this study explores the application of machine learning methodologies in drug repurposing for brain cancer therapy, focusing on targeting the epidermal growth factor receptor (EGFR). Our approach involved the developm...
详细信息
ISBN:
(纸本)9798350364200;9798350364194
this study explores the application of machine learning methodologies in drug repurposing for brain cancer therapy, focusing on targeting the epidermal growth factor receptor (EGFR). Our approach involved the development of a predictive model to estimate the half-maximal inhibitory concentration (IC50) values of compounds against EGFR, leveraging existing biological activity data of known EGFR inhibitors and molecular structure descriptors. the constructed model exhibited efficacy in predicting the inhibitory activity of compounds against EGFR. Subsequent screening of a library of known drugs using the predictive model led to the identification of several compounds with low predicted IC50 values, indicating their potential as drug candidates for further investigation. this study underscores the utility of integrating machine learning techniques into drug repurposing endeavours, offering a pragmatic approach to identifying potential therapeutic options for brain cancer treatment.
the proceedings contain 15 papers. the special focus in this conference is on Innovation and New Trends in Information Technology. the topics include: intelligent Multi-agent Distributed System for Improving and Secur...
ISBN:
(纸本)9783031473654
the proceedings contain 15 papers. the special focus in this conference is on Innovation and New Trends in Information Technology. the topics include: intelligent Multi-agent Distributed System for Improving and Secure Travel Procedures: Al-Karama-King Hussein Bridge Study Case;a New Approach for the Analysis of Resistance to Change in the Digital Transformation Context;augmented data Warehouses for Value Capture;a Parallel Processing Architecture for Querying Distributed and Heterogeneous data Sources;comprehensive data Life Cycle Security in Cloud Computing: Current Mastery and Major Challenges;systematic Mapping Study on Applications of Deep learning in Stock Market Prediction;exploring the Knowledge Distillation;intelligent Traffic Congestion and Collision Avoidance Using Multi-agent System Based on Reinforcement learning;BERT for Arabic NLP Applications: Pretraining and Finetuning MSA and Arabic Dialects;VacDist MAS for Covid-19 Vaccination Distribution: Palestine as a Case Study;Smart E-Waste Management System Utilizing IoT and DL Approaches;towards a Platform for Higher Education in Virtual Reality of engineering Sciences;Robust intelligent Control for Two Links Robot Based ACO Technique.
this study introduces a novel framework for the automatic two-dimensional tracking of padel games using monocular recordings. By integrating advanced Computer Vision and Deep learning techniques, our algorithm detects...
详细信息
ISBN:
(纸本)9783031777301;9783031777318
this study introduces a novel framework for the automatic two-dimensional tracking of padel games using monocular recordings. By integrating advanced Computer Vision and Deep learning techniques, our algorithm detects and tracks players, the court, and the ball. through homography, we accurately project detected player positions onto a two-dimensional court, enabling comprehensive tracking throughout the game. We tested the proposed algorithm using amateur video recordings of padel games found in literature. this approach remains user-friendly, cost-effective, and adaptable to various camera angles and lighting conditions. this makes it accessible to both amateur and professional players and coaches, providing a valuable tool for performance analysis. Additionally, the proposed framework holds potential for adaptation to other sports with minimal modifications, further broadening its applicability.
In this paper, we use deep reinforcement learning to enable connected and automated vehicles (CAVs) to drive in a intersection with human-driven vehicles. the multi-agent deep deterministic policy gradient (MADDPG) al...
详细信息
When delivered to the market, machine learning models face new data which are possibly subject to novel characteristics - a phenomenon known as concept drift. As this might lead to performance degradation, it is neces...
详细信息
ISBN:
(纸本)9783031777301;9783031777318
When delivered to the market, machine learning models face new data which are possibly subject to novel characteristics - a phenomenon known as concept drift. As this might lead to performance degradation, it is necessary to detect such drift and, if required, adapt the model accordingly. While a variety of drift detection and adaptation methods exists for standard vectorial data, a suitable treatment of text data is less researched. In this work we present a novel approach which detects and explains drift in text data based on their representation via transformer embeddings. In a nutshell, the method generates suitable statistical features from the original distribution and the possibly shifted variation. Based on these representations, drift scores can be assigned to individual data points, allowing a visualization and human-readable characterization of the type of drift. We demonstrate the approach's effectiveness in reliably detecting drift in several experiments.
the needle selector is a key component of the circular weft knitting machine to realize the pattern knitting, to ensure that the jacquard pattern on the fabric is complete and smooth. Due to its fast movement frequenc...
详细信息
ISBN:
(纸本)9798350364200;9798350364194
the needle selector is a key component of the circular weft knitting machine to realize the pattern knitting, to ensure that the jacquard pattern on the fabric is complete and smooth. Due to its fast movement frequency, conventional detection methods need to consume a lot of time and energy to process the data, and it is difficult to detect the movement of the knife heads effectively by human identification. In this study, GAN and convolutional neural network are mainly used to realize the detection of abnormal motion of the knife heads of the needle selector. the model not only improves the robustness and accelerates the convergence speed of the GAN model, but also realizes the data augmentation and solves the problem of insufficient abnormal data. the improved model achieves an average correct detection rate of 98.11% for three types of knife heads motion anomalies.
Federated learning (FL) is a prominent method in machine learning, that ensures privacy by enabling distributed devices to collaboratively learn a shared model without exchanging local data. this paper provides a comp...
详细信息
ISBN:
(纸本)9783031777370;9783031777387
Federated learning (FL) is a prominent method in machine learning, that ensures privacy by enabling distributed devices to collaboratively learn a shared model without exchanging local data. this paper provides a comparative analysis of various FL algorithms implemented on the Smart Python Agent Development Environment (SPADE) framework. We focus on evaluating the performance, scalability, and resilience of these algorithms across different network setups and data distribution scenarios. Our results highlight the differential impacts of decentralized versus centralized approaches, particularly under non-IID data conditions, common in real-world applications. By leveraging SPADE agents and consensus algorithms, this study not only tests algorithmic efficiency and system robustness but also explores advanced strategies like asynchronous updates and coalition-based learning, which show promise in enhancing model accuracy and reducing communication overhead.
Obstacle detection systems face challenges related to the Catastrophic forgetting problem, where old obstacles may be misclassified when training new unseen obstacles. Re-training a model from scratch for every new ob...
详细信息
Sign language recognition and understanding are challenging tasks for many people who are not familiar with it, which limits communication between deaf-mute people and others. the system presented in this paper lowers...
详细信息
ISBN:
(纸本)9783031777370;9783031777387
Sign language recognition and understanding are challenging tasks for many people who are not familiar with it, which limits communication between deaf-mute people and others. the system presented in this paper lowers the communication barrier, introducing an automatic translation layer that facilitates sign language understanding. the system uses a deep-learning model for sign language detection and a separate library for hand joint mapping. the application's architecture was designed to allow users to access the system from desktop and mobile devices. the model's results revealed an 82% accuracy, and after several tweaks on the activation function in our tests, we achieved perfect classification in our real word tests. the results of the system offered excellent accuracy, and its usability lowers the communication barrier between people, providing flexibility as the application is available for any device with a browser.
Hyperparameter Optimization (HPO) plays a significant role in enhancing the performance of machine learning models. However, as the size and complexity of (deep) neural architectures continue to increase, conducting H...
详细信息
ISBN:
(纸本)9783031777301;9783031777318
Hyperparameter Optimization (HPO) plays a significant role in enhancing the performance of machine learning models. However, as the size and complexity of (deep) neural architectures continue to increase, conducting HPO has become very expensive in terms of time and computational resources. Existing methods that automate this process still demand numerous evaluations to find the optimal hyperparameter configurations. In this paper, we present a novel approach based on model-based reinforcement learning to effectively improve sample efficiency while minimizing resource consumption. We formulate the HPO task as a Markov decision process and develop a predictive dynamics model for efficient policy optimization. Additionally, we employ the Deep Sets framework to encode the state space, which is then leveraged in meta-learning for transfer of knowledge across multiple datasets, enabling the model to quickly adapt to new datasets. Empirical studies demonstrate that our approach outperforms alternative techniques on publicly available datasets in terms of sample efficiency and accuracy.
暂无评论