Secret Image Sharing Scheme Based on Compressed Sensing
Implementation of HOG Based Feature Extraction Method
Soldier Health and Position Monitoring System using GPS and IOT Technology
A Review on the Closed-Loop Strategy for Speed Control of BLDC Motors
V/F Based Speed Controller of Induction Motor using Ann Controller - A Review
Blockchain 3.0: Towards a Secure Ballotcoin Democracy through a Digitized Public Ledger in Developing Countries
Fetal ECG Extraction from Maternal ECG using MATLAB
Brief Introduction to Modular Multilevel Converters and Relative Concepts and Functionalities
Detection of Phase to Phase Faults and Identification of Faulty Phases in Series Capacitor Compensated Six Phase Transmission Line using the Norm of Wavelet Transform
A Novel Approach to Reduce Deafness in Classical Earphones: MUEAR
A novel mathematical ECG signal analysis approach for features extraction using LabVIEW
Filtering of ECG Signal Using Adaptive and Non Adaptive Filters
Application of Polynomial Approximation Techniques for Smoothing ECG Signals
A Novel Approach to Improve the Wind Profiler Doppler Spectra Using Wavelets
Implementation of HOG Based Feature Extraction Method
One of the known strategies used by modern radars to attain good range resolution is frequency stepping. The key benefit of this method is that radar's actual instantaneous bandwidth is fairly small in comparison to its entire processing bandwidth. This permits waveforms with extremely broad overall bandwidth to be sent, allowing for great range resolution without the requirement for the expensive technology required to provide wide instantaneous bandwidth. Unwanted peaks known as grating lobes may arise in the autocorrelation function of uniform frequency stepped pulse trains. When appropriately designed stepped frequency waveforms are used, we can minimise grating lobes by employing a method that allows us to suppress grating lobes below a specific threshold and replacing linear FM (LFM) pulses of bandwidth B in place of fixed frequency pulses. Uniform PRI (Pulse Repetition Interval) Stepped Linear Frequency Modulation (SLFM) is considered here, as well as non-uniform PRI (increasing and decreasing order) SLFM with various lengths. The ambiguity function, which influences the performance of the radar, is used to calculate the peak side lobe ratio and Integrated side lobe ratio. This paper proposed a new model for SLFM (Stepped Linear Frequency Modulation) signals to eliminate side lobes.
As we all know, many more computer technologies are becoming popular for discrete applications these days, but identity verification for biometrics and security purposes is critical in industrial systems, banking systems, educational systems, and mobile systems, among other places. On that scenario identifying and recognizing the facial features is a basic requirement for authentication to reduce the embezzlement in above mentioned systems. Face detection is one of the computer technology and psychological process implemented to examine the human faces in digital images, however in face recognition system information of human face captured by camera or video frames is compared with the datasets of images. For considered system, 15 different datasets are taken for this training model to recognize the faces of different individuals. Till now lot of researches has been done on facial detection but some limitations like accuracy, real time face detection exists. This algorithm has more speed and accuracy to identify images with respect to feature extraction like nose, eyes and mouth of human being that varies from person to person. The proposed algorithm uses AI to match above unique features of individuals with databases of faces and find the name of that individual. It is used to authenticate clients via ID verification systems for preventing crime, unlocking devices, providing blind assistance, biometric systems, and payments, etc.
Communication is imparting, sharing and conveying of information, new ideas and feelings. Of these, sign language is one of the non-verbal communication methods used by people with hearing impairment. People trained in this sign language can easily understand this sign code, but it is difficult for ordinary people to interpret it. This communication barrier is a key social problem among the hearing impaired community, preventing them from accessing basic and essential services. To tackle the difficulties faced, this paper proposes a methodology for the recognition of hand gestures, which is the prime component in sign language vocabulary, based on an efficient deep Convolutional Neural Network (CNN) architecture. CNN is an effective technique in extracting distinct features and classifying data. The hand gestures are captured using a camera connected to the Raspberry Pi. a single board computer that runs the deep learning algorithm. The algorithm is trained with the preprocessed datasets. The captured image is compared against the trained datasets and algorithm recognizes the corresponding alphabets. Later the alphabets are consolidated and returned as the word or sentence. The speaker is connected to the Raspberry Pi system through which the word output is converted into voice. In addition, the system also converts the voice input to text in the form of word or sentence. This approach provides an effective mode of communication for hearing impaired people.
In India, electoral voting is done using electronically operated voting machines. Currently, the identity of the voter is validated by non-biometric process. Implementation of technology through computerized process has scope for using biometrics to validate voter's identity. Physiological or behavioral features of human are used as a biometric for personal identification. There is a large dataset of biometric patterns available, and many software systems have been developed and implemented, for recognition of face, hand shape, fingerprint, palm, iris, etc. The system proposed in this paper is implemented using embedded technology to utilize finger-vein image recognition. The system also has a MATLAB section, which will capture the vein in finger of the voter and their sample is registered to the controller. In order to cast a vote, the captured finger vein image must match the image already stored in the database along with the voter's RFID card. It the image identification failed to match with the authorized person, the system will send alert to authorities.
Braille code is a mode of written communication used by visually impaired people to learn and communicate with others. Many visually impaired people find it difficult to read books printed in Braille code. Technology has the capability to convert the Braille code printed content to voice, which would be beneficial to the visually impaired people. The aim of this project is to create a software system that enables to convert Braille code into multi-lingual text and voice output using Machine Learning and Artificial Intelligence algorithms. This paper explains the key concepts and challenges.
