Energy Optimization and Power Stack Shed Reduction of Oil Depots by using Renewable Energy Resources

Most of the industries including the oil sector are looking forward towards the renewable energy resources with proper energy management system (EMS) as it is the need of time. For this purpose, solar and wind energy are the renewable energy resources, which are obtained from natural resources and produce clean and environment -friendly electrical energy and can be used for oil depots. The proper utilization of solar and wind energy from natural resource may result in economical and cost-effective EMS. In the proposed research work, an effective energy management demonstration is delivered to ensure the ceaseless flexibility of power. Furthermore, reduction of production per unit cost to the oil sector industry by utilizing multiple objectives streamlining. In the proposed oil depot, connected loads are divided into Shiftable and Non-Shiftable loads and then apply Branch and Bound Algorithm (BnB) with binary integer linear programming (BILP). By using the BnB technique, selected shiftable loads are shifted to the low cost energy resource automatically and resultantly, we get the low price unit cost and continuous power supply. Simulation results for the above-mentioned research work are performed on MATLAB. The proposed technique helps to reduce the power stack shedding issue as well.

Covid-19 Detection using Deep Convolutional Neural Networks from X-Ray Images

Abstract— The Novel Coronavirus generally, knows as COVID-19 which first appeared in Wuhan city of China in December 2019, spread quickly around the world and became a pandemic. It has caused an overwhelming effect on daily lives, Public health, and the global economy. Many people have been affected and have died. It is critical to control and prevent the spread of COVID-19 disease by applying quick alternative diagnostic techniques. COVID-19 cases are rising day by day around the world, the on-time diagnosis of COVID-19 patients is an increasingly long and difficult process. COVID-19 patient test kits are costly and not available for every individual in poor countries. For this purpose, screening patients with the established techniques like Chest X-ray images seems to be an effective method. This study used a deep learning data augmentation on a publicly available data set and train advanced CNN models on it. The proposed model was tested using a state-of-the-art evaluation measures and obtained better results. Our model, the COVID-19 images is available at (https://github.com/ieee8023/covid-chestxray-dataset) and for Non-COVID-19 images is available at (https://www.kaggle.com/paultimothymooney/chest-xray-pneumonia). The maximum accuracy achieved in the validation was 96.67%. Our model of COVID-19 detection achieved an average F measure of 98%, and an Area Under Curve (AUC) of 99%. The results demonstrate that deep learning proved to be an effective and easily deployable approach for COVID-19 detection.

Sentiment Analysis Based on Reviews Using Machine Learning Techniques

In our daily life, people’s opinions and experiences are important sources of information. To measure the feeling of people’s opinions the term used that is called sentiment analysis. The text is the main method of communicating on the Internet in modern digital time. Sentiment analysis captures the user’s views, moods, and their opinion related to the specific services provided by the business organization in a real-time. This research focuses on Roman Urdu reviews. It has three basic classes: negative, positive, and neutral where reviews are classified. The proposed method is Analysis of different machine learning algorithms with different datasets has made and a comparison shows, SVM performs the best result on used data sets, a clear result in the form of accuracy, precision, recall, and f1 score shows the results against the specific techniques against the dataset.

Impact of Agile Methodology on Software Development Life Cycle

Software engineering strategies had been hired for decades to create software products. The most challenging task for the development of software is to select appropriate software development methodologies. Software developers use agile techniques to reduce the problems faced by the traditional waterfall process. These days, the motivation behind most programming associations is to give programming in a fast time, inside financial plan and changing situations that propelled the conveyance of Agile. The strategy that utilizes iterative expansion and prototyping is generally utilized in an assortment of industry ventures as a lightweight advancement method that could fulfil the alterations of necessities. Short cycles are utilized which can be required for proficient item delivery. In the paper, we become mindful of the impacts that the coordinated strategy has programming improvement strategies with prominence to decent inside the authoritative, efficient, and social system. Coordinated methods are not in every case great, they have a few restrictions too. In this paper, we likewise clarify the estimations of Agile, its points of interest, and its weaknesses.

An Android Based Flight Simulator using VR Technology

For training young pilots. Flight simulators enhance the safety measures, as the risk factor of severe injuries are eliminated since the training is now synthetic. However, flight simulators also require large space, large budget and does have many high end requirements, which are to be met in order to make the simulator respond and perform identical to that of a real aircraft. Flight simulators does have their hardware constraints and because of these limitations, the simulators are not of generic nature that supports different sort of aircrafts. In this paper, the simulator environment is deployed in virtual reality to simulate the similar controls on a stereoscopic environment. Deployment of the simulator is such, that experience of flying an aircraft from cockpit will give a sensational view to the user. Virtual reality is used in learning purpose, as normal person can experience what it will be like, to fly an aircraft

Tourist Guide via Image Processing Techniques

To achieve the goal of identification, image processing and recognition is performed on the actual picture transformation. The amount of information included in an image is enormous because it is a two-dimensional space. Neural network image recognition is a new type of picture recognition technology developed by modern computer innovation. In this paper we have used neural network to implement image-based location identification. Using the image data, we have evaluated our proposed model’s predictive performance. By including more hidden layers in the convolution neural network, it is feasible to improve the network's training speed and reliability by having a large amount of data. However, 80% of the dataset is used for training and the remaining 20% is used for testing in our studies. The preliminary findings have shown that using a neural network to detect photos is both successful and practical. The proposed methods serve as a guide for travelers or tourists who are unfamiliar with a country. They simply need to point the camera at any historical or well-known location to learn more about it.

Comparing Artificial Bees Colony Algorithm and Firefly Algorithm to Achieve Optimization in Route Selection Processing Time in VANETs

In achieving Intelligent Transportation System (ITS), a new trending area in networking is Vehicular Ad-hoc Networks (VANETs). It is a sub branch of Mobile Ad-hoc Networks (MANETs) where all the nodes or devices are interlinked and interconnected wirelessly. The challenges that a VANET faces while communicating within a network are signal fading, routing decision making and connectivity hitch. All these three mentioned problems have already been discussed and well researched in history by using conventional techniques as well as intelligent techniques based on artificial intelligence. Amongst all these three issues we are focusing on mitigating decision making problem for optimal route selection. In order to solve this issue, researchers have found that meta-heuristic intelligent algorithms such as, Artificial Bees Colony (ABC) and Firefly Algorithm (FFA) are more efficient algorithms as compared to traditional approach. In this paper we compared ABC and FFA to check which algorithm runs faster in order to achieve routing decision in lesser time

Used Cars Price Prediction using Machine Learning with Optimal Features

We all are needed the personal vehicle that could help us to travel from home to office and travel to vocations means we need the personal vehicle for traveling for this we purchase the new vehicle or used vehicle this is some time take so much to take decision for purchasing the new one and most difficult decision is to take how to sale the old one that is already we have keep using if we sale and what is best price we can get or gives us more benefits. More over the purchasing power of the customers is low due to the prices of the new cars. There are different methods to predict the price of the car according to market value. Our proposed method helps the both the purchase and seller for to purchase and sale their vehicle and they can predict the best for their vehicle and make their decision good for personal and business. Our proposed model performance shows that the proposed study is productive and efficient. In the proposed study the machine learning algorithm Regression helps in the outperform. Here we use the Statistical test to get the design value of P and get the optimal features and using the linear regression. First, we find the RFE and then apply the statistical test for VIF for the OLS Regression. Prediction results shows the study is efficient and effective.

Engineering Challenges in the Design of Cochlear Implants

Hearing aids such as cochlear implants have been used for a long by both adults and children. In addition, cochlear implants are used by patients who have severe hearing loss either by birth or after an accident. This paper aims to investigate the engineering challenges bounding the design of cochlear implants and present its possible solution to improve the design of implants. First, a detailed introduction of considered implants is given, followed by aspiration and advantages. Numerous engineering challenges in cochlear implants must be addressed, such as selecting and installing electrodes array inside the cochlea, dealing with the problems that occur during speech processing, noise reduction, etc.

Artificial Intelligence Based University Chatbot using Machine Learning

Today the customer support needs 27/7 and the people faced when some issues related to organization they contact the support center and the support centers are people they are sitting to serve the customer care and they need to full fill the requirement of the customer need and demand this should increase the cost of the people setting by day and night for services and organization need to reduce this cost and desire to automate this process. The proposed study will be the replacement for this used in university chatbot for help and support for peoples which are visiting the office this will also decrease the traffic of the admission office some universities are so far away from the city area and people travel a long distance to reach the university for a very ordinary work this will reduce this and allow the office staff to focus on the other productive activities. The University chatbot (UCB) we build the application using the machine learning models that successfully build the model using the machine learning algorithms, DT, RF, SVM, that can response under the domain of the university related help and support and guide the proper way for the use of university website and referee them the proper links and contact to reduce the traffic from physical office visit of the people. The results show that the Random Forest is outperform for the proposed study.