Purpose - To provide a view of Rob Kling's contribution to socio-technical studies of work. Design/methodology/approach - The five "big ideas" discussed are signature themes in Kling's own work in th...
详细信息
We measure the complexity of songs in the Million Song Dataset (MSD) in terms of pitch, timbre, loudness, and rhythm to investigate their evolution from 1960 to 2010. By comparing the Billboard Hot 100 with random sam...
详细信息
In recent years, there has been a surge in the development of 3D structure-based pre-trained protein models, representing a significant advancement over pre-trained protein language models in various downstream tasks....
详细信息
In recent years, there has been a surge in the development of 3D structure-based pre-trained protein models, representing a significant advancement over pre-trained protein language models in various downstream tasks. However, most existing structure-based pre-trained models primarily focus on the residue level, i.e., alpha carbon atoms, while ignoring other atoms like side chain atoms. We argue that modeling proteins at both residue and atom levels is important since the side chain atoms can also be crucial for numerous downstream tasks, for example, molecular docking. Nevertheless, we find that naively combining residue and atom information during pre-training typically fails. We identify a key reason is the information leakage caused by the inclusion of atom structure in the input, which renders residue-level pre-training tasks trivial and results in insufficiently expressive residue representations. To address this issue, we introduce a span mask pretraining strategy on 3D protein chains to learn meaningful representations of both residues and atoms. This leads to a simple yet effective approach to learning protein representation suitable for diverse downstream tasks. Extensive experimental results on binding site prediction and function prediction tasks demonstrate our proposed pre-training approach significantly outperforms other methods. Our code will be made public. Copyright 2024 by the author(s)
Modern electronic devices consist of a wide range of integrated circuits (ICs) from various manufacturers. Ensuring that an electronic device functions correctly requires verifying that its ICs and other component par...
详细信息
ISBN:
(纸本)9781728182445
Modern electronic devices consist of a wide range of integrated circuits (ICs) from various manufacturers. Ensuring that an electronic device functions correctly requires verifying that its ICs and other component parts are correct and legitimate. Towards this goal, we investigate using machine learning and computer vision to identify and verify integrated circuit packages using visual features alone. We propose a deep metric learning approach to learn a feature embedding to capture important visual features of the external packages of ICs. We explore several variations of Siamese networks for this task, and learn an embedding using a joint loss function. To evaluate our approach, we collected and manually annotated a large dataset of 6,387 IC images, and tested our embedding on three challenging tasks: (1) fine-grained retrieval, (2) fine-grained IC recognition, and (3) verification. We believe this to be among the first papers targeting the novel application of fine-grained IC visual recognition and retrieval, and hope it establishes baselines to advance research in this area.
The goal of this study is to find whether exposure to Deepfake videos makes people better at detecting Deepfake videos and whether it is a better strategy against fighting Deepfake. For this study a group of people fr...
详细信息
Thermography captures the temperature distribution of the human skin and is employed in various medical applications. Often it is useful to cross-reference the resulting thermograms with visual images of the patient, ...
详细信息
Thermography captures the temperature distribution of the human skin and is employed in various medical applications. Often it is useful to cross-reference the resulting thermograms with visual images of the patient, either to see which part of the anatomy is affected by a certain disease or to judge the efficacy of the treatment. An attractive approach to provide this information is to overlay the two image types and show a composite image to the clinician. Producing such an overlay however is a non-trivial task due to differences in image capturing conditions of the two modalities. In this paper we introduce an approach that produces accurate overlays of thermal and visual medical images. First unnecessary background information of the visual part are removed by an image segmentation step based on skin detection. The thermal image is then aligned through an intensity based image registration technique. Experimental results based on an set of visual-thermal image pairs demonstrate the effectiveness of the proposed approach
A linear system with a generalized frequency variable denoted by G(s) is a system which is given by replacing the variable ‘s’ in the original transfer function G0(s) with a rational function &...
详细信息
A linear system with a generalized frequency variable denoted by G(s) is a system which is given by replacing the variable ‘s’ in the original transfer function G0(s) with a rational function ‘φ(s)’, i.e., G(s) is defined by G0(φ(s)). A class of large-scale systems with decentralized information structures such as a homogeneous multi-agent systems, which has a common agent dynamics h(s)=1/φ(s), can be represented by this form. In this paper, we investigate fundamental properties of such a class of systems in terms of controllability, observability, and stability. Specifically, we first derive necessary and sufficient conditions that guarantee controllability and observability of the system G(s) based on those of subsystems G0(s) and h(s). Then we show that the Nyquist type stability criterion can be reduced to a linear matrix inequality (LMI) feasibility problem. Finally, we apply the results to stability analysis of large-scale systems in three different fields and confirm the effectiveness of the approach as a general framework which can unify variety of results for homogeneous multi-agent dynamical systems.
The university team has previously developed an X-ray imaging technique that combines binocular stereoscopic imagery with motion or kinetic depth effects (KDE). The technique is designed to enhance the screening of X-...
The university team has previously developed an X-ray imaging technique that combines binocular stereoscopic imagery with motion or kinetic depth effects (KDE). The technique is designed to enhance the screening of X-ray luggage at airport checkpoints. This paper presents initial investigations concerning the production of dual-energy X-ray (materials discriminated) multiple view sequences. The colour line-scan format images are produced by a novel image intensified X-ray system. This work is part of an ongoing collaborative research programme with the UK Home Office Scientific Development Branch (HOSDB) and US Department of Homeland Security (DHS) to develop and evaluate KDE X-ray technology.
Emerging technologies, such as Blockchain and the Internet of Things (IoT), have had an immense role in propelling the agricultural industry towards the fourth agricultural revolution. Blockchain and IoT can greatly i...
详细信息
With new database system development and new data types emerging, many applications are no longer using a monolithic, simple client/server structure, but using more than one types of database systems to store heteroge...
详细信息
暂无评论