Figure 1 - uploaded by Alvin Sarraga Alon
Content may be subject to copyright.
Source publication
A smoke detector is an instrument that detects smoke usually as a fire warning. The devices available are placed in the ceiling and they take too long to respond to smoke. These smoke alarms are helpful when the smoke is big enough to reach the ceiling and alarm that there is a fire in the area. It takes a big fire and a lot of smoke before it can...
Contexts in source publication
Context 1
... study developed a system that detects the presence of smoke automatically and tells the user about the detected smoke by using the object-detection algorithm in raspberry pi. Figure 1 shows the methodology of the study. ...
Context 2
... training, the trained model can now be use and test using the pi-camera or webcam as shown in Fig. 9. It should detect smoke and inform the user by announcing the "smoke detected" sound for every ten counts of detection via speaker or buzzer as shown in Fig. 10. ...
Context 3
... study created a 3D design prototype of the simulated home-environment as shown in Fig. 11. During the process of creating the design, the design took considerations to the size of the case so that the camera would fit and would cover the entire prototype to be detected. Figure 12 shows that the actual prototype used acrylic glass for the case and foam for the seats and Sintra board for the table, TV and the table. The size ...
Context 4
... the process of creating the design, the design took considerations to the size of the case so that the camera would fit and would cover the entire prototype to be detected. Figure 12 shows that the actual prototype used acrylic glass for the case and foam for the seats and Sintra board for the table, TV and the table. The size of the case is 15 by 10 by 7 inches. ...
Context 5
... total loss value given is a sum of the classification loss and the localization loss as shown in Fig. 13. The optimization algorithms are trying to reduce these loss values until the researchers are satisfied with the results and considered the model 'trained'. Generally, the lower the score the better the model. The X-axis accounts for the number of phases while the Y-axis reflects the overall loss rate. The study used a loss function to ...
Context 6
... system detects the smoke inside or outside the case, as long as the smoke is inside the range of the camera. Through this, the device automatically detects the smoke and it will inform the user of the detected smoke. It will trigger the alarm "smoke detected" continuously as long as it detects smoke. Fig. 14 shows the testing results using the model. Table 2 shows the testing results and Fig. 15 shows the actual testing of the system using the simulated-home ...
Context 7
... the case, as long as the smoke is inside the range of the camera. Through this, the device automatically detects the smoke and it will inform the user of the detected smoke. It will trigger the alarm "smoke detected" continuously as long as it detects smoke. Fig. 14 shows the testing results using the model. Table 2 shows the testing results and Fig. 15 shows the actual testing of the system using the simulated-home ...
Citations
... After morphological lights pairing and edge boundaries detection, the symmetry check is conducted in the candidate bounding boxes to verify the existence of the vehicle [16]. Several studies or research have been conducted using a variety of approaches or methods for object detection, particularly using deep learning's strength [17]- [21]. ...
Accidents happen everywhere and at any moment, but the road is one of the most dangerous locations where accidents occur. One of the common vehicle or road accidents is the rear-end collision, this occurs when a vehicle crashes or hits a vehicle in front of it. With the growing number of rear-end collisions, various technologies or mechanisms have been created or invented with the advent of technology to avoid and prevent rear-end collisions, such as crash sensors, a collision detection system to identify or measure the distance between two cars traveling in the same path, etc. In recent years, with the help of AI emerging technologies, some studies and research suggest brake light detection for avoidance or as prevention of rear-end collision incidents. The study focused on developing a brake light detection system for the prevention or avoidance of rear-end collision accidents using deep learning with high accuracy. The study uses the YOLOv3 algorithm for training and validation of the datasets along with the Pascal VOC and LabelImg tool for annotating the datasets. Result of testing, the system ranges from 40.0553% to 84.74234% detection accuracy. This supports that the system is capable to detect brake lights to prevent rear-end collisions
... The YOLOv3 is the choice of the system as this is one of the best algorithms for object detection [17]. Numerous studies or research have been conducted using a variety of approaches or methods for object detection, especially using deep learning's strength [18]- [22]. Also, this is easier to used and custom datasets are easy to train. ...
Vehicles have been a big part of many lives; from the time it is invented and as it increases popularity in the 20th century. Though they offer the benefit of convenience, they also have certain negative effects as they add to air pollution and global warming, as well as risks when they are not handled properly. In recent years, the number of vehicles on the road is rapidly increasing and it causes different major concerns. One of the major effects of this increasing volume of vehicles is the traffic congestion it caused on our roads especially in the urban areas. This traffic congestion became one of the major problems in many cities in the world including Metro Manila, Philippines. Many options are discussed and implemented by the traffic management but it seems that it is still unsolved. In recent years, traffic congestions became unpredictable, there are parts of the cities that don’t experience traffic congestion then suddenly traffic builds up to that area. Also, traffic congestion might happen every hour of the day. With this concern, the study proposed a system for vehicle headlight recognition for on-road vehicle detection and counting. This study focused on the detection of the headlight of every vehicle that will be seen on the perimeter of the installed camera. The system can detect headlight vehicles during daytime and nighttime as we trained the AI to recognized the headlights in these scenarios. Possible applications of this system can be in monitoring the volume of vehicles within the area and it can be used by traffic management authority in monitoring the build-up of traffic or traffic situation in an area so that they can provide an immediate solution, such as re-routing, one-way street conversions, etc.
... However, despite good results achieved the methods were not work due to some constraints caused by the suspended traffic lights in the urban areas. Several research or study have been performed using a range of techniques or methods for object identification, with deep learning's power being especially useful [22]- [26]. ...
... The system also used classifiers, the Support Vector Machine (SVM) and feed-forward backpropagation neural network [15]. Various studies or research have been carried out using various approaches or methods for object detection, especially using the power of deep learning [16]- [20]. ...
... As several studies used different deep learning and image processing methods for the license plate detection [10]- [13], this study would like to propose the same system, a license plate detection that can be used in a different application by utilizing a simple but effective algorithm that is capable of detecting license plate accurately. Numerous studies or research have been conducted using a range of techniques or methods for object detection, particularly using deep learning's ability [14]- [18]. Also, the decision to use this algorithm is due to it is easier to used and custom datasets are easy to train. ...
... MobileNet is a lightweight CNN model designed for embedded hardware platform. By introducing a depth separable convolution layer, the standard convolution is decomposed into a combination of depth convolution which only extracts features from a single channel and point convolution that fuses all channel information, thus greatly reducing the amount of parameters and realizing model acceleration [13]. e number of input channels is n i , and the size of the input characteristic graph is w i and h i . ...
In the traditional scientific research and production activities, due to the lack of sufficient communication and communication between researchers, the phenomenon of waste of scientific research resources occurs from time to time, which hinders the efficiency of scientific research output. Based on the design principle of the semantic knowledge framework, this paper puts forward the definition of ontology and semantic relationship of the collaborative system of scientific researchers. In this paper, a framework of collaborative semantic knowledge among researchers is established through decentralized semantic information exchange architecture. In this article, the simulation is verified by experiments and compared with other exchange architectures. The results of the experiment confirmed the semantic information exchange architecture based on semantic knowledge proposed in this paper is 10.39% faster than the traditional centralized method in terms of data volume; the construction speed under the data node perspective is 12.84% higher than that of the traditional centralized construction method; the subject query speed is 36.84% higher than that of the traditional centralization method; the predicate query speed is 31.58% higher than that of the traditional centralization method. The experimental results confirm that the semantic information exchange architecture based on the semantic knowledge framework is feasible, and it has excellent performance in terms of construction speed and query speed. Under the background that researchers rely more and more on collaborative technology to interact with other members, this paper has a certain reference value and exploration value and proposes a new idea of group collaboration system under the framework of semantic knowledge.
... To further improve the developed system, the variations of the Wi-Fi signals fluctuations and the Feedback mechanism of the UAV and its MCU should be further refined using other techniques or devices. Techniques like Dynamic Time Warping [21] or Inference Approach [22] to make it more efficient in identifying its position would help. ...
Unmanned Aerial Vehicle navigation systems are commonly based on wireless transmissions, such as Global Positioning System (GPS), which are widely used in UAV self-positioning activities. However, indoor environments for UAV remains unexplored to many types of research, limiting the applications of UAV in the areas where the satellite-based GPS have difficulty to penetrate. The autonomous operation of this system in outdoors relies heavily on the Global Navigation Satellite System (GNSS) receiver, which provides them with location coordinates in a global geographical system. However, the accuracy of GNSS is severely attenuated in an indoor environment where they cannot be reliably used. In this study, it aims to develop a system for Unmanned Aerial Vehicle in navigating in an indoor environment. The system uses the Wi-Fi signal and the Trilateration algorithm to do the task. A hobby-grade UAV was utilized by modifying its flight controller, and the Arduino was used to do this task. A customized remote controller with GUI using VB.net was also developed to communicate with the flight controller. The system was tested, and the accuracy of the flight path was compared to the actual flight path and the expected flight path. The developed system has an accuracy that ranges from 0.43 to 1.93m with a mean accuracy of 1.11m.
The value of money can be quickly grasped by the fact that virtually all economic, social, and other tasks are carried out and done using money. With dramatic shifts in global growth and other total human needs, the value of money is rising day after day. Money is an important asset that will allow you to run your life. The exchange of goods for products is an older custom, and you cannot buy something you want without any money. It's straightforward to use money, you just have to glance at the currency instantly, pull the appropriate sum of cash out, and that's it. But that may become a challenging job for those who cannot see. Among the most significant issues facing visually impaired people is the identification of money, particularly for paper currency. In this study, it focuses on this problem and is based on a machine vision technique called object detection. The study used Raspberry Pi 4 as a microcontroller, Pi Camera as its capturing device, and a speaker for audio in announcing the detected bill. EyeBill-PH has been done with an overall testing accuracy of 86.3%.
This study aims to developed an automated Game of the Generals "GG" pieces rank detection to eliminate the presence of an arbiter. The system can detect each GG pieces and addressed the issues of being biased by the arbiter in determining who wins the game. Upon series of experiments conducted by the proponents, the system shows 100% accuracy of detection of pieces ranking. The designed system provides improved performance on deciding whose piece wins in faceoff of both team and to display the status of every piece tapped on the device and also display whose piece win in every game. The design of the device with RFID technologies leads to the collection of data about which piece has been ready and tapped and which piece has turned next, the portion of which succeeds in their encounter with the remaining pieces left. The use of Rule-based algorithm has been introduced for decision making of an arbiter and resulted to detect and decides whose player piece that have been tapped win, loss or draw.
