Word segmentation has been shown helpful for Chinese-to-English machine translation (MT), yet the way different segmentation strategies affect MT is poorly understood. In this paper, we focus on comparing different se...
详细信息
In a hierarchically-structured cloud/edge/device computing environment, workload allocation can greatly affect the overall system performance. This paper deals with AI-oriented medical workload generated in emergency ...
详细信息
The convolutional neural network (CNN) is vulnerable to degraded images with even very small variations (e.g. corrupted and adversarial samples). One of the possible reasons is that CNN pays more attention to the most...
详细信息
The convolutional neural network (CNN) is vulnerable to degraded images with even very small variations (e.g. corrupted and adversarial samples). One of the possible reasons is that CNN pays more attention to the most discriminative regions, but ignores the auxiliary features when learning, leading to the lack of feature diversity for final judgment. In our method, we propose to dynamically suppress significant activation values of CNN by group-wise inhibition, but not fixedly or randomly handle them when training. The feature maps with different activation distribution are then processed separately to take the feature independence into account. CNN is finally guided to learn richer discriminative features hierarchically for robust classification according to the proposed regularization. Our method is comprehensively evaluated under multiple settings, including classification against corruptions, adversarial attacks and low data regime. Extensive experimental results show that the proposed method can achieve significant improvements in terms of both robustness and generalization performances, when compared with the state-of-the-art methods. Code is available at https://***/LinusWu/TENET_Training.
Convolution neural networks (CNNs) have been widely used in many applications. Field-Programmable Gate Array (FPGA) based accelerator is an ideal solution for CNNs in embedded systems. However, the single event upset ...
详细信息
ISBN:
(数字)9781728149226
ISBN:
(纸本)9781728149233
Convolution neural networks (CNNs) have been widely used in many applications. Field-Programmable Gate Array (FPGA) based accelerator is an ideal solution for CNNs in embedded systems. However, the single event upset (SEU) effect in FPGA device may have a significant influence on the performance of CNNs. In this paper, we analyze the sensibility of CNNs to SEU and present a fault-tolerant design for CNN accelerators. First, we find that SEU in processing elements (PEs) has the worst effects on CNNs since it produces proportional errors and will not get refreshed. Furthermore, it is indicated that the large positive perturbation contributes almost all of the performance loss. Based on such observations, we propose an error detecting scheme to locate incorrect PEs and give an error masking method to achieve fault-tolerance. Experiments demonstrate that the proposed method achieves similar fault-tolerant performance with the triple modular redundancy (TMR) scheme while the overhead is much lower than it.
Utilization of inter-base station cooperation for information processing has shown great potential in enhancing the overall quality of communication services (QoS) in wireless communication networks. Nevertheless, suc...
详细信息
With economic development, a great amount of hazardous material is shipped in the transport network every day. Hazardous material transportation is well known for its high potential risk. An accident can cause very se...
详细信息
With economic development, a great amount of hazardous material is shipped in the transport network every day. Hazardous material transportation is well known for its high potential risk. An accident can cause very serious economic damage and will have a negative impact on public health and the environment over the long term. Transporting hazardous materials on special lanes can reduce the risk. However, a lane reservation strategy may worsen traffic conditions for other vehicles. This paper investigates a hazardous material transportation problem with lane reservation. The problem lies in how to choose lanes to be reserved in the network and select the path for each hazardous material shipment from the reserved lanes. The goal is to obtain the best compromise between the impact on normal traffic and the transportation risk. A multiobjective integer programming model is presented for the new problem. Then, an algorithm is developed based on the ε -constraint method and a fuzzy-logic-based approach. Pareto optimal solutions are obtained by the former, and a preferred solution is selected by the fuzzy-logic-based approach. Computational results demonstrate the efficiency of the proposed algorithm using an instance based on a real network topology and randomly generated instances.
In this paper, we propose an enhanced handover scheme for cellular-connected UAVs. Specifically, our handover scheme considers the following characteristics: 1) UAV can detect multiple cells with the comparable RSRP l...
详细信息
ISBN:
(数字)9781728173276
ISBN:
(纸本)9781728173283
In this paper, we propose an enhanced handover scheme for cellular-connected UAVs. Specifically, our handover scheme considers the following characteristics: 1) UAV can detect multiple cells with the comparable RSRP levels which may cause many unnecessary handovers. The handover event trigger parameters in our scheme are dynamically adjusted to avoid a UAV to handover from a cell to another cell with the comparable RSRP level; 2)In the process of taking off, the UAV would fly through the null space of antenna lobes many times, while the time duration is normally very short. The RSRP during the UAV taking off varies quickly, so that the measurement reports may not provide an accurate channel information for the UAV. In this case, when the link quality between the UAV and the BS is below a threshold, the BS allows the link being maintained for a while with the hope that the link quality would get better again. We implement our proposed handover scheme on the NS3 platform, and compare with the current LTE handover scheme and the sojourn time estimation-based handover algorithm. Our simulation results demonstrate that our proposed scheme can significantly reduce the number of unnecessary handovers. Moreover, the network throughput of our scheme is improved, since the the communication resources taken by the unnecessary handovers is utilized by the UAV for transmitting data.
Molecular dynamics is an extensively utilized computational tool for solids, liquids and molecules simulation. Currently, much research on molecular dynamics simulation focuses on simplifying forces or parallelizing t...
详细信息
ISBN:
(数字)9781728143286
ISBN:
(纸本)9781728143293
Molecular dynamics is an extensively utilized computational tool for solids, liquids and molecules simulation. Currently, much research on molecular dynamics simulation focuses on simplifying forces or parallelizing tasks to reduce the overheads of forces computation. However, the molecular dynamics simulation still remains challenging since the communication and neighbor list construction are time-consuming in the existing algorithm. In this paper, we propose a swMD optimization strategy including a new communication mode called ghost communication to reduce superfluous communication overheads and an innovative neighbor list algorithm to improve the construction efficiency of it. Moreover, we accelerate computation by utilizing many-core resources on Sunway Taihulight and present an auto-tuning Producer-Consumer pairing algorithm to make neighbor list construction happen in fast register communication. Compared to traditional methods, swMD optimization strategy obtains a maximal 82.2% and an average of 79.4% performance improvement. We also evaluate the scalability up to 266,240 cores and the results demonstrate the high efficiency of swMD optimization strategy on communication, computation and neighbor list construction respectively.
While computing is entering a new phase in which CPU improvements are driven by the addition of multiple cores on a single chip, rather than higher frequencies. Parallel processing on these systems is in a primitive s...
详细信息
Due to the short wavelength of millimeter wave (mmWave) and high directional beamforming, the massive MIMO systems are highly vulnerable to link blockage. Beam switching to unblocked direction is an effective solution...
详细信息
ISBN:
(数字)9781728173276
ISBN:
(纸本)9781728173283
Due to the short wavelength of millimeter wave (mmWave) and high directional beamforming, the massive MIMO systems are highly vulnerable to link blockage. Beam switching to unblocked direction is an effective solution to overcome blockage and restore communication links. To this end, a set of candidate beams for beam switching should be selected before the beam is blocked. However, due to the high speed movement of the UAV, identifying the appropriate beam for an UAV with any position is not trivial. In this work, a fast link recovery approach is proposed. Specifically, our proposed beam selection method considers the spatial correlation, estimated reliability probability of the beams and signal quality. The simulation results show that the proposed method can efficiently recover the interrupted link, and the outage probability is almost reduced to 0% in the scene where the UAV moves at high speed.
暂无评论