Matrix Factorization Techniques for Recommender Systems

Data compression is an important part of information security because compressed data is more secure and easy to handle. Effective data compression technology creates efficient, secure, and easy-to-connect data. There are two types of compression algorithm techniques, lossy and lossless. These technologies can be used in any data format such as text, audio, video, or image file. The main objective of this study was to reduce the physical space on the various storage media and reduce the time of sending data over the Internet with a complete guarantee of encrypting this data and hiding it from intruders. Two techniques are implemented, with data loss (Lossy) and without data loss (Lossless). In the proposed paper a hybrid data compression algorithm increases the input data to be encrypted by RSA (Rivest–Shamir–Adleman) cryptography method to enhance the security level and it can be used in executing lossy and lossless compacting Steganography methods. This technique can be used to decrease the amount of every transmitted data aiding fast transmission while using slow internet or take a small space on different storage media. The plain text is compressed by the Huffman coding algorithm, and also the cover image is compressed by Discrete wavelet transform DWT based that compacts the cover image through lossy compression in order to reduce the cover image’s dimensions. The least significant bit LSB will then be used to implant the encrypted data in the compacted cover image. We evaluated that system on criteria such as percentage Savings percentage, Compression Time, Compression Ratio, Bits per pixel, Mean Squared Error, Peak Signal to Noise Ratio, Structural Similarity Index, and Compression Speed. This system shows a high-level performance and system methodology compared to other systems that use the same methodology.

/pdf/hiding-data-using-efficient-combination-of-rsa-cryptography-2hyeuachte.pdf

Hiding Data Using Efficient Combination of RSA Cryptography, and Compression Steganography Techniques

In today’s Internet, killer network services and applications, such as video and audio streaming, network storage, and online video games, are pushing the network infrastructure resources to the edge. By design and for the most part, the Internet is the best offer delivery ecosystem with little or no end-to-end quality-of-service (QoS) guarantees. Even, frameworks, such as IntServ and DiffServ that were designed and implemented to provide QoS guarantees, still fail to solve this problem at a wide scale. Software-defined networking (SDN) is a fast emerging networking paradigm that promises to provide end-to-end QoS guaranteeing by offering greater network flexibility, abstraction, control, and programmability to network resources. In this paper, we review, survey, and discuss the current state of the art on QoS provisioning in the area of SDN, with respect to applying the concept of autonomic computing (AC) to automatically support, provision, monitor, and maintain QoS requirements. This paper includes in-depth classification, taxonomy, and comparative analysis for the autonomic-based QoS provisioning in accordance with the famous influential and widely adopted the monitor-analyze-plan-execute-knowledge (MAPE-K) IBM architectural model for autonomic computing.

/pdf/a-survey-on-autonomic-provisioning-and-management-of-qos-in-1il0jkhvto.pdf

A Survey on Autonomic Provisioning and Management of QoS in SDN Networks

Software-defined networking (SDN) separates the network control plane from the packet forwarding plane, which provides comprehensive network-state visibility for better network management and resilience. Traffic classification, particularly for elephant flow detection, can lead to improved flow control and resource provisioning in SDN networks. Existing elephant flow detection techniques use pre-set thresholds that cannot scale with the changes in the traffic concept and distribution. This paper proposes a flow-aware elephant flow detection applied to SDN. The proposed technique employs two classifiers, each respectively on SDN switches and controller, to achieve accurate elephant flow detection efficiently. Moreover, this technique allows sharing the elephant flow classification tasks between the controller and switches. Hence, most mice flows can be filtered in the switches, thus avoiding the need to send large numbers of classification requests and signaling messages to the controller. Experimental findings reveal that the proposed technique outperforms contemporary methods in terms of the running time, accuracy, F-measure, and recall.

https://northumbria-test.eprints-hosting.org/id/document/271517

Flow-Aware Elephant Flow Detection for Software-Defined Networks

Location-based Social Networks (LBSNs) enable users to socialize with friends and acquaintances by sharing their check-ins, opinions, photos, and reviews. Huge volume of data generated from LBSNs opens up a new avenue of research that gives birth to a new sub-field of recommendation systems, known as Point-of-Interest (POI) recommendation. A POI recommendation technique essentially exploits users' historical check-ins and other multi-modal information such as POI attributes and friendship network, to recommend the next set of POIs suitable for a user. A plethora of earlier works focused on traditional machine learning techniques by using hand-crafted features from the dataset. With the recent surge of deep learning research, we have witnessed a large variety of POI recommendation works utilizing different deep learning paradigms. These techniques largely vary in problem formulations, proposed techniques, used datasets, and features, etc. To the best of our knowledge, this work is the first comprehensive survey of all major deep learning-based POI recommendation works. Our work categorizes and critically analyzes the recent POI recommendation works based on different deep learning paradigms and other relevant features. This review can be considered a cookbook for researchers or practitioners working in the area of POI recommendation.

A Survey on Deep Learning Based Point-Of-Interest (POI) Recommendations

In Real-Time Bidding (RTB) advertising, estimating the winning price is an important task in evaluating the bid cost of bid requests in Demand-Side Platforms (DSPs). The prior works utilize censored linear regression for winning price estimation by considering both winning and losing bid records. In the traditional regression models, the winning price of each bid request is based on Gaussian distribution. However, the property of Gaussian distribution is not suitable for the winning price of each bid request, and it is hard to link the physical meaning of Gaussian distribution and the winning price. Therefore, in this paper, based on our observation and analysis, the winning price of each bid request is modeled by a unique gamma distribution with respect to its features. Then we propose a gamma-based censored linear regression with regularization for winning price estimation. To derive the parameters of our proposed complicated model based on bid records, our approach is to divide this hard problem into two sub-problems, which are easier to solve. In practice, we also provide four heuristic initial parameter settings that are able to greatly reduce the computation cost when deriving the parameters. The experimental results demonstrate that our approach is highly effective for estimating the winning price compared with the state-of-the-art approaches in three real datasets.

A gamma-based regression for winning price estimation in real-time bidding advertising

We propose in this paper a classification-based elephant flow detection method for SDN environments. The proposed elephant flow detection method consists of two classifiers running on the switch and the controller, respectively. For better performance, the concept of application round is used to build the classifier running on the controller. Experimental results show that our elephant flow detection method is able to obtain high recall and F-measure.

A classification-based elephant flow detection method using application round on SDN environments

With the popularization of mobile devices and wireless networks, people are able to share their experience on points of interest (POIs) in social networks through "check-ins." Therefore, the problem of successive POI recommendation has been proposed to recommend some POIs to users so that the users are likely to check in at these POIs in the near future. In this paper, we propose a two-phase method to solve the problem of successive POI recommendation. First, we utilize the Matrix Factorization technique to analyze the interaction of users and their sequential check-in behavior with time influence and POI categories, and select the candidate categories that the user will visit. Then, after removing those POIs not belonging to the candidate categories, we fuse user preferences, temporal influence and geographical influence together and finally recommend the POIs with high scores to users. The experimental results on a real check-in dataset show that our recommendation method is better than several state-of-the-art methods in terms of precision and recall.

Successive POI Recommendation with Category Transition and Temporal Influence

In this article, we propose a novel temporal pattern mining problem, named high-utility temporal pattern mining, to fulfill the needs of various applications. Different from classical temporal pattern mining aimed at discovering frequent temporal patterns, high-utility temporal pattern mining is to find each temporal pattern whose utility is greater than or equal to the minimum-utility threshold. To facilitate efficient high-utility temporal pattern mining, several extension and pruning strategies are proposed to reduce the search space. Algorithm HUTPMiner is then proposed to efficiently mine high-utility temporal patterns with the aid of the proposed extension and pruning strategies. Experimental results show that HUTPMiner is able to prune a large number of candidates, thereby achieving high mining efficiency.

Mining High-utility Temporal Patterns on Time Interval–based Data

In Real-Time Bidding (RTB) advertising, evaluating the Click-Through Rate (CTR) of a bid request and an ad is important for bidding strategy optimization on Demand-Side Platforms (DSPs). The regression-based approaches are popular for CTR estimation in RTB since this kind of approach is highly efficient and scalable. The information of the bid request and the ad contains categorical attributes (such URL) and numerical attributes (such ad size). To vectorize the information for the input of regression-based approaches, the categorical attributes will be expanded to several binary features in general. However, some categorical attributes have infinite possible values (such as URL). Thus, for these attributes, only observed values in training will be transformed into binary features. If there is a new attribute or value in online environment, this information will be lost after vectorization. In this paper, we first exploit the feature hashing trick to transform the categorical and numerical attributes into the large fixed size vector. Since the vector is large and sparse, we propose a Softmax-based Ensemble Model, SEM, which adopts only a few key features after feature hashing for CTR estimation. The experimental results demonstrate that our proposed approach is able to adapt to the harsh environments in RTB, and outperforms the state-of-the-art approaches effectively when only less than 50 features are adopted in two real datasets.

Wen-Yueh Shih

Papers

A gamma-based regression for winning price estimation in real-time bidding advertising

A classification-based elephant flow detection method using application round on SDN environments

Successive POI Recommendation with Category Transition and Temporal Influence

Mining High-utility Temporal Patterns on Time Interval–based Data

SEM: A Softmax-based Ensemble Model for CTR estimation in Real-Time Bidding advertising