Fine-grained Prediction Research Articles

Fine-grained prediction of urban population using mobile phone location data

ABSTRACTFine-grained prediction of urban population is of great practical significance in many domains that require temporally and spatially detailed population information. However, fine-grained population modeling has been challenging because the urban population is highly dynamic and its mobility pattern is complex in space and time. In this study, we propose a method to predict the population at a large spatiotemporal scale in a city. This method models the temporal dependency of population by estimating the future inflow population with the current inflow pattern and models the spatial correlation of population using an artificial neural network. With a large dataset of mobile phone locations, the model’s prediction error is low and only increases gradually as the temporal prediction granularity increases, and this model is adaptive to sudden changes in population caused by special events.

Exploiting Future Radio Resources With End-to-End Prediction by Deep Learning

Machine learning is a powerful tool to predict user behavior and harness the vast amount of data measured in cellular networks. Predictive resource allocation is a promising approach to take advantage of the prediction for the mobility and traffic load related user behavior. This paper strives to boost the performance of under-utilized networks by predicting behavior-related information from historical data with deep learning. We first propose a hierarchical and multi-timescale radio resource management scheme for non-realtime service that only needs coarse-grained future knowledge, by taking multi-input-multi-output orthogonal frequency multi-access as an example system and high throughput as an example performance metric. Such a scheme allows the decision of resource management to be made in a central processor and base stations in different timescales and allows the knowledge to be predicted with less training samples. Then, we design a deep neural network to learn the future knowledge required for making decision directly from different types of past data with different resolutions observable in cellular networks. Simulation results show that the proposed scheme with the end-to-end knowledge prediction performs closely to the relevant optimal solution with perfect and fine-grained prediction, and provides dramatic gain over non-predictive counterpart in supporting high request arrival rate for the non-realtime service.

Time series based urban air quality predication

Urban air pollution post a great threat to human health, and has been a major concern of many metropolises in developing countries. Lately, a few air quality monitoring stations have been established to inform public the real-time air quality indices based on fine particle matters, e.g. $PM_{2.5}$, in countries suffering from air pollutions. Air quality, unfortunately, is fairly difficult to manage due to multiple complex human activities from driving to smelting. We observe that human activities' hidden regular pattern offers possibility in predication, and this motivates us to infer urban air condition from the perspective of time series. In this paper, we focus on $PM_{2.5}$ based urban air quality, and introduce two kinds of time-series methods for real-time and fine-grained air quality prediction, harnessing historical air quality data reported by existing monitoring stations. The methods are evaluated based in the real-life $PM_{2.5}$ concentration data in the year of 2013 (January - December) in Wuhan, China.

NextMe: Localization Using Cellular Traces in Internet of Things

The Internet of Things (IoT) opens up tremendous opportunities to location-based industrial applications that leverage both Internet-resident resources and phones’ processing power and sensors to provide location information. Location-based service is one of the vital applications in commercial, economic, and public domains. In this paper, we propose a novel localization scheme called NextMe , which is based on cellular phone traces. We find that the mobile call patterns are strongly correlated with the co-locate patterns. We extract such correlation as social interplay from cellular calls, and use it for location prediction from temporal and spatial perspectives. NextMe consists of data preprocessing, call pattern recognition, and a hybrid predictor. To design the call pattern recognition module, we introduce the notions of critical calls and corresponding patterns. In addition, NextMe does not require that the cell tower addresses should be bounded with concrete coordinates, e.g., global positioning system (GPS) coordinates . We validate NextMe across MIT Reality Mining Dataset, involving 500 000 h of continuous behavior information and 112 508 cellular calls. Experimental results show that NextMe achieves fine-grained prediction accuracy at cell tower level in the forthcoming 1–6 h with 12% accuracy enhancement averagely from cellular calls.

Rumors of the death of consumer genomics are greatly exaggerated

Rumors of the death of consumer genomics are greatly exaggerated

Improving dynamic prediction accuracy through multi-level phase analysis

Phase analysis, which classifies the set of execution intervals with similar execution behavior and resource requirements, has been widely used in a variety of dynamic systems, including dynamic cache reconfiguration, prefetching and race detection. While phase granularity has been a major factor to the accuracy of phase prediction, it has not been well investigated yet and most dynamic systems usually adopt a fine-grained prediction scheme. However, such a scheme can only take account of recent local phase information and could be frequently interfered by temporary noises due to instant phase changes, which might notably limit the prediction accuracy. In this paper, we make the first investigation on the potential of multi-level phase analysis (MLPA), where different granularity phase analysis are combined together to improve the overall accuracy. The key observation is that a coarse-grained interval, which usually consists of stably-distributed fine-grained intervals, can be accurately identified based on the fine-grained intervals at the beginning of its execution. Based on the observation, we design and implement a MLPA scheme. In such a scheme, a coarse-grained phase is first identified based on the fine-grained intervals at the beginning of its execution. The following fine-grained phases in it are then predicted based on the sequence of fine-grained phases in the coarse-grained phase. Experimental results show such a scheme can notably improve the prediction accuracy. Using Markov fine-grained phase predictor as the baseline, MLPA can improve prediction accuracy by 20%, 39% and 29% for next phase, phase change and phase length prediction for SPEC2000 accordingly, yet incur only about 2% time overhead and 40% space overhead (about 360 bytes in total). To demonstrate the effectiveness of MLPA, we apply it to a dynamic cache reconfiguration system which dynamically adjusts the cache size to reduce the power consumption and access time of data cache. Experimental results show that MLPA can further reduce the average cache size by 15% compared to the fine-grained scheme.

Just a Little Bit Longer: Viewing Time of Erotic Material from a Self-Control Perspective

Summary For many individuals, watching erotic material constitutes a self-control conflict in which reflective tendencies compete with impulsive urges for the control of behavior. Boundary conditions such as the ability to control attention determine which influence will prevail over the other. Here, we tested this framework in the context of viewing erotic videos. Reflective tendencies, as indicated by self-reported attitudes, predicted viewing time of erotic videos for individuals high, but not low, in attention control. By contrast, impulsive tendencies, as indicated by automatic associations toward sex, predicted viewing time for individuals low, but not high, in attention control. This effect was particularly pronounced for single individuals. The adoption of a self-control framework to research on viewing erotic material has several advantages, including a better understanding of the psychological processes involved in watching erotic material, an illustration of these processes' interactive dynamic, and a more fine-grained prediction of viewing time behavior. Copyright © 2012 John Wiley & Sons, Ltd.

Fine-Grained Parallel RNA Secondary Structure Prediction Using SCFGs on FPGA

In the field of RNA secondary structure prediction,CYK(Coche-Younger-Kasami) algorithm is one of the most popular methods using SCFG(stochastic context-free grammars) model.Accelerating SCFGs for large models and large RNA database searches becomes a challenge task in computational bioinformatics because of the O(L3) computational demands that are required.General purpose computers including parallel SMP multiprocessors or cluster systems exhibit low parallel efficiency.Furthermore,large scaled parallel computers are too expensive to be used easily for many research institutes.FPGA chips provide a new approach to accelerate CYK algorithm by exploiting fine-grained custom design.CYK algorithm shows complicated data dependence,in which the dependence distance is variable,and the dependence direction is also across two dimensions.This paper proposes a systolic-like array structure including one master PE(Processing Element) and multiple slave PEs for fine-grained hardware implementation on FPGA.By columns and assign,tasks are partitioned to PEs for load balance.Data reuse schemes reduce the need to load energy matrices from external memory.The experimental results show a factor of more than 14 speedup over the Infernal-1.0 software for 959-residue RNA sequence and a CM model with 3145 states running on a PC platform with Intel Dual-Core 2.5GHz CPU.The computational power of the accelerator is comparable to a PC cluster consisting of 20 Intel-Xeon CPUs for RNA secondary structure prediction using SCFGs,but the hardware cost and power consumption is only about 20% and 10% that of the latter respectively.

LOCUSTRA: Accurate Prediction of Local Protein Structure Using a Two-Layer Support Vector Machine Approach

Constraint generation for 3d structure prediction and structure-based database searches benefit from fine-grained prediction of local structure. In this work, we present LOCUSTRA, a novel scheme for the multiclass prediction of local structure that uses two layers of support vector machines (SVM). Using a 16-letter structural alphabet from de Brevern et al. (Proteins: Struct., Funct., Bioinf. 2000, 41, 271-287), we assess its prediction ability for an independent test set of 222 proteins and compare our method to three-class secondary structure prediction and direct prediction of dihedral angles. The prediction accuracy is Q16=61.0% for the 16 classes of the structural alphabet and Q3=79.2% for a simple mapping to the three secondary classes helix, sheet, and coil. We achieve a mean phi(psi) error of 24.74 degrees (38.35 degrees) and a median RMSDA (root-mean-square deviation of the (dihedral) angles) per protein chain of 52.1 degrees. These results compare favorably with related approaches. The LOCUSTRA web server is freely available to researchers at http://www.fz-juelich.de/nic/cbb/service/service.php.

Nonequilibrium free energy, coarse-graining, and the Liouville equation.

The Helmholtz free energy is computed for an ensemble of initial conditions for a one­ dimensional particle falling down a staircase potential, while in contact with a thermal reservoir. Initial conditions are chosen from the equilibrium canonical ensemble, with the gravitational ficld applied either as a step function (steady field) or a 6 function (pulsed perturbation). The first case lcads to a fractal steady-state distribution, while the second case leads to relaxation of a perturbed distribution back toward equilibrium. Coarse-graining is applied to the computation of the non­ equilibrium entropy, with finer resolution in phase space accompanied by an increase in the number of trajectories. The limiting fine-grained (continuum) prediction of the Liouville equation is shown to be consistent with the numerical simulations for the steady state, but with incredibly slow (loga­ rithmic) divergence appropriate to a lower-dimensional fractal distribution. On the other hand, simulations of the relaxation process show little or no sign of converging to the prediction obtained from the Liouville equation. Irreversible phase-space mixing of trajectories appears to be a neces­ sary modification to the Liouville equation, if one wants to make predictions of numerical simula­ tions in nonequilibrium statistical mechanics.