In recent years, the intermittent computing devices have become increasingly widespread and result in a greater demand for storage space. In particular, NAND flash memory is well-suited as a storage medium for the intermittent computing devices, but its "out-of-place" update characteristic leads to a garbage collection (GC) mechanism to reclaim invalid pages when the number of free pages becomes insufficient. The previous studies have shown that a suitable separation of hot and cold data (i.e., a clustering method) can significantly reduce the overhead of garbage collection and improve the performance. However, the previous studies are not suitable for the intermittent computing devices that are equipped with the limited volatile memory space and very low computing power. Therefore, we will propose a hash-based clustering system software for the intermittent computing devices to provide a suitable separation of hot and cold data. The experimental results show that the proposed method with low computational time and low volatile memory space can achieve a reduction of 8% 10%, 8% 10%, 10%, and 5% 7%, in page reads, page writes, block erases, average number of erases per block, and a reduction of 8% 11% in write amplification when compared to the previous methods (such as a DBSCAN-based clustering method and a K-means clustering method). Additionally, the proposed method can efficiently recover to the most recent state when the intermittent computing devices experience power outages.

In recent years, solid-state drives (SSDs) that adopt NAND flash memory have been widely used as the main storage devices. In particular, NAND flash memory has a special feature of “out-of-place” updates to write the up-to-date data to a free page, and the corresponding old page will become invalid. When the number of free pages in SSDs is insufficient, garbage collection (GC) will be executed to reclaim the invalid pages in a block by erasing the block. Many studies have shown that a good hot/cold data separation (i.e., clustering) can greatly reduce the overhead of GC so as to improve the SSD performance. However, previous clustering methods usually use a static number of clusters or a fixed size of granularity (i.e., a fine-grained or a coarse-grained granularity), so they may not always perform well for different kinds of workloads. Therefore, we propose a granularity-based clustering method to adaptively adjust the size of granularity groups for an appropriate number of clusters at runtime according to the update distances of logical addresses. According to the experimental results, we can improve SSD performance by reducing the overhead of GC and decrease the write amplification. Furthermore, we can show that the proposed method can utilize a fine-grained granularity to retain the record accuracy of update distances and also utilize a coarse-grained granularity to reduce the space required to record update distances.

For the purpose of promoting the utilization of T-DNA mutant seeds generated by the Taiwan Rice Insertional Mutagenesis (TRIM) program for academic research, Academia Sinica contracted Asia University to establish a T-DNA Tagged Rice Service Center (TTRSC) to handle the management, conservation and distribution of mutant rice seeds inventory. To also efficiently handle the huge amount of genomic data generated from TRIM project for those mutant seeds, a cloud computing based platform named T-DNA Tagged Rice Service Information System (TTRSIS, http:[email protected]), was built within the Asia Academic Cloud to accomplish this task. Currently, four functional modules had been established in TTRSIS: Align module took in PCR sequence, used BLASTN to search and align with Rice coding sequence (CDS) database to find the insertion point in the Rice genome. Rice gene functional characterization module kept functional characterizations of Rice genome as currently available in academic publications. Then Search module provided TTRSIS users with search options of gene names, gene id, or mutant line numbers, while Physical distribution module provided mutant line rice seed inventory and distribution for academic research. An example of using OsGA20ox1 as gene name to identify is demonstrated. TTRSIS supports researcher to query interested genes located 21 kb upstream or downstream of T-DNA insertion sites, and to rapidly search candidate mutant lines in the inventory of TTRSC. With this platform, TTRSIS offers a convenient approach for researches to use the resources in TTRSC.

An efficient approach for 2-D sheet part nesting, incorporating a novel space encoding scheme and a greedy method for placing parts, is presented. The space encoding scheme denotes the occupancy of the part and the vacancy of the material sheet by discrete strip segments with an equal width and utilizes real-number coordinates on each segment for representing the occupancy and the vacancy. The greedy method operates in an iterative fashion by generating a part sequence and searching for the best position and orientation of each part in the part sequence. The part sequences are generated by a genetic algorithm with appropriate operators. The searching, based on bound settings, results in a stable searching process that is independent of the number of the parts involved. Experimental results show that the approach proposed is able to operate in an efficient manner and the final placements for the parts are more economical in comparison with a benchmark. The greedy method is particularly efficient in cases containing parts with multiple pieces because the range of the bounds for searching is gradually reduced as the method progresses. Note to Practitioners-This paper was motivated by observing sheetmetal parts in various shapes that are arranged on a rectangular sheet manually to minimize the usage of the sheet. The manual arrangements are highly dependent on one's expertise and experience but the results may vary from case to case. Existing approaches to arrange the parts automatically are usually time-consuming for dealing with parts in complicated shapes. This paper suggests a simple approach using a new decomposition method to describe the parts and the sheet, and a part placing method to efficiently decide the position of each part in a sequence. The part sequences are automatically generated by a known searching algorithm. The proposed approach has been tested in many industrial cases and the results suggest its feasibility and efficiency. In future research, we will address the cases requiring "offsets" among parts

The goal of designing an optimal nearest-neighbor classifier is to maximize the classification accuracy while minimizing the sizes of both the reference and feature sets. A novel intelligent genetic algorithm (IGA), which is superior to conventional genetic algorithms (GAs) in solving large parameter optimization problems, is used to effectively achieve this goal. It is shown empirically that the IGA-designed classifier outperforms existing GA-based and non-GA-based classifiers in terms of classification accuracy and the total number of parameters of the reduced sets.

To efficiently execute a finite element program on a hypercube, we need to map nodes of the corresponding finite element graph to processors of a hypercube such that each processor has approximately the same amount of computational load and the communication among processors is minimized. If the number of nodes of a finite element graph will not be increased during the execution of a program the mapping only needs to be performed once. However, if a finite element graph is solution-adaptive, that is, the number of nodes will be increased discretely due to the refinement of some finite elements during the execution of a program, a run-time load balancing algorithm has to be performed many times in order to balance the computational load of processors while keeping the communication cost as low as possible. In this paper, we propose a parallel iterative load balancing algorithm (ILB) to deal with the load imbalancing problem of a solution-adaptive finite element program. The proposed algorithm has three properties. First, the algorithm is simple and easy to implement. Second, the execution of the algorithm is fast. Third, it guarantees that the computational load will be balanced after the execution of the algorithm.