Due to some abnormal changes in genes of cells, enforces cells to divide uncontrollably, due to which tumors are formed, which infiltrates and damages the normal body tissues, and this condition is called "Cancer". Lung cancer is a type of cancer where the infected cells in the lungs multiply rapidly at a high rate. This abnormal growth of cells, which eventually leads to cancer can be identified using modern data analysis. Detecting cancer symptoms at an early stage plays a crucial role for the patients who may suffer later, if not detected. One of the major problems is the increasing fad of smoking tobacco in youngsters. Air pollutants from industries which get inhaled by people are some of the main causes of increasing lung cancer in India. The main focus of this study is to predict lung cancer in different patients using Machine Learning (ML) algorithms such as a random forest classifier(RFC), k-nearest neighbour(KNN), K-means, Support vector machine(SVM), and decision tree classifier(DTC). The key objective of this research is the analysis of different machine learning algorithms based on their performance metrics.
A chatbot is a software used to help to increase user interaction during online conversations between a human and machines. A Discord bot is an AI driven tool in which tasks are automated in your discord server. Using discord bot helps us to grow a community, increase interaction and performance of the discord server. This paper focuses on to creation of a discord chatbot named spiffy which is used in discord server and developed using python, json database structure and discordAPI. The chatbot provides user basic interaction with normal human commands, allowing user to type commands as well as receive the texts. The bot will able to answer the query that is generated by the user.
The most common reason for blindness in adults in developed nations is Diabetic Retinopathy (DR). Currently, diagnosing DR involves an in-depth arduous examination of digital colour fundus pictures of the retina by a qualified practitioner. By looking for lesions connected to the vascular anomalies brought on by the illness, ophthalmologist can recognise diabetic retinopathy. Although this strategy works, it has substantial resource requirements. It has long been understood that a thorough and automated approach of detecting diabetic retinopathy is necessary, and prior initiatives have achieved excellent strides utilising image classification, pattern recognition, and machine learning. This project seeks for automated detection, grading, and segmentation of Diabetic Retinopathy. In our project we aim to improve image segmentation using UNet and to automise the project using Convolutional Neural Networks and VGG16.
The human-based disaster management programme has recently been a source of administrative and ethical concern. Sometimes it can be more harmful than beneficial. In order to take into account the newly developed Internet of Things organization, which is sufficiently evolved to create a network automatically connecting each other and forecasting every function and feature of the flood, there must be less interaction between humans and all such inventions. In this project, a wastewater disposal system is created and put into service to compensate for the losses brought on by urban flooding in metropolitan areas. For the criticality of the wastewater deposit network, the platform consists of real-time cloud computing and Internet-of-Things (IoT) control. In order to meet the demand for incorporating waste water drainage systems in any urban area in order to avoid and stop floods, we designed this architecture, technology, mathematical model, and application. This constructed framework is illustrated through the case study of the Mumbai floods of 2005. If we use this approach, we can prevent more than 40% of the harm and live.
LiFi is a communication technology that enables wireless transmission of data using light. With mobile robots finding more and more indoor applications in hospitals, museums, airports etc., indoor localisation has become all the more essential. This paper aims to demonstrate the functioning of a LiFi based localization system by the means of simulation. The mathematical time series model of NRZ-OOK modulation and the optical power distribution are prepared in MATLAB in order to evaluate the functioning of the proposed system. To validate and test the performance of the same, a white LED of wavelength 550nm is set-up as the transmitter in our system and simulated using the Optisystem software, both with and without the presence of ambient light noise. A maximum speed of 10Gbps with a BER (Bit Error Rate) of 5.15585×10 −11 is achieved for a link range of 1m in ideal conditions. This work also proposes an optimal filtering scheme that provides a high Q factor and a low BER for VLC (Visible Light Communication) systems, even in the presence of ambient light noise.
According to the World Health Organization, there are millions of visually impaired people in the world. This paper is based on the development of a system that provides aid to such people. A pi camera is used to implement the system which is based on the Tesseract OCR (Optical Character Recognition) library of OpenCV in Raspberry pi. OCR library is used to recognize text from the captured image by the pi camera module. This helps to convert the picture of the desired page taken by the camera into respective text. Finally, this text is converted into speech through headphones using the TTS (Text-to-Speech) Engine. A headset is used for hearing the converted speech. The text-to-speech application assists them to detect text from printed documents and avoiding obstructions while traveling hence a blind person can feel not visually impaired.
Future roads will look very different if the concept of Autonomous vehicles would come in existence. This can be achieved by making fully autonomous vehicles by keeping human drivers out of the loop. However, even having such a facility, people worldwide believe that the link between the car and the driver is of utmost importance to a certain extent. So making manual driving a bit easier and having some advantages of an automated vehicle, we proposed an autonomous model in which the driver is allowed to control the vehicle’s lateral and longitudinal motions. An automated vehicle has 6 levels of automation ranging from level 0 to level 5. Level 0: is entirely handled by a human; Level 2: Assisted driving Automation; Level 3: Partial Automation; Level 4: High Automation and 5 being entirely handled by a machine. In our model for "level 3," the Advanced Driving System (ADS) is capable of handling all aspects of driving under some circumstances, but a human driver is still required to be able to maintain control. Hand-gesture controlled Automated Vehicle, can carry out tasks such as line detection, road-end detection and object detection. The hand- gesture controlling can act as a semi-autonomous mode which can be attained with the help of a switch as per the need of the user. This can be done by allowing the user to control the vehicle using an accelerometer sensor connected via a hand glove, helping with the movement of the vehicle. The hand gesture controlled automated vehicle provides a number of benefits, including the ability to manage the speed of the vehicle, reduce the incidence of accidents, and easily make tight turns.
DC-DC converters have played a key role in many applications. Such applications demand high gain without any change in voltage for any changes in line and load. Quadratic Boost Converter (QBC) provides a moderately high voltage gain compared to conventional boost topology. However, stability and closed-loop performance are difficult to achieve because of three RHP zeros. A stability analysis of QBC was conducted in this paper. The design of Type II and Type III controllers for QBC is discussed in this paper. A combination of Type II and Type III controllers is proposed for a stable operation of QBC. Performance is validated and compared with the conventional PI controller.
Visually impaired people find it difficult to study from educational websites, even though they have a lot of knowledge to provide. They are unable to feel confident about using online tools to learn because of their lack of independence. This becomes a problem for almost every student when they have to search through different websites for answers to their doubts. A chatbot is a conversational AI technology that simulates human interaction. It is more comfortable for users to interact with a chatbot if it is voice-enabled. Our proposed solution is a chatbot that is voice-enabled as well as multilingual. It can interact with more than 180 global languages, although, in this paper, we have focused on the Hindi language. It can help visually impaired people as well as normal students, as they can learn by just having a conversation with the voice bot. Our voice bot can teach students many concepts regarding data structures and algorithms. It gives the user a speech-based response received from a generated .mp3 file. For the voice-bot system, which has been trained with more than 70 intents, we have utilized the RASA NLU principle. It has been deployed onto our e-learning web application. The chatbot is compatible with all the languages mentioned in the python translate module. This chatbot recognizes and converts the speech received from the microphone into text and matches with the trained intents information, and accordingly gives the most appropriate answer and converts text-to-speech and presents the text and speaks in the language selected along with multi-intent classifications. We have made a custom pipeline and also applied various policies to it to improve pipeline performance. Nearly all of the queries are correctly answered by the voice bot, which makes communication more effective.
A novel integrated approach for the assessment of the operational efficiency of the electricity distribution utilities in the Indian policy scenario is proposed and implemented. The parametric and non-parametric techniques are used along with the index number approach. The analysis of operational efficiency and its drivers will give insight to utility managers and policymakers to find out the exact cause of poor performance. Therefore, the policy, operating strategies, alternative strategies, and best practices could be framed and altered
Extreme catastrophes like hurricanes, earthquakes and floods, as well as cyber and physical threats made by people, have become worse in recent years. These disasters have badly damaged electrical networks, resulting in prolonged outages and the destruction of substations, transmission systems and power generators. To achieve this goal, new approaches to grid management and operation planning are needed. There needs to be a clear definition of how to measure and evaluate resilience so that planning and operating options can be compared and improved. Several definitions, measurements and ways to judge the strength of a power system have been suggested, but none of them are standard. The integrated energy system (IES) is one possible solution to combat bad weather. This paper gives a thorough and critical analysis of existing definitions, measures and assessment methods, as well as suggestions to make clear definitions, measures and assessment methods for power system resilience that are widely used. The paper has also discussed the resilience metrics for IES.
Online transactions of money are so much comfortable and time saving. Instead, banks continue to use the manual handling of bank checks which is the normal practice. This procedure can take several days for the money to transfer. In this project, we proposed a system that validates the cheque by retrieving details like the Payee name, Amount (in words as well as in digits), date, and bank details using optical character recognition (OCR) it also does verification of the signature on cheque and cross checks it with the image stored in the database. The proposed system uses OpenCV for image processing and segmentation of bank cheque. This system uses EasyOCR for extracting text from the image whereas a custom dataset is used to test this system and get the result. The performance and efficiency are measured on the self-generated dataset of bank cheque.
Developments in 3D display technology have attracted worldwide attention. Holographic technology reconstructs the real object for a user to analyse the movement of a object in a simulated environment. This paper analyses the innovative technology of liquid holograms, a new aspect in the future of technology. A distinctive research method has been used to produce holographic twin of water temperature movement in a bathtub. We have accomplished the invention of holographic twin of a bathtub. This paper provides the replication of liquid into holograms by using technique of holography and the strategies of generating liquid holograms. Proposed technology can be used in many other fields of technology and businesses.
The significance of smart cities is constantly growing as the world’s population is moving towards urban areas in search of new opportunities for their development and the betterment of their future. This rapid influx of migrants has increased the pressure on the services deployment, traffic congestion within the city, prevention of criminal activities, energy usage and waste reduction. This can lead to the impending failure of the management system within the cities, looming with the burden of issues. These events have triggered the remediation of such issues through the development of smart cities projects. In order to obtain a realistic answer to this challenge, several pilot programs have been initiated around the world. Smart city surveillance systems are being designed to make the urban areas smart enough to monitor the changes and activities in their ambient environment. For the handling of such rapidly growing issues, the governments along with their supporting organisations, private organisations, other non-governmental agencies working non-profitable, academics and researchers and the general public of the nations must work collaboratively on innovative ideas with the use of different technological advancements. This paper provides a survey of the various smart city initiatives for the betterment of the living standards of the residents. Various open issues and challenges have been discussed. Solutions proposed in the field, for the remediation of the looming issues, have also been looked upon. Finally, the future perspective in the domain has also been reviewed and the impact of smart city surveillance system into the people’s lives has also been looked upon.
From the past few years, Artificial Intelligence (AI) has shown remarkable progress, and its future is growing day by day. Natural Language Processing (NLP) is an application of AI. A voice assistant utilizes cloud computing to integrate AI and communicate with users in natural language. In households today, millions of devices use voice assistants due to their ease of use. Universities and schools are just starting to use smart speakers with voice assistants. Voice assistants are the greatest innovation in AI that can change people's lives in a significant way. Initially, voice assistants were introduced on smartphones, then they became popular. The idea was widely accepted by all. A voice assistant was initially used in smartphones and laptops, but now it is also found in home automation systems and smart speakers. As devices become smarter, they are interfacing with humans in a language that is easier to understand. Programs based upon desktop voice assistants recognize and respond to human voices via an integrated voice system. We will discuss the main problems and limitations of voice assistants in this paper.
In the coal mining industry, there are several incidents happening and safety is the major issue. Therefore a wireless network connection is focused in this paper which provides real time data to alert the officials about the accident to take necessary actions. Falling rubble on the workers is the leading cause of accidents in the mining industry, so to decrease this we chose an IoT made helmet project as an attempt to help this industry. But, among all these industries, the mining industry is backward among all. So, to bring new inventions within the IoT and the Mining Industry we came up with the concept of SMART HELMETS. This helmet is the life guard for the workers who work deep inside the mines. This prototype consists of ESP8266, accelerometer sensor, gas sensor and a buzzer that can detect the different hazards in the mines.
In the age of information, surveillance systems are needed to be accurate and robust in order to provide exact outcomes. This paper discusses the idea to upgrade the surveillance system of high-profile building complexes by providing a real time access of information of any visitor/guest, using face detection and recognition and also providing the real time information of visitors with the help of augmented reality. The proposed system works on the principle of identification and data retrieval from the database. At first, it registers every visitor and then captures visitor’s face data, followed by this wherever visitor comes in camera range inside campus , it recognizes the visitor’s face based on data retrieval from dataset , further it projects the visitor data at real time as an augmented reality. It has significant applications in the field of security and surveillance especially for high-profile buildings like government offices, confidential complexes and corporate offices etc.
After the recent wave of covid, many companies are yet to shift their focus on recruiting candidates directly through in-campus recruitment. Many companies still do prefer the online way of conducting interviews on platforms like meet, zoom, etc. Even forms are shared to apply to a particular company and many more variable methods. Due to this rising uncertainty, the online recruitment system has started gaining more popularity. However, this procedure presents difficulties for recruiters in managing the flood of applications and maintaining contact with the applicants. Previously, such recruitment systems were inefficient and lacked many parameters like accuracy, not upgraded and not frequently managed. Therefore, there was a need to build a website which is capable of handling all the recruitment related activities. With the help of AI-ML techniques it has become possible to rank students according to the requirements of the companies. We discuss the features and research gaps for each method in applying Machine learning and other techniques for enhancing the recruitment process.
Generally, air pollution refers to the exertion of various substances into the atmosphere that cause discomfort, disease, and death in humans, animals, and the environment. In most developing countries, air pollution reduction and sustainable development are common challenges. With the drastic urbanization and increasing megacities and concrete jungle, new types of research and services are needed. Casualties due to air pollution accidents which fall under environmental pollution accidents have increased since there is growth in chemical industrial park because of the development in economy. There is a necessity to examine the relation between megacities and air pollution, their local climates, and the impacts on global climate as a result of the day-to-day increasing number of people living in those areas. The studied papers mainly focused on nitrogen oxides (NO x ) and particulate matter (PM) in various dimensions whereas some observed the volatile organic compounds (VOCs) and ground level ozone (O 3 ). This paper presents a review study on various AQM systems and also presents various parameters like data storage, power source, visualization technologies, processing and sensors used in the researches.
The application of artificial intelligence in medicine is a developing technology that has the potential to aid in accurate diagnosis and mass screening. Complex associations can be built using input data to conduct pattern recognition, which is a significant step in the development of complex computing. An expanding issue is diabetic retinopathy. Retinopathy, a condition that poses a threat to vision, can be lessened with early detection and prompt treatment. For patients and ophthalmologists alike, any instrument that may speed up the screening process for this illness and reduce the need for trained personnel in the process would likely be beneficial.
