A scalable approach to optimize traffic signal control with federated reinforcement learning.

Intelligent Transportation has seen significant advancements with Deep Learning and the Internet of Things, making Traffic Signal Control (TSC) research crucial for reducing congestion, travel time, emissions, and energy consumption. Reinforcement Learning (RL) has emerged as the primary method for TSC, but centralized learning poses communication and computing challenges, while distributed learning struggles to adapt across intersections. This paper presents a novel approach using Federated Learning (FL)-based RL for TSC. FL integrates knowledge from local agents into a global model, overcoming intersection variations with a unified agent state structure. To endow the model with the capacity to globally represent the TSC task while preserving the distinctive feature information inherent to each intersection, a segment of the RL neural network is aggregated to the cloud, and the remaining layers undergo fine-tuning upon convergence of the model training process. Extensive experiments demonstrate reduced queuing and waiting times globally, and the successful scalability of the proposed model is validated on a real-world traffic network in Monaco, showing its potential for new intersections.

Toward Collaborative Intelligence in IoV Systems: Recent Advances and Open Issues.

Internet of Vehicles (IoV) technology has been attracting great interest from both academia and industry due to its huge potential impact on improving driving experiences and enabling better transportation systems. While a large number of interesting IoV applications are expected, it is more challenging to design an efficient IoV system compared with conventional Internet of Things (IoT) applications due to the mobility of vehicles and complex road conditions. We discuss existing studies about enabling collaborative intelligence in IoV systems by focusing on collaborative communications, collaborative computing, and collaborative machine learning approaches. Based on comparison and discussion about the advantages and disadvantages of recent studies, we point out open research issues and future research directions.

Next-generation sequencing based detection of BRCA1 and BRCA2 large genomic rearrangements in Chinese cancer patients.

BRCA1/2 mutation is a biomarker for guiding multiple solid tumor treatment. However, the prevalence of BRCA1/2 large genomic rearrangements (LGRs) in Chinese cancer patients has not been well revealed partially due to technical difficulties in LGR detection. This study utilized next-generation sequencing (NGS) to analyze the BRCA1/2 mutation profile, including LGR, in 56126 Chinese cancer patients. We also reported that two ovarian and breast cancer patients with NGS-determined BRCA1/2 LGR benefited from PARP inhibitors (PARPi). DNA sequencing identified BRCA1/2 variants (including LGR, pathogenic and likely-pathogenic variants) in 2108 individuals. Seventy patients were discovered to harbor germline LGRs in BRCA1 and 14 had germline LGRs in BRCA2. Among the LGRs detected, exon 1-2 deletion was the predominant LGR (14/70) in BRCA1, and exon 22-24 deletion was the most frequent LGR (3/14) in BRCA2. Notably, the BRCA1 exon 7 deletion was a novel LGR and was identified in six patients, suggesting a specific LGR in Chinese cancer patients. The prevalence analysis of BRCA1 and BRCA2 LGRs across multiple cancers revealed that BRCA1 LGR more frequently occurred in ovarian cancer (1.31%, 33/2526), and BRCA2 LGR was more commonly seen in cholangiocarcinoma (0.47%, 2/425). Two ovarian and breast cancer patients with BRCA1/2 LGR benefited from PARPi therapy. This is the first study to reveal the BRCA1/2 LGR profile of a Chinese pan-cancer cohort by using an NGS-based assay. Two breast and ovarian cancer patients harboring NGS-determined BRCA1/2 LGR benefited from PARPi, indicating that NGS-based detection of BRCA1/2 LGR has the potential to guide PARPi treatment.

A Brief Review of Multipath TCP for Vehicular Networks.

Multipath TCP (MPTCP) is one of the most important extensions to TCP that enables the use of multiple paths in data transmissions for a TCP connection. In MPTCP, the end hosts transmit data across a number of TCP subflows simultaneously on one connection. MPTCP can sufficiently utilize the bandwidth resources to improve the transmission efficiency while providing TCP fairness to other TCP connections. Meanwhile, it also offers resilience due to multipath data transfers. MPTCP attracts tremendous attention from the academic and industry field due to the explosive data growth in recent times and limited network bandwidth for each single available communication interface. The vehicular Internet-of-Things systems, such as cooperative autonomous driving, require reliable high speed data transmission and robustness. MPTCP could be a promising approach to solve these challenges. In this paper, we first conduct a brief survey of existing MPTCP studies and give a brief overview to multipath routing. Then we discuss the significance technical challenges in applying MPTCP for vehicular networks and point out future research directions.

Quantitative Study on the Impact of Energy Consumption Based Dynamic Selfishness in MANETs.

Cooperative communication and resource limitation are two main characteristics of mobile ad hoc networks (MANETs). On one hand, communication among the nodes in MANETs highly depends on the cooperation among nodes because of the limited transmission range of the nodes, and multi-hop communications are needed in most cases. On the other hand, every node in MANETs has stringent resource constraints on computations, communications, memory, and energy. These two characteristics lead to the existence of selfish nodes in MANETs, which affects the network performance in various aspects. In this paper, we quantitatively investigate the impacts of node selfishness caused by energy depletion in MANETs in terms of packet loss rate, round-trip delay, and throughput. We conducted extensive measurements on a proper simulation platform incorporating an OMNeT++ and INET Framework. Our experimental results quantitatively indicate the impact of node selfishness on the network performance in MANETs. The results also imply that it is important to evaluate the impact of node selfishness by jointly considering selfish nodes' mobility models, densities, proportions, and combinations.

Blockchain for Vehicular Internet of Things: Recent Advances and Open Issues.

The vehicular Internet of Things (IoT) comprises enabling technologies for a large number of important applications including collaborative autonomous driving and advanced transportation systems. Due to the mobility of vehicles, strict application requirements, and limited communication resources, the conventional centralized control fails to provide sufficient quality of service for connected vehicles, so a decentralized approach is required in the vicinity to satisfy the requirements of delay-sensitive and mission-critical applications. A decentralized system is also more resistant to the single point of failure problem and malicious attacks. Blockchain technology has been attracting great interest due to its capability of achieving a decentralized, transparent, and tamper-resistant system. There are many studies focusing on the use of blockchain in managing data and transactions in vehicular environments. However, the application of blockchain in vehicular environments also faces some technical challenges. In this paper, we first explain the fundamentals of blockchain and vehicular IoT. Then, we conduct a literature review on the existing research efforts of the blockchain for vehicular IoT by discussing the research problems and technical issues. After that, we point out some future research issues considering the characteristics of both blockchain and vehicular IoT.

Pathogenic Germline Mutations in Chinese Patients with Gastric Cancer Identified by Next-Generation Sequencing.

BACKGROUND: Gastric cancer (GC) is one of the leading causes of cancer death in China, while the nature of genetic factors related to GC has not been well-studied. OBJECTIVES: To assess the inherited genetic factors regarding pathogenic germline mutations in Chinese GC population. METHODS: Genomic profiling of DNA was performed through next-generation sequencing with 381 cancer-related genes on tissue from patients with GC between January 1, 2017, and May 7, 2019. RESULTS: 470 GC patients were included for analysis. A total of 28 (6.0%) patients were identified to harbor 25 different pathogenic or very likely pathogenic germline mutations in 15 genes. The variants fell most frequently in BRCA2 (n = 6, 1.28%), CHEK2 (n = 5, 1.06%), MUTYH (n = 3, 0.64%), CDH1 (n = 2, 0.43%), and ATM (n = 2, 0.43%). Of all the germline-mutated genes, 66.7% (n = 10) lay in the DNA damage repair pathways. Seven patients were identified to have a high TMB status, among whom two were also identified as MSI-H. Overall, 20 out of the 28 patients (71.4%) carried clinically actionable mutations. CONCLUSIONS: Our study has depicted the spectrum of pathogenic germline mutations in Chinese GC patients, which may provide valuable clues for the assessment of the genetic susceptibility and clinical management in GC.

Federated Learning for Vehicular Internet of Things: Recent Advances and Open Issues.

Federated learning (FL) is a distributed machine learning approach that can achieve the purpose of collaborative learning from a large amount of data that belong to different parties without sharing the raw data among the data owners. FL can sufficiently utilize the computing capabilities of multiple learning agents to improve the learning efficiency while providing a better privacy solution for the data owners. FL attracts tremendous interests from a large number of industries due to growing privacy concerns. Future vehicular Internet of Things (IoT) systems, such as cooperative autonomous driving and intelligent transport systems (ITS), feature a large number of devices and privacy-sensitive data where the communication, computing, and storage resources must be efficiently utilized. FL could be a promising approach to solve these existing challenges. In this paper, we first conduct a brief survey of existing studies on FL and its use in wireless IoT. Then we discuss the significance and technical challenges of applying FL in vehicular IoT, and point out future research directions.

Extended motion diffusion based change detection for airport ground surveillance.

Change detection in airport ground is important for airport security. Due to the particularity of ground environment, e.g. haze and camouflage, airport ground change detection is generally incomplete. If an incomplete detection is used as reference for the detection in subsequent frames, it may result in noticeable detection defects across the frames. In this paper, extended motion diffusion (EMD) is proposed to address the problems. The core idea of the EMD is to design a novel model insensitive to incomplete detection. Firstly the one-to-many correspondence in traditional motion diffusion is extended in the prediction step of EMD to build up correspondence from incomplete detection to intact objects. Prior information, e.g. aircraft motion prior and ground structure prior, is employed in the development of the correspondence. Then based on the correspondence a number of new samples are synthesized and filtered in the identification step of the EMD to compensate possible detection defects. Finally, the reserved samples are collected to train a foreground model, which is used in conjunction with another background model for classification. The proposed method is verified based on the Airport Ground Video Surveillance (AGVS) benchmark. Experimental results show effectiveness of the proposed algorithm in dealing with haze and camouflage.

SDN-based Handover Scheme in Cellular/IEEE 802.11p Hybrid Vehicular Networks.

With the arrival of 5G, the wireless network will be provided with abundant spectrum resources, massive data transmissions and low latency communications, which makes Vehicle-to-Everything applications possible. However, VANETs always accompany with frequent network topology changes due to the highly mobile feature of vehicles. As a result, the network performance will be affected by the frequent handover. In this paper, a seamless handover schemeis proposed where the Software-Defined Networking (SDN) and Mobile Edge Computing (MEC) technologies are employed to adapt to the dynamic topology change in VANETs. The introductionof SDN provides a global view of network topology and centralized control, which enables a stable transmission layer connection when a handover takes place, so that the upper layer performance isnot influenced by the network changes. By employing MEC server, the data are cached in advance before a handover happens, so that the vehicle can restore normal communication faster. In order toconfirm the superiority of our proposal, computer simulations are conducted from different aspects. The results show that our proposal can significantly improve the network performance when ahandover happens.

LoRa-Based Physical Layer Key Generation for Secure V2V/V2I Communications.

In recent years, Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) communication brings more and more attention from industry (e.g., Google and Uber) and government (e.g., United States Department of Transportation). These Vehicle-to-Everything (V2X) technologies are widely adopted in future autonomous vehicles. However, security issues have not been fully addressed in V2V and V2I systems, especially in key distribution and key management. The physical layer key generation, which exploits wireless channel reciprocity and randomness to generate secure keys, provides a feasible solution for secure V2V/V2I communication. It is lightweight, flexible, and dynamic. In this paper, the physical layer key generation is brought to the V2I and V2V scenarios. A LoRa-based physical key generation scheme is designed for securing V2V/V2I communications. The communication is based on Long Range (LoRa) protocol, which is able to measure Received Signal Strength Indicator (RSSI) in long-distance as consensus information to generate secure keys. The multi-bit quantization algorithm, with an improved Cascade key agreement protocol, generates secure binary bit keys. The proposed schemes improved the key generation rate, as well as to avoid information leakage during transmission. The proposed physical layer key generation scheme was implemented in a V2V/V2I network system prototype. The extensive experiments in V2I and V2V environments evaluate the efficiency of the proposed key generation scheme. The experiments in real outdoor environments have been conducted. Its key generation rate could exceed 10 bit/s on our V2V/V2I network system prototype and achieve 20 bit/s in some of our experiments. For binary key sequences, all of them pass the suite of statistical tests from National Institute of Standards and Technology (NIST).

Spectrum of Pathogenic Germline Mutations in Chinese Lung Cancer Patients through Next-Generation Sequencing.

Lung cancer is currently a leading cause of cancer-associated mortality worldwide. Despite the increasing evidences of variants that were associated with lung cancer risk, investigations of genetic factors and their roles in genetic susceptibility to lung cancer were limited. Here we systematically investigated the spectrum of pathogenic germline mutations in Chinese population with lung cancer. Genomic profiling of DNA was performed through next-generation sequencing (NGS) on tissue biopsy from 1764 Chinese lung cancer patients with a 381 cancer gene panel between January 01, 2017 and May 07, 2019. Patients with germline mutations were identified, and their clinical information were collected. Of 1764 patients with lung cancer, 67 (3.8%) patients were identified to carry pathogenic or likely pathogenic germline mutations in 25 cancer predisposition genes, with a frequency of 3.6% in lung adenocarcinoma (49/1349), 4.3% in squamous cell lung cancer (14/322), 5.6% in small cell lung cancer (4/72), and none in lung adenosquamous carcinoma (0/21), respectively. The highest pathogenic germline mutational prevalence were found in BRCA2 (0.79%), CHEK2 (0.40%), BRCA1 (0.34%), and TP53 (0.34%). Two splice mutations were reported for the first time in this study. Notably, a majority (85.5%) of the detected germline mutations fell in DNA damage repair pathways.

A Context-Aware Edge-Based VANET Communication Scheme for ITS.

We propose a context-aware edge-based packet forwarding scheme for vehicular networks. The proposed scheme employs a fuzzy logic-based edge node selection protocol to find the best edge nodes in a decentralized manner, which can achieve an efficient use of wireless resources by conducting packet forwarding through edges. A reinforcement learning algorithm is used to optimize the last two-hop communications in order to improve the adaptiveness of the communication routes. The proposed scheme selects different edge nodes for different types of communications with different context information such as connection-dependency (connection-dependent or connection-independent), communication type (unicast or broadcast), and packet payload size. We launch extensive simulations to evaluate the proposed scheme by comparing with existing broadcast protocols and unicast protocols for various network conditions and traffic patterns.

Current situation of traditional Chinese medicine on the health management / 国际中医中药杂志

Awareness of Health-Preservation management of traditional Chinese medicine (TCM) in public was investigated from June to early July in 2017 by the web of question nairein vestigation"Wenjuanxing". The result showed that 324 of 369 questionnaires were received and checked, accounting for 87.8%. In conclusion, the awareness of Health-Preservation management of TCM in public was poor, and it's important to raise the publicity of Health-Preservation management of TCM firstly in the community hospital in order to increase the awareness of people's acception.

Complete Genome Sequence of Elizabethkingia meningoseptica, Isolated from a T-Cell Non-Hodgkin's Lymphoma Patient.

An Elizabethkingia meningoseptica infection was detected at the end stage of a patient with T-cell non-Hodgkin's lymphoma. The complete genome of this isolated strain, FMS-007, was generated in one contig with a total size of 3,938,967 bp. A preliminary screening indicated that the genome contains drug resistance genes to aminoglycosides and ß-lactams. A clustered regularly interspaced short palindromic repeats (CRISPR)/CRISPR-associated proteins (CRISPR/Cas) system with 16 direct repeats and 15 spacers was identified.

Identification and characterization of a novel prokaryotic peptide: N-glycosidase from Elizabethkingia meningoseptica.

Peptide:N-glycosidase (PNGase) F, the first PNGase identified in prokaryotic cells, catalyzes the removal of intact asparagine-linked oligosaccharide chains from glycoproteins and/or glycopeptides. Since its discovery in 1984, PNGase F has remained as the sole prokaryotic PNGase. Recently, a novel gene encoding a protein with a predicted PNGase domain was identified from a clinical isolate of Elizabethkingia meningoseptica. In this study, the candidate protein was expressed in vitro and was subjected to biochemical and structural analyses. The results revealed that it possesses PNGase activity and has substrate specificity different from that of PNGase F. The crystal structure of the protein was determined at 1.9 Å resolution. Structural comparison with PNGase F revealed a relatively larger glycan-binding groove in the catalytic domain and an additional bowl-like domain with unknown function at the N terminus of the candidate protein. These structural and functional analyses indicated that the candidate protein is a novel prokaryotic N-glycosidase. The protein has been named PNGase F-II.