In response to rising labor costs, workforce shortages, and the prevalence of musculoskeletal disorders in warehouse environments, companies are looking for cost-effective motion capture (MoCap) solutions to assess and mitigate posture-related risks. Although professional MoCap systems offer high accuracy, they are often expensive, making their purchase particularly difficult for small- and medium-sized companies. This study investigates the use of a markerless MoCap system based on Azure Kinect enhanced with machine learning (ML) to avoid occlusion-related tracking errors, improve tracking accuracy and reliability, and achieve cost benefits. By applying design science research methodology, a conceptual three-layer architectural model is developed comprising (1) sensor setup and data collection, (2) model development and testing, and (3) model evaluation for decision-making. First, an experimental approach is used to quantify the proportion of artefacts. Then, a convolutional neural network is trained using benchmark data from an inertial measurement unit-based system (Captiv) to improve the tracking accuracy of the Kinect-based system. Our evaluation shows that the ML-corrected Kinect data significantly reduces deviations in key joint angles (e.g., back, elbow, and shoulder) compared to the original Kinect data, as measured by multiple performance metrics. Furthermore, the Ovako working posture assessment system is used to test the usefulness of the ML model in assessing postural risk. ML-corrected Kinect data is found to align more closely with the Captiv data while showing a higher sensitivity to hazardous postures.

Abstract Over the past 70 years, the semiconductor industry has undergone transformative changes, largely driven by the miniaturization of devices and the integration of innovative structures and materials. Two-dimensional (2D) materials like transition metal dichalcogenides (TMDs) and graphene are pivotal in overcoming the limitations of silicon-based technologies, offering innovative approaches in transistor design and functionality, enabling atomic-thin channel transistors and monolithic 3D integration. We review the important progress in the application of 2D materials in future information technology, focusing in particular on microelectronics and optoelectronics. We comprehensively summarize the key advancements across material production, characterization metrology, electronic devices, optoelectronic devices, and heterogeneous integration on silicon. A strategic roadmap and key challenges for the transition of 2D materials from basic research to industrial development are outlined. To facilitate such a transition, key technologies and tools dedicated to 2D materials must be developed to meet industrial standards, and the employment of AI in material growth, characterizations, and circuit design will be essential. It is time for academia to actively engage with industry to drive the next 10 years of 2D material research.

Human–computer interaction systems have been developed in large numbers and quickly applied to sports. Badminton is the best sport for applying robotics because it requires quick recognition and fast movement. For the development of badminton recognition and tracking systems, it is important to accurately identify badminton, venues, and opponents. In this paper, we designed and developed a badminton recognition and tracking system using two 2 000 000-pixel high-speed cameras. The badminton tracking system has a transmission speed of 250[Formula: see text]fps and the maximum speed of the badminton resonator is 300[Formula: see text]km/h. The system uses the camera link interface Camera Link to capture images of high-speed cameras and process all captured images in real time using different regions of interest settings. In order to improve accuracy, we propose a new method for judging the center point of badminton. We have proposed a detector that detects the four corner points of the field by using the contour information of the badminton court when the approximate position of the badminton court is known. We set the sensing area according to the approximate position of the badminton court and use the histogram in the sensing area to select the point closest to the contour. Specify the intersection of the line as the corner point of the badminton court. The proposed angle detector has a high detection rate. It is more than 10 times more accurate than traditional detectors. The moving badminton is detected by an elliptical detector. We propose a method to find the center of the correct ellipse from the four candidates by selecting the four candidate contours of the ellipse. Compared to conventional circular detectors and points on three-dimensional coordinates, the proposed elliptical detector reduces the error by about 3[Formula: see text]mm.

The Sentinel-2A (S2A) Multi-Spectral Imager (MSI) is a new remote sensor launched on 23 June 2015 that provides unprecedented Earth observation with high spatial, spectral and temporal resolutions. It has high potential for chlorophyll content estimation. Chlorophyll content plays a crucial role in plant photosynthesis affecting the terrestrial carbon cycle. In this research, a physical retrieval algorithm is proposed for leaf chlorophyll content from the S2A MSI data based on 4-Scale and PROSPECT models. Satellite and ground data were collected and processed in a mixed temperate forest near Borden, Ontario, Canada from May to October 2016. Preliminary validation shows an agreement between the inverted and ground measured leaf chlorophyll contents, with r = 0.77 and RMSE = 8.82 μg/cm2, which is an improvement over those generated by the Sentinel Application Platform (SNAP). Further research is ongoing, and the algorithm will be improved in the future.

This paper addresses the design of symmetric entropy-constrained multiple description scalar quantizers (EC-MDSQ) with linear joint decoders, i.e., where some of the decoders compute the reconstruction by averaging the reconstructions of individual descriptions. Thus, the use of linear decoders reduces the space complexity at the decoder since only a subset of the codebooks needs to be stored. The proposed design algorithm locally minimizes the Lagrangian, which is a weighted sum of the expected distortion and of the side quantizers' rates. The algorithm is inspired by the EC-MDSQ design algorithm proposed by Vaishampayan and Domaszewicz, and it is adapted from two to K descriptions. Differently from the aforementioned work, the optimization of the reconstruction values can no longer be performed separately at the decoder optimization step. Interestingly, we show that the problem is a convex quadratic optimization problem, which can be efficiently solved. Moreover, the generalization of the encoder optimization step from two to K descriptions increases drastically the amount of computations. We show how to exploit the special form of the cost function conferred by the linear joint decoders to significantly reduce the time complexity at this step. We compare the performance of the proposed design with multiple description lattice vector quantizers (MDLVQ) and with the multiple description scheme based on successive refinement and unequal erasure protection (UEP). Our experiments show that the proposed approach outperforms MDLVQ with dimension 1 quantization, as expected. Additionally, when more codebooks are added our scheme even beats MDLVQ with quantization dimension approaching ∞, for rates sufficiently high. Furthermore, the proposed approach is also superior to UEP with dimension 1 quantization when the rates are low.

Photosynthesis in vegetation is arguably the most important and variable part of the terrestrial carbon cycle. In terrestrial biospheric models, the photosynthesis rate of plant leaves is generally simulated based on the maximum carboxylation rate at an optimum temperature (often 25°C), which is often denoted as Vcmax25. In regional and global photosynthesis modeling, Vcmax25 is usually prescribed as constants for different plant functional types (PDF) based on ground measurements in order to capture the first order spatial variability associated with PTF distribution. However, experimental data show that Vcmax25 can vary by 2-3 factors for the same PFT, and it is also not a constant in different growing seasons because of leaf physiological change with season. It is therefore highly desirable to be able to map this critical parameter to address the issues of its spatial and temporal variabilities. Both terrestrial carbon and water cycle simulations can be greatly improved if we can achieve the global mapping of this parameter.

This work compares theoretically the performance of several representative practical multiple description (MD) frameworks with L ≥ 3 symmetric descriptions. The first scenario is the classic unequal erasure protection (UEP) scheme using a successively refinable code (SRC) and Reed-Solomon codes. The second scenario is an improvement upon UEP by applying domain partitioning and permuted Reed-Solomon codes. The third scenario uses a finer partitioning and erasure correction via repetition codes. Additionally, the MD lattice vector quantizer and another recent MD scheme are considered in the comparison. The aforementioned MD schemes are compared in terms of the expected squared error asymptotically achievable as the rate R of a description approaches ∞, assuming independent description losses. Our analysis reveals that the improvement of the second scenario upon the first one when R → ∞ can reach up to 1.68 dB, but it approaches 0 as the description loss rate p goes to 0 and L approaches ∞. Additionally, we find that the first two schemes outperform the third one with an unbounded gain when R → ∞, as p→ 0 or L → ∞. Further, we show that the first three scenarios achieve unbounded improvements over the other two as R → ∞ and p → 0. On the other hand, we point out that some of the results of our asymptotic analysis rely on strong assumptions and therefore an experimental validation is needed before applying them to practical situations.

A method to produce balanced multiple descriptions (MD) of a source is by successively refinable quantization (SRQ) in conjunction with uneven erasure protection (UEP) (Goyal, 2001; and Tian and Hemami, 2004). This work proposes an improvement to this balanced MD coding framework. In order to generate L descriptions, the set of source samples is first partitioned into L subsets of equal size, then each subset is quantized separately. Further, interleaved systematic Reed Solomon codes of codelength L and decreasing strengths are applied across the streams output by the SRQs. The improvement over the previous UEP-based MD code is evaluated using the expected distortion of the source reconstruction at the decoder as a performance measure. For a Gaussian memory-less source, the asymptotical improvement in performance, as the rate and code block length approach infin, can attain as much as 1.68 dB (for L = 3 and very low probability of description loss), with a tendency to decrease as the number of descriptions and the rate of description loss increase. In the practical setting using scalar SRQ, small rates and small L, the observed improvement generally matches the asymptotical values.