-
21.发明授权Automatic subspace clustering of high dimensional data for data mining applications 失效用于数据挖掘应用的高维数据的自动子空间聚类
公开(公告)号：US6003029A
公开(公告)日：1999-12-14
申请号：US916347
申请日：1997-08-22
CPC分类号： G06F17/30598 , G06F17/30607 , G06K9/6218 , Y10S707/99931 , Y10S707/99936 , Y10S707/99937
摘要： A method for finding clusters of units in high-dimensional data having the steps of determining dense units in selected subspaces within a data space of the high-dimensional data, determining each cluster of dense units that are connected to other dense units in the selected subspaces within the data space, determining maximal regions covering each cluster of connected dense units, determining a minimal cover for each cluster of connected dense units, and identifying the minimal cover for each cluster of connected dense units.
摘要翻译： 一种用于在高维数据中查找单元簇的方法，该方法具有以下步骤：在高维数据的数据空间内确定所选子空间中的密集单元，确定连接到所选子空间中的其他密集单元的密集单元簇 在数据空间内，确定覆盖每个连通的致密单元簇的最大区域，确定每个连接的密集单元簇的最小覆盖，以及识别每个连接密集单元簇的最小覆盖。
-
公开(公告)号：US5966967A
公开(公告)日：1999-10-19
申请号：US012074
申请日：1998-01-22
CPC分类号： F25J3/04066 , F25J3/04054 , F25J3/0406 , F25J3/0409 , F25J3/04284 , F25J3/04303 , F25J3/04309 , F25J3/04351 , F25J3/04381 , F25J3/04393 , F25J3/04412 , F25J3/04418 , F25J3/04878 , F25J2200/20 , F25J2200/34 , F25J2200/54 , F25J2215/52 , F25J2235/42 , F25J2245/42 , F25J2250/20 , F25J2250/42 , F25J2250/52
摘要： The present invention relates to a process for the cryogenic distillation of air in a distillation column system that contains at least one distillation column wherein the boil-up at the bottom of the distillation column producing the oxygen product is provided by condensing a stream whose nitrogen concentration is equal to or greater than that in the feed air stream. The process of the present invention comprises the steps of: (a) generating work energy which is at least ten percent (10%) of the overall refrigeration demand of the distillation column system; (b) work expanding a process stream to produce additional work energy such that the total work generated along with step (a) exceeds the total refrigeration demand of the cryogenic plant; and (c) using the work which is generated in excess of the refrigeration need of the distillation column system to cold compress a process stream at a temperature lower than the ambient temperature.
摘要翻译： 本发明涉及一种蒸馏塔系统中空气的低温蒸馏方法，该蒸馏塔系统含有至少一个蒸馏塔，其中产生氧产物的蒸馏塔底部的沸腾是通过将氮浓度 等于或大于进料空气流中的流量。 本发明的方法包括以下步骤：（a）产生至少10％（10％）蒸馏塔系统制冷需求的工作能量; （b）扩大工艺流程以产生额外的工作能量，使得与步骤（a）一起产生的总工作量超过了低温设备的总制冷需求; 和（c）使用超过蒸馏塔系统的制冷需要产生的工作在低于环境温度的温度下冷却工艺流。
-
23.发明授权
公开(公告)号：US5930789A
公开(公告)日：1999-07-27
申请号：US920031
申请日：1997-08-28
CPC分类号： G06F17/30548 , G06F17/30551 , G06F2216/03 , Y10S707/99931 , Y10S707/99933 , Y10S707/99935 , Y10S707/99936
摘要： A system and method for discovering similar time sequences in a database of time sequences includes a computer-implemented program which first breaks each sequence into small windows. The windows from the first sequence are compared to selected windows from the second sequence to determine which windows are similar. Pairs of similar windows are then stitched together when certain stitching constraints are met to establish pairs of similar subsequences. Likewise, pairs of similar subsequences are stitched together, and the lengths of the stitched subsequences are then compared to the overall length of the time sequences to determine whether the time sequences meet a similarity criteria.
摘要翻译： 用于在时间序列数据库中发现类似时间序列的系统和方法包括计算机实现的程序，其首先将每个序列分解成小窗口。 将来自第一序列的窗口与来自第二序列的所选窗口进行比较，以确定哪些窗口相似。 然后，当满足某些缝合约束以建立相似的子序列对时，将对的相似的窗口缝合在一起。 类似地，将相似的子序列对拼接在一起，然后将缝合子序列的长度与时间序列的总长度进行比较，以确定时间序列是否满足相似性标准。
-
24.发明授权Method and system for performing proximity joins on high-dimensional data points in parallel 失效用于在高维数据点上并行执行邻近连接的方法和系统
公开(公告)号：US5884320A
公开(公告)日：1999-03-16
申请号：US920331
申请日：1997-08-20
IPC分类号： G06F17/30
CPC分类号： G06F17/30592 , G06F17/30445 , G06F17/30498 , Y10S707/99932 , Y10S707/99945 , Y10S707/99948
摘要： A method and system for performing spatial proximity joins on high-dimensional points representing data objects of a database in parallel in a multiprocessor system. The method comprises the steps of: partitioning the data points among the processors; creating index structures for the data points of the processors in parallel; assigning the join operations to the processors using the index structures; and simultaneously redistributing and joining the data points in the processors in parallel based on a predetermined joining condition. An efficient data structure, .epsilon.-K-D-B tree, is used to provide fast access to the high-dimensional points and to minimize system storage requirements. The invention achieves fast response time and requires minimum storage space by having structurally identical indices among the processors, assigning workload based on the join costs, and redistributing the data points among the processors while joining the data whenever possible.
摘要翻译： 一种用于在多处理器系统中并行地表示数据库的数据对象的高维点处执行空间邻近连接的方法和系统。 该方法包括以下步骤：对处理器之间的数据点进行分割; 为处理器的数据点并行创建索引结构; 使用索引结构将连接操作分配给处理器; 并且基于预定的接合条件并行地重新分配和连接处理器中的数据点。 使用有效的数据结构epsilon -K-D-B树来提供对高维点的快速访问并且最小化系统存储要求。 本发明通过在处理器之间具有结构相同的索引来实现快速的响应时间并且需要最小的存储空间，基于加入成本分配工作负荷，并且在可能的情况下加入数据时在处理器之间重新分配数据点。
-
25.发明授权Distillation process using a mixing column to produce at least two oxygen-rich gaseous streams having different oxygen purities 失效使用混合塔进行蒸馏处理以产生具有不同氧纯度的至少两个富氧气流
公开(公告)号：US5865041A
公开(公告)日：1999-02-02
申请号：US071481
申请日：1998-05-01
IPC分类号： F25J3/04
CPC分类号： F25J3/04466 , F25J3/0446 , F25J3/04969 , F25J2200/06 , F25J2200/94 , F25J2215/52 , F25J2235/50
摘要： A process is set forth for the cryogenic distillation of an air feed to produce at least two oxygen-rich gaseous streams having different oxygen purities. The process uses a mixing column system in addition to a distillation column system. A key to the process is that at least two oxygen-rich liquid streams having different oxygen purities are transferred from the distillation column system to the mixing column system in order to produce the oxygen-rich gaseous streams.
摘要翻译： 阐述了一种用于空气进料的低温蒸馏以产生具有不同氧纯度的至少两种富氧气流的方法。 该方法除了蒸馏塔系统之外还使用混合塔系统。 该方法的关键是至少有两个具有不同氧纯度的富氧液体物流从蒸馏塔系统转移到混合塔系统，以产生富氧气流。
-
公开(公告)号：US5819266A
公开(公告)日：1998-10-06
申请号：US398640
申请日：1995-03-03
CPC分类号： G06Q30/02 , Y10S707/99936
摘要： A system and method for mining databases includes a computer-implemented program which identifies patterns of transaction sequences that are stored in a database and which recur in the database with a user-defined regularity. The invention first identifies which sequences are large, i.e., which recur with the defined regularity, and then determines which sequences are maximal, i.e., which large sequences are not subsets of other large sequences. The set of maximal large sequences is returned to the user to indicate recurring purchasing patterns over time.
摘要翻译： 用于挖掘数据库的系统和方法包括计算机实现的程序，其识别存储在数据库中的事务序列的模式，并且以用户定义的规则性在数据库中再现。 本发明首先识别哪些序列是大的，即以定义的规则重复的序列，然后确定哪些序列是最大的，即哪个大序列不是其他大序列的子集。 最大大序列的集合返回给用户以指示经常性购买模式随着时间的推移。
-
27.发明授权Method and system for generating a decision-tree classifier independent of system memory size 失效用于生成独立于系统内存大小的决策树分类器的方法和系统
公开(公告)号：US5799311A
公开(公告)日：1998-08-25
申请号：US646893
申请日：1996-05-08
IPC分类号： G06F17/30
CPC分类号： G06F17/30705 , G06F17/30625 , G06F2216/03 , Y10S707/99943
摘要： A method and system are disclosed for generating a decision-tree classifier from a training set of records, independent of the system memory size. The method comprises the steps of: generating an attribute list for each attribute of the records, sorting the attribute lists for numeric attributes, and generating a decision tree by repeatedly partitioning the records using the attribute lists. For each node, split points are evaluated to determine the best split test for partitioning the records at the node. Preferably, a gini index and class histograms are used in determining the best splits. The gini index indicates how well a split point separates the records while the class histograms reflect the class distribution of the records at the node. Also, a hash table is built as the attribute list of the split attribute is divided among the child nodes, which is then used for splitting the remaining attribute lists of the node. The created tree is further pruned based on the MDL principle, which encodes the tree and split tests in an MDL-based code, and determines whether to prune and how to prune each node based on the code length of the node.
摘要翻译： 公开了用于从记录的训练集合生成决策树分类器的方法和系统，与系统存储器大小无关。 该方法包括以下步骤：为记录的每个属性生成属性列表，对数字属性的属性列表进行排序，以及通过使用属性列表重复分割记录来生成决策树。 对于每个节点，分析点进行评估，以确定分区节点上的记录的最佳分割测试。 优选地，使用基尼系数索引和类别直方图来确定最佳分割。 gini指数表示分割点将记录分离成多少，而类直方图反映了节点上记录的类分布。 此外，由于分割属性的属性列表在子节点之间划分，因此构建了哈希表，然后用于分割节点的剩余属性列表。 基于MDL原理进一步修剪创建的树，MDL原理对基于MDL的代码中的树和分割测试进行编码，并根据节点的代码长度确定是否修剪和如何修剪每个节点。
-
公开(公告)号：US5706674A
公开(公告)日：1998-01-13
申请号：US785515
申请日：1997-01-17
CPC分类号： F25J3/08 , C01B23/0094 , C30B15/00 , C30B29/06 , F25J3/0285 , C01B2210/0004 , C01B2210/0006 , C01B2210/0014 , C01B2210/0045 , C01B2210/005 , F25J2200/04 , F25J2200/72 , F25J2215/58 , Y10S62/924
摘要： The present invention is directed to two embodiments of a process for recycling an impure argon effluent from a silicon crystal growing furnace using cryogenics. The first embodiment uses cryogenic distillation techniques, and the second embodiment uses cryogenic adsorption, both of which use catalytic treatments and adsorption in conjunction with their cryogenic process steps to provide a pure argon recycle stream for a silicon crystal growth furnace.
摘要翻译： 本发明涉及使用低温法从硅晶体生长炉回收不纯的氩气流出物的方法的两个实施方案。 第一实施例使用低温蒸馏技术，第二实施例使用低温吸附，两者都使用催化处理和吸附结合其低温工艺步骤为硅晶体生长炉提供纯氩循环流。
-
公开(公告)号：US5692395A
公开(公告)日：1997-12-02
申请号：US646652
申请日：1996-05-02
申请人： Rakesh Agrawal , Jianguo Xu
发明人： Rakesh Agrawal , Jianguo Xu
CPC分类号： B01D3/146 , F01K23/068 , F02C6/10 , F25J3/0209 , F25J3/0233 , F25J3/0257 , F25J3/04303 , F25J3/04448 , F25J3/04575 , F25J3/046 , F25J3/04606 , F25J3/04872 , F25J2200/04 , F25J2200/20 , F25J2200/50 , F25J2200/54 , F25J2235/02 , F25J2290/10 , F25J2290/40 , Y02E20/18 , Y10S62/927
摘要： A fluid mixture is separated by distillation in a two column system in which the feed is prefractionated in a first column having at least one separation stage above the feed and the prefractionator bottoms provides feed to a second column operating at a lower pressure. Cooling for condensing the overhead vapor of the first column is provided by indirect heat exchange with a flashed portion of the feed or with an intermediate fluid obtained from the second column. The two-column system is readily combined with a high pressure column in a three-column distillation system for separating air which is particularly useful for integration with a gasification combined cycle combustion turbine system. Optionally, three nitrogen products can be produced at three different pressures.
摘要翻译： 流体混合物通过蒸馏在两塔系统中分离，其中进料在具有在进料上方的至少一个分离阶段的第一塔中进行初分馏，并且初步分馏塔底部提供进料到在较低压力下操作的第二塔。 通过与进料的闪蒸部分或从第二塔获得的中间流体间接热交换来提供用于冷凝第一塔的塔顶蒸气的冷却。 双塔系统容易地与用于分离空气的三塔蒸馏系统中的高压塔组合，这对于与气化联合循环燃烧涡轮机系统的整合特别有用。 任选地，三种氮气产物可以在三种不同的压力下生产。
-
公开(公告)号：US5429666A
公开(公告)日：1995-07-04
申请号：US191401
申请日：1994-02-03
申请人： Rakesh Agrawal , Ravi Kumar , Tarik Naheiri , Charles F. Watson
发明人： Rakesh Agrawal , Ravi Kumar , Tarik Naheiri , Charles F. Watson
IPC分类号： B01D53/04 , B01D53/047 , C01B21/04 , B01D53/053
CPC分类号： B01D53/0476 , B01D2256/12 , B01D2257/102 , B01D2259/402 , B01D53/0446
摘要： A process for separating a feed gas mixture into a more strongly adsorbable component and a less strongly adsorbable component in a plurality of adsorbent beds containing an adsorbent selective for the more strongly adsorbable component using pressurization by product end to product end pressure equalization between beds simultaneous with cocurrent ambient and elevated pressure feed pressurization, coproduction of product and purge gas, and cocurrent depressurization for pressure equalization gas simultaneous with countercurrent evacuation. Oxygen product can be recovered from air at high recovery using the process.
摘要翻译： 一种将进料气体混合物分离成多个吸附床中的较强吸附组分和较不强吸附组分的方法，所述多个吸附剂床含有选择性较强吸附组分的吸附剂，其通过产物端部至产物端部之间的压力平衡，同时与床 并发环境和高压进料加压，产品和吹扫气体的共同生产，以及与逆流排空同时进行均压气体的并流减压。 使用该方法可以以高回收率从空气中回收氧气产物。
-
-
-
-
-
-
-
-
-
搜索结果
257 条记录 (耗时 0.032 秒)
