| 000 | 04729nam a22002657a 4500 | ||
|---|---|---|---|
| 005 | 20251104125154.0 | ||
| 008 | 251029b ||||| |||| 00| 0 eng d | ||
| 043 | _aURS | ||
| 245 |
_aArtificial Intelligence-based Manifesto System _b/ Nido, Tristan Stephen E.... [et al.]. |
||
| 260 | _cMarch 2024 | ||
| 300 |
_a125 leaves : _c28 cm. |
||
| 336 |
_2rdacontent _atext |
||
| 337 |
_2rdamedia _aunmediated |
||
| 338 |
_2rdacarrier _avolume |
||
| 502 |
_aThesis _bBachelor of Science in Computer Engineering _cUniversity of Rizal System-Morong _d2024 |
||
| 520 | _aThe study aimed to develop an Artificial Intelligence-Based Manifesto System, assessing its acceptability across dimensions like Functional Suitability, Performance Efficiency, Compatibility, Usability, Reliability, Security, Maintainability, and Portability. It also profiles respondents based on age, sex, and weight to understand differences in perception. Performance testing and generating passenger reports are part of the evaluation at Binangonan Port during 2023-2024. The study included three hundred sixty-seven (367) participants, comprising three hundred fifty-two (352) end-users and fifteen (15) experts, using frequency and percentage analysis. Performance of the Artificial Intelligence-Based Manifesto System was tested by calculating time response mean and standard deviation. Acceptability was evaluated across dimensions like functional suitability and compatibility using weighted mean analysis. An independent t-Test assessed differences based on respondent profiles, providing insights into system performance and acceptability levels. This study combined developmental and descriptive research methods to advance the Artificial Intelligence-Based Manifesto System. Using frequency and percentage analysis, researchers made significant progress in the developmental phase. Evaluation of system acceptability through weighted mean and analysis of differences based on respondent profiles enhanced understanding of functionality and user reception. The profile of respondents is categorized by age, with twenty-three (23) percent aged eighteen and below, and seventy-seven (77) percent aged nineteen and above, totaling one hundred. Similarly, the respondents' profiles are presented based on sex, with males accounting for forty-nine (49) percent and females comprising fifty-one (51) percent, summing up to one hundred. Moreover, respondents are categorized by weight, with thirty-five (35) percent weighing fifty and below, and sixty-five (65) percent weighing fifty-one and above, totaling one hundred (100) percent. The Artificial Intelligence-Based Manifesto System is rated "Very Much Acceptable" across various dimensions: Security scored highest at 4.58, followed closely by Usability at 4.57 and Maintainability at 4.55. Functional Suitability and Portability received ratings of 4.54 and 4.52, respectively. Performance Efficiency and Reliability scored favorably at 4.40 and 4.20, falling within the "Very Much Acceptable" range. Compatibility, slightly lower at 4.14, still falls within an acceptable range. Overall, the system demonstrates strong performance and reliability in manifesto management. The Artificial Intelligence-Based Manifesto System is successful, embraced by users aged nineteen and above, mainly female, with diverse weight categories. It employs Haar Cascade and LBPH algorithms for accurate face recognition. It's highly accepted, with no significant impact from age, sex, or weight, except for portability concerning sex. It generates CSV reports for managing passenger data efficiently, aiding in boat assignment and accommodation. Researchers recommend to enhance the Artificial Intelligence-Based Manifesto System by considering additional variables beyond age, sex, and weight. Improve face recognition accuracy with upgraded storage and movable, high-resolution cameras. Ensure compatibility across operating systems and develop a smaller kiosk version with a sign-up feature. Use PDF format for manifesto lists and create an internet-compatible version for easier access. Future research could explore optimizing facial recognition performance under changing light conditions and aligning the system with evolving technological standards. | ||
| 700 |
_aNido, Tristan Stephen E. _eauthor |
||
| 700 |
_aGondraneos, Ericson R. _eauthor |
||
| 700 |
_aOabel, Mark Dharyl _eauthor |
||
| 700 |
_aQuiƱones, Rheylan S. _eauthor |
||
| 700 |
_aAlfonso, Paul Arvy V. _edegree supervisor |
||
| 856 |
_3Online Request for Student Unpublished Works _uhttps://forms.gle/7LqvGGkaDrUQqz429 |
||
| 856 | _uhttps://drive.google.com/file/d/1fJ62f1-Kn4nEbCBinWA6i7j1qvXyc4KN/view?usp=drive_link | ||
| 942 |
_2lcc _cT |
||
| 999 |
_c88569 _d88566 |
||