Driving has become essential in transporting people from one place to another. However, prolonged driving could cause muscle fatigue, leading to drowsiness and microsleep. Electromyography is an important type of electro-psychological signal that is used to measure electrical activity in muscles. The current study attempted to use machine learning algorithms to classify EMG signals recorded from the trapezius muscle of 10 healthy subjects in non-fatigue and fatigue conditions. The EMG signals and the time when muscle fatigue was experienced by the subjects were recorded. The mean frequency and median frequency of the EMG signals were extracted as dataset features. Six machine learning models were used for the classification: Logistic Regression, Support Vector Machine, Naïve Bayes, k-nearest Neighbour, Decision Tree and Random Forest. The results show that both the median and mean frequency are lower when fatigue conditions exist. In term of the classification performance, the Random Forest, Decision Tree and k-nearest Neighbour classifiers produced the accuracy levels of 85.00%, 83.75% and 81.25% respectively. Thus, the highest accuracy for classifying muscle fatigue due to prolonged driving was obtained by the Random Forest classifier, using both the median and mean frequency of the EMG signals. This method of using the mean and median frequency will be useful in classifying driver’s non-fatigue and fatigue conditions during prolonged driving.

Piezoelectric material has the ability to convert mechanical energy to electrical energy and vice versa, making it suitable for use as an actuator and sensor. When used as a controller in sensor mode, the piezoelectric transducer is connected to an external electrical circuit where the converted electrical energy will be dissipated through Joule heat; also known as piezoelectric shunt damper (PSD). In this work, a PSD is used to dampen the first resonance of a cantilever beam by connecting its terminal to an RL shunt circuit configured in series. The optimal resistance and inductance values for maximum energy dissipation are determined by matching the parameters to the first resonant frequency of the cantilever beam, where R = 78.28 k? and L = 2.9 kH are found to be the optimal values. To realize the large inductance value, a synthetic inductor is utilized and here, the design is enhanced by introducing a polarized capacitor to avoid impedance mismatch. The mathematical modelling of a cantilever beam attached with a PSD is derived and simulated where 70% vibration reduction is seen in COMSOL. From experimental study, the vibration reduction obtained when using the piezoelectric shunt circuit with enhanced synthetic inductor is found to be 67.4% at 15.2 Hz. Results from this study can be used to improve PSD design for structural vibration control at targeted resonance with obvious peaks. ABSTRAK: Material piezoelektrik mempunyai keupayaan mengubah tenaga mekanikal kepada tenaga elektrik dan sebaliknya, di mana ia sesuai digunakan sebagai penggerak dan pengesan. Apabila digunakan sebagai alat kawalan dalam mod pengesan, piezoelektrik disambung kepada litar elektrik luaran di mana tenaga elektrik yang ditukarkan akan dibebaskan sebagai haba Joule; turut dikenali sebagai peredam alihan piezoelektrik (PSD). Kajian ini menggunakan PSD sebagai peredam resonan pertama pada palang kantilever dengan menyambungkan terminal kepada litar peredam RL bersiri. Rintangan optimal dan nilai aruhan bagi tenaga maksimum yang dibebaskan terhasil dengan membuat padanan parameter pada frekuensi resonan pertama palang kantilever, di mana R = 78.28 k? dan L = 2.9 kH adalah nilai optimum. Bagi merealisasikan nilai aruhan besar, peraruh buatan telah digunakan dan di sini, rekaan ini ditambah baik dengan memperkenalkan peraruh polaris bagi mengelak ketidakpadanan impedans. Model matematik palang kantilever yang bersambung pada PSD telah diterbit dan disimulasi, di mana 70% getaran berkurang pada COMSOL. Hasil dapatan eksperimen ini menunjukkan pengurangan getaran yang terhasil menggunakan litar peredam piezoelektrik bersama peraruh buatan menghasilkan 67.4% pada 15.2 Hz. Hasil dapatan kajian ini dapat digunakan bagi membaiki rekaan PSD berstruktur kawalan getaran iaitu pada resonan tumpuan di puncak ketara.