Qualcomm

About: Qualcomm is a company organization based out in Farnborough, United Kingdom. It is known for research contribution in the topics: Wireless & Signal. The organization has 19408 authors who have published 38405 publications receiving 804693 citations. The organization is also known as: Qualcomm Incorporated & Qualcomm, Inc..

Visualizing Deep Neural Network Decisions: Prediction Difference Analysis

Abstract: This article presents the prediction difference analysis method for visualizing the response of a deep neural network to a specific input. When classifying images, the method highlights areas in a given input image that provide evidence for or against a certain class. It overcomes several shortcoming of previous methods and provides great additional insight into the decision making process of classifiers. Making neural network decisions interpretable through visualization is important both to improve models and to accelerate the adoption of black-box classifiers in application areas such as medicine. We illustrate the method in experiments on natural images (ImageNet data), as well as medical images (MRI brain scans).

LTE-Advanced: Heterogeneous networks

Abstract: Long-Term Evolution (LTE) allows operators to use new and wider spectrum and complements 3G networks with higher data rates, lower latency and a flat IP-based architecture. To further improve broadband user experience in a ubiquitous and cost effective manner, 3GPP has been working on various aspects in the framework of LTE Advanced. Since radio link performance is approaching theoretical limits with 3G enhancements and LTE, the next performance leap in wireless networks will come from the network topology. LTE Advanced is about improving spectral efficiency per unit area. Using a mix of macro, pico, femto and relay base-stations, heterogeneous networks enable flexible and low-cost deployments and provide a uniform broadband experience to users anywhere in the network. This paper discusses the need for an alternative deployment model or topology using heterogeneous networks. To enhance the performance of these networks, advanced techniques are described which are needed to manage and control interference and deliver the full benefits of such networks. Range extension allows more user terminals to benefit directly from low-power base-stations such as picos, femtos, and relays. Adaptive inter-cell interference coordination provides smart resource allocation amongst interfering cells and improves inter-cell fairness in a heterogeneous network. In addition, the performance gains with heterogeneous networks using an example macro/pico network are shown.

A holistic view on hyper-dense heterogeneous and small cell networks

Abstract: The wireless industry has been experiencing an explosion of data traffic usage in recent years and is now facing an even bigger challenge, an astounding 1000-fold data traffic increase in a decade. The required traffic increase is in bits per second per square kilometer, which is equivalent to bits per second per Hertz per cell × Hertz × cell per square kilometer. The innovations through higher utilization of the spectrum (bits per second per Hertz per cell) and utilization of more bandwidth (Hertz) are quite limited: spectral efficiency of a point-to-point link is very close to the theoretical limits, and utilization of more bandwidth is a very costly solution in general. Hyper-dense deployment of heterogeneous and small cell networks (HetSNets) that increase cells per square kilometer by deploying more cells in a given area is a very promising technique as it would provide a huge capacity gain by bringing small base stations closer to mobile devices. This article presents a holistic view on hyperdense HetSNets, which include fundamental preference in future wireless systems, and technical challenges and recent technological breakthroughs made in such networks. Advancements in modeling and analysis tools for hyper-dense HetSNets are also introduced with some additional interference mitigation and higher spectrum utilization techniques. This article ends with a promising view on the hyper-dense HetSNets to meet the upcoming 1000× data challenge.

Cdma microcellular telephone system and distributed antenna system therefor

Abstract: A code division multiple access (CDMA) communication system in which cellular techniques are utilized in a wireless Private Branch Exchange (PBX) environment. A microcellular arrangement is defined in which a base station (10) communicates user information signals using CDMA communication signals with subscriber terminals. A distributed antenna system (26) is utilized in the system to provide multipath signals which facilitate signal diversity for enhanced system performance.

Cell Association and Interference Coordination in Heterogeneous LTE-A Cellular Networks

Abstract: Embedding pico/femto base-stations and relay nodes in a macro-cellular network is a promising method for achieving substantial gains in coverage and capacity compared to macro-only networks. These new types of base-stations can operate on the same wireless channel as the macro-cellular network, providing higher spatial reuse via cell splitting. However, these base-stations are deployed in an unplanned manner, can have very different transmit powers, and may not have traffic aggregation among many users. This could potentially result in much higher interference magnitude and variability. Hence, such deployments require the use of innovative cell association and inter-cell interference coordination techniques in order to realize the promised capacity and coverage gains. In this paper, we describe new paradigms for design and operation of such heterogeneous cellular networks. Specifically, we focus on cell splitting, range expansion, semi-static resource negotiation on third-party backhaul connections, and fast dynamic interference management for QoS via over-the-air signaling. Notably, our methodologies and algorithms are simple, lightweight, and incur extremely low overhead. Numerical studies show that they provide large gains over currently used methods for cellular networks.