The cost and time estimation of any construction project are very important tasks for economic impact and overrun of a construction. The tactics endure to plan, schedule, control of project time, and compute the investment to be contributed as sustainable and reliable. This research aims to assess conventional and green buildings characterized by cost and time estimation. The cost of various materials along with labour cost, plant, and machinery costs, etc. was calculated using data from market surveys, practitioner data, literature, and schedule of rates for Delhi issued by the Central Public Works Department. All these techniques of cost estimation helped in computing a more realistic construction cost of the buildings. While Critical Path Method (CPM) was used for time analysis to overcome impeded efficiency of traditional techniques of decision making such as Gantt chart as dodge time overrun of the construction. The influence of green and conventional building assessment favoured the productivity to the aspect of energy efficiency and overrun extent.

This paper proposes a real-time hand gesture recognition interface called VUCIS (Virtual User Computer Interaction System) to operate a mouse, keyboard and stylus. OpenCV and MediaPipe Hands are used to achieve this. OpenCV is utilized for its powerful image processing capabilities and computer vision. MediaPipe Hands library is used to generate 21 landmarks on a hand. By using a combination of various landmarks, a distinct gesture is assigned to a task performed by the input devices. The proposed interface allows users to interact with computers easily, reduces the need for keyboard and mouse as external hardware in certain circumstances and eliminates any form of contact with a surface, minimizing the spread of COVID-19.

This study presents the integrating of the DFA concept for the ASP problem to reduce the cost and time of assembling the product. Enhanced Fruit Fly algorithm is developed by incorporating the range of angles to the fruit fly during the initial fly as compared with the random angle selected in the general fruit fly algorithm to generate optimal assembly sequences. The fitness equation is formulated with directional feasibility data to engender optimal assembly sequences. The proposed concept is applied to the pen and motor drive assembly to test the performance of the algorithm. The results from the proposed notion are compared with the GA, ACO, FPA, and IHS for the motor drive assembly in terms of the number of levels of the assembly sequence, fitness value, number of iterations, and number of optimal sequences generated.

Tumour malignancy has caused a very high number of women's deaths. Proper hyperparametric ML technique can help to efficiently detect tumours. In this work, various algorithms to analyse the Wisconsin breast cancer data set have been studied. Deep learning with Adam Gradient Descent Learning has been used, which combines the advance features of adaptive gradient and rms propagation. Linear regression, Shallow SoftMax regression, and Deep neural network SoftMax regression are used for the classification of benign and malignant tumour and have calculated the AUC, ROC and accuracy. A unique hyperparametric change is shown in each model to work on the exactness of the model and also to chalk out correlation between different models. It is concluded in the analysis that for the WBC data set the deep neural network SoftMax regression significantly improves the accuracy from other models, and we reached a test accuracy 0f 0.956 and testing accuracy of 1.0.

The energy efficiency of sensor networks is enhanced using "Enhanced Open Shortest Path First (OSPF)" for machine-to-machine communication (M2M). The security of M2M communication for sensor network is improved using Holistic security approach. Method:Path optimization has been performed by using Lexicographic and Lightweight Reinforcement of algorithm. Finding: Achieves energy efficiency by considering the hop count, delay, distance, trust factor and residual energy of each node. Novelty: As per the comparison analysis between proposed EN- OSPF and conventional method, the proposed method shows better performance with respect to trust factors, interference factors, security, residual energy and network lifetime. A holistic security approach is implemented for the denial attack.

The modern environment has faced numerous issues due to fake news that machines or humans usually generate. It causes severe impacts in both political and social stages; therefore, each individual may face the effects of fake news. Thus, recent research mainly focuses on enabling a highly effective detection system to mitigate the negative influence of social media. A novel framework is developed to detect and classify fake news from social media automatically. In the proposed model, an Apache Spark technique is incorporated with the deep hybrid learning based on improved CNN with hybrid Black Widow Optimization (BWO) algorithm and Mothfly Optimization algorithm (MOA) (HM-BWO) and LSTM. This framework provides better classification and detection of fake news from social media environments. The proposed model is implemented into the platform of MATLAB, and its performance is analyzed through the performance metrics, including accuracy, loss, precision, F1-measure, and recall.

In today's digital world, life without computers is not possible. Nearly everything around us is on an intelligent system, helping us to lead life in a better way. The revolution brought by smart systems has increased the global productivity and has benefited the world. Intelligent Systems are useless without software. For excellence in intelligent systems, there is strong need to develop more and more reliable software. Thus, the role played by the intelligent system is appreciated in industry, education, faults prediction, information, banking and social media etc. Access to online payment, entertainment, banking systems, chatting, bill payments, organization management, nuclear reactors etc. has become easier, smarter and faster in day to day life. The goal of this research is to develop Intelligent Software System for identifying defects based in existing software modules using Machine Learning techniques. The just-in-time (JIT) defect removal ensures software quality so higher priority defects can be removed thereby enhancing reliability of the software system. Intelligent Software System (ISS) comprises programs, methodologies, rules and related documentation and information that empower the client to collaborate with a computer, its equipment i.e. hardware, or perform errands. According to Pressman, it performs a dual role. Sometimes, it behaves as a product and sometimes it becomes a vehicle for delivering a product. When software is a product, it executes two functions; firstly it transforms information i.e. produces, manages, acquires, modifies, displays, or transmits information and secondly it delivers computing potential of hardware and networks. Software controls other programs, communication of information, and helps in building other software products. But like any other invention, software has drawbacks. When the computer system or programming software demonstrates failure, a disappointment or breakdown occurs and the influence of disappointments leads to financial harm prompting monstrous loss of human lives and cash.

Neural Networks (NN) are highly valuable tools which are gaining importance in recent years due to their versatility in handling huge data from various sources and gaining meaningful insights on them. They are not only being used in recommender systems but also in real-time applications like auto path detection in autonomous vehicles. However, light is rarely shed on how secure these systems are. With the growing digital world, there are always vulnerabilities and chances to exploit. In this paper, Neural Networks are looked at through the lens of security, and a hybrid algorithm is proposed to enhance the security of neural networks by addressing the weight matrix vulnerability in a neural network. This paper proposes a novel method to involve encryption in the neural network named Encrypted Neural Network (ENN) to prevent any malicious modification of the weight matrix that may harm the training and output of the neural network. The proposed algorithm is tested against how accurately the original neural model is preserved. Finally, the accuracy of the algorithm is checked graphically against the size of the neural model and increasing complexity.