Session interest model for CTR prediction based on self-attention mechanism

Click-through rate prediction, which aims to predict the probability of the user clicking on an item, is critical to online advertising. How to capture the user evolving interests from the user behavior sequence is an important issue in CTR prediction. However, most existing models ignore the factor that the sequence is composed of sessions, and user behavior can be divided into different sessions according to the occurring time. The user behaviors are highly correlated in each session and are not relevant across sessions. We propose an effective model for CTR prediction, named Session Interest Model via Self-Attention (SISA). First, we divide the user sequential behavior into session layer. A self-attention mechanism with bias coding is used to model each session. Since different session interest may be related to each other or follow a sequential pattern, next, we utilize gated recurrent unit (GRU) to capture the interaction and evolution of user different historical session interests in session interest extractor module. Then, we use the local activation and GRU to aggregate their target ad to form the final representation of the behavior sequence in session interest interacting module. Experimental results show that the SISA model performs better than other models.

A survey on IoT application layer protocols

<span>The constant evolution in internet technology has made. The internet of things (IoT) to be the center of research fields in computer engineering. This review paper discusses the choice of an application layer protocol in an IoT system integration so first, the paper briefly defines the potential protocols. After that, it opens up a comparison between these protocols according to how they manage their overhead and messages which affects traffic management and thus starts the discussion. The main contribution of this work is the simplification of comparison between session layer protocols in the benefit of IoT applications exclusively. IoT system Standards and platforms are being improved constantly. IoT enables application devices to connect and coordinate their tacks, such applications like healthcare, smart home, and industrial automation. Several protocols have been discussed to provide effective communication for resource-limited devices. However, their traffic management is still a field for researches, to find the optimal protocol choice for different situations. The review collects the results of other works that experimentally compared application layer protocols in the IoT environment and presents the graphical and tabular compression. Finally, the conclusion summarize the choice in different applications.</span>

Network Traffic Classification by Program Synthesis

Writing classification rules to identify interesting network traffic is a time-consuming and error-prone task. Learning-based classification systems automatically extract such rules from positive and negative traffic examples. However, due to limitations in the representation of network traffic and the learning strategy, these systems lack both expressiveness to cover a range of applications and interpretability in fully describing the traffic’s structure at the session layer. This paper presents Sharingan system, which uses program synthesis techniques to generate network classification programs at the session layer. Sharingan accepts raw network traces as inputs and reports potential patterns of the target traffic in NetQRE, a domain specific language designed for specifying session-layer quantitative properties. We develop a range of novel optimizations that reduce the synthesis time for large and complex tasks to a matter of minutes. Our experiments show that Sharingan is able to correctly identify patterns from a diverse set of network traces and generates explainable outputs, while achieving accuracy comparable to state-of-the-art learning-based systems.

Service Differentiated QOS Guaranteed Cross Layer Solution for Underwater Acoustic Sensor Networks (SD-QCLS)

Physical characteristics limits the capability of sensor network in case of underwater deployment. Factors like medium delay, doppler spreads and limited bandwidth are challengers to achieve a QoS (Quality of Service) guarantee in under water acoustic sensor networks. Under these conditions maximizing the bandwidth availability with consideration for application traffic requirements is important. This work proposes a service differentiated QOS guaranteed cross layer solution to maximize the available bandwidth and life time of the network under the constraints of application traffic requirements. At all different layers of IEEE 802.15.4 protocol stack, i.e., Application Layer, Session Layer, Network Layer, MAC Layer, and PHY Layer, the solution uses network parametes to optimize available bandwidth and also QoS. The solution involves redundancy and prediction based content coding at application layer, QoS based rate control at session layer, load based routing, transmission range adjustment at physical layer for guaranteed QoS delivery over acoustic sensor network.

A Survey of Protocols and Standards for Internet of Things

The rapid growth in technology and internet connected devices has enabled Internet of Things (IoT) to be one of the important fields in computing. Standards, technologies and platforms targeting IoT ecosystem are being developed at a very fast pace. IoT enables things to communicate and coordinate decisions for many different types of applications including healthcare, home automation, disaster recovery, and industry automation. It is expected to expand to even more applications in the future. This paper surveys several standards by IEEE, IETF and ITU that enable technologies enabling the rapid growth of IoT. These standards include communications, routing, network and session layer protocols that are being developed to meet IoT requirements. The discussion also includes management and security protocols in addition to the current challenges in IoT which gives insights into the current research to solve such challenges.