Breast cancer is an occurrence of cancer that attacks breast tissue and is the most common cancer among women worldwide, affecting one in eight women. In this modern world, breast cancer image classification simplifie...
详细信息
ISBN:
(数字)9798331539603
ISBN:
(纸本)9798331539610
Breast cancer is an occurrence of cancer that attacks breast tissue and is the most common cancer among women worldwide, affecting one in eight women. In this modern world, breast cancer image classification simplifies the process of analyzing, providing objective and accurate results. By leveraging machine learning algorithms and computer vision techniques, we developed breast cancer detection. The dataset is histopathology dataset from BreakHis and UNHAS Hospital. We chose the ConvNeXt-Tiny model then modified the classifier head as the proposed method. Before the dataset is processed by the model, we augment the images by applying random horizontal and vertical flips, adjustments to brightness, contrast, saturation, and hue using color jitter. The augmentation process simulates real-world variance and enhances the model's ability to generalize to unseen data. Our proposed model gained better performance (accuracy, F1-Score) results compared two other techniques to VGG16 and SVM. According to our experiments, the F1-Score for the ConvNeXt-Tiny model with classifier head modification is higher at 0.9516, than the gain for VGG16 at 0.9292, and the gain for the SVM at 0.83.
Applications that support multimedia data such as medical pictures and videos, video broadcasting, and secure video conferencing consume vast quantities of information that require large numbers of servers to provide ...
详细信息
Federated learning has a great potential to create solutions working over different sources without data transfer. However current federated methods are not explainable nor auditable. In this paper we propose a Federa...
详细信息
The paper proposes experimental studies with software Defined Radio receivers of aerial objects onboard systems signals. It is established that the signals of the following channels are additional sources of signals, ...
详细信息
Misinformation or so called 'fake news' has become a pressing issue around the world. This research proposes modeling the spread of misinformation through Q-learning, the game of Nim, and multi-Agent simulatio...
详细信息
Large language models (LLMs) have shown impressive performance on downstream tasks by in-context learning (ICL), which heavily relies on the quality of demonstrations selected from a large set of annotated examples. R...
Abstract Risk management is often overlooked in the software industry, especially in agile methodology-based projects, which can have negative impacts on the schedule, budget, and quality of a project, eventually lead...
详细信息
Abstract Risk management is often overlooked in the software industry, especially in agile methodology-based projects, which can have negative impacts on the schedule, budget, and quality of a project, eventually leading to customer dissatisfaction. Hence, it is essential to identify the risks and prioritize them based on their level of importance. This study has utilized the Analytic Hierarchy Process (AHP) methodology for prioritizing the software risk factors identified during our previously executed risk identification phase experimental study in small and medium software enterprises that follow agile and traditional methodologies for software development. Among the 16 risk factors categorized under four different risk natures named ‘difficulties’, ‘changes’, ‘mistakes’, and ‘challenges’, the ‘challenges’ risk nature category is found to be the most significant one by the research findings, followed by ‘difficulties’, ‘mistakes’, and ‘changes’ risk natures. The results also highlight that ‘proper utilization of funds’, ‘complicated tasks’, and ‘convincing the customer with alternative technologies’ are the most significant risk factors. The study gives an insight into the possible risk factors in a software environment, along with their significance.
Smart learning environments have been considered as vital sources and essential needs since the spread of pandemic COVID 2019. COVID-19 era has drastically turned the conventional means of the educational system into ...
详细信息
Key-value stores are a key player of managing large-scale unstructured data in storage systems. Performance improvement of the LSM-tree structure has been extensively investigated, but current work primarily focuses o...
Key-value stores are a key player of managing large-scale unstructured data in storage systems. Performance improvement of the LSM-tree structure has been extensively investigated, but current work primarily focuses on cache structural optimization rather than hot-and-cold data properties. Moreover, existing and external memory components of LSM-tree rarely have uniform hot and cold attributions. In this study, we make use of the gradient and hierarchy mechanism to optimize the components catering for cache data. We design an adaptive data migration method according to hot and cold data in the cache. We reform and expand a gradient cold-hot data hierarchy (GDH) mechanism that replaces the in-memory data structure to address the problem of missing hot and cold data attributes. The hot and cold data are placed in separate cache partitions to store hot data as far the high hierarchy as possible, reducing $\mathrm{I}/\mathrm{O}$ accesses. When it comes to frequently accessed hot data, we advocate for a hotness-aware technique for data stored on a disk, where read-write performance and the cache hit rate are revamped. The experiment results reveal that our proposed GDH achieves a high cache-hit ratio and low access latency under a wide range of workloads.
Formal languages are in the core of models of computation and their behavior. A rich family of models for many classes of languages have been widely studied. Hyperproperties lift conventional trace-based languages fro...
详细信息
暂无评论