BACKGROUND: High-dimensional datasets with low sample sizes (HDLSS) are pivotal in the fields of biology and bioinformatics. One of core objective of HDLSS is to select most informative features and discarding redundant or irrelevant features. This is particularly crucial in bioinformatics, where accurate feature (gene) selection can lead to breakthroughs in drug development and provide insights into disease diagnostics. Despite its importance, identifying optimal features is still a significant challenge in HDLSS. RESULTS: To address this challenge, we propose an effective feature selection method that combines gradual permutation filtering with a heuristic tribrid search strategy, specifically tailored for HDLSS contexts. The proposed method considers inter-feature interactions and leverages feature rankings during the search process. In addition, a new performance metric for the HDLSS that evaluates both the number and quality of selected features is suggested. Through the comparison of the benchmark dataset with existing methods, the proposed method reduced the average number of selected features from 37.8 to 5.5 and improved the performance of the prediction model, based on the selected features, from 0.855 to 0.927. CONCLUSIONS: The proposed method effectively selects a small number of important features and achieves high prediction performance.

Detecting transient faults in safety-critical neural network (NN) applications operated on embedded systems has become a concern, but it is challenging to achieve high accuracy because of the open context problem and resource constraints. This study proposes an accuracy-area efficient, data-analysis-based online soft errors (SEs) and control flow errors (CFEs) detection, applicable to any NN application with low overhead. We insert code for runtime monitoring data assertion, and the data are distributed to shallow or deep detection models selectively. The shallow detection model detects CFEs by verifying runtime signatures with values obtained from simulations, and detects SEs of data having constant values according to program input. SEs of other data are verified by a deep detection model using a sliding window one-class support vector machine. Fault injection experiments on an image classification NN showed that our detector has significant detection accuracy in fault conditions.

Feature importance and interaction are among the main issues in explainable artificial intelligence or interpretable machine learning. To measure feature importance and interaction, several methods, such as H-statistic and partial dependency, have been proposed. However, it is difficult to understand the practical implications of importance and interaction. In this paper, a new method for measuring feature importance and interaction is proposed. For the classification model, we observed correctly predicted cases in a predictive model and grouped them according to the characteristics of the cases. We derived a method for feature importance and interaction from group information. For the regression model, we grouped cases according to the change in the size of the prediction error. The proposed method supports the same rationale for feature importance and interaction. It also supports the decomposition of feature importance to feature power and feature interactions. To implement the proposed method, three visualization tools, including a feature interaction graph, are implemented. Through the proposed work, we can better understand the working mechanism of a predictive model.

Metabolic syndrome is a cluster of risk factors associated with certain cardiovascular diseases. It is a chronic disease and has become an important public health issue in many countries, as it is steadily increasing owing to urbanized diets and lifestyles. The current medical diagnostic methods focus on the diagnosis of metabolic syndrome itself; however, they are not suitable for measuring its progression. Several methods have been proposed for measuring the risk of metabolic syndrome aiming to solve this problem, including the "Areal Similarity Degree" method. In this study, a robust risk index based on radar charts is proposed to overcome the weaknesses of the Areal Similarity Degree method. In the proposed method, the examination values are expressed as two types of triangles on 10 types of three-axis radar charts, and each area of the triangle is synthesized and used as a risk index. The performance of the proposed risk index is evaluated based on the data of 31,070 Korean adults obtained from the Korea Genome and Epidemiology Study health examinee (KoGES HEXA) dataset. The proposed risk index shows a high correlation with current medical diagnostic criteria, and a good diagnostic performance. It produces more stable and generalized risk index values than those from the basic Areal Similarity Degree method. In addition, its sample-independent characteristics are confirmed.

Iterative register-transfer level (RTL) simulation is essential for the edge processor design, but the RTL simulation speed is significantly slower in a system where various RTL models are complicatedly integrated. In this paper, we propose a novel metamorphic edge processor simulation framework that partitions the software part and virtualizes it in the system emulator to eject from full RTL simulation. The system emulator, which is written in a high-level language, and the Verilog simulation have different abstraction levels, thus the Verilog procedural interface (VPI) module is plugged into the Verilog simulator to connect with the virtual layer interface. In the system emulator, a Verilog RTL simulation session corresponding to a specific parameter set can be dynamically loaded at runtime to provide metamorphism by flexible partial parameter-driven RTL model replacement. We applied the proposed framework to finite impulse response (FIR) filter, and it is successfully demonstrated and achieved simulation speedup for given parameters.

In machine learning, classification involves identifying the categories or classes to which a new observation belongs based on a training set. The performance of a classification model is generally measured by the classification accuracy of a test set. The first step in developing a classification model is to divide an acquired dataset into training and test sets through random sampling. In general, random sampling does not guarantee that test accuracy reflects the performance of a developed classification model. If random sampling produces biased training/test sets, the classification model may result in bias. In this study, we show the problems of random sampling and propose balanced sampling as an alternative. We also propose a measure for evaluating sampling methods. We perform empirical experiments using benchmark datasets to verify that our sampling algorithm produces proper training and test sets. The results confirm that our method produces better training and test sets than random and several non-random sampling methods can.

BACKGROUND: Biological data such as microarrays contain a huge number of features. Thus, it is necessary to select a small number of novel features to characterize the entire dataset. All combinations of the features subset must be evaluated to produce an ideal feature subset, but this is impossible using currently available computing power. Feature selection or feature subset selection provides a sub-optimal solution within a reasonable amount of time. RESULTS: In this study, we propose an improved feature selection method that uses information based on all the pairwise evaluations for a given dataset. We modify the original feature selection algorithms to use pre-evaluation information. The pre-evaluation captures the quality and interactions between two features. The feature subset should be improved by using the top ranking pairs for two features in the selection process. CONCLUSIONS: Experimental results demonstrated that the proposed method improved the quality of the feature subset produced by modified feature selection algorithms. The proposed method can be applied to microarray and other high-dimensional data.

At system level, the on-chip temperature depends both on power density and the thermal coupling with the neighboring regions. The problem of finding the right set of input power profile(s) for accurate temperature estimation has not been studied. Considering only average or peak power density may lead either to underestimation or overestimation of the thermal crisis, respectively. To provide more realistic temperature estimation, we propose to incorporate multiple power profiles. Using the proposed statistical methods to determine the closeness between the power profiles, we apply a clustering algorithm to identify few input power profiles. We incorporate them in a thermal-aware floorplanner and empirical results show that using the single input power profile (average or peak) leads to 37% degradation in critical wire delay and 20% degradation in wire length, compared to using the multiple input power profiles.

Multimedia and DSP applications have several computationally intensive kernels which are often off loaded and accelerated by application-specific hardware. This paper presents a speculative loop pipelining technique to overcome limitations of binary translation for hardware acceleration. Although many compilers have been developed at source level, it is desirable to translate the binary targeted to popular processors onto hardware for several practical benefits. However, the translated code can be less optimized. In particular, it is difficult to optimize memory accesses on binary to exploit pipeline parallelism since memory optimization techniques require perfect dependence information for correctness and efficiency. This information is not often available at binary level or even at the source level. Our technique synthesizes the pipeline with memory dependence speculation and postpones some phases of compilation by generating a small dependence analysis code or logic which makes use of runtime values. Such speculative optimization achieves the large amount of parallelism and does not depend on any user annotation. The experimental results show a promising speedup of up to 2.53 compared with the code in which memory accesses are not optimized in the pipeline fashion due to conservative memory analysis. In addition, we have evaluated our technique at hardware level implementation on FPGA devices and achieved comparable clock frequency and power consumption compared to a conservative method while achieving significant improvement in throughput.

Role-based access control (RBAC) is a well-accepted model for access control in an enterprise environment. When we apply RBAC model to large enterprises, effective role administration is a major issue. ARBAC97 is a well-known solution for decentralized RBAC administration. ARBAC97 authorizes administrative roles by means of role ranges and prerequisite conditions, where prerequisite conditions effectively work as a restricted pool for administrative roles to pick users or permissions. Although attractive and elegant in their own right, these mechanisms have significant shortcomings. In this paper, we propose an improved role administration model named ARBAC02 to overcome the weaknesses of ARBAC97. ARBAC02 introduces the concept of organization structure for defining user and permission pools independent of roles and role hierarchies, with a refined prerequisite condition specification. In addition, we present a bottom-up approach of permission-role administration in contrast to the top-down approach in ARBAC97. As a general solution, we illustrate the applications of organization structured-based security administration with other access control models, such as access control list model and lattice-based access control model.

In the design of an embedded processor, the compiler design is tightly coupled with the underlying processor architecture, and thus it is crucial to rapidly retarget a compiler along with the change in the architecture in order to expedite the processor design. However, among many compiler writers, there is a controversial issue that has long been argued - whether a compiler can be easily retargetable while it performs sophisticated machine-specific optimizations for a new architecture configuration. We examine this issue by finding some possible cases where optimizations may be impeded on a pathway to building a retargetable compiler. For this, we developed two types of compilation frameworks called user-retargetable and developer-retargetable, and compared their performance.

Role-based access control (RBAC) is recognized as an efficient access control model for large organizations. Most organizations have some business rules related to access control policy. Delegation of authority is among these rules. RBDM0 and RDM2000 models are recently published models for role-based delegation. They deal with user-to-user delegation. The unit of delegation in them is a role. But in many cases users may want to delegate a piece of permission from a role. This paper proposes a flexible delegation model named Permission-based Delegation Model (PBDM), which is built on the well known RBAC96 model. PBDM supports user-to-user and role-to-role delegations with features of multi-step delegation and multi-option revocation. It also supports both role and permission level delegation, which provides great flexibility in authority management. In PBDM, a security administrator specify the permissions that a user (delegator) has authority to delegate to others (delegatee), then the delegator creates one or more temporary delegation roles and assigns delegatees to particular roles. This gives us clear separation of security administration and delegation.

Role-based access control (RBAC) is recognized as an excellent model for access control in an enterprise environment. In large enterprises, effective RBAC administration is a major issue. ARBAC97 is a well-known solution for decentralized RBAC administration. ARBAC97 authorizes administrative roles by means of role ranges' and prerequisite conditions'. Although attractive and elegant in their own right, we will see that these mechanisms have significant shortcomings.We propose an improved role administration model named ARBAC02 to overcome the weaknesses of ARBAC97. ARBAC02 adopts the organization unit for new user and permission pools independent of role or role hierarchy. It uses a refined prerequisite condition. In addition, we present a bottom-up approach to permission-role administration in contrast to the top-down approach of ARBAC97.