Traffic sign recognition in poor environments has always been a challenge in self-driving. Although a few works have achieved good results in the field of traffic sign recognition, there is currently a lack of traffic sign benchmarks containing many complex factors and a robust network. In this paper, we propose an ice environment traffic sign recognition benchmark (ITSRB) and detection benchmark (ITSDB), marked in the COCO2017 format. The benchmarks include 5806 images with 43,290 traffic sign instances with different climate, light, time, and occlusion conditions. Second, we tested the robustness of the Libra-RCNN and HRNetv2p on the ITSDB compared with Faster-RCNN. The Libra-RCNN performed well and proved that our ITSDB dataset did increase the challenge in this task. Third, we propose an attention network based on high-resolution traffic sign classification (PFANet), and conduct ablation research on the design parallel fusion attention module. Experiments show that our representation reached 93.57% accuracy in ITSRB, and performed as well as the newest and most effective networks in the German traffic sign recognition dataset (GTSRB).

The smart grid is vulnerable to network attacks, thus requiring a high detection rate and fast detection speed for intrusion detection systems. With a fast training speed and a strong model generalization ability, the extreme learning machine (ELM) perfectly meets the needs of intrusion detection of the smart grid. In this paper, the ELM is applied to the field of smart grid intrusion detection. Aiming at the problem that the randomness of input weights and hidden layer bias in the ELM cannot guarantee the optimal performance of the ELM intrusion detection model, a genetic algorithm (GA)-ELM algorithm based on a genetic algorithm (GA) is proposed. GA is used to optimize the input weight and hidden layer bias of the ELM. Firstly, the input weight and hidden layer bias of the ELM are mapped to the chromosome vector of a GA, and the test error of the ELM model is set as the fitness function of the GA. Then, the parameters of the ELM intrusion detection model are optimized by genetic operation; the input weight and bias, corresponding to the minimum test error, are selected to improve the performance of the ELM model. Compared with the ELM and online sequential extreme learning machine (OS-ELM), the GA-ELM effectively improves the accuracy, detection rate and precision of intrusion detection and reduces the false positive rate and missing report rate.

Purpose: To study the protective effects of a combination of temozolomide (TMZ) and whole brain radiotherapy (WBT) on neurocognition, and its effect on the quality of life (QoL) in patients with brain metastasis (BM) from solid tumors, relative to WBT alone. Methods: A total of 256 BM patients were enrolled and divided into two groups treated with either WBT plus TMZ, or WBRT alone. All patients received 30 Gy WBT, with or without concomitant TMZ (75 mg/m 2 /day) during the irradiation period, and subsequently up to six cycles of TMZ (150 mg/m 2 /day). Results: The mean intracranial objective response (IOR) for all patients was 44.80 % while the IOR for WBT arm and WBT+TMZ group arm were 32.48 and 56.56 %, respectively (p = 0.03). The median intracranial overall survival (OS) for all the patients was 7.70 months. The median OS for WBT alone group (6.53 months) was significantly shorter than that of the WBT + TMZ arm (9.57 months). Statistically significant difference in quality of life (QoL) was observed between both arms at six months. Moreover, WBT+TMZ group had higher incidence of toxicity, when compared to WBT-only group. Conclusion: These results suggest that co-application of WBT and TMZ improves intracranial ORR and median OS in BM patients, relative to the use of WBT alone. Although the side effects may be increased as a result of addition of TMZ, toxicity is tolerable and manageable.

In this work, we summarized several fundamental theorems of the entire functions and explored how their zeros determine those functions. The background of this work is based on Elias M. Stein and Rami Shakarachi, and their lectures about functions that are holomorphic in the whole complex plane that once were taught at Princeton University. First, we introduced Jensen’s formula and gave detailed proof. This relates the values of a meromorphic function inside a disk with its boundary values on the circumference and with its zeros and poles. Next, we studied the proof of Weierstrass infinite products and the definition of canonical factors. Last, Hadamard’s factorization theorem and a few main lemmas were introduced. We showed the proof of the Hadamard factorization theorem and solved its several applications through using examples. Hadmard’s theory is well demonstrated in this article, and we showed the rigor and scientific validity of the theory through examples.

Glaucoma being the second most common blinding disease, OD (optic disc) segmentation and OC (optic cup) segmentation are important steps in the auxiliary diagnosis for glaucoma. However, due to the small size of OC and its weak contrast with the surrounding areas, the traditional segmentation method is difficult to define the OC boundary accurately. This paper proposes a multi-feature fusion method for OC segmentation with the depth learning algorithm. Our proposed method obtains the accuracy (Dice) of difficult sample segmentation of 22.8%, and the AUC of attention mechanism retinal vascular extraction algorithm of 0.9808 in RIM-ONEV3, and the improved network convergence speed is increased by 66.6%.