Collaborative perception improves task performance by expanding the perception range through information sharing among agents. Immutable heterogeneity poses a significant challenge in collaborative perception, as participating agents may employ different and fixed perception models. This leads to domain gaps in the intermediate features shared among agents, consequently degrading collaborative performance. Aligning the features of all agents to a common representation can eliminate domain gaps with low training cost. However, in existing methods, the common representation is designated as the representation of a specific agent, making it difficult for agents with significant domain discrepancies from this specific agent to achieve proper alignment. This paper proposes NegoCollab, a heterogeneous collaboration method based on the negotiated common representation. It introduces a negotiator during training to derive the common representation from the local representations of each modality's agent, effectively reducing the inherent domain gap with the various local representations. In NegoCollab, the mutual transformation of features between the local representation space and the common representation space is achieved by a pair of sender and receiver. To better align local representations to the common representation containing multimodal information, we introduce structural alignment loss and pragmatic alignment loss in addition to the distribution alignment loss to supervise the training. This enables the knowledge in the common representation to be fully distilled into the sender. The experimental results demonstrate that NegoCollab significantly outperforms existing methods in common representation-based collaboration approaches. The mechanism of obtaining common representations through negotiation provides a more reliable and flexible option for common representations in heterogeneous collaborative perception.

Named data networking (NDN) has been regarded as a promising scheme for next-generation network architecture, with network security remaining a key issue. In NDN, a new Distributed Denial of Service (DDoS) attack model called the interest flooding attack (IFA) has emerged and poses a serious threat to NDN. In addition, to increase the complexity of detection and defense against attacks, a variant of the IFA called the collusive interest flooding attack (CIFA) has emerged recently. Although many IFA and CIFA detection methods have been proposed, most existing countermeasures focus solely on detecting either IFA or CIFA. More importantly, to the best of our knowledge, there is no research on effective detection scheme for scenarios where IFA and CIFA coexist in a blending attack yet. In this paper, motivated by the concept that network traffic exhibits time series characteristics, we propose an attack identification and detection scheme based on WEASEL (Word ExtrAction for time SEries cLassification) aimed at accurately identifying and detecting the blending IFAs in NDN.

Perceptual Lossless Compression (PLC) is a novel compression standard directed by the Audio Video coding Standard (AVS) work group. It defines a lightweight, low-latency, and visually lossless image compression framework, which offers an alternative mezzanine codec for most user-agnostic on-chip compression scenarios, alleviating the tension between growing transmission demands and expensive integration upgrades. In this paper, the technical designs in the development process of PLC will be fully introduced. The balance between feature modeling and ASIC implementation costs will be present throughout. A high throughput and low hardware complexity implementation will be detailed and evaluated namely HIM. Hopefully, the design of the PLC standard and HIM framework will bring new inspiration for the emerging low-latency interaction systems.

Cross-component chroma prediction plays an important role in improving coding efficiency for H.266/VVC. We use the differences between reference samples and the predicted sample to design an attention model for chroma prediction, namely luma difference-based chroma prediction (LDCP). Specifically, the luma differences (LDs) between reference samples and the predicted sample are employed as the input of the attention model, which is designed as a softmax function to map LDs to chroma weights nonlinearly. Finally, a weighted chroma prediction is conducted based on the weights and chroma reference samples. To provide adaptive weights, the model parameter of the softmax function can be determined based on the template (T-LDCP) or offline learning (L-LDCP), respectively. Experimental results show that the T-LDCP achieves BD-rate reductions of 0.34%, 2.02%, and 2.34% for the Y, Cb, and Cr components, and the L-LDCP brings 0.32%, 2.06%, and 2.21% BD-rate savings for Y, Cb, and Cr components, respectively. The L-LDCP introduces slight encoding and decoding time increments, i.e., 2% and 1%, when integrated into the latest VVC test model version 18.0. Besides, the LDCP can be implemented by a pixel-level parallelization which is hardware-friendly.

In order to enhance and improve labor productivity, we have developed an automated system for evaluating the worker’s skills by using labeled latent Dirichlet allocation (L-LDA). Since the L-LDA learns the characteristic motions automatically, we do not need to find and define any features of the motion. The elemental processes are analyzed by the L-LDA. The worker’s skills are evaluated based on the analyzed time series elemental process data. The evaluated worker’s skills are correctness, stability, speed, and rhythm of the work. The results confirmed that our proposed evaluation system is capable of automatically providing a new analysis over the conventional evaluation method with only working time. For example, an evaluation experiment was done to one subject. This result showed the speed category to be lower than the other categories. Then, we know that the subject lacks parallelism work skill. These results give new knowledge that never obtained by the conventional evaluation method.

This paper describes a fuzzy proficiency evaluation system by using myoelectric potential. This system evaluates proficiency level in soldering operation as an example of manufacturing process an industry. We classified them as beginners and experts, and confirmed the difference by proficiency level by analyzing the surface myoelectric potential measured during work. As the result, the difference found at the integrated myoelectric potential during the operation. This difference decreased with the number of operations, and this was confirmed by the degree of proficiency. Therefore depending on proficiency level as a numerical value in which the difference appeared, the displacement of the integrated myoelectric potential of the working time and the previous work was converted into fuzzy degree, and the degree of proficiency was defined and evaluated using their affiliation degree. As the results, we succeeded in designing an evaluation system in which differences appeared in proficiency level.

Productivity improvements in manufacturing industries are strongly sought after while considering the reduced labor power in developed countries. In response to these needs, a quantified evaluation method of worker's proficiency is key to realizing sophisticated skill developments. In previous studies, worker's proficiency in manufacturing operations was evaluated by the number of products produced per unit time or takt time. Therefore, it is difficult to understand how workers accomplish the manufacturing operations and/or tasks with specific motions and objects derived from the hand, body, and eye movements. To overcome this limitation, we investigated the quantified degree of worker's skills in four elemental processes using methods to evaluate the sophistication level between sensory and motor connectivity in the human brain's information processing. To realize these methods, we conducted a three-month experiment and measured eye and body movements of 20 participants working on a manufacturing line. Our method defines the four elemental processes to show the differences in the degree of worker's proficiency between experts and novices. The quantified evaluation results indicated that expert workers had higher proficiency levels for every elemental process compared with novice workers. These results show the possibility that novices are not as proficient as experts when memorizing correct procedures as they are more likely to discriminate a specific point to accomplish tasks due to immature memory functions within the brain.

In this study, we analyzed a body information feature in the soldering process in order to develop an evaluative method of the worker skills. First, we found the three types body information features. The found features were the work position, the way to hold a soldering iron, and the effect of the dominant eye and the age. Using the features of the work position and the way to hold a soldering iron, we classified the work rank into four classes. As a result of evaluating operation time and the product quality for these classes, it was confirmed that operation time and the product quality were improved as the work rank improves.

As the level of hospital informatization raises, it is possible to obtain huge amount of physiological data from bedside monitor and other medical instruments. The goal for this work is to recognize diseases from physiological data by unique combinations of representative patterns for different dis eases. The representative patterns are clustered from the original physiological time series data, e.g. pulse, respiration rate, blood pressure, heart rate and oxygen saturation rate. Within a disease, to compose the set of representative patterns into a interrelated structure, we bring in Allen’s interval relations to describe the temporal relations between each of two neighboring patterns. We use Chinese Restaurant Process (CRP) to draw the uncertainty of every temporal relations that links two representative patterns. The two algorithms are combined into the model we use in this work, called probabilistic model. The experimental results suggests our model has potential in recognizing diseases.

We present a non-volatile flip-flop with a feature to back-up the state in a ferroelectric transistor (FEFET) during power failure or supply gating. The data is stored in the form of polarization of the ferroelectric (FE) layer in the gate stack of the FEFET. The proposed flip-flop utilizes the non-volatility of the three-terminal FEFET to optimize the data backup and restore operations. We perform an extensive device-circuit analysis to provide insights into the design of the proposed flip-flop. We discuss the optimization of the FE thickness in the gate stack of the FEFET to introduce suitable non-volatility and present the implications at the circuit level. Our analysis shows that by virtue of the three terminal structure of the FEFET and the order of magnitude difference in the current for the two polarization states, the design of the backup/restore module is considerably simplified. Compared to a FE capacitor based non-volatile flip-flop, the proposed flip-flop achieves 40%--50% smaller backup delay, 27%--40% lower backup energy, comparable restore delay and up to an order of magnitude lower restore energy. While the FE capacitor based design leads to 76% area penalty compared to a conventional (volatile) flip-flop, the proposed design incurs only 35% area overhead.