Recommendation System for Purchasing Goods Based on the Decision Tree Algorithm

Over the past few years, interest in applications related to recommendation systems has increased significantly. Many modern services create recommendation systems that, based on user profile information and his behavior. This services determine which objects or products may be interesting to users. Recommendation systems are a modern tool for understanding customer needs. The main methods of constructing recommendation systems are the content-based filtering method and the collaborative filtering method. This article presents the implementation of these methods based on decision trees. The content-based filtering method is based on the description of the object and the customer’s preference profile. An object description is a finite set of its descriptors, such as keywords, binary descriptors, etc., and a preference profile is a weighted vector of object descriptors in which scales reflect the importance of each descriptor to the client and its contribution to the final decision. This model selects items that are similar to the customer’s favorite items before. The second model, which implements the method of collaborative filtering, is based on information about the history of behavior of all customers on the resource: data on their purchases, assessments of product quality, reviews, marked product. The model finds clients that are similar in behavior and the recommendation is based on their assessments of this element. Voting was used to combine the results issued by individual models — the best result is chosen from the results of two models of the ensemble. This approach minimizes the impact of randomness and averages the errors of each model. The aim: The purpose of work is to create real competitive recommendation system for short period of time and minimum costs.

Transport Triggered Array Processor for Vision Applications: Near-threshold Performance Loss Compensation Through Inherent Parallelism of Vision Array Processors

<div>Operating at reduced voltages promises substantial energy efficiency improvement, however the downside is significant down-scaling of clock frequency. This paper propose vision chips as excellent fit for low-voltage operation. Low-level sensory data processing in many Internet-of-Things (IoT) devices pursue energy efficiency by utilizing sleep modes or slowing the clocking to the minimum. To curb the share of stand-by power dissipation in those designs, near-threshold/sub-threshold operational points or ultra-low-leakage processes in fabrication are employed. Those limit the clocking rates significantly, reducing the computing throughputs of individual processing cores. In this contribution we explore compensating for the performance loss of operating in near-threshold region ($V_{dd}=$0.6V) through massive parallelization. Benefits of near-threshold operation and massive parallelism are optimum energy consumption per instruction operation and minimized memory round-trips, respectively. The Processing Elements (PE) of the design are based on Transport Triggered Architecture. The fine grained programmable parallel solution allows for fast and efficient computation of learnable low-level features (e.g. local binary descriptors and convolutions). Other operations, including Max-pooling have also been implemented. The programmable design achieves excellent energy efficiency for Local Binary Patterns computations. </div><div>Our results demonstrates that the inherent properties of chip processor and vision applications allow voltage and clock frequency aggressively without having to compromise performance. </div>

Transport Triggered Array Processor for Vision Applications: Near-threshold Performance Loss Compensation Through Inherent Parallelism of Vision Array Processors

<div>Operating at reduced voltages promises substantial energy efficiency improvement, however the downside is significant down-scaling of clock frequency. This paper propose vision chips as excellent fit for low-voltage operation. Low-level sensory data processing in many Internet-of-Things (IoT) devices pursue energy efficiency by utilizing sleep modes or slowing the clocking to the minimum. To curb the share of stand-by power dissipation in those designs, near-threshold/sub-threshold operational points or ultra-low-leakage processes in fabrication are employed. Those limit the clocking rates significantly, reducing the computing throughputs of individual processing cores. In this contribution we explore compensating for the performance loss of operating in near-threshold region ($V_{dd}=$0.6V) through massive parallelization. Benefits of near-threshold operation and massive parallelism are optimum energy consumption per instruction operation and minimized memory round-trips, respectively. The Processing Elements (PE) of the design are based on Transport Triggered Architecture. The fine grained programmable parallel solution allows for fast and efficient computation of learnable low-level features (e.g. local binary descriptors and convolutions). Other operations, including Max-pooling have also been implemented. The programmable design achieves excellent energy efficiency for Local Binary Patterns computations. </div><div>Our results demonstrates that the inherent properties of chip processor and vision applications allow voltage and clock frequency aggressively without having to compromise performance. </div>

A Photo Identification Framework to Prevent Copyright Infringement with Manipulations

In recent years, copyright infringement has been one of the most serious problems that hamper the development of the culture and arts industry. Due to the limitations of existing image search services, these infringements have not been properly identified and the number of infringements has been increasing continuously. To uncover these infringements and handle big data extracted from copyright photos, we propose a photo copyright identification framework to accurately handle manipulations of stolen photos. From a collage of cropped photos, regions of interest (RoIs) are detected to reduce the influence of cropping and identify each photo by Image RoI Detection. Binary descriptors for quick database search are generated from the RoIs by Image Hashing robustly to geometric and color manipulations. The matching results of Image Hashing are verified by measuring their similarity using the proposed Image Verification to reduce false positives. Experimental results demonstrate that the proposed framework outperforms other image retrieval methods in identification accuracy and significantly reduces the false positive rate by 2.8%. This framework is expected to identify copyright infringements in practical situations and have a positive effect on the copyright market.

A Modified Binary Descriptor for Object Detection

The reliability of computer vision applications highly depends on the extraction of compact, fast, and accurate and robust feature description. This paper presents a better and modified binary descriptor based on ORB (oriented and rotated brief) with the SVM-RBF-RFE (support vector machine-radial basis function-recursive feature elimination) to achieve a better extraction and representation of local binary descriptors. This work presents the extensive comparison of the proposed modified descriptor with the state-of-the-art binary descriptors on various datasets. The results show that the proposed descriptor is highly distinctive and efficient as compared to the other state-of-the-art binary descriptors. The experiments were performed on the four benchmark datasets PASCAL, CALTECH, COIL, and OXFORD to demonstrate the robustness and effectiveness of the proposed descriptor. The robustness and effectiveness of the proposed descriptor is tested under the various transformations like scaling, rotation, noise, intensity variation.