Search

With the advancement of technologies like 5G, cloud computing, and microservices, the complexity of network management systems and the variety of technical components have greatly increased. This rise in complexity has rendered traditional operations and maintenance methods inadequate for current monitoring and maintenance demands. Consequently, artificial intelligence for IT operations (AIOps), which harnesses AI and big data technologies, has emerged as a solution. AIOps plays a crucial role in enhancing service quality and customer satisfaction, boosting engineering productivity, and reducing operational costs. This article delves into the primary tasks involved in AIOps, such as anomaly detection, and log fault analysis and classification. A significant challenge identified in many AIOps tasks is the scarcity of fault sample data, indicating a natural alignment of these tasks with few-shot learning. Inspired by model-agnostic meta-learning (MAML), we propose a new anomaly detector, MAML-KAD, for application in various AIOps tasks. Observations confirm that meta-learning algorithms effectively enhance AIOps tasks, showcasing the wide-ranging application prospects of meta-learning algorithms in the field of AIOps. Moreover, we introduced an AIOps platform that embeds meta-learning within its diagnostic core and features streamlined log collection, caching, and alerting to automate the AIOps workflow. [ABSTRACT FROM AUTHOR]

An intelligent land vehicle utilizes onboard sensors to acquire observed states at a disorderly intersection. However, partial observation of the environment occurs due to sensor noise. This causes decision failure easily. A collision relationship-based driving behavior decision-making method via deep recurrent Q network (CR-DRQN) is proposed for intelligent land vehicles. First, the collision relationship between the intelligent land vehicle and surrounding vehicles is designed as the input. The collision relationship is extracted from the observed states with the sensor noise. This avoids a CR-DRQN dimension explosion and speeds up the network training. Then, DRQN is utilized to attenuate the impact of the input noise and achieve driving behavior decision-making. Finally, some comparative experiments are conducted to verify the effectiveness of the proposed method. CR-DRQN maintains a high decision success rate at a disorderly intersection with partially observable states. In addition, the proposed method is outstanding in the aspects of safety, the ability of collision risk prediction, and comfort. [ABSTRACT FROM AUTHOR]

Very recently, two new two-dimensional (2D) layered semi-conducting materials MoSi 2 N 4 and WSi 2 N 4 were successfully synthesized in experiments, and a large family of these two 2D materials, namely MA 2 Z 4 , was also predicted theoretically (Science, 369, 670 (2020)). Motivated by this exciting family, in this work, we systematically investigate the mechanical, electronic and optical properties of monolayer and bilayer MoSi 2 P 4 and MoSi 2 As 4 by using the first-principles calculation method. Numerical results indicate that both monolayer and bilayer MoSi 2 Z 4 (Z = P, As) present good structural stability, isotropic mechanical parameters, moderate bandgap, favorable carrier mobilities, remarkable optical absorption, superior photon responsivity and external quantum efficiency. Especially, due to the wave-functions of band edges dominated by d orbital of the middle-layer Mo atoms are screened effectively, the bandgap and optical absorption hardly depend on the number of layers, providing an added convenience in the experimental fabrication of few-layer MoSi 2 Z 4 -based electronic and optoelectronic devices. We also build a monolayer MoSi 2 Z 4 -based 2D optoelectronic device, and quantitatively evaluate the photocurrent as a function of energy and polarization angle of the incident light. Our investigation verifies the excellent performance of a few-layer MoSi 2 Z 4 and expands their potential application in nanoscale electronic and optoelectronic devices. [ABSTRACT FROM AUTHOR]

Citrus sinensis (L.) Osbeck is an important economic product in South China, but the presence of quarantine pests in this product proposes the potential threat to international trade security. To find a proper phytosanitary cold treatment for Bactrocera dorsalis (Hendel) (Diptera: Tephritidae), commonly called oriental fruit fly, one of the most serious quarantine insects in navel orange, eggs in petri dish and larvae in navel orange fruits were exposed to a 1.7 °C cold chamber for 0–11 days to compare the tolerance to cold treatment. The 2nd instar larva (4 days) is the most tolerant stage, and the estimated time for 99.9968% mortality at the 95% confidence level is 11.3 (9.5, 14.6) days. Then 15 days was selected as the target time for the confirmatory tests, resulting in no survivors from 37,792 treated larvae with the efficacy of 99.9921% mortality at the 95% confidence level. The quality assessments were conducted to compare the effect on the navel orange fruit between cold treatment and the conventional cold storage. Results indicated that the cold treatment did not negatively affect the fruit quality. Therefore, this cold treatment showed potential as a commercial quarantine treatment for navel orange in international trade. [ABSTRACT FROM AUTHOR]

Sialic acid-binding Ig-like lectin 8 (Siglec-8) is expressed on the surface of human eosinophils, mast cells, and basophils—cells that participate in allergic and other diseases. Ligation of Siglec-8 by specific glycan ligands or antibodies triggers eosinophil death and inhibits mast cell degranulation; consequences that could be leveraged as treatment. However, Siglec-8 is not expressed in murine and most other species, thus limiting preclinical studies in vivo. Based on a ROSA26 knock-in vector, a construct was generated that contains the CAG promoter, a LoxP-floxed-Neo-STOP fragment, and full-length Siglec-8 cDNA. Through homologous recombination, this Siglec-8 construct was targeted into the mouse genome of C57BL/6 embryonic stem (ES) cells, and chimeric mice carrying the ROSA26-Siglec-8 gene were generated. After cross-breeding to mast cell-selective Cre-recombinase transgenic lines (CPA3-Cre, and Mcpt5-Cre), the expression of Siglec-8 in different cell types was determined by RT-PCR and flow cytometry. Peritoneal mast cells (dual FcεRI+ and c-Kit+) showed the strongest levels of surface Siglec-8 expression by multicolor flow cytometry compared to expression levels on tissue-derived mast cells. Siglec-8 was seen on a small percentage of peritoneal basophils, but not other leukocytes from CPA3-Siglec-8 mice. Siglec-8 mRNA and surface protein were also detected on bone marrow-derived mast cells. Transgenic expression of Siglec-8 in mice did not affect endogenous numbers of mast cells when quantified from multiple tissues. Thus, we generated two novel mouse strains, in which human Siglec-8 is selectively expressed on mast cells. These mice may enable the study of Siglec-8 biology in mast cells and its therapeutic targeting in vivo. [ABSTRACT FROM AUTHOR]

Sialic acid-binding Ig-like lectin 8 (Siglec-8) is expressed on the surface of human eosinophils, mast cells, and basophils-cells that participate in allergic and other diseases. Ligation of Siglec-8 by specific glycan ligands or antibodies triggers eosinophil death and inhibits mast cell degranulation; consequences that could be leveraged as treatment. However, Siglec-8 is not expressed in murine and most other species, thus limiting preclinical studies in vivo. Based on a ROSA26 knock-in vector, a construct was generated that contains the CAG promoter, a LoxP-floxed-Neo-STOP fragment, and full-length Siglec-8 cDNA. Through homologous recombination, this Siglec-8 construct was targeted into the mouse genome of C57BL/6 embryonic stem (ES) cells, and chimeric mice carrying the ROSA26-Siglec-8 gene were generated. After cross-breeding to mast cell-selective Cre-recombinase transgenic lines (CPA3-Cre, and Mcpt5-Cre), the expression of Siglec-8 in different cell types was determined by RT-PCR and flow cytometry. Peritoneal mast cells (dual FcεRI⁺ and c-Kit⁺) showed the strongest levels of surface Siglec-8 expression by multicolor flow cytometry compared to expression levels on tissue-derived mast cells. Siglec-8 was seen on a small percentage of peritoneal basophils, but not other leukocytes from CPA3-Siglec-8 mice. Siglec-8 mRNA and surface protein were also detected on bone marrow-derived mast cells. Transgenic expression of Siglec-8 in mice did not affect endogenous numbers of mast cells when quantified from multiple tissues. Thus, we generated two novel mouse strains, in which human Siglec-8 is selectively expressed on mast cells. These mice may enable the study of Siglec-8 biology in mast cells and its therapeutic targeting in vivo.

To address the problem of model error and tracking dependence in the process of intelligent vehicle motion planning, an intelligent vehicle model transfer trajectory planning method based on deep reinforcement learning is proposed, which is able to obtain an effective control action sequence directly. Firstly, an abstract model of the real environment is extracted. On this basis, a deep deterministic policy gradient (DDPG) and a vehicle dynamic model are adopted to jointly train a reinforcement learning model, and to decide the optimal intelligent driving maneuver. Secondly, the actual scene is transferred to an equivalent virtual abstract scene using a transfer model. Furthermore, the control action and trajectory sequences are calculated according to the trained deep reinforcement learning model. Thirdly, the optimal trajectory sequence is selected according to an evaluation function in the real environment. Finally, the results demonstrate that the proposed method can deal with the problem of intelligent vehicle trajectory planning for continuous input and continuous output. The model transfer method improves the model's generalization performance. Compared with traditional trajectory planning, the proposed method outputs continuous rotation-angle control sequences. Moreover, the lateral control errors are also reduced., Competing Interests: The authors declare no conflict of interest.