32:, uncertainty or data veracity is one of the defining characteristics of data. Data is constantly growing in volume, variety, velocity and uncertainty (1/veracity). Uncertain data is found in abundance today on the web, in sensor networks, within enterprises both in their structured and unstructured sources. For example, there may be uncertainty regarding the address of a customer in an enterprise dataset, or the temperature readings captured by a sensor due to aging of the sensor. In 2012 IBM called out
133:
are subject to a joint probability distribution. This covers the case of correlated uncertainty, but also includes the case where there is a probability of a tuple not belonging in the relevant relation, which is indicated by all the probabilities not summing to one. For example, assume we have the
40:
report that presents a comprehensive analysis looking three to ten years into the future seeking to identify significant, disruptive technologies that will change the world. In order to make confident business decisions based on real-world data, analyses must necessarily account for many different
118:-coordinates stored, the probability of different values may depend on the distance from the recorded coordinates. As distance depends on both coordinates, it may be appropriate to use a joint distribution for these coordinates, as they are not
41:
kinds of uncertainty present in very large amounts of data. Analyses based on uncertain data will have an effect on the quality of subsequent decisions, so the degree and types of inaccuracies in this uncertain data cannot be ignored.
99:. For example, if readings are taken of temperature and wind speed, each would be described by its own probability distribution, as knowing the reading for one measurement would not provide any information about the other.
221:
Proceedings of the 1st
Workshop on Management and mining Of Uncertain Data in conjunction with the 25th International Conference on Data Engineering, 2009
210:
Habich Volk; Clemens Utzny; Ralf
Dittmann; Wolfgang Lehner. "Error-Aware Density-Based Clustering of Imprecise Measurement Values".
107:
247:
237:
77:
219:
Volk
Rosentahl; Martin Hahmann; Dirk Habich; Wolfgang Lehner. "Clustering Uncertain Data With Possible Worlds".
119:
96:
135:
242:
167:
81:
65:
57:
84:. There are three main ways to do represent uncertainty as probability distributions in such a
53:
25:
190:
17:
52:
is found in abundance on social media, web and within enterprises where the structured and
45:
212:
Seventh IEEE International
Conference on Data Mining Workshops, 2007. ICDM Workshops 2007
85:
231:
60:
may only be an approximation of the actual process. When representing such data in a
28:
that makes it deviate from the correct, intended or original values. In the age of
49:
110:. For example, if readings are taken of the position of an object, and the
61:
29:
95:, each uncertain attribute in a tuple is subject to its own independent
130:
150:
Then, the tuple has 10% chance of not existing in the database.
56:
may be old, outdated, or plain incorrect; in modeling where the
140:
76:One way to represent uncertain data is through
8:
106:, multiple attributes may be described by a
191:"ORION: Managing Uncertain (Sensor) Data"
184:
182:
180:
159:
44:Uncertain data is found in the area of
72:Example data model for uncertain data
7:
14:
34:managing uncertain data at scale
80:. Let us take the example of a
108:joint probability distribution
1:
68:model needs to be selected.
264:
129:, all the attributes of a
168:Global Technology Outlook
78:probability distributions
38:global technology outlook
97:probability distribution
134:following tuple from a
136:probabilistic database
104:correlated uncertainty
24:is data that contains
93:attribute uncertainty
144:(a, 0.4) | (b, 0.5)
82:relational database
248:Statistical theory
189:Prabhakar, Sunil.
66:uncertain database
58:mathematical model
148:
147:
127:tuple uncertainty
64:, an appropriate
54:unstructured data
255:
238:Machine learning
224:
215:
202:
201:
198:Computer Science
195:
186:
175:
174:
172:
164:
141:
18:computer science
263:
262:
258:
257:
256:
254:
253:
252:
228:
227:
218:
209:
206:
205:
193:
188:
187:
178:
173:(Report). 2012.
170:
166:
165:
161:
156:
74:
46:sensor networks
12:
11:
5:
261:
259:
251:
250:
245:
240:
230:
229:
226:
225:
216:
204:
203:
176:
158:
157:
155:
152:
146:
145:
86:database model
73:
70:
22:uncertain data
13:
10:
9:
6:
4:
3:
2:
260:
249:
246:
244:
241:
239:
236:
235:
233:
222:
217:
213:
208:
207:
199:
192:
185:
183:
181:
177:
169:
163:
160:
153:
151:
143:
142:
139:
137:
132:
128:
123:
121:
117:
113:
109:
105:
100:
98:
94:
89:
87:
83:
79:
71:
69:
67:
63:
59:
55:
51:
48:; text where
47:
42:
39:
35:
31:
27:
23:
19:
220:
211:
197:
162:
149:
126:
124:
115:
111:
103:
101:
92:
90:
75:
43:
37:
33:
21:
15:
243:Data mining
120:independent
232:Categories
154:References
50:noisy text
62:database
30:big data
223:. IEEE.
214:. IEEE.
36:in its
114:- and
194:(PDF)
171:(PDF)
131:tuple
26:noise
125:In
102:In
91:In
16:In
234::
196:.
179:^
138::
122:.
88:.
20:,
200:.
116:y
112:x
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.