A desktop partner bot who chats with you when you are bored. The bot is built with an artificial intelligence algorithm. It chats with you as a real person with amusing replies which doesn’t make the user know he is really talking to a bot. The bot is built with a limited dictionary but uses a great algorithm to imitate a real person. The bot can be used to find you an amusing partner and help you in bad times. The AI desktop partner comes with a real life person imitation (RLPI) System designed in 2013 for putting forward a real time intelligent chatting session for users. The algorithm used here has a intelligently built in logic and is designed to better chat with Indians since it’s dictionary is better configured as per Indian mentality.
Computer Engineering
Computer engineering is a discipline that integrates several fields of electrical engineering and computer science required to develop computer hardware and software. Computer engineers usually have training in electronic engineering develop computer hardware and software. Computer engineers usually have training in electronic engineering (or electrical engineering), software design, and hardware-software integration instead of only software engineering or electronic engineering. Computer engineers are involved in many hardware and software aspects of computing, from the design of individual micro controllers, microprocessors, personal computers, and supercomputers, to circuit design.
Computer software engineers develop, design, and test software. Some software engineers design, construct, and maintain computer programs for companies. Some set up networks such as intranets
for companies.Computer software engineers can also work in application design. This involves designing or coding new programs and applications to meet the needs of a business or individual. Computer software engineers can also work as freelancers and sell their software products/applications to an enterprise/individual.
Computer Engineering Projects
This college campus recruitment system provides options like student login, company login and an admin login. This software system provides an option to the students to create their profiles and upload all their details including their marks onto the system. The admin can check each student details and can remove faulty accounts. The system also consists of a company login where various companies visiting the college can view a list of students in that college and their respective resumes. The software system allows students to view a list of companies who have posted for vacancy. The admin has overall rights over the system and can moderate and delete any details not pertaining to college placement rules. The project is beneficial for college students, various companies visiting the campus for recruitment and even the college placement officer. The system handles student as well as company data and efficiently displays all this data to respective sides.
An automatic answer checker application that checks and marks written answers similar to a human being. This software application is built to check subjective answers in an online examination and allocate marks to the user after verifying the answer. The system requires you to store the original answer for the system. This facility is provided to the admin. The admin may insert questions and respective subjective answers in the system. These answers are stored as notepad files. When a user takes the test he is provided with questions and area to type his answers. Once the user enters his/her answers the system then compares this answer to original answer written in database and allocates marks accordingly. Both the answers need not be exactly same word to word. The system consists if in build artificial intelligence sensors that verify answers and allocate marks accordingly as good as a human being.
The seo optimization and suggestion consists of an entire search engine for analyzing and ranking websites and also suggesting seo tips. The search engine analyzes websites and ranks them accordingly. A website grading algorithm allows the search engine to appropriately read and access the website content. It analyzes and stores analytic data for various websites. This data is used to rank the website accordingly.
The seo suggestion page is used to provide seo tips for a website. The suggester consists of a website box to enter the website url. Once entered, the system crawls the website analyzes its data and provides appropriate solutions for optimizing it for better seo performance.
The software project points out various drawbacks in the website and provides tips solutions for the same.
The online artificial dietician is a bot with artificial intelligence about human diets. It acts as a diet consultant similar to a real dietician. Dieticians are educated with nutrient value of foods. A dietician consults a person based on his schedule, body type, height and weight. The system too asks all this data from the user and processes it. It asks about how many hour the user works, his height, weight, age etc. The system stores and processes this data and then calculates the nutrient value needed to fill up users needs. The system then shows an appropriate diet to the users and asks if user is ok with it, else it shows other alternate diets to fill up users needs.
The College bot project is built using artificial algorithms that analyses user’s queries and understand user’s message. This System is a web application which provides answer to the query of the student. Students just have to query through the bot which is used for chating. Students can chat using any format there is no specific format the user has to follow. The System uses built in artificial intelligence to answer the query. The answers are appropriate what the user queries. The User can query any college related activities through the system. The user does not have to personally go to the college for enquiry. The System analyses the question and than answers to the user. The system answers to the query as if it is answered by the person. With the help of artificial intelligence, the system answers the query asked by the students. The system replies using an effective Graphical user interface which implies that as if a real person is talking to the user. The user just has to register himself to the system and has to login to the system. After login user can access to the various helping pages. Various helping pages has the bot through which the user can chat by asking queries related to college activities. The system replies to the user with the help of effective graphical user interface. The user can query about the college related activities through online with the help of this web application. The user can query college related activities such as date and timing of annual day, sports day, and other cultural activities. This system helps the student to be updated about the college activities.
The credit card fraud detection features uses user behavior and location scanning to check for unusual patterns. These patterns include user characteristics such as user spending patterns as well as usual user geographic locations to verify his identity. If any unusual pattern is detected, the system requires revivification.
The system analyses user credit card data for various characteristics. These characteristics include user country, usual spending procedures. Based upon previous data of that user the system recognizes unusual patterns in the payment procedure. So now the system may require the user to login again or even block the user for more than 3 invalid attempts.
This project deals with an innovative rather an interesting manner of intimating the message to the people using a wireless electronic display board which is synchronized using the RF waves based software technology. This will help us in passing any message almost immediately without any delay just by sending a message by using windows software. Which is better and more reliable than the old traditional way of pasting the message on notice board. This proposed technology can be used in many public places, malls or big buildings to enhance the security system and also make awareness of the emergency situations and avoid many dangers. Using various commands is used to display the message onto the display board. This technology is used to control the display board and for conveying the information through a message sent from authenticated user. (INTERNATIONAL CONFERENCE PAPER AVAILABLE)
The Rationing distribution system also called public distribution system distributes food items to the poor. Major commodities include rice, wheat, sugar and kerosene. In this system QR codes will be provided instead of current ration cards. Users database is stored which is provided by Government. The Smart Card must be scanned by the customer to show the details of items allocated by government, and then it checks customer details with stored data to distribute material in ration shop. Biometric i.e. Fingerprint scanning will be done for security and authentication purpose. (INTERNATIONAL CONFERENCE PAPER AVAILABLE )
RFID is an acronym for Radio Frequency Identification. RFID is one member in the family of Automatic Identification and Data Capture (AIDC) technologies and is a fast and reliable means of identifying just about any material object. This project can be used for security purpose where it gives information about the authorized persons and unauthorized persons. This can be applied in real time systems as such in recording the attendance, in the companies, airports for accessing the passports and in industries to know who are authorized. RFID is increasingly used with biometric technologies for security. Primarily, the two main components involved in a Radio Frequency Identification system are the Transponder (tags that are attached to the object) and the Interrogator (RFID reader). Communication between the RFID reader and tags occurs wirelessly and generally doesn’t require a line of sight between the devices. RFID tags are categorized as either active or passive. Active RFID tags are powered by an internal battery and are typically read/write, i.e., tag data can be rewritten and/or modified. An active tag's memory size varies according to application requirements; some systems operate with up to 1MB of memory. Passive RFID tags operate without a separate external power source and obtain operating power generated from the reader. This project uses passive tags. Read-only tags are typically passive and are programmed with a unique set of data (usually 32 to 128 bits) that cannot be modified. The reader has three main functions: energizing, demodulating and decoding. The antenna emits radio signals to activate the tag and to read and write data to it. (INTERNATIONAL CONFERENCE PAPER AVAILABLE )
This paper present design and implement bus alert system for visually impaired people based on microcontroller unit Arduino NANO with ZigBee and speed sensor. The blind people in the bus stop provide with the ZigBee unit which is recognized by ZigBee in bus and the indication is made in bus that the blind people is present in the bus stop. The blind people give the input about the place they want to travel through keypad. Then input is analyzed by Arduino and it send the signal to ZigBee in blind unit. The corresponding bus receive the signal by ZigBee in bus unit and send the bus number to transreceiver in blind. These bus number is converted to audio by voice IC APR 9600 and the bus number is announced through headphone and also displayed in LCD for normal people. Then the speed sensor continuously measures speed of wheel if the bus stopped at the bus stop, it send the signal to blind unit and converted to audio. This intimate bus stopped at stop. Then blind people take correct bus parked in front of them. (INTERNATIONAL CONFERENCE PAPER AVAILABLE)
Modern digital cameras rely on the sequential execution of separate image processing steps to produce realistic images. The first two steps are usually related to denoising and demosaicking where the former aims to reduce noise from the sensor and the latter converts a series of light intensity readings to color images. Modern approaches try to jointly solve these problems, i.e. joint denoising-demosaicking which is an inherently ill-posed problem given that two-thirds of the intensity information is missing and the rest are perturbed by noise. While there are several machine learning systems that have been recently introduced to solve this problem, the majority of them relies on generic network architectures which do not explicitly take into account the physical image model. In this work we propose a novel algorithm which is inspired by powerful classical image regularization methods, large-scale optimization, and deep learning techniques. Consequently, our derived iterative optimization algorithm, which involves a trainable denoising network, has a transparent and clear interpretation compared to other black-box data driven approaches. Our extensive experimentation line demonstrates that our proposed method outperforms any previous approaches for both noisy and noisefree data across many different datasets. This improvement in reconstruction quality is attributed to the rigorous derivation of an iterative solution and the principled way we design our denoising network architecture, which as a result requires fewer trainable parameters than the current state-of-the-art solution and furthermore can be efficiently trained by using a significantly smaller number of training data than existing deep demosaicking networks.
The representation-based learning methods, such as sparse representation-based classification and low-rank representation, show effective and robust for image clustering and classification. However, these methods essentially belong to the transductive methods and they cannot deal with the new samples. Meanwhile, the original high-dimensional data contains a large amount of redundant information. If the original data are directly performed, it will not only degrade the performance of the algorithm but also lead to a sharp increase in the amount of computation. Therefore, a novel robust sparse low-rank preserving projection (SLRPP) is presented for dimensionality reduction, in which both the essential similarity structure of the observed data and the optimal feature representation are simultaneously obtained. By alternatively iterating the augmented Lagrangian multiplier method and the eigendecomposition, the framework of the SLRPP can be solved. The experimental results on six image databases proved that our SLRPP algorithm can achieve a competitive performance compared with the state-of-the-art subspace learning methods.
Skeleton-based human action recognition has recently attracted increasing attention thanks to the accessibility and the popularity of 3D skeleton data. One of the key challenges in action recognition lies in the large variations of action representations when they are captured from different viewpoints. In order to alleviate the effects of view variations, this paper introduces a novel view adaptation scheme, which automatically determines the virtual observation viewpoints over the course of an action in a learning based data driven manner. Instead of re-positioning the skeletons using a fixed human-defined prior criterion, we design two view adaptive neural networks, i.e., VA-RNN and VA-CNN, which are respectively built based on the recurrent neural network (RNN) with the Long Short-term Memory (LSTM) and the convolutional neural network (CNN). For each network, a novel view adaptation module learns and determines the most suitable observation viewpoints, and transforms the skeletons to those viewpoints for the end-to-end recognition with a main classification network. Ablation studies find that the proposed view adaptive models are capable of transforming the skeletons of various views to much more consistent virtual viewpoints. Therefore, the models largely eliminate the influence of the viewpoints, enabling the networks to focus on the learning of action-specific features and thus resulting in superior performance. In addition, we design a two-stream scheme (referred to as VA-fusion) that fuses the scores of the two networks to provide the final prediction, obtaining enhanced performance. Moreover, random rotation of skeleton sequences is employed to improve the robustness of view adaptation models and alleviate overfitting during training. Extensive experimental evaluations on five challenging benchmarks demonstrate the effectiveness of the proposed view-adaptive networks and superior performance over state-of-the-art approaches.
In this paper, we propose an image completion algorithm based on dense correspondence between the input image and an exemplar image retrieved from Internet. Contrary to traditional methods which register two images according to sparse correspondence, in this paper we propose a hierarchical PatchMatch method that progressively estimates a dense correspondence which is able to capture small deformations between images. The estimated dense correspondence has usually large occlusion areas that correspond to the regions to be completed. A nearest neighbor field (NNF) interpolation algorithm interpolates a smooth and accurate NNF over the occluded region. Given the calculated NNF, the correct image content from the exemplar image is transferred to the input image. Finally, as there could be a color difference between the completed content and the input image, a color correction algorithm is applied to remove the visual artifacts. Numerical results show that our proposed image completion method can achieve photo realistic image completion results.
In this paper, we describe a novel enhancement method for images containing filamentous structures. Our method combines a gradient sparsity constraint with a filamentous structure constraint for the effective removal of clutter and noise from the background. The method is applied and evaluated on three types of data: 1) confocal microscopy images of neurons; 2) calcium imaging data; and 3) images of road pavement. We found that the images enhanced by our method preserve both the structure and the intensity details of the original object. In the case of neuron microscopy, we find that the neurons enhanced by our method are better correlated with the original structure intensities than the neurons enhanced by well-known vessel enhancement methods. Experiments on simulated calcium imaging data indicate that both the number of detected neurons and the accuracy of the derived calcium activity are improved. Applying our method to real calcium data, more regions exhibiting calcium activity in the full field of view were found. In road pavement crack detection, smaller or milder cracks were detected after using our enhancement method.
Deep convolutional neural networks (CNNs) have been successfully applied on no-reference image quality assessment (NR-IQA) with respect to human perception. Most of these methods deal with small image patches and use the average score of the test patches for predicting the whole image quality. We discovered that image patches from homogenous regions are unreliable for both neural network training and final image quality score estimation. In addition, image patches with complex structures have much higher chances of achieving better image quality prediction. Based on these findings, we enhanced the conventional CNN-based NR-IQA algorithm to avoid homogenous patches for the network training and quality score estimation. Moreover, we also use a variance-based weighting average to bias the final image quality score to the patches with complex structure. The experimental results show that this simple approach can achieve state-of-the-art performance compared with well-known NR-IQA algorithms.
Abstract: For image retrieval methods based on bag of visual words, much attention has been paid to enhancing the discriminative powers of the local features. Although retrieved images are usually similar to a query in minutiae, they may be significantly different from a semantic perspective, which can be effectively distinguished by convolutional neural networks (CNN). Such images should not be considered as relevant pairs. To tackle this problem, we propose to construct a dynamic match kernel by adaptively calculating the matching thresholds between query and candidate images based on the pairwise distance among deep CNN features. In contrast to the typical static match kernel which is independent to the global appearance of retrieved images, the dynamic one leverages the semantical similarity as a constraint for determining the matches. Accordingly, we propose a semantic-constrained retrieval framework by incorporating the dynamic match kernel, which focuses on matched patches between relevant images and filters out the ones for irrelevant pairs. Furthermore, we demonstrate that the proposed kernel complements recent methods such as Hamming embedding, multiple assignment, local descriptors aggregation and graphbased re-ranking, while it outperforms the static one under various settings on off-the-shelf evaluation metrics. We also propose to evaluate the matched patches both quantitatively and qualitatively. Extensive experiments on five benchmark datasets and large-scale distractors validate the merits of the proposed method against the state-of-the-art methods for image retrieval.
Abstract Synthesizing high-quality images from text descriptions is a challenging problem in computer vision and has many practical applications. Samples generated by existing textto-image approaches can roughly reflect the meaning of the given descriptions, but they fail to contain necessary details and vivid object parts. In this paper, we propose Stacked Generative Adversarial Networks (StackGAN) to generate 256?256 photo-realistic images conditioned on text descriptions. We decompose the hard problem into more manageable sub-problems through a sketch-refinement process. The Stage-I GAN sketches the primitive shape and colors of the object based on the given text description, yielding Stage-I low-resolution images. The Stage-II GAN takes Stage-I results and text descriptions as inputs, and generates high-resolution images with photo-realistic details. It is able to rectify defects in Stage-I results and add compelling details with the refinement process. To improve the diversity of the synthesized images and stabilize the training of the conditional-GAN, we introduce a novel Conditioning Augmentation technique that encourages smoothness in the latent conditioning manifold. Extensive experiments and comparisons with state-of-the-arts on benchmark datasets demonstrate that the proposed method achieves significant improvements on generating photo-realistic images conditioned on text descriptions.
ABSTRACT
Although Generative Adversarial Networks (GANs) have shown remarkable success in various tasks, they still face challenges in generating high quality images. In this paper, we propose Stacked Generative Adversarial Networks (StackGAN) aimed at generating high-resolution photo-realistic images. First, we propose a two-stage generative adversarial network architecture, StackGAN-v1, for text-to-image synthesis. The Stage-\@slowromancapi@ GAN sketches primitive shape and colors of the object based on given text description, yielding low-resolution images. The Stage-\@slowromancapii@ GAN takes Stage-\@slowromancapi@results and text descriptions as inputs, and generates high-resolution images with photo-realistic details. Second, an advanced multi-stage generative adversarial network architecture, StackGAN-v2, is proposed for both conditional and unconditional generative tasks. Our StackGAN-v2 consists of multiple generators and discriminators in a tree-like structure; images at multiple scales corresponding to the same scene are generated from different branches of the tree. StackGAN-v2 shows more stable training behaviour than StackGAN-v1 by jointly approximating multiple distributions. Extensive experiments demonstrate that the proposed stacked generative adversarial networks significantly outperform other state-of-the-art methods in generating photo-realistic images.
Abstract—We propose an algorithm for real-time 6DOF pose tracking of rigid 3D objects using a monocular RGB camera. The key idea is to derive a region-based cost function using temporally consistent local color histograms. While such region-based cost functions are commonly optimized using first-order gradient descent techniques, we systematically derive a Gauss-Newton optimization scheme which gives rise to drastically faster convergence and highly accurate and robust tracking performance. We furthermore propose a novel complex dataset dedicated for the task of monocular object pose tracking and make it publicly available to the community. To our knowledge, it is the first to address the common and important scenario in which both the camera as well as the objects are moving simultaneously in cluttered scenes. In numerous experiments - including our own proposed dataset - we demonstrate that the proposed Gauss-Newton approach outperforms existing approaches, in particular in the presence of cluttered backgrounds, heterogeneous objects and partial occlusions.
Pedestrian misalignment, which mainly arises from detector errors and pose variations, is a critical problem for a robust person re-identification (re-ID) system. With bad alignment, the background noise will significantly compromise the feature learning and and matching process. To address this problem, this paper introduces the pose invariant embedding (PIE) as a pedestrian descriptor. First, in order to align pedestrians to a standard pose, the PoseBox structure is introduced, which is generated through pose estimation followed by affine transformations. Second, to reduce the impact of pose estimation errors and information loss during PoseBox construction, we design a PoseBox fusion (PBF) CNN architecture that takes the original image, the PoseBox, and the pose estimation confidence as input. The proposed PIE descriptor is thus defined as the fully connected layer of the PBF network for the retrieval task. Experiments are conducted on the Market1501, CUHK03, and VIPeR datasets. We show that PoseBox alone yields decent re-ID accuracy, and that when integrated in the PBF network, the learned PIE descriptor produces competitive performance compared with the stateof-the-art approaches.
Signal decomposition is a classical problem in signal processing, which aims to separate an observed signal into two or more components each with its own property. Usually each component is described by its own subspace or dictionary. Extensive research has been done for the case where the components are additive, but in real world applications, the components are often non-additive. For example, an image may consist of a foreground object overlaid on a background, where each pixel either belongs to the foreground or the background. In such a situation, to separate signal components, we need to find a binary mask which shows the location of each component. Therefore it requires to solve a binary optimization problem. Since most of the binary optimization problems are intractable, we relax this problem to the approximated continuous problem, and solve it by alternating optimization technique. We show the application of the proposed algorithm for three applications: separation of text from background in images, separation of moving objects from a background undergoing global camera motion in videos, separation of sinusoidal and spike components in one dimensional signals. We demonstrate in each case that considering the non-additive nature of the problem can lead to significant improvement.
Abstract
The prediction of epileptic seizures has been an essential problem of epilepsy study. The calcium imaging video data images the whole brain-wide neurons activities with electrical discharge recorded by calcium fluorescence intensity (CFI). In this paper, using the zebrafish's brain-wide calcium image video data, we propose a data-driven approach to effectively detect the systemic change-point, and further predict the epileptic seizures. Our approach includes two phases: offline training and online testing. Specifically, during offline training, we extract features and confirm the existence of systemic change-point, then estimate the ratio of unchanged system duration to interictal period duration. For online testing, we implement a statistical model to estimate the change-point, and then predict the onset of epileptic seizure. The testing results show that our proposed approach could effectively predict the time range of future epileptic seizure. Furthermore, we explore the macroscopic patterns of epileptic and control cases, and extract features based on the pattern difference, then implement and compare the classification performance from four machine learning models. Based on the data structure, we also propose a new method to discretize related features, and combine with hierarchical clustering to better visualize and explain the pattern difference between epileptic and control cases.
Abstract—We propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The mapping is represented as a deep convolutional neural network (CNN) that takes the low-resolution image as the input and outputs the high-resolution one. We further show that traditional sparse-coding-based SR methods can also be viewed as a deep convolutional network. But unlike traditional methods that handle each component separately, our method jointly optimizes all layers. Our deep CNN has a lightweight structure, yet demonstrates state-of-the-art restoration quality, and achieves fast speed for practical on-line usage. We explore different network structures and parameter settings to achieve tradeoffs between performance and speed. Moreover, we extend our network to cope with three color channels simultaneously, and show better overall reconstruction quality
ABSTRACT As a result of the popularity of smart mobile devices and the low cost of surveillance systems, visual data are increasingly being used in digital forensic investigation. Digital videos have been widely used as key evidence sources in evidence identification, analysis, presentation, and report. The main goal of this paper is to develop advanced forensic video analysis techniques to assist the forensic investigation. We first propose a forensic video analysis framework that employs an efficient video/image enhancing algorithm for the low quality of footage analysis. An adaptive video enhancement algorithm based on contrast limited adaptive histogram equalization (CLAHE) is introduced to improve the closed-circuit television (CCTV) footage quality for the use of digital forensic investigation. To assist the video-based forensic analysis, a deeplearning-based object detection and tracking algorithm are proposed that can detect and identify potential suspects and tools from footages
Abstract The predictive learning of spatiotemporal sequences aims to generate future images by learning from the historical frames, where spatial appearances and temporal variations are two crucial structures. This paper models these structures by presenting a predictive recurrent neural network (PredRNN). This architecture is enlightened by the idea that spatiotemporal predictive learning should memorize both spatial appearances and temporal variations in a unified memory pool. Concretely, memory states are no longer constrained inside each LSTM unit. Instead, they are allowed to zigzag in two directions: across stacked RNN layers vertically and through all RNN states horizontally. The core of this network is a new Spatiotemporal LSTM (ST-LSTM) unit that extracts and memorizes spatial and temporal representations simultaneously. PredRNN achieves the state-of-the-art prediction performance on three video prediction datasets and is a more general framework, that can be easily extended to other predictive learning tasks by integrating with other architectures.
Abstract—Although Generative Adversarial Networks (GANs) have shown remarkable success in various tasks, they still face challenges in generating high quality images. In this paper, we propose Stacked Generative Adversarial Networks (StackGAN) aiming at generating high-resolution photo-realistic images. First, we propose a two-stage generative adversarial network architecture, StackGAN-v1, for text-to-image synthesis. The Stage-I GAN sketches the primitive shape and colors of the object based on given text description, yielding low-resolution images. The Stage-II GAN takes Stage-I results and text descriptions as inputs, and generates highresolution images with photo-realistic details. Second, an advanced multi-stage generative adversarial network architecture, StackGANv2, is proposed for both conditional and unconditional generative tasks. Our StackGAN-v2 consists of multiple generators and discriminators in a tree-like structure; images at multiple scales corresponding to the same scene are generated from different branches of the tree. StackGAN-v2 shows more stable training behavior than StackGAN-v1 by jointly approximating multiple distributions. Extensive experiments demonstrate that the proposed stacked generative adversarial networks significantly outperform other stateof-the-art methods in generating photo-realistic images.
Abstract:
LATEST PROJECTS 2020
Many of the times manual form filling technique is used to fill domicile and leaving certificate in schools. Because of this lots of papers are used. Schools staff are store this all documents. To store this papers and files are very risky. To solve this problem the domicile and leaving certificate forms fill software is used. To fill the form just create the student login ID. Because of these staff is easily store the documents of students. To find out the student information need to login the respected student ID number. Due to this no need to do paper work and all students information are secure.
The main functionality of this project is to access the passport details of a passport holder through RFID technology. For this purpose the authorized person is given an RFID card. This card contains an integrated circuit that is used for storing, processing information through modulating and demodulating of the radio frequency signal that is being transmitted. Thus, the data stored in this card is referred as the passport details of the person. Passport verification and checking is a very time consuming process. This proposed system simplifies the process by giving the authorized person an RFID tag containing all the passport details like name, passport number and nationality etc. Once, the person places the card in front of the RFID card reader, it reads the data and verifies it with that data present in the system and if it matches then it displays the details of the passport holder. Here we use microcontroller from 8051 family. For display a 16X2 LCD is used. The status also can be retrieved from this system by pressing the status button interfaced to a microcontroller.
Pulse oximetry is a widely used medical measurement instrument and it is a non-invasive and painless test that measures oxygen saturation level in our blood that can easily detect small changes in oxygen. In the current Covid-19 situation, it has become important to track the oxygen level of multiple patients at the same time remotely without getting into contact with the patient.So, in this project, we build a pulse oximeter using MAX30100 Pulse oximeter and ESP32 that will track the Blood Oxygen level and send the data via internet by connecting to a Wi-Fi network. This way, we can monitor multiple patients remotely by maintaining social distance with the patients. The obtained data will be shown as a graph which makes it easier for tracking and analyzing the patient’s condition. Previously, we have also built other heart rate monitors using pulse sensors. And if you are interested in other Covid-19 related projects, you can check out the Human body thermometer, Smart IR Thermometer for fever monitoring, and Wall-Mount Temperature scanner that we build earlier.
Pulse oximetry is a widely used medical measurement instrument and it is a non-invasive and painless test that measures oxygen saturation level in our blood that can easily detect small changes in oxygen. In the current Covid-19 situation, it has become important to track the oxygen level of multiple patients at the same time remotely without getting into contact with the patient.So, in this project, we build a pulse oximeter using MAX30100 Pulse oximeter and ESP32 that will track the Blood Oxygen level and send the data via internet by connecting to a Wi-Fi network. This way, we can monitor multiple patients remotely by maintaining social distance with the patients. The obtained data will be shown as a graph which makes it easier for tracking and analyzing the patient’s condition. Previously, we have also built other heart rate monitors using pulse sensors. And if you are interested in other Covid-19 related projects, you can check out the Human body thermometer, Smart IR Thermometer for fever monitoring, and Wall-Mount Temperature scanner that we build earlier.
When there is a spread of infectious diseases in community, routine monitoring of body temperature can aid early detection and segregation of persons with fever and respiratory symptoms with others, which is an effective measure to prevent the spread of infectious diseases. There are few methods for measuring body temperature, categorized as oral, rectal, armpit, ear and forehead. Automatic body temperature measuring machine or non-contact thermometers are gaining popularity these days because of their advantages. We can measure body temperature without bringing the device in contact. So, the chances of infection and transferable diseases automatically get reduced. Here ultrasonic sensor is used for sensing the person. If the fore head of person is come in front of ultrasonic sensor then body temperature is check by temperature sensor and green led gets ON. If body temperature is greater than its normal range then red led and buzzer will be ON. The temperature will be monitored using OLED. This system will continuously monitor the body temperature of every individual in particular entrance and thus will overcome the problem regarding absenteeism of security guard. Also, when the person is detected using proximity sensor, sanitizer will be sprayed on hands of that person.
IOT has become a part of the modern world; the significance and utilization are increasing with each passing day. This approach is to design an efficient and real-time wireless networks to monitor power consumption of electrical appliances. The proposed system design eliminates the involvement of human in electricity maintenance. The user can monitor energy consumption in watts from a webpage by providing a channel id for the load. A sensor is set at the heap to ascertain current, a circuit is utilized to figure voltage and with these two, power can be computed. This project permit to get the power values and control gadgets from anyplace on the planet. Wi-Fi unit performs IOT operation by sending energy data of the load to the webpage which can be accessed through the channel id of the device. In the proposed system, consumer can do power management by knowing energy usage time to time. This proposed system utilizes an Arduino microcontroller. The unit which is generated can be displayed on the webpage through the Wi-Fi module.
In the present billing system the distribution companies are unable to keep track of the changing maximum demand of consumers. The consumer is facing problems like receiving due bills for bills that have already been paid as well as poor reliability of electricity supply and quality even if bills are paid regularly. The remedy for all these problems is to keep track of the consumers load on timely basis, which will held to assure accurate billing, track maximum demand and to detect threshold value. These are all the features to be taken into account for designing an efficient energy billing system. The present project “IOT Based Smart Energy Meter” addresses the problems faced by both the consumers and the distribution companies. The paper mainly deals with smart energy meter, which utilizes the features of embedded systems i.e. combination of hardware and software in order to implement desired functionality. The paper discusses comparison of Node MCU and other controllers, and the application of Wi-Fi modems to introduce ‘Smart’ concept. With the use of SERVER & Wi-Fi modem the consumer as well as service provider will get the used energy reading with the respective amount, Consumers will even get notification. When they are about to reach their threshold value, that they have set. Also with the help of Wi-Fi modem the consumer can monitor his consumed reading and can set the threshold value through webpage. This system enables the electricity department to read the meter readings monthly without a person visiting each house. This can be achieved by the use of Node Mcu unit that continuously monitor and records the energy meter reading in its permanent (non-volatile) memory location. This system continuously records the reading and the live meter reading can be displayed on webpage to the consumer on request. This system also can be used to disconnect the power supply of the house when needed.
This project IOT Garbage Monitoring system is a very innovative system which will help to keep the cities clean. This system monitors the garbage bins and informs about the level of garbage collected in the garbage bins via a web page. For this the system uses ultrasonic sensors placed over the bins to detect the garbage level and compare it with the garbage bins depth. The NodeMCU microcontroller, LCD screens Wifi modem for sending data and a buzzer. The system is powered by a 5V transformer. The LCD screen is used to display the status of the level of garbage collected in the bins. Whereas a web page is built to show the status to the user monitoring it. The web page gives a graphical view of the garbage bins and highlights the garbage collected in color in order to show the level of garbage collected. The LCD screen shows the status of the garbage level. The system puts on the buzzer when the level of garbage collected crosses the set limit. Thus this system helps to keep the city clean by informing about the garbage levels of the bins by providing graphical image of the bins via a web page.