Intelligent Voice Instructor-Assistant System for Collaborative and Interactive Classes

College classes are becoming increasingly large.A critical component in scaling class size is the collaboration and interactions among instructors,teaching assistants,and students.We develop a prototype of an intelligent voice instructorassistant system for supporting large classes,in which Amazon Web Services,Alexa Voice Services,and self-developed services are used.It uses a scraping service for reading the questions and answers from the past and current course discussion boards,organizes the questions in JavaScript object notation format,and stores them in the database,which can be accessed by Amazon web services Alexa skills.When a voice question from a student comes,Alexa is used for translating the voice sentence into texts.Then,Siamese deep long short-term memory model is introduced to calculate the similarity between the question asked and the questions in the database to find the best-matched answer.Questions with no match will be sent to the instructor,and instructor’s answer will be added into the database.Experiments show that the implemented model achieves promising results that can lead to a practical system.Intelligent voice instructor-assistant system starts with a small set of questions.It can grow through learning and improving when more and more questions are asked and answered.

创建软件定义网络中的进程级纵深防御体系结构

云计算因其资源的弹性和可拓展性,在为用户提供各项服务时,相对于传统方式占据了先机.在用户考虑是否转向云计算时,一个极其重要的安全风险是:攻击者可以通过共享的云资源对云用户发起针对虚拟机的高效攻击.虚拟机作为云服务的基本资源,攻击者在攻击或者租用了某虚拟机之后,通过在其中部署恶意软件,并针对云内其他虚拟机发起更大范围的攻击行为,如分布式拒绝服务型攻击.为防止此种情况的发生,提出基于软件定义网络的纵深防御系统,以及时检测可疑虚拟机并控制其发出的流量,抑制来自该虚拟机的攻击行为并减轻因攻击所受到的影响.该系统以完全无代理的非侵入方式检测虚拟机状态,且基于软件定义网络,对同主机内虚拟机间或云主机间的网络流量进行进程级的监控.实验结果表明了该系统的有效性.

End-to-end dilated convolution network for document image semantic segmentation

Semantic segmentation is a crucial step for document understanding.In this paper,an NVIDIA Jetson Nano-based platform is applied for implementing semantic segmentation for teaching artificial intelligence concepts and programming.To extract semantic structures from document images,we present an end-to-end dilated convolution network architecture.Dilated convolutions have well-known advantages for extracting multi-scale context information without losing spatial resolution.Our model utilizes dilated convolutions with residual network to represent the image features and predicting pixel labels.The convolution part works as feature extractor to obtain multidimensional and hierarchical image features.The consecutive deconvolution is used for producing full resolution segmentation prediction.The probability of each pixel decides its predefined semantic class label.To understand segmentation granularity,we compare performances at three different levels.From fine grained class to coarse class levels,the proposed dilated convolution network architecture is evaluated on three document datasets.The experimental results have shown that both semantic data distribution imbalance and network depth are import factors that influence the document’s semantic segmentation performances.The research is aimed at offering an education resource for teaching artificial intelligence concepts and techniques.

Efficient Priority Packet Recovery Based on Network Coding in DVB-IPDC System

In DVB-IPDC system, due to the constraints of handheld devices and the broadcast nature of wireless network, packet loss is inevitable. ECDR-NC proposed is a retransmission encoding packet selection algorithm based on the dynamic information updating, which can find the current most effective complete decoding packet. ECDR-NC can not only avoid the redundant encoding packets due to the overlapping among encoding packets, but also reduce the computational complexity compared with the traditional encoding schemes. Furthermore, the retransmission upper bound of ECDR-NC is fully controlled. In time-sensitive applications, to maximize the aggregate number of recovery packets while minimizing the total number of discarded packets due to the time limit according to the priority preference, the adaptive priority scheme EPNC is formulized, and the weighted relation graph is constructed to find the maximum-weighted encoding packets sequence according to the decoding gains. In the same network environment, the performances comparisons between PNC and EPNC show that EPNC is more efficient and more rational, and the average discarded packets ratios ofEPNC can be reduced about 18%~27%. The main contributions of this paper are an effective retransmission encoding packet selection algorithm ECDR-NC proposed, and a new adaptive priority recovery scheme EPNC introduced into DVB-IPDC system.

Attribute-Based Signature with Policy-and-Endorsement Mechanism

In this paper a new signature scheme,called Policy-Endorsing Attribute-Based Signature,is developed to correspond with the existing Ciphertext-Policy Attribute-Based Encryption.This signature provides a policy-and-endorsement mechanism.In this mechanism a single user,whose attributes satisfy the predicate,endorses the message.This signature allows the signer to announce his endorsement using an access policy without having to reveal the identity of the signer.The security of this signature,selfless anonymity and existential unforgeability,is based on the Strong Diffie-Hellman assumption and the Decision Linear assumption in bilinear map groups.

Recent progress and trends in predictive visual analytics

A wide variety of predictive analytics techniques have been developed in statistics, machine learning and data mining; however, many of these algorithms take a black-box approach in which data is input and future predictions are output with no insight into what goes on during the process. Unfortunately, such a closed system approach often leaves little room for injecting domain expertise and can result in frustration from analysts when results seem snurious or confusing. In order to allow for more human-centric approaches, the visualization community has begun developing methods to enable users to incorporate expert knowledge into the pre- diction process at all stages, including data cleaning, feature selection, model building and model validation. This paper surveys current progress and trends in predictive visual ana- lytics, identifies the common framework in which predictive visual analytics systems operate, and develops a summariza- tion of the predictive analytics workfiow.

A Brief Review of Network Embedding

Learning the representations of nodes in a network can benefit various analysis tasks such as node classification, link prediction, clustering, and anomaly detection. Such a representation learning problem is referred to as network embedding, and it has attracted significant attention in recent years. In this article, we briefly review the existing network embedding methods by two taxonomies. The technical taxonomy focuses on the specific techniques used and divides the existing network embedding methods into two stages, i.e., context construction and objective design. The non-technical taxonomy focuses on the problem setting aspect and categorizes existing work based on whether to preserve special network properties, to consider special network types, or to incorporate additional inputs. Finally, we summarize the main findings based on the two taxonomies, analyze their usefulness,and discuss future directions in this area.

System architecture for high-performance permissioned blockchains

Blockchain(BC),as an emerging distributed database technology with advanced security and reliability,has attracted much attention from experts who devoted to efinance,intellectual property protection,the internet of things(IoT)and so forth.However,the inefficient transaction processing speed,which hinders the BC’s widespread,has not been well tackled yet.In this paper,we propose a novel architecture,called Dual-Channel Parallel Broadcast model(DCPB),which could address such a problem to a greater extent by using three methods which are dual communication channels,parallel pipeline processing and block broadcast strategy.In the dual-channel model,one channel processes transactions,and the other engages in the execution of BFT.The parallel pipeline processing allows the system to operate asynchronously.The block generation strategy improves the efficiency and speed of processing.Extensive experiments have been applied to BeihangChain,a simplified prototype for BC system,illustrates that its transaction processing speed could be improved to 16K transaction per second which could well support many real-world scenarios such as BC-based energy trading system and Micro-film copyright trading system in CCTV.

Provably Secure Role-Based Encryption with Revocation Mechanism

Role-Based Encryption （RBE） realizes access control mechanisms over encrypted data according to the widely adopted hierarchical RBAC model. In this paper, we present a practical RBE scheme with revocation mechanism based on partial-order key hierarchy with respect to the public key infrastructure, in which each user is assigned with a unique private-key to support user identification, and each role corresponds to a public group-key that is used to encrypt data. Based on this key hierarchy structure, our RBE scheme allows a sender to directly specify a role for encrypting data, which can be decrypted by all senior roles, as well as to revoke any subgroup of users and roles. We give a full proof of security of our scheme against hierarchical collusion attacks. In contrast to the existing solutions for encrypted file systems, our scheme not only supports dynamic joining and revoking users, but also has shorter ciphertexts and constant-size decryption keys.

Global optimum encoding packet selection mechanism based on opportunistic network coding for wireless network retransmission

Packet loss cannot be avoided in wireless network due to wireless transmission medium particularity, therefore improving retransmission efficiency is meaningful to wireless transmission. The current retransmission packet selection mechanisms based on oppornistic network coding （ONC） face low retransmission efficiency and high computational complexity problems. To these problems, an optimized encoding packet selection mechanism based on ONC in wireless network retransmission （OONCR） is proposed. This mechanism is based on mutual exclusion packets and decoding gain concepts, and makes full use of ONC advantages. The main contributions of this scheme are to control the algorithm eomplexity of the maximum encoding packets selection effectively, avoid the redundancy encoding packets due to the overlapping among encoding packets, and take the encoding packet local and global optimization problem into consideration. Retransmission efficiency is evaluated according to the computational complexity, the throughput, the retransmission redundancy ratio, and the number of average retransmission. Under the various conditions, the number of average retransmission of OONCR is mainly lower than that of other typical retransmission packet selection schemes. The average retransmission redundancy ratios of OONCR are lower about 5%-40% compared with other typical schemes. Simultaneously the computational complexity of OONCR is comparatively lower than that of other typical schemes.