Cristina Amor Rosales

Cristina Amor Rosales

Auto-generated profile, based on publicly available information

Cristina Amor Rosales

Batangas State University–The National Engineering University

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 October 2024 in Natural and Engineering Sciences
Verified
Journal Article
Open access
SSShaowei Shi
Shaowei Shi
FCFelicito Caluyo
Felicito Caluyo
RHRowell Hernandez
Rowell Hernandez
JSJeffrey Sarmiento Sarmiento
Jeffrey Sarmiento Sarmiento
CRCristina Amor Rosales
Cristina Amor Rosales
The prompt detection of plant diseases mitigates adverse effects on plants. Convolutional neural networks (CNN) and intense learning are extensively utilized in computer vision and recognition of pattern tasks. Scientists presented several DL algorithms for the detection of plant illnesses. Deep learning (DL) models need many parameters, resulting in extended training durations and complicated implementation on compact devices. This research presents a unique DL model utilizing the inception tier and residual connections. Depthwise differentiated convolution is employed to decrease the variable count. The suggested model has undergone training and evaluation using three distinct plant disease databases. The level of accuracy achieved on the PlantVillage database is 97.2%, on the rice disease database is 98.4%, and on the cassava database is 96.3%. The suggested model attains superior accuracy relative to state-of-the-art DL methods while utilizing fewer variables.

17 October 2024 in Natural and Engineering Sciences
Verified
Journal Article
Open access
WTWeichao Tan
Weichao Tan
CCCelso Bation Co
Celso Bation Co
RMRowell M.HErnandez
Rowell M.HErnandez
JSJeffrey Sarmiento Sarmiento
Jeffrey Sarmiento Sarmiento
CRCristina Amor Rosales
Cristina Amor Rosales
With the popularization of new energy vehicles, lithium battery systems, as the main components of new energy vehicles, have the characteristics of short life cycles and harmful substances inside. The green treatment of lithium battery systems has become a research hotspot. Disassembly and recycling are essential means of reusing waste in lithium battery systems. Due to the wide variety of lithium battery systems, the lack of unified design standards, and the high flexibility requirements for disassembly, manual disassembly is currently the primary method used. However, this method can cause health hazards to oneself when dismantling some harmful components. The optimization of the dismantling process route for lithium batteries is a crucial step before dismantling, which directly determines the economic benefits of dismantling. However, unlike general electromechanical products, lithium batteries have prominent safety issues during the dismantling process, so the safety requirements for their dismantling process route are relatively high. Given the substantial absence of parametric evaluation and modification in prior research, this work investigates the influence of the most significant factors on the power density of biosensors. A conduction-based framework was employed to ascertain these variables, and the calculations were performed utilizing a neural network. The neural network was developed with Particle Swarm Optimization (PSO). Based on this, this article considers studying the optimization method of the lithium battery safety disassembly process to maximize safety and economic benefits comprehensively. Based on the essential characteristics of lithium-ion battery systems, an analysis is conducted on the allocation method of difficulty level for human-machine cooperation tasks and the impact indicators of task allocation. Then, a product disassembly hybrid diagram is established, and on this basis, multiple sets of human-machine cooperation disassembly sequences are generated. Finally, a multi-objective optimization model for disassembly cost, difficulty, and time is established. Finally, taking the Tesla Model 1sPBS waste lithium battery as an example, the safety prediction model for dismantling the waste lithium battery and the optimization model for the safety dismantling process route were solved to verify the effectiveness of the above optimization method.

20 June 2012 in ASEAN Journal on Science and Technology for Development
Verified
Journal Article
Open access
PDF file
PMP.M Macatangay
P.M Macatangay
EME.C Mangundayao
E.C Mangundayao
CRC.A.M Rosales
C.A.M Rosales
Development of useful composite materials out of agricultural waste has become a desirable option in recycling. This led to the production of composite boards being used in the construction industry. In this paper, three types of available agricultural wastes in the province of Batangas — peanut shells, corn husks and banana sheath — were independently utilized in the production of composite boards. The raw materials were either air or sun dried, then crushed (for peanut shells) and extracted (for banana sheath and corn husks) before mixing with the binder. Urea formaldehyde (UF) was used as binder for peanut shells and banana sheaths while cleaned used plastic bags were chopped and mixed with corn husks before subjecting to hot compress machine. For each mat, the followingproportions were used:1000 gm banana fibres, 500 gm of UF mixed with 250 gm of water; 720 gm of crushed peanut shells, 133 gm UF with 12% resin content; 40% corn husks, 60% plastic strips by weight. The physical and mechanical characteristics like modulus of rupture (MOR), internal bond, face screw head test (FSHT) or Nail Head Pull through (NHPT), water absorption and thicknessswelling were determined for each board and the results were compared to the values set by the Philippine National Standards (PNS). Based on statistical results, the corn husk-plastic composite boards conformed to all parameters in the PNS; the density, thickness swelling, IBS, and NHPT/ FSHT of peanut shell-resin composite boards conformed to the PNS; and the thickness swelling,density, MOR and NHPT/FSHT of the banana sheath-UF composite boards conformed to the PNS.

30 October 2024 in Natural and Engineering Sciences
Verified
Journal Article
Open access
LZLiu Zigui
Liu Zigui
FCFelicito Caluyo
Felicito Caluyo
RHRowell Hernandez
Rowell Hernandez
JSJeffrey Sarmiento Sarmiento
Jeffrey Sarmiento Sarmiento
CRCristina Amor Rosales
Cristina Amor Rosales
Integrated communication networks (CN) have proven successful in tracking environmental activities, wherein several sensors are installed throughout diverse surroundings to gather data or observe certain events. CNs, comprising several interacting detectors, have proven effective in various applications by transmitting data via diverse transmission methods inside the communication system. The erratic and constantly changing surroundings necessitate conventional CNs to engage in frequent conversations to disseminate the latest data, potentially incurring substantial connection expenses through joint data gathering and dissemination. High-frequency communications are prone to failure due to the extensive distance of data transfer. This research presents a unique methodology for multi-sensor environmental monitoring networks utilizing autonomous systems. The transmission system can mitigate elevated communication costs and Single Point of Failing (SPOF) challenges by employing a decentralized method that facilitates in-network processing. The methodology employs Boolean systems, enabling a straightforward verification process while preserving essential details about the dynamics of the communication system. The methodology further simplifies the data collection process and employs a Reinforcement Learning (RL) technique to forecast future events inside the surroundings by recognizing patterns.

1 January 2026 in Indonesian Journal of Electrical Engineering and Computer Science
Verified
Journal Article
Open access
PDF file
RSRenz Raniel V. Serrano
Renz Raniel V. Serrano
JDJen Aldwayne B. Delmo
Jen Aldwayne B. Delmo
CRCristina Amor M. Rosales
Cristina Amor M. Rosales
Vehicle classification plays a vital part in the development of intelligent transportation systems (ITS) and modern traffic management, where the ability to detect and identify vehicles accurately in real time is essential for maintaining road efficiency and safety. This paper presents an enhancement to the YOLOv8m model by refining its activation function to achieve higher accuracy and faster response in diverse traffic and environmental situations. In this study, two alternative activation functions—Mish and Swish—were integrated into the YOLOv8m structure and tested against the model’s default sigmoid linear unit (SiLU). Training and evaluation were carried out using a comprehensive dataset of vehicles captured under different lighting and weather conditions. The experimental findings show that the modified activation design leads to better model convergence, improved generalization, and a noticeable boost in detection performance, recording up to 5.4% higher accuracy and 6.6% better mAP scores than the standard YOLOv8m. Overall, the results confirm that fine-tuning activation behavior can make deep learning models more adaptive and reliable for vehicle classification tasks in real-world intelligent transportation environments.

1 November 2017 in Journal of Sensors
Verified
Journal Article
Open access
PDF file
CRCristina Amor Rosales
Cristina Amor Rosales
HLHyun Jong Lee
Hyun Jong Lee
WKWonjae Kim
Wonjae Kim
CPChang Kyu Park
Chang Kyu Park
This study focused on the analysis of the frequency spectra of impact sounding test performed on composite slabs with different interlayer condition. Distinct and consistent characteristics of the frequency spectra were observed from the impact signals. The consistency of results for bonding condition at varying temperature was also investigated. Results of laboratory tests were compared to different bonding condition observed in the field. Finally, a proposed decision matrix analysis was presented and successfully identified the interface bonding condition. The proposed decision matrix is composed of four zones characterizing each interlayer condition based on the features of impact signals. Field and laboratory assessment conform to decision matrix result.