Browsing by Author "Athavani, Shahin"

Now showing 1 - 12 of 12
  • No Thumbnail Available
    Item
    Animal detection and classification
    (AIKTC, 2022-05) Athavani, Shahin; Khan, Amaan Ahmad (18ET09); Shaikh, Afridi Anwar Ali (18ET39); Shaikh, Saif Hisamuddin (18ET45)
    According to UN report on biodiversity which says that there are 1 million species are at risk of extinction. In this project , we will be implementing the use of Deep learning algorithms to detect animal and take necessary actions to save them. The proposed system in this project is a image based animal detection system based on Faster R-CNN. The project will involve the use of various resources for implementation , such as : Python , CNN , OpenCV , YOLOv3 , Google Colab , Numpy , Pandas
  • No Thumbnail Available
    Item
    Coal mine monitoring system using Zigbee
    (AIKTC, 2018-05) Athavani, Shahin; Khan, Asif Ali (11ET21); Shaikh, Mohd. Zaid (11ET54); Shaikh, Tajammul (11ET57); Khan, Ibrahim A. (13ET74)
    Today safety of miners is a major challenge. Miner’s health and life is vulnerable to several critical issues, which includes not only the working environment, but also the after effect of it. Mining activities release harmful and toxic gases in turn exposing the associated workers into the danger of survival. This puts a lot of pressure on the mining industry. To increase the productivity and reduce the cost of mining along with consideration of the safety of workers, an innovative approach is required. Miner’s health is in danger mainly because of the toxic gases which are very often released in underground mines. These gases cannot be detected easily by human senses. This project investigates the presence of toxic gases in critical regions and their effects on miners. A real time monitoring system using wireless sensor network, which includes multiple sensors, is developed. This system monitors surrounding environmental parameters such as temperature, humidity and multiple toxic gases. This system also provides an early warning, which will be helpful to all miners present inside the mine to save their life before any casualty occurs. The system uses ZigBee technology to establish wireless sensor network. It is wireless networking standard IEEE 802.15.4, which is suitable for operation in harsh environment.
  • No Thumbnail Available
    Item
    Developing an user-friendly online shopping web-site
    (AIKTC, 2022-05) Athavani, Shahin; Alvi, Azeem Rais (18ET08); Molawade, Rohit (18ET30); Choudhry, Darshan (19DET06); Shirsat, Aniket (18ET10)
    This case provides a real-world semester long project-oriented case study for students enrolled in an electronic commerce course that has a significant development component. The case provides the technical framework in the form of functional requirements for students to design and build a fully functional transaction processing e-commerce Web site over the course of a semester based on the company, products and/or services, content, and graphic images they choose. The case is divided into three assignments. The first assignment is a basic e-commerce Web site that emphasizes site layout, navigation, text formatting, inserting graphics, and the content necessary to market products and services online. Additional complexity is added in the second assignment, an enhanced e-commerce Web site. In this assignment students will create their own graphics images, menus, and image maps, use JavaScript to create image rollovers and image swaps, dynamically generate Web pages based on the contents of a database, and use a form to send data to an email address. The third assignment is a full-fledged transaction processing e-commerce Web site with a virtual shopping cart and checkout processing procedures. The case can to be used in a course where the students have little or no prior programming or relational database experience. The case was written so that the creation of the student's e-commerce Web site is not dependent upon the student's e-commerce development software, graphics tool set, Web server, Web programming environment, or relational database management system. Teaching notes containing suggested instructions, possible development environments, Web server configurations hints, individual assignment objectives, and a sample solution to the final assignment are provided.
  • No Thumbnail Available
    Item
    Digital image watermarking in transform domian
    (AIKTC, 2017-05) Athavani, Shahin; Malim, Sameer (13ET31)
    Visual Cryptographic methods are not sufficient to solve all image security related issues. Watermarking is the art of hiding secret image in ways that prevent the detection of hidden images. Multimedia documents are very easy to copy and distribute in an illicit manner. Copyright labelling is a process that may help to reduce their illicit copying. If this document is copied the copy will also contain the label. This label (or watermark) should be robust enough to withstand normal image processing activities (like image compression, transforming to different format) that do not significantly alter the image appearance. In fractal image compression the encoding step is computationally expensive, because every range block must be compared to all domain blocks in the codebook to find the best-matched one during the coding procedure. In this paper, a fast fractal encoding algorithm is proposed. Simulation results show that the runtime of the proposed algorithm is reduced greatly compared to the existing methods. At the same time, the new algorithm also achieved high compression ratio.
  • No Thumbnail Available
    Item
    E-healthcare system using ML and IOT
    (AIKTC, 2022-05) Athavani, Shahin; Kotian, Tanushree Prabhakar (18ET02); Mhatre, Manasi Mahendra (18ET03); Sayed, Salahuddin (18ET36)
    Health definitely has been a measure criterion during the last two year particularly due to pandemic. An idea of immediate assistance is like boon for one and all. Smart health monitoring system is one way of early analysis of your current health state to prevent it for further complications. It checks basic concepts like pulse acquisition module, body temperature acquisition module, heart rate acquisition module, and blood pressure acquisition module, etc. It not only reduces the health care cost but also make efficient use of the time period by reduce visit to physician office, hospitalizations, and diagnostic testing procedure. Health monitoring systems have rapidly evolved during the past two decades and have the potential to change the way health care is currently delivered. Although smart health monitoring systems automate patient monitoring tasks and, thereby improve the patient workflow management, their efficiency in clinical settings is still debatable. This project presents a review of smart health monitoring systems and an overview of their design and modelling.
  • No Thumbnail Available
    Item
    Fire extinguisher using sound waves
    (AIKTC, 2019-05) Athavani, Shahin
    The fire extinguishing techniques used nowadays are having various drawbacks. The need for new fire extinguishing techniques is very important as fire accidents causes damages. This project demonstrates an idea of a developing device which can extinguish fire using sound. Traditional fire extinguishers, such as chemical foam or water, are used successfully but pose the threat of severely damaging indoor equipment, whereas an acoustic wave fire extinguisher would protect them from further damage caused by the fire. The low frequency acoustic waves produced from a subwoofer tend to extinguish the flames. This project aims to analyze the effect of different frequencies of sound wave on flames and also to study the behavior of acoustic wave propagation in the collimator and surrounding environment. To find the range of frequencies within which fire extinguishes. Three different sources of flames were used with three different state of fuel (solid, liquid and gas). The converged collimator used to increase the air velocity output as compared to an ordinary collimator design. The variation of high and low pressure which is then coupled with high flow air velocity, causes disturbances in air-fuel ratio at the flame boundary, is one of the reason leading to flame extinction. In this project, the frequency range needed to suppress the flames is in between 30 to 95 Hz. By hitting fire with the low-frequency sound waves in the 30 to 60 hertz range, the device separates oxygen from fuel. The pressure wave is going back and forth, and that agitates where the air is. That specific space is enough to keep the fire from reigniting.
  • No Thumbnail Available
    Item
    House price prediction
    (AIKTC, 2022-05) Athavani, Shahin; Shaikh, Meraj Muzammil(18ET40); Shaikh, Rahmat Ali(16ET25); Ansari, Raisuddin(19DET05); Khan, Adil(17ET21)
    Machine learning plays a major role from past years in image detection, spam reorganization, normal speech command, product recommendation and medical diagnosis. Present machine learning algorithm helps us in enhancing security alerts, ensuring public safety and improve medical enhancements. Machine learning system also provides better customer service and safer automobile systems. We create a housing cost prediction model in view of machine learning algorithm models for example, XGBoost, Linear regression and neural system on look at their order precision execution. We in that point recommend a housing cost prediction model to support a house vender or a real estate agent for better information based on the valuation of house. Those examinations exhibit that Linear regression algorithm, in view of accuracy, reliably outperforms alternate models in the execution of housing cost prediction.
  • No Thumbnail Available
    Item
    Image fusion using DWT for medical applications
    (AIKTC, 2019-05) Athavani, Shahin; Magar, Mohini (15ET04); Phadtare, Rohini (14ET05); Shah, Shama (15ET07); Sayyed, Alisha (15ET06)
    Medical image fusion is the process of registering and combining mul- tiple images from single or multiple imaging modalities to improve the imaging quality and reduce randomness and redundancy in order to in- crease the clinical applicability of medical images for diagnosis and assess- ment of medical problems. Multimodal medical image fusion algorithms and devices have shown notable achievements in improving clinical accu- racy of decisions based on medical images. The domain where image fusion is readily used nowadays is in medical diagnostics to fuse medical images such as CT(Computed Tomography),MRI(Magnetic Resonance Imaging). This project aims to present a new algorithm to improve the quality of mul- timodality medical image fusion using Discrete Wavelet Transform (DWT) approach Discrete Wavelet transform has been implemented using di erent fusion techniques including pixel averaging, maximum, minimum methods for medical image fusiontion technique is applied in detecting the type of leaf disease. The experimental results show that the proposed algorithms give watermarked images with good visual quality and survival to number of image attacks such as salt and pepper noise, Gaussian noise, speckle noise, median ltering, cropping, rotation, translation.
  • No Thumbnail Available
    Item
    Improved spam detection in social network using machine learning
    (AIKTC, 2020-05) Athavani, Shahin; Shaikh, Owais (17DET36); Shaikh, Arshinaaz (17DET61); Kazi, Adil (17DET41)
    The large use of social media has tremendous impact on our society, culture, business with potentially positive and negative effects. Now-a-days, due to the increase in use of online social networks, the fake news for various commercial and political purposes has been emerging in large numbers and widely spread in the online world. The existing systems are not efficient in giving a precise statistical rating for any given news. Also, the restrictions on input and category of news make it less varied. This paper develops a method for automating fake news detection for various events. We are building a classifier that can predict whether a piece of news is fake based on data sources, thereby approaching the problem from a purely NLP perspective.
  • No Thumbnail Available
    Item
    Vehicle tracking system using GPS and GSM technology
    (AIKTC, 2017-05) Athavani, Shahin; Kaskar, Saif(14DET79); Shaikh, Junaid(14DET110); Syed, Riyayat (14DET105); Rawal, Nabeel (14DET102)
    Vehicle tracking system uses GPS and GSM to track and provide complete location information to user over mobile phone. This project gives minute by minute update about vehicle location by sending SMS through GSM modem. This SMS contain longitude and latitude of the Location of vehicle. Microcontroller is the central processing unit CPU of our project. Arduino gets the coordinates from GPS modem and then it send this information to the user in Text SMS. GSM modem is used to send this information via SMS will be sent to the owner of the vehicle.
  • No Thumbnail Available
    Item
    Water quality monitoring and control in IoT
    (AIKTC, 2019-05) Athavani, Shahin; Ansari, Sahil (16DET76); Khan, Tehrina (16DET98); Khan, Kulna (16DET92); Khan, Afzal (16DET90)
    Water adds fuel to our life.No life exist without water.Traditionally for testing and controlling water qualities it was send in the laboratories which was quiet time consuming.To ensure the safe supply of drinking water the quality should be monitored in real time,for that purpose new approach IOT (Internet of Things) based water quality monitoring has been proposed. The Internet of Things (IoT) has the potential to revolutionize the water industry, as more of its technology is connected to the web. In the proposed system water quality parameters are measured by different sensors such as pH, turbidity and temperature for communicating data onto a platform. The measured values from the sensors can be processed by the core controller and if the water is being detected as dirty then the particular parameters are being controlled for making the water safe for drinking purposes.
  • No Thumbnail Available
    Item
    Weapon detection and classification using CNN
    (AIKTC, 2022-05) Athavani, Shahin; Chaudhary, Mohammed Abid (18ET28); Sayed, Abu Sufiyan (18ET34); Shaikh, Mohd Danish (18ET43)
    Gun violence in a lot of areas remains stubbornly high. Therefore, limiting gun violence has been a priority in recent years. In this presentation, we will be implementing the use of Deep learning algorithms to detect any firearms / weapons in real time, to improve response times and reduce potential harm. The increase of video surveillance in public spaces, and the proliferation of body cameras for police can potentially be leveraged for gun detection systems. Video systems could alert police and surveillance personnel when a gun is detected in real time, resulting in prompter action. The proposed system in this presentation is a weapon detection system that makes use of TensorFlow object detection API. The project will involve the use of various resources for implementation, such as: Python, TensorFlow object detection API, OpenCV, Google Collab, NumPy etc.