VOLUME 10, ISSUE 8, AUGUST 2022

Abstract: Action and identification problems are the challenges that visually impaired people often encounter in their lives. The high price of existing commercial intelligent auxiliary equipment has placed enormous economic pressure on most visually impaired people in developing countries. Visually impaired individuals are a growing segment of our population ,the inability to read has a substantive negative impact on their quality of life. Printed text(books, magazines, menus, labels, etc.) still represents a sizable portion of the information this group needs to have unrestricted access . Hence, developing method by which text can be retrieved and read out loud to the visually impaired is critical.

In order to solve this problem, this work proposes a smart wearable system that performs image recognition.The system adopts the method of storage and local cooperative processing. The storage mainly performs image processing, while the local unit only uploads images and feedback results. Therefore, the processor of the system does not need to use expensive high-performance hardware, and the cost to a great extend. The main aim of this system is to build an automatic face recognition assistant using existing hardware associated, software programs with innovative algorithms.

Keywords: Face recognition device, image recognition, algorithms.

Abstract: A combined random carrier pulse width modulation principle in space vector pulse width to generate random pulse width modulation generation using an asymmetric frequency multicarrier called multicarrier random space vector pulse width modulation. The space vector pulse width modulation switching vectors with different frequency carrier are chosen with the aid of a random bi-nary bit generator. The multi carrier random space vector modulation generates the pulses with a randomized triangular carrier (1 to 4 kHz), while the conventional random pulse width modulation method contains a random pulse position with a fixed frequency triangular carrier. The four carrier signals with different frequencies of (1 to 4 kHz) are made to generate the randomness carrier. In order to merge these random carrier signals four 3x1 multiplexers are used, and finally, the MUX output is given to the 4x1 Multiplexer. The 8 bit pseudo random binary sequence as well as 16 bit pseudo random binary sequence generator are used to generate random 0 and 1 sequence which manipulate the random combination of four different carrier frequency signals. These voltage source inverter are needed in order to provide several advantages such as Harmonics elimination. The simulation study is performed through MATLAB/Simulink for a space vector pulse width modulation based Grid connected Inverter.

Keywords: pulse width modulation; random PWM; space vector PWM; voltage source PWM inverter; acoustic noise

Abstract: This electronic Object detection, which aims to automatically mark the coordinates of objects of interest in pictures or videos, is an extension of image classification. In recent years, it has been widely used in intelligent traffic management, intelligent monitoring systems, military object detection, and surgical instrument positioning in medical navigation surgery, etc. COVID-19, a novel coronavirus outbreak at the end of 2019, poses a serious threat to public health. Many countries require everyone to wear a mask in public to prevent the spread of coronavirus. To effectively prevent the spread of the coronavirus, we present an object detection method based on single-shot detector (SSD), which focuses on accurate and real-time face masks detection in the supermarket. We make contributions in the following three aspects: 1) presenting a lightweight backbone network for feature extraction, which based on SSD and spatial separable convolution, aiming to improve the detection speed and meet the requirements of real-time detection; 2) proposing a Feature Enhancement Module (FEM) to strengthen the deep features learned from CNN models, aiming to enhance the feature representation of the small objects; 3) constructing COVID-19-Mask, a large-scale dataset to detect whether shoppers are wearing masks, by collecting images in two supermarkets. The experiment results illustrate the high detection precision and real-time performance of the proposed algorithm.

Keywords: CNN, Deep Learning, Feature Enhancement Module (FEM), Single Shot Detector (SSD).

Abstract: This electronic Object detection, which aims to automatically mark the coordinates of objects of interest in pictures or videos, is an extension of image classification. In recent years, it has been widely used in intelligent traffic management, intelligent monitoring systems, military object detection, and surgical instrument positioning in medical navigation surgery, etc. COVID-19, a novel coronavirus outbreak at the end of 2019, poses a serious threat to public health. Many countries require everyone to wear a mask in public to prevent the spread of coronavirus. To effectively prevent the spread of the coronavirus, we present an object detection method based on single-shot detector (SSD), which focuses on accurate and real-time face masks detection in the supermarket. We make contributions in the following three aspects: 1) presenting a lightweight backbone network for feature extraction, which based on SSD and spatial separable convolution, aiming to improve the detection speed and meet the requirements of real-time detection; 2) proposing a Feature Enhancement Module (FEM) to strengthen the deep features learned from CNN models, aiming to enhance the feature representation of the small objects; 3) constructing COVID-19-Mask, a large-scale dataset to detect whether shoppers are wearing masks, by collecting images in two supermarkets. The experiment results illustrate the high detection precision and real-time performance of the proposed algorithm.

Keywords: CNN, Deep Learning, Feature Enhancement Module(FEM), Single Shot Detector(SSD).

Abstract: Arc faults are significant with respect to reliability and safety concern for electrical systems which can cause stoppage in intermittent operation and electrical shock hazards which can even result in fire. Arc fault in such vast systems are random and challenging which makes the study of arc fault detection using arc signature difficult. The high-frequency content of the arc requires fast sampling, which are having long memory, which requires proper data storage for fast processing and analyzing the arc. As signal to noise ratio is low and arc signal are not periodic in nature, commercialized existing techniques like Fourier Transform do not work well since they depend on recognizing pattern with time domain or frequency domain. In contrast, wavelet Transform (WT), recently developed method for analyzing, provides a time and frequency approach to analyze target signals with several resolutions. This review paper proposal proposes a method based on Wavelet Packet analysis which has the localization characteristics to detect low-voltage DC arc fault. The mother wavelet selection is studied as well by using various orders of Daubechies wavelet. Efforts have been made in this study to incorporate and review approximately all important techniques and philosophies of arc fault detection. This comprehensive and exhaustive survey will reduce the difficulty of new researchers to evaluate different WT based techniques with a set of references of all concerned contributions.

Keywords: Arc fault analysis, arc flash, dc distribution, dc microgrid safety, signal processing, wavelet transform (WT)

Abstract: In recent years, road traffic has become a serious problem across the globe. Current statistics reveals that a person averagely spends around 4-6 months of his/her life time by simply waiting at traffic signal during his travel. Generally, traffic police can control traffic in several junctions of cities by implementing either hard coded automatic traffic light control system or through manual intervention. However, the conventional hard code controlled traffic light signal which operates with a fixed time slots is found to be poor efficient since it does not consider the instantaneous traffic density. Hence, the density based traffic control system available at lowest expenditure will be helpful. The motivation for this work has been originated from the observation carried out at traffic signals located at Nizwa and Muscat cities of Oman. The proposed system includes timer which runs for a specific time and IR sensor is used to count the number of vehicles passing by during that time period.

Keywords: IR sensor, Pilot lamp, Arduino, Traffic control.

Abstract: Solar energy is one of the most capable and environmentally responsive energy source. The main purpose of present study is to evaluate a multi criteria decision making model to report the significant solar panels evaluation criteria’s. The criteria’s are identified for evaluation through literature review and identification of the most momentous criteria’s, which can assist in achieving to high degree of performance is evaluated from DEMATEL Technique. The solar panels evaluation dimensions are extracted from the sources of literature review to persuade sustainability. The priority importance of the criteria’s, which are originated from the dimensions of solar energy is done for locking sustainability. Eleven technical criterias i.e. Maintenance and handling, Installation cost, Availability of land, Technological drag, Payback period, Average temperature, Capital cost, Climate, Efficiency and reliability, Power factor and capacity factor, and Transmission problem are evaluated to define the crucial criteria’s. 10 point linkert scale is used to understand the weights of the criteria’s under DEMATEL method. It is found that a criteria named as “Climate” have received the weight vector of 0.1029 with first priority ranking, which is followed by “Availability of land” and “payback period” in the second and third state of priority ranking.

Keywords: Solar Panels, Evaluation, Selection, Criteria’s, critical thinking.

Abstract: The application can be used by all people. This app provides a simple interface for maintenance of customer’s, employer’s information and also to place the orders of milk and its products. It will handle all type of customer’s details, product-order details, payment details, employee’s information, product details, dairy details too.

Keywords: Dairy management system, dairy business, managing dairy data, milk product, RSA algorithm.

Abstract: The utilization of skeleton information for human stance acknowledgment is a major examination theme in the human-computer collaboration field. This research proposes latest computation found various highlights and learning the rules to improve the precision of human stance. First and foremost, a 219-layer vector is defined, which includes point elements and distance highlights. The regular learning process combined with arbitrary subset techniques to produce a variety of tests and highlights for more refined sub-classifier classification execution for various cases during human stance categorization. Finally, four human stance datasets are used to assess the performance of our proposed technique. The results show that our algorithm can detect a spectrum of human positions and that findings acquired using a standard learning systems strategy are much more explicable than results conventional AI techniques and CNNs.

Keyword - IOT, SIFT, Pressure detection, Movements detection.

Abstract: The goal of this project is to collect remote electrical characteristics such as voltage, current, and frequency, and to send these real-time values, together with the power station temperature, over the GSM network using a GSM modem / phone. This project also includes the use of an Electromagnetic Relay to protect the electrical circuits. When the electrical parameters surpass the predefined values, this Relay is activated. This system can also provide real-time electrical parameters as SMS messages on a regular basis (depending on time settings). Electrical characteristics such as current and voltage will be compared to their rated value on a regular basis to safeguard the distribution and power transformer from overload, short circuit faults, overvoltages , and surges. Under such circumstances, the entire device is shut down, with transfers detecting it and the electrical switch being killed instantly. This project takes use of a microcontroller, which is a type of onboard computer. This internal computer is capable of communicating effectively with the many sensors in use. The substation becomes intelligent as a result of the usage of GSM, since it is able to communicate alarms and information as well as accept commands.’

Keywords: Microcontroller, Real time monitoring, transformer, Substation, Arduino Uno, Temp Sensor, Voltage Sensor, Current Sensor.