Abstract

We present a modular and multi-level framework for the differential diagnosis of malignant melanoma. Our framework integrates contextual information and evidence at the lesion, patient, and population levels, enabling decision-making at each level. We introduce an anatomic-site aware masked transformer, which effectively models the patient context by considering all lesions in a patient, which can be variable in count, and their site of incidence. Additionally, we incorporate patient metadata via learnable demographics embeddings to capture population statistics. Through extensive experiments, we explore the influence of specific information on the decision-making process and examine the tradeoff in metrics when considering different types of information. Validation results using the SIIM-ISIC 2020 dataset indicate including the lesion context with location and metadata improves specificity by 17.15% and 7.14%, respectively, while enhancing balanced accuracy. The code is available at https://github.com/narenakash/meldd. Keywords: Melanoma Diagnosis · Differential Recognition · Ugly Duckling Context · Patient Demographics · Evidence-Based Medicine.

Abstract

Drug design involves the process of identifying and designing molecules that bind well to a given receptor. A vital computational component of this process is the protein–ligand interaction scoring functions that evaluate the binding ability of various molecules or ligands with a given protein receptor binding pocket reasonably accurately. With the publicly available protein–ligand binding affinity data sets in both sequential and structural forms, machine learning methods have gained traction as a top choice for developing such scoring functions. While the performance shown by these models is optimistic, there are several hidden biases present in these data sets themselves that affect the utility of such models for practical purposes such as virtual screening. In this work, we use published methods to systematically investigate several such factors or biases present in these data sets. In our analysis, we highlight the importance of considering sequence, protein–ligand interaction, and pocket structure similarity while constructing data splits and provide an explanation for good protein-only and ligand-only performances in some data sets. Through this study, we provide to the community several pointers for the design of binding affinity predictors and data sets for reliable applicability.

Abstract

Afghanistan is situated close to the area where the Indian, Arabian, and Eurasian tectonic plates converge. The consequent seismic hazard causes the region to be repeatedly struck by major earthquakes. However, there is a lack of seismic instrumentation in the region, and only limited historical ground motions are available thus presenting a challenge for structural designers. Due to the absence of information and a database of ground motions, buildings in the region are often built without guidance from seismic codes. Consequently, the earthquakes in the region continue to cause enormous destruction to the built environment of the region. On 22 June 2022, the southeastern region of the country was struck by a major Mw 6.2 earthquake having a maximum modified Mercalli intensity of IX. In this study, synthetic

Abstract

Internet of Vehicles (IoV) is a wireless network, which employs well-established Internet protocols and networks to share information between vehicles, people, and infrastructure by utilising Vehicular Adhoc Networks (VANETs). IoV aims to increase road user safety and lower accident rates. It is one of the main components of an intelligent transportation system (ITS). ITS appears as the most crucial component since the cities in any country are evolving into digital civilisations as a result of the smart city concept, regardless of whether people are travelling within the city, to work, in school, or for other purposes. It can also be used to improve infrastructure utilisation and road safety (i.e., reduction in road accidents), in addition to enhancing traffic management and easing congestion. However, IoV-driven ITS is susceptible to several forms of attacks because of the insecure communication among the participating entities. We, therefore, propose a secure authentication protocol for IoV-driven ITS to stop these attacks from happening (in short, SAKP-ITS). Its resistance to a number of potential attacks is confirmed by the security analysis of the proposed SAKP-ITS. Additionally, SAKP-ITS is juxtaposed with other comparable competing methods put out in an IoV environment. Additionally, it has been found that SAKP-ITS outperforms competing schemes in terms of critical metrics like communication costs, computation costs, and security and functionality attributes. To test the effect of the proposed SAKP-ITS on the critical performance attributes, a practical implementation of SAKP-ITS

Abstract

Weak measurements introduced by Aharonov, Albert and Vaidman (AAV) can provide informations about the system with minimal back action. Weak values of product observables (commuting) or higher moments of an observable are informationally important in the sense that they are useful to resolve some paradoxes, realize strange quantum effects, reconstruct density matrices, etc. In this work, we show that it is possible to access the higher moment weak values of an observable using weak values of that observable with pairwise orthogonal post-selections. Although the higher moment weak values of an observable are inaccessible with Gaussian pointer states, our method allows any pointer state. We have calculated product weak values in a bipartite system for any given pure and mixed pre selected states. Such product weak values can be obtained using only the measurements of local weak values (which are defined as single system weak values in a multi- partite system). As an application, we use higher moment weak values and product weak values to reconstruct unknown quantum states of single and bipartite systems, respectively. Further, we give a necessary separability criteria for finite dimensional systems using product weak values and certain class of entangled states violate this inequality by cleverly choosing the product observables and the post selections. By such choices, positive partial transpose (PPT) criteria can be achieved for these classes of entangled states. Robustness of our method which occurs due to inappropriate choices of quantum observables and noisy post-selections is also discussed here. Our method can easily be generalized to the multi-partite systems

Abstract

The popularity of High-Frequency Trading (HFT) or algorithmic trading has surged in the last ten years, largely due to the exponential increase in computing power. However, while software solutions for HFT have become increasingly optimized over time, they are still plagued by network stack, and kernel-user space separation overheads. Order book construction is a crucial step in any HFT system, as it provides a market snapshot on which trading decisions must be based and executed. This paper proposes a simple linear data structure for tracking the order book and a hybrid binary-linear search algorithm to maintain the top bid and ask offers corresponding to marketdepth, on FPGAs. Our approach takes into account that most trading activity occurs on the top of the bid and offer sides. Through design analysis and experimentation, we demonstrate that our simple approach is scalable and practical, outperforming previous methods. Index Terms—HFT, order book, FPGA

Abstract

During the past decade promising methods for computational prediction of electron ionization mass spectra have been developed. The most prominent ones are based on quantum chemistry (QCEIMS) and machine learning (CFM-EI, NEIMS). Here we provide a threefold comparison of these methods with respect to spectral prediction and compound identification. We found that there is no unambiguous way to determine the best of these three methods. Among other factors, we find that the choice of spectral distance functions play an important role regarding the performance for compound identification.

Abstract

How do higher-order interactions influence the dynamical landscape of a network of the second-order phase oscillators? We address this question using three coupled Kuramoto phase oscillators with inertia under pairwise and higher-order interactions, in search of various collective states, and new states, if any, that show marginal presence or absence under pairwise interactions. We explore this small network for varying phase lag in the coupling and over a range of negative to positive coupling strength of pairwise as well as higher-order or group interactions. In the extended coupling parameter plane of the network we record several well-known states such as synchronization, frequency chimera states, and rotating waves that appear with distinct boundaries. In the parameter space, we also find states generated by the influence of higher-order interactions: The 2+1 antipodal point and the 2+1 phase-locked states. Our results demonstrate the importantance of the choices of the phase lag and the sign of the higher-order coupling strength for the emergent dynamics of the network. We provide analytical support to our numerical results.

Abstract

One of the most significant recent advances in technology is the advent of unmanned aerial vehicles (UAVs), i.e., drones. They have widened the scope of possible applications and provided a platform for a wide range of creative responses to a variety of challenges. The Internet of Drones (IoD) is a relatively new concept that has arisen as a consequence of the combination of drones and the Internet. The fifth-generation (5G) and beyond cellular networks (i.e., drones in networks beyond 5G) are promising solutions for achieving safe drone operations and applications. They may have many applications, like surveillance or urban areas, security, surveillance, retaliation, delivering items, smart farming, film production, capturing nature videos, and many more. Due to the fact that it is susceptible to a wide variety of cyber-attacks, there are certain concerns regarding the privacy and security of IoD communications. In this paper, a secure blockchain-enabled authentication key management framework with the big data analytics feature for drones in networks beyond 5G applications is proposed (in short, SBBDA-IoD). The security of SBBDA-IoD against multiple attacks is demonstrated through a detailed security analysis. The Scyther tool is used to perform a formal security verification test on the SBBDA-IoD’s security, confirming the system’s resistance to various potential attacks. A detailed comparative analysis has identified that SBBDA-IoD outperforms the other schemes by a significant margin. Finally, a real-world implementation of SBBDA-IoD is shown to evaluate its effect on several measures of performance.

Abstract

It is generally known that in a mixture of coupled active and inactive nonlinear oscillators, the entire system may stop oscillating and become inactive if the fraction of active oscillators is reduced to a critical value. This emerging phenomenon, called the “aging transition,” can be analytically predicted from the view point of cluster synchronization. One can question whether a model-free, data-driven framework based on neural networks could be used to foretell when such a system will cease oscillation. Here, we demonstrate how a straightforward ESN with trained output weights can accurately forecast both the temporal evaluation and the onset of collapse in coupled paradigmatic limit-cycle oscillators. In particular, we have demonstrated that an ESN can identify the critical fraction of inactive oscillators in a large all-to-all, small-world, and scale-free network when it is trained only with two nodes (one active and the other inactive) selected from three different pre-collapse regimes. We further demonstrate that ESN can anticipate aging transition of the network when trained with the mean-field dynamics of active and inactive oscillators.