scholarly journals Novel Recommendation System for Tourist Spots Based on Hierarchical Sampling Statistics and SVD++

2019 ◽  
Vol 2019 ◽  
pp. 1-15 ◽  
Author(s):  
Guangli Li ◽  
Jin Hua ◽  
Tian Yuan ◽  
Jinpeng Wu ◽  
Ziliang Jiang ◽  
...  
Keyword(s):  
Recommendation System ◽  
Clustering Algorithms ◽  
Research Work ◽  
Economic Benefits ◽  
User Preference ◽  
The Novel ◽  
The Mean ◽  
Hierarchical Sampling ◽  
Sampling Statistics ◽  
User Ratings

Recommendation system for tourist spots has very high potential value including social and economic benefits. The traditional clustering algorithms were usually used to build a recommendation system. However, clustering algorithms have the risk on falling into local minimums, which may decrease the final recommendation performance heavily. Few works focused their research on tourist spots recommendation and few recommendation systems consider the population attributes information for fitting the user implicit preference. To address the problem, we focused our research work on designing a novel recommendation system for tourist spots. First a new dataset named “Smart Travel” is created for the following experiments. Then hierarchical sampling statistics (HSS) model is used to acquire the user preference for different population attributes. A new recommendation list named LA is generated in turn by fitting the excavated the user preference. More importantly, SVD++ algorithm rather than those traditional clustering algorithms is used to predict the user ratings. And a new recommendation list named LB is generated in turn on the basis of rating predictions. Finally, the two lists LA and LB are fused together to boost the final recommendation performance. Experimental results demonstrate that the mean precision, mean recall, and mean F1 values of the proposed recommendation system improve about 7.5%, 6.2%, and 6.5%, respectively, compared to the best competitor. The novel recommendation system is especially better at recommending a group of tourist spots, which means it has higher practical value.

scholarly journals User Preference Based Mobile Application Recommendation

2019 ◽  
Vol 9 (1S) ◽  
pp. 162-165
Keyword(s):  
User Interface ◽  
User Experience ◽  
Mobile Application ◽  
Large Scale ◽  
Recommendation System ◽  
Research Work ◽  
User Preference ◽  
Memory Requirement ◽  
Traditional Methods

Application recommendation is one of the larger scales and sophisticated recommendation system currently exists. In this research work, we devised an approach which will deal with suggesting application based on users click on a particular application. The approach described in this paper is efficient and with less memory requirement than other traditional methods. This paper also includes the details about the implementation of the approach with User Interface. The paper also provides the details that how it can be implemented on a large scale. The approach is implemented in a mobile-based platform with react native support. The main objective of this paper is to describe an approach, which will be efficient and completely based on users data. The main objective of an Application Recommendation to recommend applications to increase user experience and recommend application based on their needs. Companies like Google, Apple, Samsung etc. are implementing it also.

scholarly journals Serendipity Identification Using Distance-Based Approach

2021 ◽  
Vol 5 (1) ◽  
pp. 9
Author(s):  
Widhi Hartanto ◽  
Noor Akhmad Setiawan ◽  
Teguh Bharata Adji
Keyword(s):  
Collaborative Filtering ◽  
Recommendation System ◽  
Average Distance ◽  
Clustering Algorithms ◽  
Ground Truth ◽  
User Preference ◽  
Common Definition ◽  
Definition Of

The recommendation system is a method for helping consumers to find products that fit their preferences. However, recommendations that are merely based on user preference are no longer satisfactory. Consumers expect recommendations that are novel, unexpected, and relevant. It requires the development of a serendipity recommendation system that matches the serendipity data character. However, there are still debates among researchers about the available common definition of serendipity. Therefore, our study proposes a work to identify serendipity data's character by directly using serendipity data ground truth from the famous Movielens dataset. The serendipity data identification is based on a distance-based approach using collaborative filtering and k-means clustering algorithms. Collaborative filtering is used to calculate the similarity value between data, while k-means is used to cluster the collaborative filtering data. The resulting clusters are used to determine the position of the serendipity cluster. The result of this study shows that the average distance between the recommended movie cluster and the serendipity movie cluster is 0.85 units, which is neither the closest cluster nor the farthest cluster from the recommended movie cluster.

STRUKTUR NARASI NOVEL CA BAU KAN, KARYA REMY SYLADO ANALISIS SEMIOTIK

2017 ◽  
Vol 4 (1) ◽  
pp. 70
Author(s):  
Sri Sabakti
Keyword(s):  
Narrative Structure ◽  
Literary Analysis ◽  
The Novel ◽  
Basic Scheme ◽  
Library Research ◽  
The Mean

This research is aimed to expose the narrative structure of the novel Ca Bau Kan by using semiotical theory. The source of the data is the novel Ca Bau kan written by Remy Silado and published by KPG, eight edition, 2004. The data is collected by doing the library research. The teory applied in this research is the emiotical theory, especially the literary analysis of Subur Laksono Wardoyo that the analysis of the text of prose can be applied by using three fases; the analysis of the basic scheme narrative, the analysis of mean signifier, and the analysis of syntagmatics and pragmatics. The result of this research showed that the narrative structure in the novel CBK that (1) the life of Tinung before being a ca bau kan, (2) the life of Tinung as a ca bau kan, and (3) the life of Tinung after not being a ca bau kan anymore. Based on the narrative structure, it was found that “ Love is only one. No measurement is needed” is the mean signifier and able to be clarified by the analysis of syntagmatics-paradigmatics based on the biner oposition of weak x strong.AbstrakPenelitian ini bertujuan mengungkapkan stuktur narasi dalam novel Ca Bau Kan (CBK) dengan menggunakan teori semiotika. Penelitian ini menggunakan sumber data novel CBK karya Remy Silado yang diterbitkan oleh KPG, cetakan kedelapan tahun 2004. Pengumpulan data dilaksanakan dengan teknik kepustakaan. Teori yang digunakan dalam penelitian ini adalah teori semiotika, khususnya analisis sastra menurut Subur Laksono Wardoyo bahwa analisis teks prosa dapat dilakukan melalui tiga tahap, yaitu: analisis skema naratif dasar, analisis signifier utama, dan analisis sintagmatik-paradigmatik. Hasil penelitian menggambarkan bahwa struktur narasi pada novel CBK adalah sebagai berikut: 1) kehidupan Tinung sebelum menjadi ca bau kan, 2) kehidupan Tinung sebagai ca bau kan, dan 3) kehidupan Tinung setelah tidak menjadi ca bau kan. Berdasarkan struktur narasi, maka didapatkan bahwa “Cinta cuma satu, kagak perlu takaran” merupakan penanda utama dan dapat diperjelas melalui analisis sintagmatik-paradigmatik yang didasarkan atas sebuah oposisi biner lemah x kuat.

Identification of Agricultural Management Zones Through Clustering Algorithms with Thermal and Multispectral Satellite Imagery

2017 ◽  
Vol 25 (Suppl. 1) ◽  
pp. 121-140
Author(s):  
R. B. Arango ◽  
A. M. Campos ◽  
E. F. Combarro ◽  
E. R. Canas ◽  
I. Díaz
Keyword(s):  
Satellite Imagery ◽  
Precision Agriculture ◽  
Clustering Algorithms ◽  
Economic Benefits ◽  
Agricultural Management ◽  
Landsat 8 ◽  
Special Equipment ◽  
Management Zones ◽  
Ndvi Index ◽  
Cost Efficient

Precision Agriculture entails the appropriate management of the inherent variability of soil and crops, resulting in an increase of economic benefits and a reduction of environmental impact. However, site-specific treatments require maps of the soil variability to identify areas of land that share similar properties. In order to produce these maps, we propose a cost-efficient method that combines clustering algorithms with publicly available satellite imagery. The method does not require exploring the parcels with any special equipment or taking samples of the soil for laboratory analysis. The proposed method was tested in a case study for three vineyard parcels with topographical dissimilarities. The study compares different spectral and thermal bands from the Landsat 8 satellite as well as vegetation and moisture indices to determine which one produces the best clustering. The experimental results seem promising for identification of agricultural management zones. The findings suggest that thermal bands produce better clustering than those based on the NDVI index.

scholarly journals Novel Radiographic Indexes for Elbow Stability Assessment: Part B—Preliminary Clinical Study

2021 ◽  
Author(s):  
Francesco Luceri ◽  
Davide Cucchi ◽  
Enrico Rosagrata ◽  
Carlo Eugenio Zaolino ◽  
Alessandra Menon ◽  
...  
Keyword(s):  
Case Series ◽  
Radiographic Evaluation ◽  
Healthy Population ◽  
X Rays ◽  
The Novel ◽  
Level Of Evidence ◽  
Orthopaedic Surgeons ◽  
Joint Congruency ◽  
Radiological Parameters ◽  
The Mean

Abstract Introduction The coronoid process plays a key-role in preserving elbow stability. Currently, there are no radiographic indexes conceived to assess the intrinsic elbow stability and the joint congruency. The aim of this study is to present new radiological parameters, which will help assess the intrinsic stability of the ulnohumeral joint and to define normal values of these indexes in a normal, healthy population. Methods Four independent observers (two orthopaedic surgeons and two radiologists) selected lateral view X-rays of subjects with no history of upper limb disease or surgery. The following radiographic indexes were defined: trochlear depth index (TDI); anterior coverage index (ACI); posterior coverage index (PCI); olecranon–coronoid angle (OCA); radiographic coverage angle (RCA). Inter-observer and intra-observer reproducibility were assessed for each index. Results 126 subjects were included. Standardized lateral elbow radiographs (62 left and 64 right elbows) were obtained and analysed. The mean TDI was 0.46 ± 0.06 (0.3–1.6), the mean ACI was 2.0 ± 0.2 (1.6–3.1) and the mean PCI was 1.3 ± 0.1 (1.0–1.9). The mean RCA was 179.6 ± 8.3° (normalized RCA: 49.9 ± 2.3%) and the mean OCA was 24.6 ± 3.7°. The indexes had a high-grade of inter-observer and intra-observer reliability for each of the four observers. Significantly higher values were found for males for TDI, ACI, PCI and RCA. Conclusion The novel radiological parameters described are simple, reliable and easily reproducible. These features make them a promising tool for radiographic evaluation both for orthopaedic surgeons and for radiologists in the emergency department setting or during outpatient services. Level of evidence Basic Science Study (Case Series). Clinical relevance The novel radiological parameters described are reliable, easily reproducible and become handy for orthopaedic surgeons as well as radiologists in daily clinical practice.

Effects of Personalized and Aggregate Top-N Recommendation Lists on User Preference Ratings

2021 ◽  
Vol 39 (2) ◽  
pp. 1-38
Author(s):  
Gediminas Adomavicius ◽  
Jesse Bockstedt ◽  
Shawn Curley ◽  
Jingjing Zhang
Keyword(s):  
Recommender Systems ◽  
Laboratory Experiments ◽  
User Preference ◽  
Online Retailer ◽  
Product Recommendations ◽  
Preference Ratings ◽  
User Ratings

Prior research has shown a robust effect of personalized product recommendations on user preference judgments for items. Specifically, the display of system-predicted preference ratings as item recommendations has been shown in multiple studies to bias users’ preference ratings after item consumption in the direction of the predicted rating. Top-N lists represent another common approach for presenting item recommendations in recommender systems. Through three controlled laboratory experiments, we show that top-N lists do not induce a discernible bias in user preference judgments. This result is robust, holding for both lists of personalized item recommendations and lists of items that are top-rated based on averages of aggregate user ratings. Adding numerical ratings to the list items does generate a bias, consistent with earlier studies. Thus, in contexts where preference biases are of concern to an online retailer or platform, top-N lists, without numerical predicted ratings, would be a promising format for displaying item recommendations.

Utilizing an Adaptive Controller (Azadi Controller) for Trajectory Planning of PUMA 560 Robot

2011 ◽  
Vol 403-408 ◽  
pp. 4880-4887
Author(s):  
Sassan Azadi
Keyword(s):  
Steady State ◽  
Trajectory Planning ◽  
Positive Feedback ◽  
Fuzzy Controller ◽  
Research Work ◽  
Adaptive Controller ◽  
The Novel ◽  
Transient Responses ◽  
Simulation Results ◽  
Good Substitute

This research work was devoted to present a novel adaptive controller which uses two negative stable feedbacks with a positive unstable positive feedback. The positive feedback causes the plant to do the break, therefore reaching the desired trajectory with tiny overshoots. However, the two other negative feedback gains controls the plant in two other sides of positive feedback, making the system to be stable, and controlling the steady-state, and transient responses. This controller was performed for PUMA-560 trajectory planning, and a comparison was made with a fuzzy controller. The fuzzy controller parameters were obtained according to the PSO technique. The simulation results shows that the novel adaptive controller, having just three parameters, can perform well, and can be a good substitute for many other controllers for complex systems such as robotic path planning.

Predicting Text Legibility over Textured Digital Backgrounds for a Monocular Optical See-Through Display

2017 ◽  
Vol 26 (1) ◽  
pp. 1-15 ◽  
Author(s):  
Vito Modesto Manghisi ◽  
Michele Gattullo ◽  
Michele Fiorentino ◽  
Antonio Emmanuele Uva ◽  
Francescomaria Marino ◽  
...  
Keyword(s):  
Image Analysis ◽  
Augmented Reality ◽  
The Novel ◽  
User Test ◽  
User Ratings ◽  
Background Image ◽  
Text Legibility

Text legibility in augmented reality with optical see-through displays can be challenging due to the interaction with the texture on the background. Literature presents several approaches to predict legibility of text superimposed over a specific image, but their validation with an AR display and with images taken from the industrial domain is scarce. In this work, we propose novel indices extracted from the background images, displayed on an LCD screen, and we compare them with those proposed in literature designing a specific user test. We collected the legibility user ratings by displaying white text over 13 industrial background images to 19 subjects using an optical see-through head-worn display. We found that most of the proposed indices have a significant correlation with user ratings. The main result of this work is that some of the novel indices proposed had a better correlation than those used before in the literature to predict legibility. Our results prove that industrial AR developers can effectively predict text legibility by simply running image analysis on the background image.

Sign in / Sign up

Export Citation Format

Share Document