One of the problems in the medical field is incorrect diagnosis, particularly over-diagnosis and under diagnosis. One of the illnesses that is currently researched upon is pneumonia. Several methodologies are employed to further validate this diagnosis. Often, to achieve the goal, medical experts rely on an x-ray image. In this study, the basis is still x-ray images with the incorporation of image processing and machine learning. MobileNetV2 is utilized as the convolution neural network model. The produced frozen graph is injected to Android Studio to produce an android mobile application which will serve as a diagnostic tool. The mobile application has high accuracy and considered reliable because of testing and validation results. This study generally aims to provide a reliable low-cost aid for medical professionals in diagnosing pneumonia.

Split air conditioning units are crucial for ensuring the thermal comfort of buildings. Conventional scheduling or pre-timed system activities result in high consumption and wasted energy. This study proposes an intelligent control system for automatic setpoint adjustment in an educational building based on real-time indoor and outdoor environmental and room occupancy data. Principal component analysis was used to identify energy consumption components in ramp-up and steady-state power usage scenarios. K-means clustering was then used to categorize environmental scenarios and occupancy patterns to identify operational states, predict power consumption and environmental variables, and generate fuzzy inference system rules. The application of rough set theory eliminated rule redundancy by at least 99.27% and enhanced computational speed by 96.40%. After testing using real historical data from an uncontrolled environment and occupant thermal comfort satisfaction surveys reflecting a range of ACU setpoints, the enhanced inference system achieved daily average power savings of 25.56% and a steady-state power period at 63.24% of the ACU operating time, as compared to conventional and variable setpoint operations. The proposed technique provides a basis for dynamic and data-driven decision-making, enabling sustainable energy management in smart building applications.

Typical building directories are commonly seen on signages where people walk pass by it barely noticing. RamNav is an advance, responsive, and complete directory which enables people to locate a specific room in the building through speech recognition and give the information they need. The directory system caters speech recognition feature used for performing query and output the room details for queries such as: floor level, nearby room names, maplike image, and a predefined QR code that the user can scan using their phones to show a copy of query result in their mobile devices. The main tools used by the researchers for this project are the Microsoft Speech Services for the Speech-to-Text API, Python programming using PyCharm IDE, and Tkinter as the Python GUI library. RamNav has been exceptional in acquiring and processing the speech of the user even on different environment situations and met all the proponents desired output. It attained an accuracy rate of 98.12% overall for its speech recognition features. Meanwhile, a keyword recognition rate of 97.05% on 518 total keywords for the reliability objective.

The COVID-19 pandemic has introduced the new normal of introducing contactless transactions and interactions. This made voice assistive systems useful to business process requiring company to client communications. A generative-based interactive speech artificial intelligence for Asia Pacific College's (APC) Admissions Office is discussed in this paper. It collects data from user's voice input and generates a response that answers questions and inquiries concerning the services of the office. Software tests revealed an average accuracy in getting the right answers to questions of 88%. The system was able to provide the correct response in the presence of background noise at 91.5%. The average response time of the system was 2.36 seconds.

The development of a model for identifying smokers in closed-circuit video (CCTV) footage is presented in this research work employing the MobileNetv2 - SSD (Single Shot MultiBox Detector) algorithm. The vitality of the research hinges in its ability to automatically monitor and enforce no-smoking policies in the Philippines, improving public health and safety. With the usage of this model, smoking infractions can be reduced while also alleviating the workload of manual monitoring while providing prompt solutions. According to the research’s finding, the proposed model exhibits excellent results in terms of accuracy, precision, sensitivity/recall, specificity, and F1-score evaluation. The following test results for the MobileNetV2 SSD algorithm were obtained for the detection of smokers: Accuracy: 0.9722, Precision: 0.9728, Sensitivity/Recall: 0.9722, Specificity: 0.9722, and F1-score: 0.9722. These findings demonstrate the developed model’s efficacy and durability in accurately recognizing smoking incidents in CCTV footage. This study’s findings pave the way for further research, such as adding multimodal data and building real-world applications of the smoker detection system.