Prototype Of Detection System Research Articles

IoT Sensor-Based Convolutional Neural Network System for Concealed Weapon Detector for Security Enhancement

Security has been a major concern in our societies due to the rise in crime rate, most especially in a crowded area. Concealed weapons have been posing a significant threat to government, law enforcement, security agencies, and civilians. Existing weapons detection systems seem to be not culpable of detecting concealed weapons without the cooperation of the person being searched. There remains a need for a weapons detector that can detect and identify concealed weapons for security enhancement in Nigeria. For this purpose, computer vision methods and a deep learning approach were applied for the identification of a weapon from captured images downloaded from the internet as a prototype for the study. Recent work in deep learning and machine learning using convolutional neural networks has shown considerable progress in the areas of object detection and recognition. The CNN algorithms are trained on the collected datasets to identify and differentiate between weapons and non-weapons. We built a concealed weapon detection system prototype and conducted a series of experiments to test the system's accuracy, precision, and false positives. The models were compared by evaluating their average values of sensitivity, specificity, F1 score, accuracy, and the area under the receiver operating characteristic curve (AUC). The experimental findings clearly demonstrated that the ResNet-50 model performed better than the VGG-16 and Alex Net models in terms of sensitivity, specificity, and accuracy.

Prototype of chili pathogen early detection system by using multispectral NIR/NUV

Prototype of chili pathogen early detection system by using multispectral NIR/NUV

Multivariate impedance spectroscopy method for the measuring of quality and status of electric power oils

With the rapid development of power technology and the complexity of power system equipment, efficient and accurate assessment of the quality and condition of electric power equipment oil (EPEO) has become particularly critical. EPEO is an important factor to ensure the stable operation of power equipment, and its quality and state directly affect the safety and reliability of equipment. However, there are many challenges with traditional oil measuring techniques, which often rely on destructive testing, which not only increases maintenance costs, but can also cause damage to the equipment itself. In the face of these limitations, there is an urgent need to study new oil detection technologies and methods to meet the high standards of modern power systems for high efficiency, non-destructive and comprehensive analytical capabilities. In this paper, a new EPEO measuring technique based on multivariable impedance spectroscopy (MIS) is proposed. Through in-depth analysis of oil's impedance response characteristics under electric field excitation with different frequency., a new approach is provided for the comprehensive evaluation of oil's performance. MIS technology not only has the characteristics of non-destructive testing, ensuring the non-destructive measuring of EPEO, but also its rapid response and real-time analysis ability significantly improves the monitoring efficiency. Based on the proposed MIS detection method, a detection system and experimental prototype which can detect and evaluate the performance and quality of power oil more accurately are designed. Compared with the traditional measuring device, the measuring device utilized in this method can employ three variables. Specifically, it covers a frequency range for the detectable excitation signal spanning from 1 to 100 kHz, an amplitude range from 0.1 to 11.7 V, and a temperature range from −100 °C to 100 °C. The MIS detection method has the capability to identify a variety of parameters, including the dielectric constant, volume resistivity, and dielectric loss factor, among others. This method encompasses a broader spectrum of parameters compared to traditional detection methods, which typically focus on one or two detectable indicators. The correctness and feasibility of the proposed multivariable impedance spectrum detection technique are verified, which provides a new way for the comprehensive evaluation of oil's performance.

Characterisation of a high granularity multi-channel prompt γ-ray detection system prototype for proton range verification based on the PETsys TOFPET2 ASIC

Proton therapy requires range verification in order to exploit its full potential. One of the most promising approaches is to monitor prompt gamma-rays produced by nuclear interactions of the therapeutic particles in the patient tissues. A detector with a wide energy range from 100 keV to 15 MeV and excellent time resolution is required to achieve millimetric precision in proton range. During patient treatment, the detector count rates are usually above 106 s-1 and the fraction of pile-up events is very high for commonly used fast inorganic scintillators. We are investigating a full acceptance approach with increased granularity in order to reduce the size of the scintillators and consequently the count rate per channel. Stacking the scintillators in matrices requires suitable multi-channel photo-multipliers and a fitting acquisition system. Here, we present two geometries of CeBr3 crystals 5×5×20 mm3 and 10×10×30 mm3, together with modern silicon photo-multipliers (SiPM) adapted to work with the PETsys TOFPET2 ASIC. The TOFPET2 ASIC was developed for Time-of-Flight Positron Emission Tomography (TOF-PET) applications. Here we show its potential for higher gamma-ray energies and future hybrid imaging. First results of energy resolution of 6.1%–7.8% are achieved at 3.42 MeV using a 241Am9Be source. The time resolution was found to be below 100 ps and studies of the count rates and the dead time of the full system were performed. Different SiPM models are analysed for their impact on the coincidence time resolution.

Penerapan IoT pada Sistem Deteksi Kadar Air dan Level Tangki Stasiun SPBU

The development of the gas station business is currently very tempting for entrepreneurs, it can be witnessed that lately many gas station constructions have begun in the city to remote villages though. One of the most important things that is sometimes overlooked by gas station entrepreneurs is the quality of the fuel they sell and in general, monitoring the contents of the tank at gas stations is done manually. The purpose of the study was to design a Prototype of the Water Content Detection System and tank level, which aims to help gas station managers measure water content and monitor fuel content in gas station tanks automatically and realtime so that fuel quality is maintained, information can be monitored through web-based systems and mobile applications with Internet of Things technology. The IoT system design consists of an Arduino Uno R4 microcontroller, HC-SR04 ultrasonic sensor, conductivity sensor, and selenoid valve. The accuracy test results of the ultrasonic sensor used are good enough to measure the contents of the tank with an average error of 1.3%, while the conductivity sensor measurement has an average error of 0.292% with a validation process using the centrifuge method, The selenoid valve works well which is activated through a web-based monitoring application and a mobile application.

Precision Gas Leakage Detection System with Integrated Sensors

Gas leaks pose significant safety risks in both residential and industrial settings, making gas leakage detectors essential safety devices for many years. These detectors serve the crucial function of identifying the presence of hazardous gases, such as carbon monoxide, and activating an alarm system to promptly alert occupants of the building. This innovative gas leak detection system leverages mobile technology, integrating phone calls, SMS, WhatsApp, and GPS location services. Additionally, it features a unique capability to shut off the power supply in the affected area, providing a real-time and effective means of gas leak detection and containment. This gas leakage detection system prototype has been successfully developed and tested with gases such as BUTANE and PROPENE. The experimental results demonstrate that the system can detect gas leaks in less than a minute. The primary objective of this gas detection project is to implement a security system for identifying gas leaks in closed environments. It utilizes MQ-2 sensors designed to function effectively within enclosed spaces. Furthermore, this system can be seamlessly integrated with other security and safety systems for enhanced overall protection.

Prototype of Water Level and Rainfall Detection System as Flood Warning Based On Blynk Iot Application

Rainfall in the rainy season can last for about six months, resulting in continuous rain and increasing the amount of water that causes flooding. The community does not directly get information or be informed when it rains. To anticipate these problems, the Prototype of Water Level and Rainfall Detection System as a Flood Warning Based on the Blynk IoT Application is considered effective for developing a rainfall and water level monitoring system. By using the tool design method, flowchart, system analysis (SDLC), and testing using the black box testing method. The system detects the distance between the sensor and the water surface. If the distance to the water level is close to the sensor, the system will report a flood and then switch to the Blynk software. The mobile will display a message and the system can enter all distances into the program.

Prototype Detection System Of Papaya Murability Using Fuzzy Logic Method Based On Color Sensor

Product selection based on the ripeness quality of papaya fruit is one of the stages in the processing of plantation products. At this time, the process of sorting papaya fruit is still using manual methods, especially in estimating the level of ripeness. Papaya is considered a climacteric fruit where respiration occurs and its ethylene production suddenly increases and then rapidly falls off. Fruit with a low respiration rate has a longer shelf life than fruit with a high respiration rate. To overcome this problem, this research created a prototype of a papaya fruit ripeness detection system using a color sensor-based fuzzy logic method. This fruit maturity detector can provide information related to fruit ripeness (unripe, half ripe, and ripe) which is determined from the color of the papaya fruit which is then processed using the Mamdani fuzzy logic method. The results of the prototype design can measure fruit with an accuracy rate of 93.33% of the 30 data tested by using tools that are in a cool place, with low intensity of incoming sunlight.
 Keywords: Papaya fruit ripeness, TCS3200 Sensor, Mamdani Fuzzy Logic.

Localization and imaging of internal hidden defects in concrete slabs based on deep learning of vibration signals

Internal hidden defects such as delamination and voids are common distress of concrete slabs and the localization of these defects is important for structural safety. This paper develops a damage inspection method that is feasible for locating and imaging internal defects of concrete slabs based on deep learning of impact-caused vibration signals. To alleviate the problem of low efficiency of manual signal collection, a prototype of mobile detection system is developed for the automatic generation and acquisition of vibration signals. Two optimized deep learning models in the framework convolutional neural network (CNN) are proposed for 1D time series signal and 2D time-frequency spectrogram to address the problems of low recognition accuracy and long training time of the traditional network, where the principal component analysis (PCA) and squeeze and excitation (SE) modules are incorporated respectively for a better feature learning and extraction of vibration signals of internal defects. The softmax layer is added in the networks to calculate the state probability value for the completion of damage contour maps. The network proposed in this paper is used to systematically compare the training and recognition effects of the data collected by contact senor (accelerometer) and air coupled sensor (microphone). The experiments show that the detection accuracy of the one-dimensional (1D) and two-dimensional (2D) network based on the accelerometer-acquired data reaches 90.4% and 93.4%, respectively. The generalizability of trained models is also validated based on the independent dataset from other research and actual concrete floor of a multistorey building. In the future, the prototype of the hardware system can be further improved by embedding GPS information to realize the real-time automatic localization of hidden defects of engineering structures.

Detection of non‐suicidal self‐injury based on spatiotemporal features of indoor activities

AbstractNon‐suicide self‐injury (NSSI) can be dangerous and difficult for guardians or caregivers to detect in time. NSSI refers to when people hurt themselves even though they have no wish to cause critical or long‐lasting hurt. To timely identify and effectively prevent NSSI in order to reduce the suicide rates of patients with a potential suicide risk, the detection of NSSI based on the spatiotemporal features of indoor activities is proposed. Firstly, an NSSI behaviour dataset is provided, and it includes four categories that can be used for scientific research on NSSI evaluation. Secondly, an NSSI detection algorithm based on the spatiotemporal features of indoor activities (NssiDetection) is proposed. NssiDetection calculates the human bounding box by using an object detection model and employs a behaviour detection model to extract the temporal and spatial features of NSSI behaviour. Thirdly, the optimal combination schemes of NssiDetection is investigated by checking its performance with different behaviour detection methods and training strategies. Lastly, a case study is performed by implementing an NSSI behaviour detection prototype system. The prototype system has a recognition accuracy of 84.18% for NSSI actions with new backgrounds, persons, or camera angles.

Safety Helmet‐Wearing Detection System for Manufacturing Workshop Based on Improved YOLOv7

Safety helmets play a vital role in protecting workers’ heads. In order to improve the accuracy of the detection model in complex environments, such as complex backgrounds and different lighting and distances, we propose a safety helmet‐wearing detection algorithm based on the improved YOLOv7. In the backbone network, 16‐channel features are used to replace 3‐channel RGB features. Structured pruning is performed in the head network, and the loss function is replaced by SIoU. Experiments on the “helmet‐head,” “helmet‐data,” and “helmet” data sets show that the mAP and F1 of YOLOv7_ours improved in this paper are better than Faster RCNN, YOLOv5, and YOLOv7 series models. On image data of different application scenarios, light intensity, and color depth, YOLOv7_ours has better stability and higher accuracy and can detect at 112.4FPS (1000/8.9). Based on the improved YOLOv7_ours, we integrated face recognition technology and text‐to‐speech (TTS) to realize helmet detection, identity recognition, and automatic voice reminder capabilities and developed a safety helmet‐wearing detection prototype system. We verified the feasibility of the helmet detection algorithm and system in the semifinished product manufacturing workshop.

Sistem Pendeteksi Posisi Kendaraan Kecil pada Dump Truck Tambang menggunakan Modul Radio Frekuensi 433 MHz dan Radar Ultrasonik

Accidents with mining dump trucks are still common, especially those with small vehicles located in mining locations. The limited visibility of the driver of the large dump truck to see small vehicles around it cause these accidents. This paper presents a small vehicle detection system prototype designed to improve the visibility of the dump truck’s driver. This system works by initially a dump truck detecting the 433 MHz radio frequency, which indicates the small vehicle is around the dump truck. A buzzer sound, controlled by Fuzzy logic according to the distance of small vehicles, also equips the system. It then triggers the truck’s ultrasonic radar to sense the position of small vehicles. The warning information will be displayed on the 16 x 2 LCD. At the same time, a TFT LCD presents the angle and distance of small vehicles. With this system, a dump truck's driver can realize the presence of small vehicles earlier and detect the position and distance of those vehicles.

Multi-channel parallel ultrasound detection based on a photothermal tunable fiber optic sensor array.

A multi-channel parallel ultrasound detection system based on a photothermal tunable fiber optic sensor array is proposed. The resonant wavelength of the ultrasound sensor has a quadratic relationship with the power of a 980-nm heating laser. The maximum tuning range is larger than 15 nm. Through photothermal tuning, the inconsistent operating wavelengths of the Fabry-Perot (FP) sensor array can be solved, and then a multiplexing capacity of up to 53 can be theoretically realized, which could greatly reduce the time required for data acquisition. Then, a fixed wavelength laser with ultra-narrow linewidth is used to interrogate the sensor array. The interrogation system demonstrates a noise equivalent pressure (NEP) as low as 0.12 kPa, which is 5.5-times lower than the commercial hydrophone. Furthermore, a prototype of a four-channel ultrasound detection system is built to demonstrate the parallel detection capability. Compared with the independent detection, the SNR of parallel detection does not deteriorate, proving that the parallel detection system and the sensor array own very low cross talk characteristics. The parallel detection technique paves a way for real-time photoacoustic/ultrasound imaging.

Designing an early flood detection system prototype in riverbank settlements

There is still a lot of use of the floodgates in the main hole to drain the residential water into the river is still operated manually by someone in charge of opening and closing the floodgates. It is less efficient and often happens to the operator, so the water overflows and can lead to flooding. In this final task, a prototype of an early flood detection system and the automation of sewerage in a settlement located on the riverbanks. The control of floodgates on the main hole works automatically according to the signal from a sensor that reads the state of the water level. Main hole floodgates will work when the river water enters it at a specific limit that sensors will read and provide information on the level of river water in it to someone via WhatsApp to prevent river water from entering the settlement. When the main hole door is closed automatically, the residential water flow will be directed to a temporary reservoir. When the temporary reservoir is full, the sensor will signal to activate the discharge pump that will be discharged into the river to dispose of the water in the reservoir. The design and testing of flood early detection prototype tools and residential water disposal automation can work well by the design principle.

Acoustic threat detection and direction finding system

In this paper, an acoustic threat detection system is investigated as preliminary study of one of the anti-terrorism systems. The proposed system is a prototype of acoustic threats detection, classification, and direction finding system. For this purpose, an experiment is performed to test the capability of a proposed warning system to perform the task accurately. The direction of the sound source is determined by means of two microphones. The angle to the acoustic threat is calculated based on time difference of arrival (TDOA). The limitations of the system are discussed and some possible solutions are introduced to improve the performance of the system.

Sistem Pendeteksi Ancaman Keamanan Rumah Dengan Menggunakan Telegram Berbasis Internet Of Things

The comfort and safety of a house is the dream of any home owner, even a house that has a modern security system will be more in demand than a house with an ordinary security system. By utilizing existing technology, it is possible to create an excellent security system from theft and fire. In order to overcome these problems, a prototype of a security threat detection system was made using telegrams based on the internet of things. This can minimize the inconvenience of home owners when they are not at home in a long time, such as the owner of the house going out of town or abroad. The design of this smart home uses the NodeMCU ESP8266 Wifi Module as a controller, the telegram application as a notification when an unknown person opens a door or window, and when a fire occurs. The sensor used to detect the security of burglars is a Magnetic Door Switch, this sensor is placed on doors and windows. The sensor used to detect fire indications is the Flame Sensor which is placed on the ceiling of the house

Real Time Driver Drowsiness Detection using OpenCV and Facial Landmarks

In recent years driver fatigue is one of the major causes of vehicle accidents in the world. Major studies have suggested that around 20% of all road accidents are fatigue related. Drowsy Driving can be extremely dangerous, a lot of road accidents are related to the driver falling asleep while driving and subsequently losing control of the vehicle. However, initial signs of fatigue and drowsiness can be detected before a critical situation arises. A direct way of measuring driver fatigue is measuring the state of the driver i.e. drowsiness. So it is very important to detect the drowsiness of the driver to save life and property. This project is aimed towards developing a prototype of drowsiness detection system which detects the eye closure, yawning and head tilt of the driver and give warning to driver upon detecting drowsiness.

Implementation of an Available Parking Space Detection System in Hectic Parking Lots

Parking automation has been developed for locating available parking spaces inside a parking lot with new technologies, such as automatic collection, capacity, or empty spaces’ detection; to both reduce search time and avoid crowds of vehicles waiting to park in it. A simple detection system of available spaces, within the Faculty and Staff parking lot of the Engineering and Chemistry Departments at the Autonomous University of Chihuahua, Mexico (UACH), was set up. First, an analysis of vehicle capacity was carried out to establish the peak hours of vehicles’ entrances and compare it to the parking lots’ capacity. For one working week (6 days), it was determined that Tuesdays have the highest vehicle occupancy, and Saturdays are the days with the least traffic. Second, the geometric design of the parking lot (divided into two areas because of the terrain topography: upper and bottom levels), its dimensions and location of parking spots and marks on the pavement for traffic directions, were obtained from its blueprint, to visualize how the surveillance cameras can be oriented to cover the area. A detection system prototype was created for a specific area of the parking lot, using an artificial vision technique to perform the video extraction, while the digital image processing was developed in MATLAB. To complement and achieve the objective, Object- Oriented Programming (OOP) was used to obtain the count analysis as well as the availability/occupancy of each of the parking areas. This information is shown on a web page, with a simple driver-friendly design, since it has each parking space number and its availability in blue with the word “Available” or, in the opposite case, the word “Taken” in pink.

Early Warning System Prototype of Train Arrival Based on Internet of Things

This article discusses how to build a remote detection system prototype. An example of its application is for example to turn on a siren when it detects the arrival of a train at an unguarded rail crossing. The device to be produced is expected to be able to reduce and even prevent traffic accidents that often occur at unattended rail crossings. The specific objectives of the research are: (1) Producing a prototype design for the distance detection system at unattended rail crossings; and (2) Obtain good performance from the prototype design of the distance detection system at unattended rail crossings. Specific targets of research are prototypes of distance detection systems at unguarded rail crossings that are performing well and well validated, nationally accredited journals, and IPR. The method of implementation uses development techniques (Research and Development) which refers to Pressman (2006: 409). This activity is carried out for 6 months, in outline the steps are: description and analysis of needs, design, making system prototypes, and system testing. The instruments used included checklists and questionnaires. The data obtained from the questionnaire were analyzed quantitatively to test whether the results met the predetermined indicators. The tool developed has special specifications, namely having a Lora-R02 transmitter and receiver module, a GPS module, a 900A SIM module which are all assembled as IOT using the Arduino Mega 2560.From the results of testing the prototype tool, all tool sensors can work well at a distance of less than 100 meters and only partial sensors work at distances greater than 100 meters. Meanwhile, the Lora module can begin to detect the arrival of objects at a distance of 300 meters.

SILICON CARBIDE NEUTRON DETECTOR PROTOTYPE TESTING AT THE JSI TRIGA REACTOR FOR ENHANCED BORDER AND PORTS SECURITY

In 2016, the “E-SiCure” project (standing for “Engineering Silicon Carbide for Border and Port Security”), funded by the NATO Science for Peace and Security Programme was launched. The main objective is to combine theoretical, experimental and applied research towards the development of radiation-hard SiC-based detectors of special nuclear materials (SNM), with the end goal to enhance border and port security barriers. Prototype neutron detectors, configured as 4H-SiC-based Schottky barrier diodes, were developed for the detection of secondary charged particles (tritons, alphas and lithium atoms) which are the result of thermal neutron reactions on 10B and 6LiF layers above the surface of the 4H-SiC diodes. We designed a stand-alone prototype detection system, consisting of a preamplifier, shaping amplifier and a multichannel analyser operated by a laptop computer, for testing of neutron detector prototypes at the Jožef Stefan Institute (JSI) TRIGA reactor using a broad beam of reactor neutrons. The reverse bias for the detector diode and the power to electronic system were provided by a standalone battery-powered voltage source. The detector functionality was established through measurements using an 241Am alpha particle source. Two dedicated experimental campaigns were performed at the JSI TRIGA reactor. The registered pulse height spectra from the detectors, using both 10B and 6LiF neutron converting layers, clearly demonstrated the neutron detection abilities of the SiC detector prototypes. The computed neutron detection sensitivity of the single prototype detectors demonstrates that scaling SiC detectors into larger arrays, of dimensions relevant for border and port radiation detectors, could enable neutron sensitivity levels matching gas-based detector technology.