In this paper, we present fabrication and performance evaluation of three-dimensional (3D) printed and embroidered textile-integrated passive ultra high frequency radio frequency identification (RFID) platforms. The antennas were manufactured by 3D printing a stretchable silver conductor directly on an elastic band. The electric and mechanical joint between the 3D printed antennas and microchips was formed by gluing with conductive epoxy glue, by printing the antenna directly on top of the microchip structure, and by embroidering with conductive yarn. Initially, all types of fabricated RFID tags achieved read ranges of 8–9 meters. Next, the components were tested for wetting as well as for harsh cyclic strain and bending. The immersing and cyclic bending slightly affected the performance of the tags. However, they did not stop the tags from working in an acceptable way, nor did they have any permanent effect. The epoxy-glued or 3D printed antenna–microchip interconnections were not able to endure harsh stretching. On the other hand, the tags with the embroidered antenna–microchip interconnections showed excellent wireless performance, both during and after a 100 strong stretching cycles. Thus, the novel approach of combining 3D printing and embroidery seems to be a promising way to fabricate textile-integrated wireless platforms.

No abstract

No abstract

In the evaluation of traditional college talents’ teaching ability, the importance of evaluation indicators lacks evaluation, and the evaluation results are relatively random. In order to improve the evaluation efficiency of university scientific research talents, this study combines BP neural network and fuzzy mathematical theory to build an evaluation model. Combining the talent training process and ability requirements of colleges and universities, a secondary index system is proposed, and the weight of the evaluation index is determined by combining data collection. This paper first normalizes the samples, determines the training and test samples, and then uses trial and error to determine the number of hidden layer neurons. Then use fuzzy mathematics theory to construct fuzzy similarity matrix to describe the fuzzy relationship between factor domain and judgement domain. Calculate membership to get comprehensive evaluation results. Finally, this paper uses statistical methods to draw the results into statistical charts and combines the simulation results to obtain performance comparison results. The feasibility of the model is verified by experimental research, and the model can be applied to practice, and can provide theoretical reference for subsequent related research.

No abstract

The fabrication and analysis of a flexible and stretchable 3D printed passive ultra‐high frequency (UHF) radio‐frequency identification (RFID) tag are presented. The tag is fabricated on a flexible 3D printed Ninjaflex substrate and the conductive part of the tag consists of stretchable silver conductive paste dispensed with direct write method. The details of the 3D printing of the substrate, the characterisation of the substrate material at the UHF band, the direct write dispensing of the tag antenna, and the simulation and wireless measurement results of the fabricated tag are outlined. Moreover, to verify the flexibility and stretchability of the tag, strain reliability results of the tag are presented. Measurement results show that initially the manufactured tag achieves a 10.6 m read range. After 100 times of harsh stretching, the read range is still 7.4 m. Overall, the performance of the tag is robust and concludes that the fabrication methodology can be used in the manufacturing of RFID tags for future identification and sensing applications.

No abstract

Multi-task learning with transformer encoders (MTL) has emerged as a powerful technique to improve performance on closely-related tasks for both accuracy and efficiency while a question still remains whether or not it would perform as well on tasks that are distinct in nature. We first present MTL results on five NLP tasks, POS, NER, DEP, CON, and SRL, and depict its deficiency over single-task learning. We then conduct an extensive pruning analysis to show that a certain set of attention heads get claimed by most tasks during MTL, who interfere with one another to fine-tune those heads for their own objectives. Based on this finding, we propose the Stem Cell Hypothesis to reveal the existence of attention heads naturally talented for many tasks that cannot be jointly trained to create adequate embeddings for all of those tasks. Finally, we design novel parameter-free probes to justify our hypothesis and demonstrate how attention heads are transformed across the five tasks during MTL through label analysis.