Breathing is one of the vital signs used to assess the physical health of a subject. Non-contact-based measurements of both breathing rate and changes in breathing rate help monitor health condition of subjects more flexibly. In this paper, we present an improved real-time camera-based adaptive breathing monitoring system, which includes real time (1) adaptive breathing motion detection, (2) adaptive region of interest detection to eliminate environmental noise, (3) breathing and body movement classification, (4) respiration rate estimation, (5) monitor change in respiration rate to examine overall health of an individual, and (6) online adaptation to lighting. The proposed system does not pose any positional and postural constraint. For evaluation, 30 videos of 15 animals are tested with drugs to simulate various medical conditions and breathing patterns, and the results from the proposed system are compared with the outputs of an existing FDA-approved invasive medical system for patient monitoring. The results show that the proposed method performs significantly correlated RR results to the reference medical device with the correlation coefficient equal to 0.92 and p -value less than 0.001, and more importantly the proposed video-based method is demonstrated to produce alarms 10 to 20 s earlier than the benchmark medical device. Graphical abstract The proposed system flowchart to extract the respiratory pattern from video.

<em>Oil palm smallholders require knowledge of fertilization because the fertilization is an influential factor in the productivity of fresh fruit bunches. On the other hand, the oil palm smallholders generally don’t have fertilizer expertise and they face a difficulty in determining good fertilization (good in type, dosage, time and manner) based on various literatures. Therefore, a simple application that can provide recommendations for palm oil fertilization is developed. The recommendations are based on expert knowledge that have been written in various literatures. Like an expert system, the application is designed by compiling knowledge base, constructing an inference engine and creating a prototype. The knowledge bases, that are facts and rules, are prepared using rule-based reasoning approach, the inference engine is compiled using forward chaining methods and the prototype is made using a visual basic application in a spreadsheet application. The application design uses facts of plant varieties, phases or age of plants, soil types, nutrient deficiency in soil and plants, rainfall, fertilizer content, and nutrient properties (synergies or antagonist) on fertilizers. The Applications made capable of providing fertilization recommendations by conducting forward chaining based on data-given facts and rules that have been made on the knowledge base.</em>

No abstract

No abstract

No abstract