Symptoms of laryngeal cancer manifest primarily through voice changes, and its diagnosis relies solely on laryngoscopy examinations, lacking objective indicators of voice alterations. Recent advances in deep learning have opened possibilities for vocal-based laryngeal cancer screening. However, the practical medical application remains constrained due to relatively low accuracy. In this paper, we propose a method that combines patient information and voice analysis with a CNN model to address this issue. Experiments demonstrate a 8% improvement in accuracy when additional information is embedded alongside voice signals, compared to using voice data alone in deep learning models. This approach holds promise for more effective laryngeal cancer screening and diagnosis.

This paper proposes an efficient quantum train engine (EQuaTE), a novel tool for quantum machine learning software which plots gradient variances to check whether our quantum neural network (QNN) falls into local minima (called barren plateaus in QNN). EQuaTE can be realized via dynamic analysis of the undetermined probabilistic qubit states. Furthermore, the proposed EQuaTE is capable of HCI-based visual feedback such that software engineers can recognize barren plateaus via visualization, allowing the modification of QNN based on this information.

In the FAT32 file system, a null byte in the metadata means that there is no file or folder. Since the metadata are stored consecutively, if the first byte of a metadata field is null, the operating system does not read data anymore. In this study, we propose an anti-forensic technique referred to as "NULL Byte injection", which hides files or folders by injecting null bytes into the metadata field of the FAT32 file system. We presented 3 injection methods for hiding, and we evaluated the effectiveness and limitations of each injection method through experiments. As a result, we confirmed that our technique can hide files or folders in Windows OS. Based on the injection method, different effects were observed. We also confirmed that our methods can hide files or folders and bypass the detection of several forensic tools. Our technique can contribute to preventing such anti-forensic attacks by exploiting the mechanism of the file system to hide data.

User comments provide valuable information for requirements analysis. To effectively extract requirements from user comments, it is important to determine informative user comments. However, existing studies have mainly focused on NLP-based methods for analyzing user comments, rather than defining a set of user comments to be analyzed. If target user comments are not clearly determined, duplicate requirements can be discovered or new requirements cannot be discovered. To tackle this problem, we present a new method which defines a set of target corpora from user comments. Our method automatically defines a set of target corpora to be analyzed by identifying underlying temporal changes in user comments. We applied our method to real-world user comments collected from a mobile application store. We confirmed that our method successfully defined a set of corpora which aids the effective requirements elicitation, and facilitated discovering new requirements while avoiding the derivation of redundant requirements.

Designing and maintaining a software system's architecture typically involve making numerous design decisions, each potentially affecting the system's functional and nonfunctional properties. Understanding these design decisions can help inform future decisions and implementation choices and can avoid introducing regressions and architectural inefficiencies later. Unfortunately, design decisions are rarely well documented and are typically a lost artifact of the architecture creation and maintenance process. The loss of this information can thus hurt development. To address this shortcoming, we develop RecovAr, a technique for automatically recovering design decisions from the project's readily available history artifacts, such as an issue tracker and version control repository. RecovAr uses state-of-the-art architectural recovery techniques on a series of version control commits and maps those commits to issues to identify decisions that affect system architecture. While some decisions can still be lost through this process, our evaluation on Hadoop and Struts, two large open-source systems with over 8 years of development each and, on average, more than 1 million lines of code, shows that RecovAr has the recall of 75% and a precision of 77%. Our work formally defines architectural design decisions and develops an approach for tracing such decisions in project histories. Additionally, the work introduces methods to classify whether decisions are architectural and to map decisions to code elements. Finally, our work contributes a methodology engineers can follow to preserve design-decision knowledge in their projects.

Android's communication model has a major security weakness: malicious apps can manipulate other apps into performing unintended operations and can steal end-user data, while appearing ordinary and harmless. This paper presents SEALANT, a technique that combines static analysis of app code, which infers vulnerable communication channels, with runtime monitoring of inter-app communication through those channels, which helps to prevent attacks. SEALANT's extensive evaluation demonstrates that (1) it detects and blocks inter-app attacks with high accuracy in a corpus of over 1,100 real-world apps, (2) it suffers from fewer false alarms than existing techniques in several representative scenarios, (3) its performance overhead is negligible, and (4) end-users do not find it challenging to adopt.

Android's flexible communication model allows interactions among third-party apps, but it also leads to inter-app security vulnerabilities. Specifically, malicious apps can eavesdrop on interactions between other apps or exploit the functionality of those apps, which can expose a user's sensitive information to attackers. While the state-of-the-art tools have focused on detecting inter-app vulnerabilities in Android, they neither accurately analyze realistically large numbers of apps nor effectively deliver the identified issues to users. This paper presents SEALANT, a novel tool that combines static analysis and visualization techniques that, together, enable accurate identification of inter-app vulnerabilities as well as their systematic visualization. SEALANT statically analyzes architectural information of a given set of apps, infers vulnerable communication channels where inter-app attacks can be launched, and visualizes the identified information in a compositional representation. SEALANT has been demonstrated to accurately identify inter-app vulnerabilities from hundreds of real-world Android apps and to effectively deliver the identified information to users. (Demo Video: https://youtu.be/E4lLQonOdUw)

Customer requirements are critical factors in the success of a software project. Owing to their importance, several methods for understanding customer requirements have been studied in requirements engineering. Although previous studies have mainly focused on the elicitation and analysis of requirements, a method for validating elicited requirements from the customers' perspective has not been actively studied. In this paper, we propose a customer requirements validation (Curve) method using the mental model technique, which is used for analyzing customers' behaviors and their mental states. The Curve provides clear criteria for requirements validation, an integrated framework for evaluating requirements, and it enables prioritization of key requirements based on customers' inner needs. Through this method it is possible to produce software products that better satisfy customers' true needs.