacks against it. Real time collection of terrorism data can be a source of great use for counter terrorism measures. But to process such huge growing data one need the efficient methodologies to practically visualize the complex unstructured data. Data Science provides efficient way to process infinite growing data with time with distributive frame works, statistical and mathematical computation modeling, clusters etc.. We had developed a model to analyze real time terrorism data with the help of data science in python to solve the existing and growing problem of terrorism in India. The Data Science Model is based on the Global Terrorism Database (GTD) which contains the records off terrorist attacks since 1970. The model is used for the visualization of the Real-Time-Data of the terrorist attacks with the help of data manipulation tools in python. It is an intelligent early warning model which includes the Terrorist attack in India since 1970. The model proposes the statistical model, analysis, correlation and findings in the Punjab region. It includes the analysis of geospatial data, REST API (Foursquare API), data manipulation with pandas, clustering with folium, seaborn, plotly and other data visualization tools.
COVID-19 coronavirus disease is the latest virus in the new century. The World Health Organization- WHO organization announced that COVID-19 disease is a pandemic that leads to thousands of death in short time of spam. A quick and accurate diagnosis of COVID-19 shows an important role in its prevention. This study is based on a fusion-based Self-Diagnosis Expert System Empowered by the Leven-berg Marquardt Algorithm for the diagnosis of diseases. Leven-berg Marquardt has been implemented for the classification of different symptoms of the diseases and relates the results for their diagnosis. The MatLab software was used for the simulation purpose. The proposed fusion-based LB increased the accuracy in the training and validation process to be 10 times more efficient than the existing. The fusion technique achieved an overall accuracy of 98.86%, and 99.09% in all performance metrics which included TNR, precision, and FPR statistical parameters.
To enhance the accuracy of face recognition in a classroom environment using Recurrent Neural Network (RNN). The study consists of 2 groups i.e Recurrent Neural Network and Multi Cascaded Convolutional Neural Network (MTCNN) with sample size of 10 for each group. Gpower software is used to determine sample size with power value 0.8 and alpha is 0.05. Proposed model has an improved accuracy of 95.44% in facial detection and tracking than existing model of 91.73% with significance value of 0.97 (p¿0.05). End result of proposed model Recurrent neural network provides better accuracy when compared with Multi cascaded convolutional neural network.
Introducing YOLO, another way to deal with object identification. Previous object detection function re-uses separators to create location. All things considered, we present the identification object as a repetitive problem in geographically separated jump boxes and related class opportunities. All acquisition pipes are an independent entity, they may be well developed to begin to finish directly on-site operations. Our integrated design is very fast. Our Consequences should be discarded photo rotations continuously at 45 edge every second. An additional moderate practice of the organization, YOLO, processes 155 shocking casings per second. Compared to the best class identification frameworks, YOLO makes many limitations yet very different to expect misleading sides on the basis. Finally, YOLO learns the typical presentation of articles. It overcomes other local techniques, including SSD and R-CNN, while summarizing from conventional images to as diverse as art.
Blockchain technology has major advantages in improving management processes in many industries, such as increasing the security and trust level, protecting data from forgery, and decreasing transaction costs. The paper discusses the impact of blockchain technology as a digital transformer on construction projects and improving management processes and its effects across the four elements: Business, Technology, Industry, and Society. The construction industry deals with many other entities with a large volume of transactions, creating a great environment to utilize blockchain technology to improve these processes. This study aims to determine the impact of blockchain technology on project management in the construction industry. Therefore, the collected data is from secondary data as there have been few cases discussing the implementation of blockchain within the construction industry, which significantly impacts project management through an efficient monetary exchange, building information modeling, smart contracts, and increased supply chain management transparency. As a result, blockchain technology has a positive impact and the ability to increase the efficiency of the construction project management process. This research has intelligibly discussed the importance of digital transformation in the present time, as well as the role of blockchain technology in the construction field along with project management.
Machine learning is the study of computer algorithms that get better on their own as a result of usage of information and experience. It is seen as a neighbourhood of AI. The aim is to find accuracy in predicting the harvesting stages using Convolutional Neural Networks algorithm compared with a Decision Tree algorithm. This study contains a total of 2 groups, the convolutional neural network algorithm is analysed in the group 1 (10 samples), and the Decision Tree in the group 2 (10 samples). The accuracy and efficiency of each of the models are compared. This paper is to improve the efficiency of the algorithm used in the harvesting stages. The proposed model appears to be efficient and faster than the existing algorithm and the mean accuracy of detection is ±1SD. The final outcome of the existing system, Convolutional Neural Networks algorithm, is compared with the outcome of the novel Decision Tree algorithm and the proposed model proved to be having higher efficiency than the existing model.
