Early detection of plant diseases is essential for effective crop disease management to prevent yield loss. In this study, we developed a methodology classifying in rice leaves using four deep learning models and dataset with 2658 images healthy diseased leaves. Four models, namely LeafNet, Modified MobileNetV2, Xception, were compared. The LeafNet model involved updates LeafNet's architectural parameters, whereas transfer techniques applied the MobileNetV2 Xception pretrained models....

This paper presents an indoor positioning system (IPS) and motion tracking for the elderly, who are staying alone. The is able to track elderly location based on room that they currently situated recognizes whether moving or sitting. A smart wearable device featuring MPU6050 sensor, BLE beacon Raspberry Pi Zero W developed. sensory data from will be analyzed study type of publish MQTT server. For tracking, multiple 3 used as scanners scan its signal strength datasets have also been developed...

Electroencephalogram (EEG) signals are critical in interpreting sensorimotor activities for predicting body movements. However, their efficacy identifying intralimb movements, such as the dorsiflexion and plantar flexion of foot, remains suboptimal. This study aims to explore whether various EEG signal quantities can effectively recognize movements facilitate development Brain-Computer Interface (BCI) devices foot rehabilitation. research involved twenty-two healthy, right-handed...

Behavioral changes in daily home activities may be linked with health problems. Therefore, anomaly detection on sequence pattern of is important for healthcare monitoring. In this paper, an method based Long Short-Term Memory (LSTM) neural network proposed to detect anomalies activities. A comparison study LSTM and Hidden Markov Model (HMM) was conducted evaluate their performance under different training set size model's hyperparameters. The experimental results demonstrated that comparable...

Several studies on micro-expression recognition have contributed mainly to accuracy improvement. However, the computational complexity receives lesser attention comparatively and therefore increases cost of for real-time application. In addition, majority existing approaches required at least two frames (i.e., onset apex frames) compute features every sample. This paper puts forward new facial graph based 68-point landmarks using Facial Action Coding System (FACS). The proposed feature...

Solar trackers rely on a direct-current (DC) motor driver circuit to control the movement of solar panel. However, conventional DC drivers used in tracking system do not provide any options for speed and torque control. Hence, fixed leads either too fast or slow movement. Usually, output is set maximum. If load (solar panels' weight) small, maximum fully utilized therefore energy wasted. So, adjustable shows great potential commercialization because highly efficient can improves total...

Numerous research works have been put forward over the years to advance field of facial expression recognition which until today, is still considered a challenging task. The selection image color space and use alignment as preprocessing steps may collectively pose significant impact on accuracy computational cost emotion recognition, crucial optimize speed-accuracy trade-off. This paper proposed deep learning-based pipeline that can be used predict detected face regions in video sequences....

<span>An Internet of Things (IoT) FPGA-based home hub to automate control operations in a environment was designed and built. The proposed system uses an FPGA as its local analytic engine with IoT platform store the sensory data. programmed Verilog HDL using Quartus II provided by Altera. WiFi capability extended through ESP8266 chip ease interfacing various sensors connected it. can be configured monitored web application coded JavaScript. Various test cases were carried out on...

The number of older people is increasing in many countries. By 2030, it estimated that 15% the overall population will be comprised aged 65 and above. Hence, monitoring tracking elder activities to ensure they live an active life has become a major research topic recent years. In this work, elderly sub-activity system developed detect based on their physical indoor location. location combined project enhance context (i.e. sub-activities as defined project). An by using Bluetooth Low Energy...

The relationship between individuals and their thermal environment is pivotal not only for comfort but also health productivity. Thermal comfort, as defined by ASHRAE, reflects an individual's satisfaction with ambient conditions can be gauged using the ASHRAE scale. In past, traditional prediction models such Predicted Mean Vote (PMV) were used to evaluate comfort. Nevertheless, emergence of machine learning provides a more dynamic approach predict occupants. However, subjective nature...

Thermal comfort refers to the process of determining a pleasant working temperature by considering various environmental, occupational, and personal factors. With widespread adoption Internet Things (IoT) technologies, there is potential develop an IoT-based embedded system that directly integrates sensor data with building information collect necessary environmental factors for thermal comfort. This paper outlines development implementation remote monitoring, which gathers such as humidity...

The independent living of the elderly population is very much a concern and threaten due to their high tendency in falling. As worldwide aging grows tremendously, there need reliable fall detection solution which operates real-time at accuracy supports large scale implementation. Highly promising tool like Field Programmable Gate Array (FPGA) had been commonly used as hardware accelerator many emerging embedded vision based systems its performance low power consumption. result, it main...

Recent discovered technologies have exposed many new theories and possibilities to improve our standard of living. Medical assistance has been a major research topic in the past, efforts were put simplify process following treatment prescriptions. This paper summarizes work done developing LoRa driven medical adherence system order medicine for elderlies. The designed is composed two sections; embedded hardware device use patients at home Web application manage all along with their medicines...

In this paper, a self-attention based neural network architecture to address human activity recognition is proposed. The dataset used was collected using smartphone. contribution of paper multi-layer multi-head for and compared two strong baseline architectures, which are convolutional (CNN) long-short term (LSTM). dropout rate, positional encoding scaling factor also been investigated find the best model. results show that proposed model achieves test accuracy 91.75%, comparable result when...

In this paper, a flexible, high computation speed and cost effective field programmable gate array (FPGA)-based controller for an induction motor with field-oriented control, (FOC) is presented. All the control functions including space vector modulation based PWM waveform generation, algorithm rotor flux position estimation have been realized using FPGA to reduce total part count of hardware prototype hence provide low solution. The constructed FOC IC consists 6844 logic elements Cyclone,...

Purpose Power management of a wireless sensor node is important and needs to be designed efficiently without wasting excessive energy. The purpose this paper report on the improvement power node. Design/methodology/approach design involves implementation solar recharging technology with single‐ended primary inductance converter (SEPIC) in order achieve management. Findings combination SEPIC shows promising results for supplying Research limitations/implications idea can extended many other...

Abstract A two-stage 0.18μ m CMOS driver amplifier (DA) for WiMAX 3.3 to 3.8 GHz using common source (CS) inductive degeneration is presented in this paper. The first-stage a modified cascode with inter-stage inductor matching while the later stage conventional CS amplifier. On-wafer measurement shows an average voltage gain of 26.3 dB 3 bandwidth 0.8 GHz, output 1 compression (P dB) 12.2 dBm and power added efficiency (PAE) 45% at 3.5 consuming 25 mW from 1.8 V supply. At input proposed are...

We present in this paper a novel dataset (MMU VAAC) for violent actions against children recognition. This original has been recorded using Microsoft Kinect with the usage of child mannequin. MMU VAAC contains skeleton joints, depth, and RGB modalities.

The elderly population is experiencing high growth in most countries. In Malaysia, a majority of the households are dual-earner families, leaving their parents at home. Without caretakers to look after them, aging may be susceptible accidents. Therefore, an action recognition system which can automatically identify actions and whereabouts home needed. this paper, development testing wearable device with motion detection indoor positioning based on Random Forest Classifier presented....

<span>The world population of the elderly is expected to have a continuous growth and number living in solitude also increase coming years. As our health decline with age, early detection possible deterioration becomes important. Behavioral changes in-home activities can be used as an indicator decline. For example, routine activities. Past research mainly focused on detecting anomalies each type individually. In this paper, anomaly model detect collectively for day proposed. The...