Search

A persistent purpose for self-powered and wearable electronic devices is the fabrication of graphene-PVDF piezoelectric nanogenerators with various co-solvents that could provide enhanced levels of durability and stability while generating a higher output. This study resulted in a piezoelectric nanogenerator based on a composite film composed of graphene, and poly (vinylidene fluoride) (PVDF) as a flexible polymer matrix that delivers high performance, flexibility, and cost-effectiveness. By adjusting the co-solvent in the solution, a graphene-PVDF piezoelectric nanogenerator can be created (acetone, THF, water, and EtOH). The solution becomes less viscous and is more diluted the more significant the concentration of co-solvents, such as acetone, THF, and EtOH. Additionally, when the density is low, the thickness will be thinner. The final film thickness for all is ~25 µm. Furthermore, the- crystal phase becomes more apparent when graphene is added and combined with the four co-solvents. Based on the XRD results, the peak changes to the right, which can be inferred to be more dominant with the β-phase. THF is the co-solvent with the highest piezoelectric output among other co-solvents. Most of the output voltages produced are 0.071 V and are more significant than the rest.

Recently, human activity recognition (HAR) techniques have made remarkable developments in the field of machine learning. In this paper, we classify human gestures using data collected from a curved piezoelectric sensor, including elbow movement, wrist turning, wrist bending, coughing, and neck bending. The classification process relies on data collected from a sensor. Machine learning algorithms enabled with K-mer are developed and optimized to perform human gesture recognition (HGR) from the acquired data to achieve the best results. Three machine learning algorithms, namely support vector machine (SVM), random forest (RF), and k-nearest neighbor (k-NN), are performed and analyzed with K-mer. The input parameters such as subsequence length (K), number of cuts, penalty parameter (C), number of trees (n_estimators), maximum depth of the tree (max_depth), and nearest neighbors (k) for the three machine learning algorithms are modified and analyzed for classification accuracy. The proposed model was evaluated using its accuracy percentage, recall score, precision score, and F-score value. We achieve promising results with accuracy of 94.11 ± 0.3%, 97.18 ± 0.4%, and 96.90 ± 0.5% for SVM, RF, and k-NN, respectively. The execution time to run the program with optimal parameters is 19.395 ± 1 s, 5.941 ± 1 s, and 3.832 ± 1 s for SVM, RF, and k-NN, respectively.

Taiwan’s rowing has achieved well performance in the Asian Games, but it has not in the Olympics. To get good results, in addition to the hard work and solid and effective training on weekdays, the qualification of the players is one of the key factors. Therefore, this research attempts to construct an artificial intelligence (AI) evaluation algorithm for rowing athletes to obtain advantages in the sports field, and can start from the athletes. The AI algorithm involves the hierarchical analysis method (AHP) is adopted to invite experts and scholars in the rowing field to answer the expert questionnaire. The TOPSIS (technique for order performance by similarity to ideal solution) method is then applied to calculate the ranking of material selection indicators, aiming to construct an evaluation model for rowers. The main research result shows that physicality is considered as the highest priority among the four main criteria of talent identification, following in a descending order by specialism, reaction and psychological elements. The propose model established by the most beneficial decision model for identification of talented rowers in the future.

Membrane bioreactors (MBRs) have been widely used from biotechnological fermentation to municipal and industrial wastewater treatment. However, membrane fouling is the major obstacle that hinders faster commercialisation of MBRs. Extracellular polymeric substances (EPS) secreted by bacteria are the main fouling components, which are mainly composed of proteins and carbohydrates. Although it is clear that proteins play major roles in the fouling formation mechanisms, very little is known about fouling protein characteristics. This study focused on the identification and characterization of different proteins present in EPS and their relationship with three different membrane materials, polyacrylonitrile (PAN), polyvinylidene fluoride (PVDF), polytetrafluoroethylene (PTFE) in a laboratory-scale MBR setup. Results showed that the largest and the most hydrophilic (average MW = 56.14 kDa, GRAVY = −0.191) proteins deposited on hydrophilic PAN membrane, whereas the smallest and the most hydrophobic (average MW = 46.67 kDa, GRAVY = −0.001) proteins deposited on hydrophobic PTFE membranes. Smaller proteins were responsible for the fouling of membranes with large pores, and vice versa. Characteristics of chaperonin and outer membrane proteins, identified in all membranes, may facilitate the design of anti-fouling membranes.

In this paper, the finite element method (FEM) is used to study the incremental sheet forming process of pyramidal shape. The material used is aluminium alloy 5052. The tool, a hemispherical ball-head with a diameter (d = 4 mm) made of HSS tool steel, is used to press down on the sheet metal causing locally plastic deformation. The comparison between spiral tool path, spiral-step tool path and z-level tool path is carried out. Moreover, the final thickness distribution is investigated. The results indicate that the minimal thickness can be found on the corner of wall angle in SPIF process. Under the same step over, spiral-step tool path can obtain the deepest depth for pyramidal shape. The maximum formability for successful forming of the pyramidal shape with depth 60 mm is wall angles 65 ∘ .