Neural Architecture Search For Skin Cancer Detection

Neural Architectural Search (NAS) is a novel method capable of achieving state-of-the-art performance with limited computational resources and time. These coupled factors have resulted in its increasing popularity in many domains. NAS helps to discover an effective architecture for a given task. In parallel, learning through tests, a technique used in human learning aims at improving learning results: a chain of new assessments are conducted with increasing difficulty; the learner uses them to discover susceptible points, and those susceptible points are further addressed to pass the evaluation effectively. When applied in the case of learning in machines, this technique enhances their learning ability and is called Learning by passing tests(LPT). We propose to use the LPT technique in combination with NAS, particularly for Differentiable Architecture Search(DARTS), Progressive Differentiable Architecture Search(PDARTS) and, Partially Connected Differentiable Architecture Search(PCDARTS) to solve the medical challenge of Skin Cancer Classification. A bilevel optimization algorithm is formulated using LPT and is applied on the HAM10000 dataset and the Kaggle Skin Cancer: Malignant Vs. Benign dataset. Our LPT algorithm coupled with NAS can attain better performance than the traditional NAS methods and different state-of-the-art models for the given classification task.

Spatially and temporally resolved measurements of turbulent Rayleigh-Bénard convection by Lagrangian particle tracking of long-lived helium-filled soap bubbles

We present spatially and temporally resolved velocity and acceleration measurements of turbulent RayleighBénard convection spanning the whole volume (~ 1 m³) of a cylindrical sample with aspect ratio one. With the "Shake-The-Box" (STB) Lagrangian particle tracking (LPT) algorithm, we were able to instantaneously track up to 560,000 particles, corresponding to mean inter-particle distances down to 6 - 8 Kolmogorov lengths. We used the data assimilation scheme ‘FlowFit’, which involves continuity and Navier-Stokesconstraints, to map the scattered velocity and acceleration data on cubic grids, herewith recovering the smallest flow scales. Lagrangian and Eulerian visualizations reveal the dynamics of the large-scale circulation and its interplay with small scale structures, such as thermal plumes and turbulent background fluctuations. As a result, the complex time-dependent behavior of the LSC comprising azimuthal rotations, torsional oscillation and sloshing can be extracted from the data. Further, we found more seldom dynamic events, such as spontaneous reorientations of the LSC in the data from long-term measurements.

Approximate and robust bounded job start scheduling for Royal Mail delivery offices

Motivated by mail delivery scheduling problems arising in Royal Mail, we study a generalization of the fundamental makespan scheduling $$P||C_{\max }$$ P | | C max problem which we call the bounded job start scheduling problem. Given a set of jobs, each specified by an integer processing time $$p_j$$ p j , that have to be executed non-preemptively by a set of m parallel identical machines, the objective is to compute a minimum makespan schedule subject to an upper bound $$g\le m$$ g ≤ m on the number of jobs that may simultaneously begin per unit of time. With perfect input knowledge, we show that Longest Processing Time First (LPT) algorithm is tightly 2-approximate. After proving that the problem is strongly $${\mathcal {N}}{\mathcal {P}}$$ N P -hard even when $$g=1$$ g = 1 , we elaborate on improving the 2-approximation ratio for this case. We distinguish the classes of long and short instances satisfying $$p_j\ge m$$ p j ≥ m and $$p_j<m$$ p j < m , respectively, for each job j. We show that LPT is 5/3-approximate for the former and optimal for the latter. Then, we explore the idea of scheduling long jobs in parallel with short jobs to obtain tightly satisfied packing and bounded job start constraints. For a broad family of instances excluding degenerate instances with many very long jobs, we derive a 1.985-approximation ratio. For general instances, we require machine augmentation to obtain better than 2-approximate schedules. In the presence of uncertain job processing times, we exploit machine augmentation and lexicographic optimization, which is useful for $$P||C_{\max }$$ P | | C max under uncertainty, to propose a two-stage robust optimization approach for bounded job start scheduling under uncertainty aiming in a low number of used machines. Given a collection of schedules of makespan $$\le D$$ ≤ D , this approach allows distinguishing which are the more robust. We substantiate both the heuristics and our recovery approach numerically using Royal Mail data. We show that for the Royal Mail application, machine augmentation, i.e., short-term van rental, is especially relevant.

The Hybrid Genetic Algorithm of Single-Machine Materials Manufacturing Process with Periodic Maintenance

This paper investigates single machine materials manufacturing process with periodic maintenance, which has been proved as a NP-hard problem. Such that, combining the advantages of the classic List Scheduling (LS) algorithm, the Longest Processing Time first (LPT) algorithm and the genetic algorithm, two hybrid genetic algorithm (LS-GENETIC algorithm and LPT-GENETIC algorithm) were proposed to solve the problem. Computational results have shown that both LS-GENETIC algorithm and LPT-GENETIC algorithm perform satisfactorily.

WORST-CASE PERFORMANCE EVALUATION ON MULTIPROCESSOR TASK SCHEDULING WITH RESOURCE AUGMENTATION

We study the worst-case performance of approximation algorithms for the problem of multiprocessor task scheduling on m identical processors with resource augmentation, whose objective is to minimize the makespan. In this case, the approximation algorithms are given k (k ≥ 0) extra processors than the optimal off-line algorithm. For on-line algorithms, the Greedy algorithm and shelf algorithms are studied. For off-line algorithm, we consider the LPT (longest processing time) algorithm. Particularly, we prove that the schedule produced by the LPT algorithm is no longer than the optimal off-line algorithm if and only if k ≥ m - 2.