PeTelCoDS—Personalized Television Content Delivery System: A Leap into the Set-Top Box Revolution
01 Jan 2016-pp 271-278
TL;DR: A method and system which assists the user to choose which Programs on which Channels to watch without any inputs from the Viewer about his “L likes” or “Dislikes” is proposed.
Abstract: At home, on the television, the sheer number of Channels and the vast number of Programs on each Channel has itself made the task of identifying the “appropriate” program to watch difficult for the common user. There is a need of a system to generate suggestions/recommendation to the common user about which Programs to watch and when. In this paper, we propose a method and system which assists the user to choose which Programs on which Channels to watch without any inputs from the Viewer about his “Likes” or “Dislikes”. It learns from the Viewer Implicitly over time and learns all the patterns that the Viewer exhibits over the course of Television watching.
Citations
More filters
TL;DR: In this article , the authors present a case study wherein they have focused on using the ELI5 XAI toolkit in conjunction with LIME (Local Interpretable Model-agnostic Explanations) and SHAP (SHapley Additive exPlanations) algorithmic frameworks in Python, for determining if a patient is diabetic or not, based on a randomized clinical trial dataset.
3 citations
TL;DR: In this paper , the authors proposed a novel paradigm of research in cricket analytics known as the timing index, based on a real life IoT-based implementation and case study, which is based on an amalgam of different factors such as bat speed, back lift angle, max. bat speed and impact bat speed.
2 citations
TL;DR: In this article , the authors aim to bank upon the state-of-the-art literature that has been written previously in this regard and derive though provoking research questions, along with few recommendations that can be viably used in developing frameworks and mechanisms for the synergic co-existence of these two challenging, yet interesting fields of AI and HCI.
2 citations
TL;DR: In this paper , a comparative analysis of machine learning algorithms for exoplanet detection is presented, which identifies the pros and cons of different algorithms for analysing certain forms of data.
TL;DR: In this paper , the authors used Data Analysis Expressions and Microsoft power bi to determine the player analytics on website that can be easily available for everyone to find out the best players.
Abstract: Cricket is a hugely popular sport, the popularity of the shorter forms of cricket, and particularly T20 cricket, is undoubtedly increasing apparently complicated the process of player selection. Visual Insights of players performance help in find out the best players. Data Analysis Expressions and Data Visualization has the potential to revolutionize the pruning process by creating the insights from huge datasets. The goal of the project is to create dashboards using Data Analysis Expressions and Microsoft power bi to determine the player analytics on website that can be easily available for everyone. The project is divided in to five dashboards. The first module focuses on selecting a team from total players. The second dashboards comprise of entire matches summary that exist in the dataset. The third dashboard provides the players who could have the potential to hold the winning possibilities over 90 percent. The fourth dashboard provides the analytics of every player. The final dashboard generates analytics based on the user requirements.
References
More filters
Book•
13 May 2011
TL;DR: The amount of data in the authors' world has been exploding, and analyzing large data sets will become a key basis of competition, underpinning new waves of productivity growth, innovation, and consumer surplus, according to research by MGI and McKinsey.
Abstract: The amount of data in our world has been exploding, and analyzing large data sets—so-called big data— will become a key basis of competition, underpinning new waves of productivity growth, innovation, and consumer surplus, according to research by MGI and McKinsey's Business Technology Office. Leaders in every sector will have to grapple with the implications of big data, not just a few data-oriented managers. The increasing volume and detail of information captured by enterprises, the rise of multimedia, social media, and the Internet of Things will fuel exponential growth in data for the foreseeable future.
4,700 citations
TL;DR: This article developed a process model to describe whole viewing sessions, and a typology of factors influencing the viewing process is presented, concluded by a research program, concluding by a review of the empirical evidence on viewing behavior and showing that viewing behavior can vary tremendously from the moment the TV set is turned on until it is turned off again.
Abstract: Television viewing often is a sequence of a multitude of activities that can vary tremendously from the moment the TV set is turned on until it is turned off again. Previous models of individual viewing behavior as well as empirical studies have focused on isolated aspects of viewing only, such as the frequency and duration of viewing or patterns of selecting a specific program. This paper draws attention to the complete process of TV viewing. We develop a process model to describe whole viewing sessions. Furthermore, a review of the empirical evidence on viewing behavior and a typology of factors influencing the viewing process are presented, concluded by a research program.
45 citations
01 Dec 2005
TL;DR: This work focuses on the tune factor and derive temporal patterns of TV watching, based on panel data, which provide new insights concerning Portuguese TV viewers' behavior.
Abstract: Audiometer systems provide enormous amounts of detailed TV watching data. Several relevant and interdependent factors may influence TV viewers' behavior. In this work we focus on the tune factor and derive temporal patterns of TV watching, based on panel data. Clustering base attributes are originated from 1440 binary minute-related attributes, capturing the TV watching status (watch/not watch). Since there are around 2500 panel viewers a data reduction procedure is first performed. K-means algorithm is used to obtain daily clusters of viewers. Weekly patterns are then derived which rely on daily patterns. The obtained solutions are tested for consistency and stability. Temporal TV watching patterns provide new insights concerning Portuguese TV viewers' behavior
12 citations
TL;DR: Reliability analysis indicates that the scale is internally consistent with co‐efficient alpha high across both pilot and main studies, and confirmatory factor analysis supports the two‐factor measurement model – “advertising triggers” and “RCD empowerment”.
Abstract: Purpose – The purpose of this paper is to describe the development of a scale (SITUZAP) to measure the situational factors that trigger channel switching, specifically within the television environment.Design/methodology/approach – The domain construct is defined and 14 potential scale items were drawn from the literature and qualitative research. The scale was purified during the pilot phase and three scale items removed. The scale was re‐tested during the main study via an independent sample, confirming the two‐dimensional nature of the scale.Findings – Reliability analysis indicates that the scale is internally consistent with co‐efficient alpha high across both pilot and main studies. Moreover, confirmatory factor analysis supports the two‐factor measurement model – “advertising triggers” and “RCD empowerment”. The test‐retest result (r=0.662) further provides evidence of stability within the scale. The scale has also been verified for content, criterion, discriminant, and nomological validity. All ot...
11 citations