In recent years, infrastructure facilities have been noticeably deteriorating and need to be inspected. The use of pipe-inspection robots has been investigated, but the robots developed so far are too large for smaller pipes. As the robot is downsized, however, the cables used for communication and power transmission disturb the movement of the robot. In this report, we utilized microwave guided modes propagating along a pipe wall as a communication method. An experimental robot platform for small-diameter pipe inspection was constructed. We confirmed the feasibility of the communication method by conducting a 3D electromagnetic field simulation and experiments on the transmission properties. In particular, the experiments on data communication and picture transmission demonstrated the possibility of communication with the robot. A small pipe-travelling robot platform for experiments on wireless communication was designed and fabricated. We confirmed that the prototype robot was able to communicate wirelessly by using microwave guided modes propagating along the pipe wall.

Glaucoma, which can cause irreversible damage to the sight of human eyes, is conventionally diagnosed by visual field (VF) sensitivity. However, it is labor-intensive and time-consuming to measure VF. Recently, optical coherence tomography (OCT) has been adopted to measure retinal layers thickness (RT) for assisting the diagnosis because glaucoma makes structural changes to RT and it is much less costly to obtain RT. In particular, RT can assist in mainly two manners. One is to estimate a VF from an RT such that clinical doctors only need to obtain an RT of a patient and then convert it to a VF for the diagnosis. The other is to predict future VFs by utilizing both past VFs and RTs, i.e., the prediction of progression of VF over time. The two computational tasks are performed as two data mining tasks because currently there is no knowledge about the exact form of the computations involved. In this paper, we study a novel problem which is the integration of the two data mining tasks. The motivation is that both the two data mining tasks deal with transforming information from the RT domain to the VF domain such that the knowledge discovered in one task can be useful for another. The integration is non-trivial because the two tasks do not share the way of transformation. To address this issue, we design a progression-agnostic and mode-independent (PAMI) module which facilitates cross-task knowledge utilization. We empirically demonstrate that our proposed method outperforms the state-of-the-art method for the estimation by 6.33% in terms of mean of the root mean square error on a real dataset, and outperforms the state-of-the-art method for the progression prediction by 3.49% for the best case.

Prediction of glaucomatous visual field loss has significant clinical benefits because it can help with early detection of glaucoma as well as decision-making for treatments. Glaucomatous visual loss is conventionally captured through visual field sensitivity (VF ) measurement, which is costly and time-consuming. Thus, existing approaches mainly predict future VF utilizing limited VF data collected in the past. Recently, optical coherence tomography (OCT) has been adopted to measure retinal layers thickness (RT ) for considerably more low-cost treatment assistance. There then arises an important question in the context of ophthalmology: are RT measurements beneficial for VF prediction? In this paper, we propose a novel method to demonstrate the benefits provided by RT measurements. The challenge is management of the two heterogeneities of VF data and RT data as RT data are collected according to different clinical schedules and lie in a different space to VF data. To tackle these heterogeneities, we propose latent progression patterns (LPPs), a novel type of representations for glaucoma progression. Along with LPPs, we propose a method to transform VF series to an LPP based on matrix factorization and a method to transform RT series to an LPP based on deep neural networks. Partial VF and RT information is integrated in LPPs to provide accurate prediction. The proposed framework is named deeply-regularized latent-space linear regression (\em DLLR). We empirically demonstrate that our proposed method outperforms the state-of-the-art technique by 12% for the best case in terms of the mean of the root mean square error on a real dataset.

Conventionally, glaucoma is diagnosed on the basis of visual field sensitivity (VF). However, the VF test is time-consuming, costly, and noisy. Using retinal thickness (RT) for glaucoma diagnosis is currently desirable. Thus, we propose a new methodology for estimating VF from RT in glaucomatous eyes. The key ideas are to use our new methods of pattern-based regularization (PBR) and pattern-based visualization (PBV) with convolutional neural networks (CNNs). PBR effectively conducts supervised learning of RT-VF relations in combination with unsupervised learning from non-paired VF data. We can thereby avoid overfitting of a CNN to small sized data. PBV visualizes functional correspondence between RT and VF with its nonlinearity preserved. We empirically demonstrate with real datasets that a CNN with PBR achieves the highest estimation accuracy to date and that a CNN with PBV is effective for knowledge discovery in an ophthalmological context.

Dense measurements of visual-field, which is necessary to detect glaucoma, is known as very costly and labor intensive. Recently, measurement of retinal-thickness can be less costly than measurement of visual-field. Thus, it is sincerely desired that the retinal-thickness could be transformed into visual-sensitivity data somehow. In this paper, we propose two novel methods to estimate the sensitivity of the visual-field with SITA-Standard mode 10-2 resolution using retinal-thickness data measured with optical coherence tomography (OCT). The first method called Affine-Structured Non-negative Matrix Factorization (ASNMF) which is able to cope with both the estimation of visual-field and the discovery of deep glaucoma knowledge. While, the second is based on Convolutional Neural Networks (CNNs) which demonstrates very high estimation performance. These methods are kinds of multi-view learning methods because they utilize visual-field and retinal thickness data simultaneously. We experimentally tested the performance of our methods from several perspectives. We found that ASNMF worked better for relatively small data size while CNNs did for relatively large data size. In addition, some clinical knowledge are discovered via ASNMF. To the best of our knowledge, this is the first paper to address the dense estimation of the visual-field based on the retinal-thickness data.

In this paper, we propose a method to cluster the spacial patterns of the visual field in glaucoma patients to analyze the progression patterns of glaucoma. The degree of progression in the visual field of glaucoma patients can be divided into several regions by straight line boundaries, we call this specific structure Direct Product Structure in this paper. Since we can observe the direct product structure in the visual fields, we propose a bottom-up hierarchical clustering method to embed this structure into the clustering structure. In our method, according to the minimum description length (MDL) principle, we select the best cluster division so that the total code length required for encoding the data as well as the clustering structure is minimum. We can thereby select the clusters that are robust to the noise in the position of the direct product structure for clustering. We demonstrate the effectiveness of our method using an artificial dataset and a real glaucoma dataset. Our proposed method performed better than existing methods for both datasets. For the real glaucoma dataset in particular, our method discovered the characteristic progressive patterns of glaucoma as specific features of clusters. These patterns agree with clinical knowledge. Furthermore, we show that our clusters can be applied to improve the accuracy of predicting glaucoma progression. Thus, our clusters contain rich information of glaucoma, and hence can contribute to further development in glaucoma research.

We propose database-aware regression methods for extrapolation from few measurements in the context of quantitative prognosis. The idea is to leverage a database of patients with similar conditions to increase the effective number of samples when we train a predictive model. Applying the proposed method to a database of glaucoma patients, we were able to predict the disease condition at a future time point significantly more accurately than the conventional patient-wise linear regression approach. In fact, our prediction was 50% more accurate than the conventional approach when three or less measurements were available and with only two measurements at least as accurate as the conventional approach with six measurements. Moreover, the proposed method can provide spatially localized prediction and also the (localized) speed of progression, which are valuable for doctors in making decisions.

How to estimate the shortest routing length when certain blocks are considered as routing obstacles is becoming an essential problem for block placement because HPWL, is no longer valid in this case. Although this problem is well studied in computational geometry (Mitchell, 2000), the research results are neither well-known to the CAD community nor presented in a way easy for CAD researchers to ultilize their establishment. With the help of some recent notions in block placement, this paper interprets the research result in Atallah and Chen (1991) and de Rezende et al. (1985), which gives the best algorithm for this problem as we know, in a way more concise and more friendly to CAD researchers. Besides, we also tailor its algorithm to VLSI CAD application. As the result, we present a method that estimates the shortest obstacle-avoiding routing length in 0(M2+ N) time for a placement with M blocks and N 2-pin nets.

This paper describes an application of SVM (support vector machines) to interactive document retrieval using active document showing. Some works have been done to apply classification learning like SVM to relevance feedback and obtained successful results. However they did not fully utilize characteristic of example distribution in document retrieval. We propose heuristics to bias document showing according to distribution of examples in document retrieval. This heuristic is executed by selecting examples to show a user in neighbors of positive support vectors, and it improves learning efficiency. We implemented a SVM-based interactive document retrieval system using our proposed heuristic, and compare it with conventional systems like Rocchio-based system and a SVM-based system without the heuristic. We conducted systematic experiments using large data sets including over 500,000 paper articles and confirmed our system outperformed other ones

The wire length estimation is the bottleneck of packing based block placers. To cope with this problem, we present a fast wire length estimation method in this paper. The key idea is to bundle the 2-pin nets between block pairs, and measure the wire length bundle by bundle, instead of net by net. Previous bundling method [5] introduces a huge error which compromises the performance. We present an errorfree bundling approach which utilizes the piecewise linear wire length function of a pair of blocks. With the function implemented into a lookup table, the wire length can be computed promptly and precisely by binary search. Furthermore, we show that 3-pin nets can also be bundled, resulting in a further speedup. The effectiveness of our method is verified by experiments.

This paper reports a new document retrieval method using non-relevant documents. Especially, this paper reports a comparison of retrieval efficiency between one class support vector machine (SVM) based and support vector data description (SVDD) based interactive document retrieval method using non-relevant documents only. From a large data set of documents, we need to find documents that relate to human interesting in as few iterations of human testing or checking as possible. In each iteration a comparatively small batch of documents is evaluated for relating to the human interesting. We applied active learning techniques based on support vector machine for evaluating successive batches, which is called relevance feedback. Our proposed approach has been very useful for document retrieval with relevance feedback experimentally. The traditional relevance feedback needs a set of relevant and non-relevant documents to work usefully. However, the initial retrieved documents, which are displayed to a user, sometimes don't include relevant documents. In order to solve this problem, we propose a new feedback method using information of non-relevant documents only. We named this method non-relevance feedback document retrieval. The non-relevance feedback document retrievals are based on one class support vector machine and support vector data description. Our experimental results show that one class support vector machine based method can retrieve relevant documents efficiently using information of non-relevant documents only.

We attempt to develop a crossarm reuse judgment system based on rust images that uses machine learning techniques. The system consists of a digital camera and a standard note book personal computer (PC). We estimate the degree of accuracy of the judgment of various pattern classification methods without special image processing techniques such as the extraction of features. The results show that a support vector machine is the most suitable instrument for this judgment system. We obtain the high degree of accuracy by compressing the image data in order to decrease the number of features.

This paper reports a new document retrieval method using non-relevant documents. From a large data set of documents, we need to find documents that relate to human interesting in as few iterations of human testing or checking as possible. In each iteration, a comparatively small batch of documents is evaluated for relating to the human interesting. We applied active learning techniques based on support vector machine for evaluating successive hatches, which is called relevance feedback. Our proposed approach has been very useful for document retrieval with relevance feedback experimentally. The relevance feedback needs a set of relevant and non-relevant documents to work usefully. However, the initial retrieved documents, which are displayed to a user, sometimes don't include relevant documents. In order to solve this problem, we propose a new feedback method using information of non-relevant documents only. We named this method non-relevance feedback document retrieval. The non-relevance feedback document retrieval is based on one-class support vector machine. Our experimental results show that this method can retrieve relevant documents using information of non-relevant documents only.

We investigate the following data mining problems from the document retrieval: From a large data set of documents, we need to find documents that relate to human interest as few iterations of human testing or checking as possible. In each iteration a comparatively small batch of documents is evaluated for relating to the human interest. We apply active learning techniques based on support vector machine for evaluating successive batches, which is called relevance feedback. Our proposed approach has been very useful for document retrieval with relevance feedback experimentally. In this paper, we adopt several representations of the vector space model and several selecting rules of displayed documents at each iteration, and then show the comparison results of the effectiveness for the document retrieval in these several situations.

We investigate the following data mining problems from the document retrieval: From a large data set of documents, we need to find documents that relate to human interesting in as few iterations of human testing or checking as possible. In each iteration a comparatively small batch of documents is evaluated for relating to the human interesting. We apply active learning techniques based on Support Vector Machine for evaluating successive batches, which is called relevance feedback. Finally, our proposed approach is very useful for document retrieval with relevance feedback experimentally.

The sequence-pair was proposed in 1995 as a representation of the packing of rectangles of general structure. Since then, there have been efforts to expand its applicability over simple rectangles. This paper proposes a unified way to represent the packing of a set of rectilinear blocks, including arbitrary concave rectilinear blocks. Our idea is in the representation of a general block by a collection of rectangle blocks with additional constraints, Some sequence-pairs of rectangle blocks with such constraints may not be feasible, i.e., there is no corresponding parking. A necessary and sufficient condition of feasible sequence-pair is given by the properties of the horizontal and vertical constraint graphs. Furthermore, it is proved that any packing is represented by a feasible sequence-pair. The condition includes dimensions of blocks involved. If we limit the rectilinear blocks to L-shaped ones, a necessary and sufficient condition can be represented only in terms of the topology of the sequence-pair, without dimensions of blocks. A packing algorithm is designed as an SA search of the generated sequence-pairs. Experimental results show the effectiveness of the proposed method.

The sequence-pair was proposed in 1995 as a rep- resentation of the packing of rectangles of general structure. Since then, there have been efforts to expand its applicability over simple rectangles. This paper proposes a unified way to represent the packing of a set of rectilinear blocks, including arbitrary concave rectilinear blocks. Our idea is in the repre- sentation of a general block by a collection of rectangle blocks with additional constraints. Some sequence-pairs of rectangle blocks with such constraints may not be feasible, i.e., there is no corresponding packing. A necessary and sufficient condition of feasible sequence-pair is given by the properties of the horizontal and vertical constraint graphs. Furthermore, it is proved that any packing is represented by a feasible sequence-pair. The condition includes dimensions of blocks involved. If we limit the rectilinear blocks to L-shaped ones, a necessary and sufficient condition can be represented only in terms of the topology of the sequence-pair, without dimensions of blocks. A packing algorithm is designed as an SA search of the generated sequence-pairs. Experimental results show effectiveness of the proposed method. Index Terms—Compaction, layout, packing, placement, se- quence-pair.

This paper proposes a placement method for a mixed set of hard, soft, and pre-placed modules, based on a placement topology representation called sequence-pair. Under one sequence-pair, a convex optimization problem is efficiently formulated and solved to optimize the aspect ratios of the soft modules. The method is used in two ways: i) directly applied in simulated annealing to present the most exact placement method, ii) applied as a post process in an approximate placement method for faster computation. The performance of these two methods are reported using MCNC benchmark examples.

In a typical very large scale integration/printed circuit board (VLSI/PCB) design, some modules are preplaced in advance, and the other modules are requested to be placed without overlap with each other and with these preplaced modules. The presence of such obstacles introduces inconsistency to a coding scheme, called sequence pair, which has been proposed for an obstacle free placement problem. We solve this difficulty by proposing a procedure called "adaptation" which transforms an inconsistent sequence pair to a consistent one with the utmost consideration for minimizing the modification. It is shown that a simulated annealing is well organized so that it tests only feasible placements by the adaptation procedure. As a design example, a Microelectronics Center of North Carolina (MCNC) benchmark data "ami49" is packed with treating ten modules among 49 modules as preplaced ones. Further, a PCB example which includes 32 free modules and four preplaced modules (connectors) is laid out successfully by our method with a conventional wiring estimation followed by a commercial router.

A new method of packing the rectangles is proposed with applications to integrated circuit (IC) layout design. A special work-sheet, called the bounded-sliceline grid, is introduced. It consists of special segments that dissect the plane into rooms to which binary relations "right-of" and "above" are associated such that any two rooms are uniquely in either relation. A packing is obtained through an assignment of the modules into the rooms followed by a compaction procedure. Changing the assignments by swapping the contents of two rooms, a simulated annealing strategy is implemented to search for a good packing. Empirical results show that hundreds of rectangles are packed with a quite good quality in area efficiency. A wide adaptability is demonstrated specific to IC layout design. Ideas to handle a multilayer, nonrectangular chips with L-shaped modules are suggested.

A fundamental issue in floorplanning is in how to represent candidate solutions. A representation called sequence-pair was recently proposed. Seq-pair is so general as to represent an area minimum placement, and also efficient because it does not represent any overlapping placement. However, seq-pair is not expressive enough since channels are not represented. The paper gives a mapping from seq-pair to rectangular dissection, which represents channels by line segments. Consequently, candidate arrangements of modules and channels are successfully represented with the generality and the efficiency inherited from the seq-pair.

Article VLSI/PCB placement with obstacles based on sequence-pair Share on Authors: H. Murata Japan Advanced Institute of Science and Technology, Japan Japan Advanced Institute of Science and Technology, JapanView Profile , K. Fujiyoshi Tokyo University of Agriculture and Technology, Japan Tokyo University of Agriculture and Technology, JapanView Profile , M. Kaneko Japan Advanced Institute of Science and Technology, Japan Japan Advanced Institute of Science and Technology, JapanView Profile Authors Info & Claims ISPD '97: Proceedings of the 1997 international symposium on Physical designApril 1997 Pages 26–31https://doi.org/10.1145/267665.267675Online:01 April 1997Publication History 38citation300DownloadsMetricsTotal Citations38Total Downloads300Last 12 Months7Last 6 weeks1 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access

A new method of packing rectangles (modules) is presented with applications to IC layout design. It is based on the bounded-sliceline grid (BSG) structure. The BSG dissects the plane into rooms associated with binary relations "right-to"and "above" such that any two rooms are uniquely in either relation. A packing is obtained through an assignment of modules on the BSG. Followed by physical realization BSG-PACK. A simulated annealing searches for a goon packing of all packings by changing the assignments. Experiments showed that hundreds of rectangles are easily packed in a small rectangle area (chip) with quite good quality in area efficiency. A wide adaptability is demonstrated specific to IC layout design. Remarkable examples are: the chip is not necessarily rectangle, L-shaped modules and modules which are allowed to partially overlap each other can be handled.

The earliest and the most critical stage in VLSI layout design is the placement. The background is the rectangle packing problem: given a set of rectangular modules of arbitrary sizes, place them without overlap on a plane within a rectangle of minimum area. Since the variety of the packing is uncountably infinite, the key issue for successful optimization is the introduction of a finite solution space which includes an optimal solution. This paper proposes such a solution space where each packing is represented by a pair of module name sequences, called a sequence-pair. Searching this space by simulated annealing, hundreds of modules have been packed efficiently as demonstrated. For applications to VLSI layout, we attack the biggest MCNC benchmark ami49 with a conventional wiring area estimation method, and obtain a highly promising placement.

The first and the most critical stage in VLSI layout design is the placement, the background of which is the rectangle packing problem: Given many rectangular modules of arbitrary site, place them without overlapping on a layer in the smallest bounding rectangle. Since the variety of the packing is infinite (two-dimensionally continuous) many, the key issue for successful optimization is in the introduction of a P-admissible solution space, which is a finite set of solutions at least one of which is optimal. This paper proposes such a solution space where each packing is represented by a pair of module name sequences. Searching this space by simulated annealing, hundreds of modules could be successfully packed as demonstrated. Combining a conventional wiring method, the biggest MCNC benchmark ami49 is challenged.