Thermal issues seriously restrict the quality, reliability, and lifetime of semiconductor chips. To prevent thermal runaway situations, modern processors deploy numerous on-die thermal sensors to collect temperature information, which is then used to guide dynamic thermal management (DTM) mechanisms. Accurate on-chip temperature information is critical for DTM as temperature overestimation will degrade the performance by an unnecessary invocation of thermal control mechanisms, and underestimation will result in the reliability issues of the systems. In this article, two effective techniques are proposed to achieve an accurate on-chip temperature sensing. The first technique is a synergistic calibration method for forecasting the actual temperatures of noisy thermal sensors. Second, we propose a full thermal characterization technique based on convolutional neural networks (CNNs) to accurately recover the entire thermal maps by using a limited number of thermal sensors. In a realistic scenario, these two techniques can be used in combination to provide a more accurate thermal monitoring. By utilizing the sophisticated infrared imaging setup, the effectiveness of the proposed techniques is validated on a real 45-nm AMD quad-core chip. The simulation results show that the methods achieve significant improvements compared with existing techniques in the literature. The successful implementation of the proposed methods will significantly improve the efficiency of DTM.

Using embedded thermal sensors, high‐performance microprocessors employ dynamic thermal management techniques to measure runtime thermal behaviour so as to prevent thermal runaway situations. However, on‐chip thermal sensors are highly susceptible to noise, which results in a higher probability of false alarms and unnecessary responses. In this study, the authors propose a set of methods based on principal component analysis (PCA) to address the problem of recovering precisely the full thermal map from the on‐chip thermal sensors when the sensor readings have been corrupted by noise. The authors utilise simulated annealing algorithm to devise method that determines the optimal thermal sensor locations, which can obtain superior results compared with the available literature. On this basis, the authors also propose a practical method for full thermal reconstruction to estimate the accurate temperatures of full chip, which would not need to know a‐priori temperature information at each spatial distribution of thermal map. The experimental results confirm that the authors’ proposed methods are stable in the case of noisy thermal sensor observations, which can achieve a high fidelity thermal monitoring.

Compositional Zero-Shot Learning (CZSL) aims to learn visual concepts (i.e., attributes and objects) from seen compositions and combine them to predict unseen compositions. Existing visual encoders in CZSL typically use traditional visual encoders (i.e., CNN and Transformer) or image encoders from Visual-Language Models (VLMs) to encode image features. However, traditional visual encoders need more multi-modal textual information, and image encoders of VLMs exhibit dependence on pre-training data, making them less effective when used independently for predicting unseen compositions. To overcome this limitation, we propose a novel approach based on the joint modeling of traditional visual encoders and VLMs visual encoders to enhance the prediction ability for uncommon and unseen compositions. Specifically, we design an adaptive fusion module that automatically adjusts the weighted parameters of similarity scores between traditional and VLMs methods during training, and these weighted parameters are inherited during the inference process. Given the significance of disentangling attributes and objects, we design a Multi-Attribute Object Module that, during the training phase, incorporates multiple pairs of attributes and objects as prior knowledge, leveraging this rich prior knowledge to facilitate the disentanglement of attributes and objects. Building upon this, we select the text encoder from VLMs to construct the Adaptive Fusion Network. We conduct extensive experiments on the Clothing16K, UT-Zappos50K, and C-GQA datasets, achieving excellent performance on the Clothing16K and UT-Zappos50K datasets.

Integrating the relaying drone and non-orthogonal multiple access (NOMA) technique into post-disaster emergency communications (PDEComs) is a promising way to accomplish efficient network recovery. Motivated by the above, by optimizing the drone three-dimensional (3D) deployment optimization and spectrum allocation, this paper investigates a quality of service (QoS)-driven sum rate maximization problem for drone-and-NOMA-enhanced PDEComs that aims to improve the data rate of cell edge users (CEUs). Due to the non-deterministic polynomial (NP)-hard characteristics, we first decouple the formulated problem. Next, we obtain the optimal 3D deployment with the aid of a long short-term memory (LSTM)-based recurrent neural network (RNN). Then, we transform the spectrum allocation problem into an optimal matching issue, based on which the Hungarian algorithm is employed to solve it. Finally, the simulation results show that the presented scheme has a significant performance improvement in the sum rate compared with the state-of-the-art works and benchmark scheme. For instance, by adopting the NOMA technique, the sum rate can be increased by 9.72% and the needs of CEUs can be satisfied by enabling the relaying drone. Additionally, the convergence, complexity, and performance gap caused by iterative optimization are discussed and analyzed.

Dynamic thermal management (DTM) mechanisms utilize embedded thermal sensors to collect fine-grained temperature information for monitoring the real-time thermal behavior of multi-core processors. However, embedded thermal sensors are very susceptible to a variety of sources of noise, including environmental uncertainty and process variation. This causes the discrepancies between actual temperatures and those observed by on-chip thermal sensors, which seriously affect the efficiency of DTM. In this paper, a smoothing filter-based Kalman prediction technique is proposed to accurately estimate the temperatures from noisy sensor readings. For the multi-sensor estimation scenario, the spatial correlations among different sensor locations are exploited. On this basis, a multi-sensor synergistic calibration algorithm (known as MSSCA) is proposed to improve the simultaneous prediction accuracy of multiple sensors. Moreover, an infrared imaging-based temperature measurement technique is also proposed to capture the thermal traces of an advanced micro devices (AMD) quad-core processor in real time. The acquired real temperature data are used to evaluate our prediction performance. Simulation shows that the proposed synergistic calibration scheme can reduce the root-mean-square error (RMSE) by 1.2 ${}^{\circ }$ C and increase the signal-to-noise ratio (SNR) by 15.8 dB (with a very small average runtime overhead) compared with assuming the thermal sensor readings to be ideal. Additionally, the average false alarm rate (FAR) of the corrected sensor temperature readings can be reduced by 28.6%. These results clearly demonstrate that if our approach is used to perform temperature estimation, the response mechanisms of DTM can be triggered to adjust the voltages, frequencies, and cooling fan speeds at more appropriate times.

In recent decades, the noncontact displacement motion detection via interferometric radar, especially for monitoring vital signs like heartbeat and respiration, has become a significant research area. This article introduces an advanced time-domain phase demodulation technique that overcomes the limitations of frequency-domain features by reconstructing detailed motion patterns. Facing the challenges posed by the inevitable dynamic dc offset of complex scatterers and the complex calibration steps required for time-domain demodulation, our method utilizes chord length to recover the magnitude of the Doppler phase and introduces a cross-product-based technique for determining polarity, thus constructing polar chords. This separate calculation of Doppler phase magnitude and direction is insensitive to stringent central optimal conditions and circumvents complex calibration steps. In addition, this article introduces a pioneering adaptive segmentation method capable of detecting motion details of complex scatterers, thereby expanding the application scope of our algorithm. Both simulations and experiments show that the proposed phase demodulation technique based on polar chord accumulation can accurately reconstruct the normalized motion without phase ambiguity and improve the accuracy with a root mean square error two times lower than other conventional methods. The computational efficiency is 15 times faster than other methods when processing pendulum motion signals within 2 min. In addition, this method is also able to recover similar feature points to photoplethysmography (PPG) in heartbeat signal detection.