Segmentation of kidneys, kidney tumors and kidney cysts from contrast-enhanced CT images has significant potential to facilitate large-scale imaging and radiological analysis. However, the task is challenging due to t...
ISBN:
(数字)9783031548062
ISBN:
(纸本)9783031548055;9783031548062
Segmentation of kidneys, kidney tumors and kidney cysts from contrast-enhanced CT images has significant potential to facilitate large-scale imaging and radiological analysis. However, the task is challenging due to the considerable variation in tumor scales between different cases, which is not effectively addressed by conventional segmentation methods. In this paper, we propose a method called dynamic resolution that addresses this issue by dynamically adjusting the image resolution for each sample during training and testing, thus achieving a balance between targets with different scales. We also present a technique that uses publicly available unlabelled datasets to improve the robustness of the model without requiring additional manual labelling. We evaluated our method on the KiTS23 competition dataset and the results demonstrate its superiority over the existing state-of-the-art nnUnet, with improvements of 1.2%, 3.9% and 4.9% on kidney, tumor+cyst and tumor respectively.
In a rapidly evolving digital marketplace, the ability to enable features and services dynamically on SaaS products in alignment with market conditions and pricing strategies is essential for sustaining competitivenes...
ISBN:
(纸本)9783031623615;9783031623622
In a rapidly evolving digital marketplace, the ability to enable features and services dynamically on SaaS products in alignment with market conditions and pricing strategies is essential for sustaining competitiveness and improving the user experience. This demo paper presents Pricing4SaaS, a reference architecture designed to enhance the integration and management of pricing-driven feature toggles in SaaS systems. It centralizes the configuration of the pricing structure, spreading its changes across the whole application every time it is modified, while securing state synchronization between both the client and server. Additionally, a case study integrating a reference implementation of Pricing4SaaS inside a Spring+React PetClinic project demonstrates how such approach can be leveraged to optimize developer productivity, reducing technical debt, and improving operational efficiency.
With the development of society and the accelerated pace of life, insomnia has become a problem that affects people's physical and mental health. How to alleviate the problem of insomnia and improve the quality of...
ISBN:
(纸本)9783031604867;9783031604874
With the development of society and the accelerated pace of life, insomnia has become a problem that affects people's physical and mental health. How to alleviate the problem of insomnia and improve the quality of sleep has become the focus of people's attention. Therefore, it is meaningful to design a suitable mobile sleep aid audio APP product for insomnia people. This paper proposes a method for designing a mobile sleep aid audio APP based on Kano-AHP-QFD theoretical model. Firstly, the study used a questionnaire to obtain insomnia patients' opinions on the 16 requirements of mobile sleep aid audio APP and use Kano model to categorize the requirements by attributes. Secondly, Analytic Hierarchy Process (AHP) was used to analyze the weights of the requirements, and then sort the weights of the requirements for the design of mobile sleep aid audio APP. Lastly, by using Quality Function Deployment (QFD), the customer's requirements and expectations were changed into product design features and ensure that these design features are met. In this paper, by uniting three classic quality management tools, we conduct a design study on mobile sleep aid audio app and verify the possibility of its method in solving similar design problems. This paper can not only provide a practical mobile sleep aid audio design for people with insomnia, but also provide methodological references for other mobile app designs.
In this paper, we study the Fully Homomorphic Encryption system proposed by Craig Gentry, Amit Sahai, and Brent Waters in [3]. We present a restated version of the proposed cryptosystem, and consider the ciphertexts r...
ISBN:
(纸本)9783031645280;9783031645297
In this paper, we study the Fully Homomorphic Encryption system proposed by Craig Gentry, Amit Sahai, and Brent Waters in [3]. We present a restated version of the proposed cryptosystem, and consider the ciphertexts resulting from the use of this system, to find patterns in them. For this task, we train a machine learning pipeline, utilizing Topological Data Analysis. We show that for secure parameters chosen according to the available literature, this machine learning approach can simply guess what the plain text should have been in a majority of cases (accuracy > 70%), in very good time complexity (< O(n(3))). This attack was ineffective against the base Learning With Errors (LWE) problem, which hints at a possible flaw somewhere in the reduction from LWE to the cryptosystem.
The pseudo-coloring problem (PsCP) is a combinatorial optimization challenge that involves assigning colors to elements in a way that meets specific criteria, often related to minimizing conflicts or maximizing some f...
ISBN:
(纸本)9789819771806;9789819771813
The pseudo-coloring problem (PsCP) is a combinatorial optimization challenge that involves assigning colors to elements in a way that meets specific criteria, often related to minimizing conflicts or maximizing some form of utility. A variety of metaheuristic algorithms have been developed to solve PsCP efficiently. However, these algorithms sometimes struggle with the quality of solutions, impacting their ability to achieve optimal or near-optimal results reliably. To overcome these issues, this study introduces an adapted conscious neighborhood-based crow search algorithm (CCSA) and a massive variant of CCSA specifically tailored for PsCP. The performance of CCSA and MCCSA are evaluated on real and synthetic images and compared with state-of-the-art optimizers. The results showed that the adapted CCSA and MCCSA outperformed offering an effective strategy for image pseudo-colorization.
Cylindrical Algebraic Decomposition is a computer algebra tool with many applications, from robotics to biochemistry. But it can be very sensitive to the ordering of the variables, which may be partially prescribed by...
详细信息
ISBN:
(纸本)9783031645280;9783031645297
Cylindrical Algebraic Decomposition is a computer algebra tool with many applications, from robotics to biochemistry. But it can be very sensitive to the ordering of the variables, which may be partially prescribed by the problem, but generally has at least some freedom. While various algorithmic heuristics to choose the best variable order exist, we are looking at using new machine learning models to pick the variable order directly. Of those machine learning methods we have currently implemented, Feed-forward networks seem the most successful (though some others are nearly as good), and much better than a traditional hand crafted heuristic such as Brown's. We also explore an implementation of Graph Neural Networks as well as possible data pollution in current CAD datasets.
This paper presents an industrial case study examining challenges faced by software architects and developers during planning and assessing the correctness of event-driven communication behaviour. We present a novel a...
ISBN:
(纸本)9783031707964;9783031707971
This paper presents an industrial case study examining challenges faced by software architects and developers during planning and assessing the correctness of event-driven communication behaviour. We present a novel approach for visualizing the communication paths of an event-driven microservice system. Service-local documentation is used to create a global view of the runtime behaviour. We show that this visualization approach can significantly reduce the time required to understand an architecture, while additionally improving accuracy and confidence.
Predicting future successful teams of experts who can effectively collaborate is challenging due to the experts' temporality of skill sets, levels of expertise, and collaboration ties, which is overlooked by prior...
ISBN:
(纸本)9783031560262;9783031560279
Predicting future successful teams of experts who can effectively collaborate is challenging due to the experts' temporality of skill sets, levels of expertise, and collaboration ties, which is overlooked by prior work. Specifically, state-of-the-art neural-based methods learn vector representations of experts and skills in a static latent space, falling short of incorporating the possible drift and variability of experts' skills and collaboration ties in time. In this paper, we propose (1) a streaming-based training strategy for neural models to capture the evolution of experts' skills and collaboration ties over time and (2) to consume time information as an additional signal to the model for predicting future successful teams. We empirically benchmark our proposed method against state-of-the-art neural team formation methods and a strong temporal recommender system on datasets from varying domains with distinct distributions of skills and experts in teams. The results demonstrate neural models that utilize our proposed training strategy excel at efficacy in terms of classification and information retrieval metrics. The codebase is available at https://***/fani-lab/OpeNTF/tree/ecir24.
The seminal work by Impagliazzo and Rudich (STOC'89) demonstrated the impossibility of constructing classical public key encryption (PKE) from one-way functions (OWF) in a black-box manner. Quantum information has...
ISBN:
(纸本)9783031683930;9783031683947
The seminal work by Impagliazzo and Rudich (STOC'89) demonstrated the impossibility of constructing classical public key encryption (PKE) from one-way functions (OWF) in a black-box manner. Quantum information has the potential to bypass classical limitations, enabling the realization of seemingly impossible tasks such as quantum money, copy protection for software, and commitment without one-way functions. However, the question remains: can quantum PKE (QPKE) be constructed from quantumly secure OWF? A recent line of work has shown that it is indeed possible to build QPKE from OWF, but with one caveat. These constructions necessitate public keys being quantum and unclonable, diminishing the practicality of such "public" encryption schemes-public keys cannot be authenticated and reused. In this work, we re-examine the possibility of perfect complete QPKE in the quantum random oracle model (QROM), where OWF exists. Our first main result: QPKE with classical public keys, secret keys and ciphertext, does not exist in the QROM, if the key generation only makes classical queries. Therefore, a necessary condition for constructing such QPKE from OWF is to have the key generation classically "un-simulatable". Previous results (Austrin et al. CRYPTO'22) on the impossibility of QPKE from OWF rely on a seemingly strong conjecture. Our work makes a significant step towards a complete and unconditional quantization of Impagliazzo and Rudich's results. Our second main result extends to QPKE with quantum public keys. The second main result: QPKE with quantum public keys, classical secret keys and ciphertext, does not exist in the QROM, if the key generation only makes classical queries and the quantum public key is either pure or "efficiently clonable". The result is tight due to these existing QPKEs with quantum public keys, classical secret keys, quantum/classical ciphertext and classical-query key generation require the public key to be mixed instead of pure;or require quantum-
Heap-based memory vulnerabilities are significant contributors to software security and reliability. The presence of these vulnerabilities is influenced by factors such as code coverage, the frequency of heap operatio...
ISBN:
(纸本)9783031646256;9783031646263
Heap-based memory vulnerabilities are significant contributors to software security and reliability. The presence of these vulnerabilities is influenced by factors such as code coverage, the frequency of heap operations, and the specific execution order. Current fuzzing solutions aim to efficiently detect these vulnerabilities by utilizing static analysis or incorporating feedback on the sequence of heap operations. However, these solutions have limited practical applicability and do not comprehensively address the temporal and spatial aspects of heap operations. In this paper, we propose a dedicated fuzzing technique called CtxFuzz to efficiently discover heap-based temporal and spatial memory vulnerabilities without requiring any domain knowledge. CtxFuzz utilizes context heap operation sequences (the sequences of heap operations such as allocation, deallocation, read, and write that are associated with corresponding heap memory addresses) as a new feedback mechanism to guide the fuzzing process. By doing so, CtxFuzz can explore more heap states and trigger more heap-based memory vulnerabilities, both temporal and spatial. We evaluate CtxFuzz on 9 real-world open-source programs and compare their performance with 5 state-of-the-art fuzzers. The results demonstrate that CtxFuzz outperforms most fuzzers in terms of discovering heap-based memory vulnerabilities. Moreover, Our experiments led to the identification of 10 zero-day vulnerabilities (10 CVEs).
暂无评论