Since a high dropout rate for university students is a significant risk to local communities and countries, a dropout prediction model using machine learning is an active research domain to prevent students from dropping out. However, it is challenging to fulfill the needs of consulting institutes and the office of academic affairs. To the consulting institute, the accuracy in the prediction is of the utmost importance; to the offices of academic affairs and other offices, the reason for dropping out is essential. This paper proposes a Student Dropout Prediction (SDP) system, a hybrid model to predict the students who are about to drop out of the university. The model tries to increase the dropout precision and the dropout recall rate in predicting the dropouts. We then analyzed the reason for dropping out by compressing the feature set with PCA and applying K-means clustering to the compressed feature set. The SDP system showed a precision value of 0.963, which is 0.093 higher than the highest-precision model of the existing works. The dropout recall and F1 scores, 0.766 and 0.808, respectively, were also better than those of gradient boosting by 0.117 and 0.011, making them the highest among the existing works; Then, we classified the reasons for dropping out into four categories: “Employed”, “Did Not Register”, “Personal Issue”, and “Admitted to Other University.” The dropout precision of “Admitted to Other University” was the highest, at 0.672. In post-verification, the SDP system increased counseling efficiency by accurately predicting dropouts with high dropout precision in the “High-Risk” group while including more dropouts in total dropouts. In addition, by predicting the reasons for dropouts and presenting guidelines to each department, the students could receive personalized counseling.

Shared-memory based parallel programming with OpenMP and Posix-thread APIs is becoming more common to fully take advantage of multiprocessor computing environments. One of the critical risks in the multithreaded programming is data races which are hard to debug and greatly damaging to parallel applications if they are uncaughted. Although ample effort has been made in building specialized data race detection techniques, the state of art tools such as Intel thread checker still have various functionality and performance problems. In this paper, we present an efficient data race detection mechanism named ADAT (Adaptive Dynamic Analysis Tool). ADAT analyzes target program models to categorize the race engines (RDC: Race-Detection Classification) and then selects adequate engines to detect races automatically based upon the RDC (ECPS: Engine Code Property Selector). ADAT constructs an emperically optimal set of race engines in the aspect of labeling, filtering, and detection. In addition to RDC and ECPS, we have implemented an OpenMP parser and a source instrument or in ADAT to support OpenMP programs. The functionality and efficiency of ADAT are compared with those of Intel thread checker by using a set of OpenMP based kernel programs. The experimental results show that ADAT can detect data races with more challenging target program models and can achieve a couple of orders of magnitude faster processing time than Intel thread checker.

Data races are common in interrupt-driven programs and have already led to well-known real-world problems. Unfortunately, existing dynamic tools for reporting data races in interrupt-driven programs are not only unsound, but they also fail to verify the existence of data races in such programs. This paper presents an efficient and scalable on-the-fly technique that precisely detects, without false positives, apparent data races in interrupt-driven programs. The technique combines a tailored lightweight labeling scheme to maintain logical concurrency between the main program and every instance of its interrupt handlers with a precise detection protocol that analyzes conflicting shared memory accesses by storing at most two accesses for each shared variable. We implemented a prototype of this technique, called iRace, on top of the Avrora simulation framework. An empirical evaluation of iRace revealed the presence of data races in some existing TinyOS components and applications with a worst-case slowdown of only about 6 times on average and an increased average memory consumption of only about 20% in comparison with the original program execution. The evaluation also proved that the labeling scheme alone generates an average runtime overhead of only about 0.4x while consuming only about 12% more memory than the original program execution.

To apply UAVs (Unmanned Aerial Vehicle) into different fields, including research and industry, and expand it quickly, reliable but modular software is required. The existing flight control software (FCS) of the UAV consists of various types of modules categorized into different layers, and it is responsible for coordinating, monitoring, and controlling the vehicle during its flight. This paper proposes mpFCS, a structure of UAV flight control software, which provides portability to its modules and is easy to expand. The mpFCS consists of four segments and several modules within the segments. mpFCS provides portability for each module within the segment. Existing software does not provide portability for its modules because of the tight coupling resulting from its different and private interfaces. The mpFCS uses interfaces of the standard airborne software architecture to transfer data between its modules. Moreover, the structure provides portability for its modules to run in the standard airborne software environment. In order to verify the mpFCS, we tested the mpFCS with the conformance test suite of the airborne software that provides the testing environment for the interfaces and modules of the software. The mpFCS passed the test. Test results show that all modules of the mpFCS are portable. Additionally, portable modules can be interoperable with other software, and the structure is expandable with new modules that use standard airborne software interfaces.

Airborne health management systems prevent functional failure caused by errors or faults in airborne software. The on-the-fly repairing of atomicity violations in ARINC 653 concurrent software is critical for guaranteeing the correctness of software execution. This paper introduces RAV (Repairing Atomicity Violation), which efficiently treats atomicity violations. RAV diagnoses an error on the fly by utilizing the training results of software and treats to control access to the shared variable of the thread where the error has occurred. The evaluation of RAV measured the time overhead by applying methods found in previous works and RAV to five synthesis programs containing an atomicity violation.