Volume 11 | Issue 5 |

 Abstract

Wearing a safety helmet, gloves and shoes while working is crucial for protecting workers from injuries, which can range from mild to severe. In industrial settings, workers are often exposed to hazardous materials, dangerous machinery, and other potential hazards that can cause injury. A safety helmet, gloves and shoes detection can help to prevent injuries by absorbing the impact of a falling object or other traumatic force. This project proposes the use of an AI-based visual examination system for safety gear detection and face recognition in manufacturing and construction industries. The system employs a CNN algorithm to detect the presence or absence of safety helmet, gloves and shoes as well as recognize the faces of workers. In case of any safety gear violation or unauthorized personnel, the system triggers an alert through email or SMS to the concerned authorities. The alert contains relevant information about the violation, including the location, time, and identity of the worker. The system can help employers maintain a safe work environment and avoid costly legal repercussions resulting from workplace accidents.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

CNN algorithm, Workers safety, Work environment and Manufacturing

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Crime analysis and prevention is a methodical methodology for locating and examining criminal behaviour trends. Our algorithm can identify places with a high likelihood of crime and may depict crime-prone zones, which are regions with a high level of crime. As technology in computerised systems advances, crime data analysts may be able to assist law enforcement officials in hastening the investigation of crimes. The main goals of this research are to categorise different types of crime using clustering approaches that are based on frequency and regulations. The crime data in this project is analysed using a clustering approach, and the K-Means algorithm is employed to cluster the recorded data. Following categorization and clustering, we may forecast a crime using the previous incidents' historical data. The suggested technique can identify places with a greater likelihood of crime and can discriminate between areas with a higher crime rate.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Crime Analysis, data mining, clustering, prediction.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Hydraulic jumps are mostly used as energy dissipators to release extra water flow energy downstream of hydraulic structures like spillways and sluice gates. The properties of hydraulic jumps produced on smooth and bumpy beds are examined in this study utilising laboratory experiments. In both smooth and rough bed conditions, the study of leap will be conducted on a horizontal bed. A 6 m long, 0.30 m wide, and 0.75 m deep rectangular flume was used for the experimental programme. This experiment will be conducted in a rectangular flume, which is made up of a rough bed that is created by inserting a rectangular wooden strip at regular intervals. Sequent water depth and beginning water depth are measured for various bed surfaces. The distance jump from the gate and the subsequent depth ratio were shorter on the rough bed than on a smooth one. When the discharge condition altered, the hydraulic parameters starting water depth, subsequent water depth, and flow rate were measured.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Bed characteristic, Stilling basin, Froude's number, Sequent depth, Energy dissipation, Hydraulic jump

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

In this project, with applications including scene understanding, medical image analysis, robotic perception, video surveillance, augmented reality, and image compression, among many others, image segmentation is the main key topic in this project's use of computer vision and image processing. In the literature, a number of picture segmentation methods have been created. A common label is given to all the visual components or pixels that fall under the same category. In addition to the class label and object bounding box, the Mask R-CNN returns the binary object mask as well. In terms of segmenting pixels, Mask R-CNN is effective.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Convolutional Neural Networks (CNNs), Convolutional Neural Networks (CNNs), Labelled Data, Binary Masks, Computer Vision.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Today's high social economic development and environmental problems have led many western societies to emphasize the importance of a safe and reliable service. In addition, Micro-grids are often used to deliver power efficiently and utilize renewable energy sources efficiently. In this analysis, various optimization algorithms are implemented for direct operation of a standard Micro-grid (MG) mill connected to renewable energy sources to cover the power mismatch or to store surplus of energy when required. The problem proposed with Improved Whale optimization algorithm (IWOA) to mitigate both running expense and net pollution was conceived as a multi-objective problem. The suggested algorithm is evaluated on a standard MG with stand-alone and grid connected mode of operation and contrasts its superior results.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Micro grid, IWOA, wind, biomass, solar and Hydro turbines.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Modern vehicles rely on a multitude of sensors and cameras to both understand the environment around them and assist the driver in different situations. Lane detection is an overall process as it can be used in safety systems such as the lane departure warning system (LDWS). Lane detection may be used in steering assist systems, especially useful at night in the absence of light sources. Although developing such a system can be done simply by using global positioning system (GPS) maps, it is dependent on an internet connection or GPS signal, elements that may be absent in some locations. Because of this, such systems should also rely on computer vision algorithms. In this paper, we improve upon an existing lane detection method, by changing two distinct features, which in turn leads to better optimization and false lane marker rejection. We propose using a probabilistic Hough transform, instead of a regular one, as well as using a parallelogram region of interest (ROI), instead of a trapezoidal one. By using these two methods we obtain an increase in overall runtime of approximately 30%, as well as an increase in accuracy of up to 3%, compared to the original method.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

computer vision, steering assist systems, lane detection, autonomous driving, Hough transform, Patterns thereon, automation of driving system, vanishing point detection, exploitation, Hough Transformation Space, Region of Interest, Canny Edge Detection.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

There is a wide variety of robots used for different applications, ranging from simple to complex. The concept presented here focuses on acquiring data from hazardous places, specifically radiation-affected areas. These areas encompass various types of radiation, such as ultraviolet radiation, nuclear radiation, x-ray radiation, and electromagnetic radiation. These places are dangerous for humans to enter, making remote-controlled robotic vehicles ideal for gathering data on the surrounding environmental conditions. Although it is challenging to create other types of radiation for demonstration purposes, our project generates electromagnetic radiation to prove the concept practically. Radiation refers to energy that originates from a source and travels through space. In our project, the source is created using a power transmitting coil, while a power receiving coil is arranged on the robotic vehicle to capture the electromagnetic radiation when the vehicle enters the radiation-affected area. Electromagnetic radiation is associated with an electric field and a magnetic field. When the vehicle approaches this field, the buzzer integrated into the moving mechanism automatically activates. The alarm in the form of a loud buzzer sound indicates the strength of the field or the proximity of the vehicle to the source. Additionally, our robotic vehicle is equipped with a DTH11 sensor, capable of measuring temperature and humidity, as well as a harmful gas sensor that can detect various toxic gases, including carbon dioxide. Furthermore, we have incorporated a live video monitoring system, featuring a 2D camera placed on the moving mechanism. This Wi-Fi camera enables the live video broadcast of the robot's surroundings. The innovative aspect of our design lies in the ability to control the camera through a remote control unit, allowing it to be transported as needed. Such cameras are highly beneficial for securing open land surrounded by buildings. Moreover, this robotic vehicle can also be employed in deep forests to collect environmental data while providing monitoring capabilities. To transmit the live video, we use a V380 Wi-Fi camera, which establishes a wireless communication link to the corresponding smartphone through the V380 Pro app. These wireless cameras offer greater flexibility compared to wired cameras, as they are not limited by wires, enabling the equipped vehicle to move freely in the field. The robot or remote-controlled vehicle is controlled via an RF communication system, allowing movement in all directions, including reverse. The mechanism is driven by DC motors, independently controlled through an H-Bridge IC. The remote control unit is constructed using an 89c2051 microcontroller chip, while the vehicle control circuit and data acquisition system are built using an Arduino Uno board. Note: One crucial aspect of this project is to hold the collected data until the robot returns to its home position, where it is controlled by the remote. This is essential to ensure accurate data from the radiation-affected area. To achieve this, a data hold key is provided, and the data remains unchanged until the release key is activated.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Smart Surveillance,Robotic Vehicles,Radiation detection,Data collection,coil.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Abstract: Energy is fundamental for financial turn of events and development. With the quick turn of events and development of the economy, society needs more power. Alongside the comprehension that unreasonable energy creation can destructively affect our current circumstance. Sun oriented energy is nature's most bountiful method for getting energy. Monetary impetuses to make sunlight- based cells more savvy and productive have persuaded the improvement of different dissipation techniques like drenching, plating, thick film testimony, and meager film statement. Ordinarily, for sun- oriented energy to work successfully and store energy in structures, a great deal of room as rooftops and ground is expected to introduce sun powered chargers These solar panels' need for space is a major hedge to their commercialisation. Transparent solar cells( TSC) have been used by experimenters as a result to this debit. By converting glass wastes into solar cells, it finds a result to this issue. These cells produce energy by collecting and using extraneous light from vehicles' windows and structures, making optimum use of available architectural space. About nine different transmission photovoltaic ( TPV) technology types are presently being delved with the thing of achieving high translucency with electrical performance perfect for solar panels This review composition's main thing is to detail all of the most cutting- edge photovoltaic transmission styles with an average transmission of at least 20 published since 2007. Including demonstrating the procedures

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Key-words:- Electricity generation. Photovoltaic effect, Energy conversion, Transparent conductive oxide, Efficiency, Durability, Nanotechnology, Thin-film solar cell, transparent flexible battery

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

One of the main objectives of smart cities is to provide an efficient street lighting system. Lighting can account for 10% to 38% of the total energy bill in typically cities worldwide. Every year, a lot of money is wasted on inefficient lighting, and bad lighting also makes things unsafe. Every engineer who works in this field is interested in the idea of creating a new system for streetlights that illuminates large areas with the highest intensity of light while consuming little electricity. So we propose a next generation street lighting system using green energy to control and monitor the lighting infrastructure based on the traffic in order to ensure the efficient usage of conventional energy. The proposed system is also equipped with surveillance cameras to increase the security of people and also reduce the risk of accidents by ensuring that vehicles do not exceed the speed limit.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Internet of Things, LDR Sensor, Infrared Sensor, ESP-32 cam module, Green energy

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

A intracranial tumor is a complaint caused by the growth of abnormal cells in the brain. There are two main orders of intracranial tumors non- cancerous(benign) intracranial tumor and cancerous(malignant) intracranial tumor. With the growth of artificial intelligence, deep literacy models are used to diagnose intracranial tumor by taking images with magnetic resonance imaging.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Brain tumor detection and classification, Yolo, Mobile Net-v2

  License

Creative Commons Attribution 4.0 and The Open Definition