International Conference on Humanoid, Nanotechnology, Information Technology,Communication and Control, Environment and Management 

About: International Conference on Humanoid, Nanotechnology, Information Technology,Communication and Control, Environment and Management is an academic conference. The conference publishes majorly in the area(s): Fuzzy logic & Image processing. Over the lifetime, 1183 publications have been published by the conference receiving 4355 citations.

Common Garbage Classification Using MobileNet

Abstract: Garbage classification is the first step in waste segregation, recycling, or reuse. MobileNet was used to generate a model that classifies common trash according to the following categories: glass, paper, cardboard, plastic, metal, and other trash. A dataset of 2527 trash images in.jpg extension was used for the training. The model used transfer learning from a model trained on the ImageNet Large Visual Recognition Challenge dataset. The TensorFlow for Poets git repository was cloned as a working directory to retrain the MobileNet model in 500 steps. The resulting baseline model, with a final test accuracy of 87.2% was optimized and quantized. In the Andoid app development, the optimized model (with 89.34% confidence) is preferred over the quantized model (with 1.47% confidence) based on the test using a plastic image. The model app was successfully installed in a Samsung Galaxy S6 Edge}+textbf{{mobile phone. The installed mobile app successfully identified a cardboard material in an image with a}{cardboard container. It is recommended to rerun the training using more steps as this may improve the quantized model performance since a quantized model is fit for mobile devices than models with no quantization.

Low cost smart security camera with night vision capability using Raspberry Pi and OpenCV

Abstract: In order to further maintain peace and provide security to people now a day, Closed-circuit television (CCTV) surveillance system is being utilized This study focused on the design and implementation of a low cost smart security camera with night vision capability using Raspberry Pi (RPI) and OpenCV The system was designed to be used inside a warehouse facility It has human detection and smoke detection capability that can provide precaution to potential crimes and potential fire The credit card size Raspberry Pi (RPI) with Open Source Computer Vision (OpenCV) software handles the image processing, control algorithms for the alarms and sends captured pictures to user's email via Wi-Fi As part of its alarm system, it will play the recorded sounds: “intruder” or “smoke detected” when there is a detection The system uses ordinary webcam but its IR filter was removed in order to have night vision capability

Identification of diseases in rice plant (oryza sativa) using back propagation Artificial Neural Network

Abstract: In this study, digital image processing was incorporated to eliminate the Subjectiveness of manual inspection of diseases in rice plant and accurately identify the three common diseases to Philippine's farmlands: (1) Bacterial leaf blight, (2) Brown spot, and (3) Rice blast. The image processing section was built using MATLAB functions and it comprises techniques such as image enhancement, image segmentation, and feature extraction, where four features are extracted to analyze the disease: (1) fraction covered by the disease on the leaf; (2) mean values for the R, G, and B of the disease; (3) standard deviation of the R, G, and B of the disease and; (4) mean values of the H, S and V of the disease. The Backpropagation Neural Network was used in this project to enhance the accuracy and performance of the image processing. The database of the network involved 134 images of diseases and 70% of these were used for training the network, 15% for validation and 15% for testing. After the processing, the program will give the corresponding strategic options to consider with the disease detected. Overall, the program was proven 100% accurate.

Path planning for mobile robots using genetic algorithm and probabilistic roadmap

Abstract: Mobile robots have been employed extensively in various environments which involve automation and remote monitoring. In order to perform their tasks successfully, navigation from one point to another must be done while avoiding obstacles present in the area. The aim of this study is to demonstrate the efficacy of two approaches in path planning, specifically, probabilistic roadmap (PRM) and genetic algorithm (GA). Two maps, one simple and one complex, were used to compare their performances. In PRM, a map was initially loaded and followed by identifying the number of nodes. Then, initial and final positions were defined. The algorithm, then, generated a network of possible connections of nodes between the initial and final positions. Finally, the algorithm searched this network of connected nodes to return a collision-free path. In GA, a map was also initially loaded followed by selecting the GA parameters. These GA parameters were subjected to explorations as to which set of values will fit the problem. Then, initial and final positions were also defined. Associated cost included the distance or the sum of segments for each of the generated path. Penalties were introduced whenever the generated path involved an obstacle. Results show that both approaches navigated in a collision-free path from the set initial position to the final position within the given environment or map. However, there were observed advantages and disadvantages of each method. GA produces smoother paths which contributes to the ease of navigation of the mobile robots but consumes more processing time which makes it difficult to implement in realtime navigation. On the other hand, PRM produces the possible path in a much lesser amount of time which makes it applicable for more reactive situations but sacrifices smoothness of navigation. The presented advantages and disadvantages of the two approaches show that it is important to select the proper algorithm for path planning suitable for a particular application.

Detection of Corn Leaf Diseases Using Convolutional Neural Network With OpenMP Implementation

Abstract: Maize is particularly one of the substantial crop supplies in the Philippines next to rice. The production of the maize crop plays a critical factor in the country's food industry. Disease is one of the major biotic and abiotic constraints to reduce crop yield. Some methods have advantages and disadvantages in contrary to using different accuracies and validity. The main objective of this study is to detect the disease through the leaf in the corn. This paper studied the benefit of both Convolutional Neural Network and OpenMP for disease identification. The study is effective with the objective of identifying and classifying what kind of disease is present in the leaf through the Convolutional Neural Network classifier. Alongside the usage of Convolutional Neural Network and OpenMP implementation, it unites its advantages especially on the sector of execution time rate. The system algorithm was tested using images that were captured for each disease in the corn leaf which was verified by an agriculturist and with the use of Raspberry Pi. As a result, the percent was met with an accuracy of 93%, 89%, and 89% in detecting Leaf Blight, Leaf Rust, and Leaf Spot, respectively. The use of Convolutional Neural Network via OpenMP allowed a high percentage of classification in classifying leaf diseases.