Smart Computing- Book ISBN- 978-81-953658-1-4

Authors:-Shubham Mahajan, Kaushal Maru, Akshar Patel, Brijesh Asodariya, Utpal Patel 

Abstract :-IoT Technology is bringing a revolution in many fields of human endeavour. By making everything smart and creating a space of automation between devices to work intelligently, Iot based devices are transforming our working methods by making them more efficient and reliable. When used in agriculture, this technology can give many benefits to the people involved in farming activities. Smart farming is enabled by using such automation based IoT devices in agriculture. In order to increase productivity in farms, certain parameters to be considered include soil characteristics like moisture, temperature, humidity, etc., which help a farmer make decisions based on specific values. Various sensors deployed in the field measure these parameters based on which the Arduino Board microcontroller takes decisions to provide different functionalities like irrigation, smoke and intruder detection, etc. Farmers are provided on time and accurate information through web pages. Crop Suggestion Module in these systems is an additional benefit for the farmer.

Keywords: - IOT (Internet of Things), Agriculture, Arduino board, Sensors, DHT11, PIR Sensor, Automation, Irrigation

Authors:-Bharat Tank, S.S.P.M. Sharma, Sanjay Hadiya

Abstract :-Technology is the most crucial thing for healthcare, not only for sensing the parameter but also for communication, recording, and display devices. It is essential to measure various medical parameters.  Hence the latest trend in healthcare parameter measurement and communication method using IOT is adopted. Internet of things catalyzes healthcare and plays a prominent role in a wide range of healthcare applications.   In this project, the Arduino Nano microcontroller is used as a gateway to communicate to various sensors such as EMG, MAX30100 and ADXL335. The microcontroller picks the data from the multiple sensors and shows a result on LCD or sends the data on the website with the help of the WIFI module (ESP8266). The controller is also connected with a buzzer and LED to alert a caretaker. Caretaker and doctor can access that data on a website ex. thingspeak. This system consumes low power and is easy to set up.

Keywords: - EMG, MX30100, ADXl335, Arduino Nano, IOT

Authors:-  Dércio Anselmo Bobo, Ankita Gandhi, Jay Gandhi

Abstract :-On a daily basis, people can experience a moment of stress for different reasons. It can become dangerous to mental health when this moment of stress is too frequent. Previous papers have laboratory environment, which can lead to bias output because of the ground truth. This paper studies the possibility of detecting if a person is under stress or no, using machine learning classification algorithms and an unobtrusive wearable device where the person will use it on a daily basis, and the data will be collected and sent to our system. We can use various physiological signals to detect stress, such as Electrocardiogram (ECG), Galvanic Skin Response (GSR), and Blood Volume (BV). This physiological signal is used as input in different machine learning techniques to measure a person's stress. Most papers show that support vector machines have the best average classification. Applying the support vector machine, KNN and random forest were able to compare the three algorithms, and the SVM recorded the highest accuracy.indicated that we can use physiological signals to detect if a person is under stress or not. However, researchers have conducted experiments in the traditional method in a 

Keywords: - Stress Detection, Machine Learning (ML), Human-computer Interaction (HCI), Wearable Devices, Physiological Signals

Authors:- Meet Patel, Manshi Shah

Abstract :-During the last decades, Android with IoT app development became an area of concern. IoT is an ongoing platform for all upcoming technology in the IT world. Humanity is now becoming smarter with the new arrival of technology in the field of Science and Technology. Security-related appliances are now a crucial aspect. IoT is the server-client environment that allows data communication between all the devices connected with a network. Gas leaks can be hazardous to health and the environment. Leaks of natural gas into the atmosphere are especially harmful due to their global warming potential. Thus it is necessary to have a high-level mechanism to detect and prevent methane leak, especially for home applications. Smart Trolley for LPG gas monitoring and Leakage System is the best solution that detects methane leakage within a fraction of seconds. Along with fire detection, the trolley is the equipment for data reading.

Keywords: - HX711, Flame Sensor, Gas Sensor, Firebase Database, Security, Home Appliance, Load Cell, Arduino, ESP8266

Authors:- Amita Contractor, Rutvik Mehta, Sumitra Menaria

Abstract :-Phishing attack detection is one of the most challenging challenges currently facing online social network users. This study presents a different phishing detection technique to identify gaps and offer solutions to current phishing detection problems. As shown, no techniques have been proposed to address phishing, including Machine Learning (ML) based, Nature Inspired (NI) based, heuristic, blacklist based and whitelist based techniques. However, the ML-based techniques give more accuracy in terms of classification.ML algorithms cannot deal with big datasets; hence they can be combined with NI algorithms to build fast and improved models for phishing detection. Although some surveys on phishing detection techniques exist, very few focused on ML-based and Ni-based techniques. Therefore, this study presents ML-based and NI-based phishing detection techniques. The survey reveals the various shortcomings of phishing detection techniques, including limited dataset, use of third-party services (age of the domain, search engine query, etc.), use of small feature set, use of classification rules, use of blacklist and whitelist, etc. There is an obvious need for efficient and reliable solutions for phishing detection.

Keywords: - Phishing detection; Phishing website; Phishing email; Machine learning; Nature-inspired techniques; Social engineering

 

Authors:- Shefali Rana, Jay Gandhi, Abhijitsinh Parmar

Abstract :-Device-to-device (D2D) communication is expected to play a significant role shortly as it promises ultra-low latency for communication among users. With the advanced communication technology, the number of users and applications are increasing exponentially and leading towards the shortage of resources and an increase in power consumptions, demand for higher data rates. The data traffic on the base station also increases with the number of users. To fulfill the needs of cellular users in 5G, D2D communication considered a famous solution. However, there are several challenges associated with D2D communication. In this paper, various methods for resource management for D2D communication are discussed extensively. Other important aspects such as security and interference management are taken into consideration. In this paper, we discuss the key characteristics of D2D communication and its usage scenarios, specialised features, and areas of effective research. Finally, we conclude with the potential future research directions.

Keywords: - Device to Device Communication (D2D), Security, Interference Management, Resource Management, Latency, 5G.

Authors:- Banshri Modhiya, Poonam Faldu, Gauri Yadav

Abstract :-A chatbot is a computer application that interacts with users conversing in a natural language in a similar way to imitate a human travel agent. Successful implementation of a chatbot system can analyze user preferences and predict collective intelligence. In most cases, it can provide better user-centric recommendations. Hence, the chatbot is becoming an integral part of future consumer services. This paper is an implementation of our proposed work travel Chatbot on Goa visit. Example: If anyone wants to visit Goa, how this travel Chatbot minimizes the user efforts, all the information related to Goa including hotels to stay, food, bookings, greatest offers, can all the bookings can be made using 100% safe sites that will not be harmful to user's device and privacy concerns.

Keywords: - Chatbot, Verified, Goa visit, Safe transaction

Authors:- Warisahmed Nashrullah Bunglawala

Abstract :-In this era of technology, one of the most trending and well-known technology is Artificial Intelligence. Top tech industries like Amazon, Google, Microsoft and Apple, and small scale businesses have been acquiring this technology quickly. Also, today having a website or Web App is mandatory for all the businesses in the market to provide fluency and easy accessibility. Due to this, Web Development is also growing at an unpredictable rate. Everyone wants secure and scalable Web Apps or websites. And the desire of users for enhanced experience along with the customized content is ever-growing. The user is searching for smart feature-packed Web Applications with highly personalized UX. So here come the questions that, can we relate this two highly growing and must needed technology? If yes, then how AI will affect Web Development? Or how AI will contribute to Web Development? To answer this question, I have tried to cover all aspects like introductions to AI and Web Development, in what way AI features can be used while building a website or web apps, and how they contribute to each other; with some detailed analysis that includes what the positive and negative impacts of AI in Web Development are. Also, I will be answering the question about what is the future of AI in Web Development.

Keywords: - Artificial Intelligence (AI), Web Development, Machine Learning (ML), Deep Learning, Web Applications (Web Apps), Web Sites

Authors:- Jigisha Patel, Brijesh Vala, Makhduma Saiyad

Abstract :-Since ancient times, agriculture is one of the most critical occupations in India. India is considered the world’s second-largest in outputs. Agriculture is the most critical sector and plays a vital role in the Indian economy, which contributes around 17% of total GDP and 60% of the entire workforce, according to the assessment of 2018. Different seasonal, economic and biological patterns affect crop production, but sudden changes in these patterns lead to a significant loss to farmers. Crop yield prediction is a fundamental issue in agriculture. By analysing various relevant factors, like location, crop type, PH value of soil, type of soil, percentage of nutrients like Phosphorous (P), Nitrogen(N), Potassium(K), humidity, temperature and amount of rainfall, we can forecast crop yield using Machine Learning. Different approaches have been used to produce models and interpret final effects, such as Regression, K-means, Decision Trees, Random Forests, Support Vector Machines, Bayesian Networks, Artificial Neural Networks, etc. Such approaches help analyse the environment, soil and water processes heavily involved in crop growth and precision farming. An overview of some of the latest supervised and unsupervised machine learning models linked to crop yield in literature is highlighted in this survey paper.

Keywords: - Crop yield Prediction, Machine Learning, Agriculture, Classification, Regression

Authors:-  Sakshi Rane

Abstract :-Smart light is one of the best possible ways to save electricity wasted due to the unnecessary use of street lights at night when there is no passage of vehicles at night on the streets. Smart street lights are being installed as a solution to this problem, which turns on only when there is a passage of vehicles or trespassers. This can be done by installing sensors that would be programmed so that when they sense any vehicle or trespasser, the street lights will be turned on simultaneously. Moreover, the smart light system in this paper behaves like usual street lights that turn on all night. The ideal behaviour of the smart street light system is that no one needs to the turn-off of street lights at night. Whenever someone sees street lights, they turn them on, and whenever no one sees street lights at night, they turn them off. The smart street light system consists of LED lights, brightness sensors and motion sensors. The light turns on before pedestrians and vehicles come and turn off or reduce brightness when there is no one. It will be difficult for pedestrians and vehicles to distinguish our smart street lights and the conventional street lights because our streetlights all turn on before they come.

Keywords: - Arduino UNO, PIR Sensor, Automatic Control, Accelerated Use of LED Lights, LDR Sensors, Central Monitoring Station, and Interconnecting Cables

Authaors:- Ankit Jasoliya, Nikunj Bhavsar, Apurva Keskar

Abstract :-Ad-hoc networks have lots of challenges than traditional networks. It has challenges like infrastructure less and self-organizing networks. They don't have any fixed infrastructure. In MANETS, there will be no centralized authority to manage the network. Nodes have to rely on other nodes to keep the network connected. In MANET, routing is a critical task due to the highly dynamic environment. Later on, many routing protocols have been proposed for mobile ad hoc networks and prominent among them are DSR, AODV, TORA and NCPR. This research paper provides an overview of these protocols by presenting their limitations, benefits, functionality and characteristics and then makes their comparative analysis to analyze their performance.

Keywords: - A AODV, DSR, mobile ad hoc networks (MANETs), topology control algorithm, topology control

Authors:- Urvashi Parmar, Yoothika Patel, Mosam Patel

Abstract :-Air pollution worldwide is a growing threat to human health and the natural environment. The earth's atmosphere is full of air which contains gases such as Nitrogen, Oxygen, Carbon Monoxide and traces of some rare elements. Humans need an atmosphere of air free from contaminants, a condition crucial for human life and health. Any change in the natural composition of air may cause grave harm to life forms on earth. Air pollution is the presence of one or more contaminants in the atmosphere, such as gases in a quantity that can harm humans, animals and plants. This review focuses on the research done in data mining and machine learning for predicting and detecting the quality of air and air pollution hotspots.

Keywords: - Air pollution, Hotspot area, Machine learning, Data mining

Authors:- Aniruddh Patel, Rishi Shah, Parth Vyas, Utsav Patel, Kiran Parmar

Abstract :-Mobile technologies offer the ability to incorporate field support engineers effortlessly into business systems [1], resulting in innovative ways of engineer-to-customer engagement. We explain the findings of our survey in this paper on the criteria of using a mobile application in field service [4][14] and complaint management. After a summary of the problems facing these types of apps and an overview of the design of the service management system used, we present the findings of our usability report.

Keywords: - Mobile application, Field service, B2B Business, CIC

Authors:- Amul Ghodasara, Manish Jangid, Hrishikesh Ghadhesaria, Harshil Dungrani, Brijesh Vala, Ravi Parikh

Abstract :-The main goal of this project is to design an accurate solar tracker and share information through IoT. In this work, sensing of the sun position carried out in two stages, primary and secondary. Preliminary stage or indirect sensing performed via sun-earth relationship as a coarse adjustment and second stage or direct sensing performed via a set of LDR sensors as output tuning to trims the azimuth and altitude angles. If the weather is cloudy or dusty, the tracking system uses primary stage or sun-earth geometrical relationships only to identify the location of the sun; so the system tracks the position of the sun regardless of the weather condition. The energy extracted from photovoltaic (PV) or any solar collector depends on solar irradiance. For maximum energy extraction from the sun, the solar collector panel should always be normal to the incident radiation. Solar trackers move the solar collector to follow the sun path and keep the solar collector's orientation at an optimal tilt angle. Solar tracking system improves the energy efficiency of photovoltaic (PV) panels substantially. The project is divided into two parts; hardware and software. Hardware parts generally composed of solar panels, two motors, an LDR sensor module, temperature sensor, humidity sensor and electronic circuit. The software part represents the thinking behaviour of the system. That is how the system acts under several weather conditions. This paper designs and develops an automatic solar tracking system using Light Dependent Resistor (LDR) and DC motors on a mechanical structure with gear arrangement. It is implemented through an Arduino UNO controller based on Sun-Earth Geometry. The results indicated that the automatic solar tracking system is more reliable and efficient than a fixed one.

Keywords: - Arduino UNO, LDR, Photovoltaic (PV) panel, Solar Tracking System, Humidity Sensor, Temperature Sensor, Omni phobic material, IOT 

Authors:- Parth P. Sharma, Ankit Gupta, Hardik Parmar, Devang Patidar, Krupali Rana, Devangini Dave

Abstract :-In today's modern world everyone is so busy in their day to day life and in that hectic life sometime people tend to eat unhealthy fast food or food that has less nutritious value, everyone from a small business man to some owner of million-dollar company or a common man, everyone needs to eat food. Food is an essential for all human beings. This year pandemic of covid-19 has shown us eating healthy food is a must to keep ourselves fit. There is no food that can cure the virus of course but eating nutritious diet can boost your immune system and helps you keep fit and active. Proper food can give you some long-term life benefits and protect you from any disease. Eating healthy diet is not limiting your food, or staying away or depriving yourself from the food that you love. Rather, it about enjoying what you eat, feeling great about it, having more energy, and boosting your mood. If you go to some nutrition expert then they will definitely suggest certain food that’s healthy for you and other will recommend something else. Our idea is to make you aware of what you are eating and what your body is getting from that. Eating food that is as close as possible to the way nature made it can make a huge difference to the way you think, look, and feel. By using these simple tips, you can cut through the confusion and learn how to create and stick to a tasty, varied, and nutritious diet that is as good for your mind as it is for your body. Few changes towards a healthy food diet in our routine can do wonders. A better and easy is to make a few small changes at a time. Keeping your goals modest can help you achieve more in the long term without feeling deprived or over whelmed by a major diet overhaul.

Think of planning a healthy diet as a number of small, manageable steps like adding a salad to your diet once a day or some healthy juice or eating an apple in the morning.

As your small changes become habit, you can continue to add more healthy choices. Our application focuses on providing the best possible idea/ Recipes to the user to fulfill their need so feasting tasting, healthy and nutritious diet.

Keywords: - Food, Recipe recommendation, Healthy food, Food Recipe Recommendation System

Authors:- Barot Kajal, Brijesh Vala, Warish Patel

Abstract  :-These days hardly anyone goes to the polls because of their tight schedule. There are numerous reasons, and some may need to go to the polls, we may need to wait in long lines, many may be drained due to their tight schedules. So we have created a web-based voting system. But this system has some drawbacks. Phishing attackers legally obtain passwords from clients and they go to critical sites with the correct secret passwords. Consider a web-based voting system for corporate organizations, voting once a year to elect a president, secretary, or critical manager. In the current system, every voter has to gather at one place on the Election Day and cast their vote. In this method, we are using another scheme which is known as visual cryptography. In this plan, we are using visual data for security. Here we are dividing the unique picture into two into four which are placed in separate databases. At whatever point these two offers are intertwined with each other, we get the original picture. When we get the original picture, it is used as a secret password. This system is very helpful and acceptable for online remote voting. This system is an electronic application so that the web can evaluate it through any valid personal space on the planet.

Keywords: - Verification, Online voting, Visual Cryptography, Phishing attack, Cyber security, Privacy, Secret password  

Authors:-Anjali J. Rajput, Pratik K. Patel, Jaimeel Shah

Abstract :- In  a democratic country like India (which is the largest democracy in the world), voting plays a significant role in selecting government officials and showing our opinion on how the governing body to be formed. Blockchain platforms are already available, and many companies have already begun applying blockchains to their business. It is used in industry, but it can also be applied as a service and make voting more accessible. Online voting is an alternative to the old paper ballot system and the currently popular electronic voting machines (EVM). An electronic voting portal should offer security and integrity and the transparency of votes and voters' privacy. Therefore, NRIs and adult internet users can cast their ballots in a matter of seconds despite their location on the day of the election. This will be easy and more secure. In the current system, there's a high risk of false votes and damage to property. People don't want to stand in enormous queues and wait for a long time. Also, people who conduct the election have to follow a completely different procedure for voting, which takes more time, and there's no transparency. The paper also presents the state of the art of some blockchain frameworks for e-voting. This paper presents a literature review of the techniques used to tackle voting challenges.

Keywords: - Blockchain, E-voting system, P2P network, Smart Contract, Ethereum, Decentralised, High security, Solidity, Truffle

 

 

Authors:- Harsh Teckchandani, Krishna Patel, Michael Enbibel

Abstract :-Music is the mirror of one's emotion. In simple words, we can say that music relates to a person's state of emotion or mood. We observe that some new technology and new methods are arising every day, and competing to this, we have proposed a music player based on the user's emotion through facial expression. Emotion can be recognized from a person's face easily by others. What if we can implement this method (i.e. emotion detection) on a machine?. We have developed an application that detects emotion through the machine's webcam and displays the set of songs commonly said as playlists based on emotion. Here, in this paper, we have used CNN classifier for neural network model and OpenCV to detect faces and train model to detect emotion.

Keywords: - Machine Learning, Image processing, OpenCV, Tensor Flow, Tkinter, HAAR cascade, WAMP server, MySQL

Authors:- Brijesh Vala, Parth Patidar, Rishabh Gupta, Meet Javiya, Atufa Faruqui

Abstract :-Notice Boards are playing a vital role in the day to day life. By replacing conventional analogue type notice boards with android controlled digital notice boards, we can display text, videos, and notices easily and efficiently. Here the admin can manage the notice board through his android app. So information can be sent from any point in the world and can be displayed in seconds. Android is used to send information, and Raspberry Pi connected to the internet at the reviving side. Moreover, we have added a Virtual assistant, which can interact with the notice board. The virtual assistant will hear some common sentences and will display the output accordingly.

Keywords: - Internet of Things (IoT), Virtual Assistant (V.A.), Raspberry PI (RPI)

Authors:- Praveen Kumar, Gokul Modi, Surendra Singh, Rohan Choksey, Bipin Chaudhary

Abstract :-Ride-sharing (RS) has great value in saving energy and alleviating traffic pressure. Existing studies can be improved for better efficiency. Therefore, we propose a new ride-sharing model, where each driver has a requirement that if the driver shares a ride with a rider, the shared route percentage exceeds the expected rate of the driver. Customers are both price and delay-sensitive, and drivers are strategic and self-scheduling. We prove that optimizing the matching decisions have a first-order effect on the system performance. We show that fixing the matching decisions and optimizing only the pricing decisions does not generally maximize matchings.

Similarly, we show that fixing the pricing decisions and optimizing only the matching decisions is not optimal in general. Finally, we show that optimizing in only one dimension (either pricing or matching) has no benefit to the firm under some conditions. In contrast, joint pricing and matching optimization can lead to a significant performance increase.

Keywords: - Vehicles, Roads, Real-time ride-sharing, Machine Learning, Recommender System, Dynamic Pricing.

Authors:- Amit Singh, Mayank Shukla, Abhishek Yadav, Nirali Bhaliya

Abstract :-Plant Identification of the plant ailments is the key to stopping the losses in the yield and extent of the agricultural product. The research of the plant ailments implies the research of visually observable patterns viewed on the plant. Health monitoring and ailment detection on the plant is very imperative for sustainable agriculture. It is very hard to screen the plant illnesses manually. It requires a first-rate quantity of work, expertise in plant diseases and additionally requires immoderate processing time. Hence, image processing is used for the detection of plant diseases. Plant Disease Identification includes photo acquisition, picture pre-processing, picture segmentation, characteristic extraction and classification. In our proposed work, AlexNet, which is used as a feature extractor, plays a very crucial role in helping to classify plant diseases. We have proposed an image-processing based technique to identify plant diseases. This method takes an image of the affected plant disease as input. It will extract the key features using filters, and extracted features are then compared with the trained model (contains datasets of sample images) to detect the type of plant disease. Our Proposed work is simple, quick, and does not require any costly equipment.

Keywords: - Image Processing, AlexNet, Skin diseases, Feature Extraction

Authors:- Vraj Patel, Meet Soni, Janvi Patel

Abstract :-Rapid progress in digital data acquisition techniques have led to huge volume of data. More than 80 percent of today’s data is composed of unstructured or semi-structured data. The recovery of similar patterns and trends to see the text data from huge volume of data is a big issue. Text mining is a process of extracting interesting and nontrivial patterns from huge amount of text documents. There lie many techniques and tools to mine the text documents and discover the information for future and process in decision making. The choice of selecting the right and appropriate text mining technique helps to recover the speed and slows the time and effort required to get valuable information. This paper briefly discusses and analyzes the text mining techniques and their applications. With the advancement of technology, more and more data is available in digital form. Among which, most of the data (approx. 85%) is in unstructured textual form. Thus, it has become essential to build better techniques and algorithms to get useful and interesting data from the large amount of textual data. Hence, the field of information extraction and text mining became popular areas of research, to get interesting and needful information

Keywords: - Text Classification, Book Classification, K-Nearest Neighbor, Support Vector Machine, Naïve-Bayes, Convolutional Neural Network

Authors:- Aman Pant, Yuvraj Goyal, Krish Panchani, Tushar Parmar, Prashant Sahatiya

Abstract :-Maintaining the attendance record with day to day activities is a challenging task. The conventional method of calling each student's name is time-consuming, and there is always a chance of proxy attendance. The following system is based on face recognition to maintain the attendance record of students. The daily attendance of students is recorded subject-wise, which is stored already by the administrator. As the corresponding subject arrives, the system automatically starts taking snaps and applying face detection and recognition technique to the given image. They recognise students are marked as present and their attendance update with corresponding time and subject id. After comparing them with the reference image stored in a database, we have used modified LBPH (Linear Binary Pattern histogram) to detect the faces in images. The attendance sheet will keep in the CSV. After that sheet matches the timetable, and a message will be sent to the faculty.

Keywords: - Modified LBPH(Linear binary pattern histogram), Image processing, Face recognition, CSV file,  Database.