Jennifer C. Dela Cruz

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

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 Philippines 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.

Antenna Characterization and Determination of Path Loss Exponents for 677 MHz Channel Using Fixed and Portable Digital Terrestrial Television

This paper presents propagation measurements results using Integrated Services Digital Broadcast-Terrestrial (ISDB-T) to investigate the characteristics of 6MHz wideband Digital Terrestrial Television channel at 677MHz for flxed and portable reception. Empirical measurements were done at predetermined measurement points consisting of 21 radials for a total of 92 locations extending to 20 kilometers around the National Broadcasting Network (NBN) digital transmitter. Characterizations were conducted using antenna heights of 9m (flxed reception), 3m (flxed reception), and 1.5m (portable reception). Modulation Error Rate (MER), power received, fleld strength and delay proflles were captured to help characterize the channel in an urban area in and around Metro Manila at day time for temperatures ranging from 26 - C to 32 - C. Measured fleld strength was compared to NTC F(50;90) curves. Polynomial flt using least square errors was used to plot the fleld strength coverage of NBN. For large-scale fading, it is observed that signal power conforms to Log Normal distribution. The study helped identify problem sites within the coverage. These are locations within the coverage area or at the outskirts of the coverage area where DTV signal is not received at all. A more accurate description of the DTT channel will lead to a better design of the parts of the Digital Television system from the network to transmitting system and receiving equipment. Path loss exponents computed for the three antenna heights can be helpful in developing empirical prediction models.

Full-wave AC-DC converter in CMOS 0.18 micron for vibration electromagnetic energy harvest

This paper presents the design and implementation of full-wave AC-DC converter in 0.18 micron CMOS technology. Five sample voltages were taken from vibration electromagnetic harvester technology (VEHT) and simulated in three operating temperatures of 0, 25, and 70 degrees Celsius. The simulation results yielded: a maximum average power efficiency of 95.02% at 0°C 95.61% at 25°C, and 91.05% at 70°C; and an average regulation percentage of 10.45% at 0°C, 24.91% at 25°C, and 10.15% at 70°C.

Development of low-cost embedded-based electrooculogram blink pulse classifier for drowsiness detection system

This paper discusses the development of a low-cost embedded-based electrooculogram (EOG) blink pulse classifier. A signal conditioning circuit from a single quad operational amplifier (Op-Amp) and an Arduino based on the ATmega32u4 AVR 8-bit microcontroller board comprised the major components of the embedded-based classifier. The evaluation of the nearest neighbor algorithm classifier resulted to an accuracy of 87.14%, precision of 93.33% and sensitivity of 80.00%. Further, based on the participants who evaluated the drowsiness detection system the results were 3.38 and 4.13 with verbal interpretations of comfortable and very convenient respectively.

Design and development of a material impact tester using neural network for concrete ratio classification

Concrete can be molded to any shape and size, and once hardened it can withstand tremendous amount of compressive loads. This ability of concrete makes it the most widely used material in construction and thus, a need for identification and prediction of its compressive strength. Nondestructive tests have been solely preferred for this purpose and a drop-impact test machine prototype named; Material Strength Impact Tester requires a validation of its test results. The study implements an Artificial Neural Network in evaluating the test results from three concrete class ratios. The resulting test and validation of the sample specimens from the developed prototype showed a strong correlation to its corresponding concrete class ratio. The study strengthens the claim of the previous literature as to the prototypes functionality as a drop-impact testing machine.

Facial fluid synthesis for assessment of acne vulgaris using luminescent visualization system through optical imaging and integration of fluorescent imaging system

Acne vulgaris, commonly called as acne, is a skin problem that occurs when oil and dead skin cells clog up in a person’s pores. This is because hormones change which makes the skin oilier. The problem is people really do not know the real assessment of sensitivity of their skin in terms of fluid development on their faces that tends to develop acne vulgaris, thus having more complications. This research aims to assess Acne Vulgaris using luminescent visualization system through optical imaging and integration of image processing algorithms. Specifically, this research aims to design a prototype for facial fluid analysis using luminescent visualization system through optical imaging and integration of fluorescent imaging system, and to classify different facial fluids present in each person. Throughout the process, some structures and layers of the face will be excluded, leaving only a mapped facial structure with acne regions. Facial fluid regions are distinguished from the acne region as they are characterized differently.

Soil pH and nutrient (Nitrogen, Phosphorus and Potassium) analyzer using colorimetry

The study was about creating a device that can use colorimetry to determine the Nitrogen, Phosphorus and Potassium content and pH of the soil to be cultivated by using the chemicals of the Soil Test Kit in giving nutrient recommendations. Trials were done to produce the actual color reaction of the reactants which served as the color references. The RGB values were extracted using TCS3471 color sensor and an LDR color sensor. The device was tested using three samples each for every nutrient and pH with ten trials each. The benchmark value used was 0.05 to have a 95% level of confidence. The computed value of Chi-Square was equal to 0 using the table for the critical values 0.05 corresponds to the critical value of 3.841. Therefore, computed value was less than the critical value which can be concluded that there was no significant difference between the proposed device reading the soil pH and nutrient content and the human resource reading.

Items-mapping and route optimization in a grocery store using Dijkstra's, Bellman-Ford and Floyd-Warshall Algorithms

The study applies three shortest-path-finding algorithms namely Dijkstras, Bellman-Ford and Floyd- Warshall Algorithms into a grocery store to provide users the shortest path to be traversed by the user while getting the items on their grocery list. The application created is a server-client-based system with the client being an application installed in an android tablet while the server application is a C# program based on Microsoft Visual Studio Environment. The path lengths provided by the three algorithms are equal for most instances but they differ on computational time based on different number of items in the list. Actual tests were conducted in a grocery store and the time spent to buy, distance travelled by the user and steps taken have all been reduced after using the application.

Design of microstrip TV antenna for in-campus digital broadcast system at 479 MHz

The Philippine television industry is currently in the phase of transition from analog into digital broadcast. Along with the upcoming Mapua Institute of Technologys in campus digital television broadcast, the study aims to design and characterize a working microstrip patch antenna optimized to receive the digital broadcast at 479 MHz. Using a simulation tool, High Frequency Structural Simulator (HFSS), four antennas with different specifications were designed and three antennas were made for every design. The Rectangular and circular patch design was used using two different materials, fiber glass (FR-4) and PTFE (Duroid 5880). Using a consumer grade ISDB-T Digital TV Box, the testing of signal level was done in four key locations inside the vicinity of the campus and two test points for every location. Comparing the average resulting received signal level for each design, it was found out that the Circular FR-4 is the only antenna that achieved a perfect picture on all 8 test point locations. Moreover, the Circular FR-4 is the smallest antenna with a lateral dimension of 7inx7in, -18.704dB return loss, VSWR of 1.2602, and a bandwidth of 222 MHz. Surprisingly, at 479 MHz, it was found out that each of the 4 antenna design performs better than the stock antenna that is commercially available.

Microcontroller-based fertilizer dispenser for rice crop

With this study, the researchers explored the potentials of innovating the distribution of fertilizers, improving the distribution of fertilizers in rice crops and made it more efficient. Statistical tests were conducted to determine significant difference in yield in a rice crop season. Particularly with the help of previous reviews of related literature on color sensor, color analysis, leaf color chart, a microcontroller-based fertilizer dispenser for rice crops was developed and ended up with a significant difference in rice yield at a 5% level of significance.