Author name cluster

Gonen Singer

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

1 author row

EAAI Journal 2024 Journal Article

Resource allocation in ordinal classification problems: A prescriptive framework utilizing machine learning and mathematical programming

Lior Rabkin
Ilan Cohen
Gonen Singer

Ordinal classification tasks that require the allocation of limited resources are prevalent in various real-world scenarios. Examples include assessing disease severity in the context of medical resource allocation and categorizing the quality of machines as good, medium, or bad to schedule maintenance treatment within capacity constraints. We propose a comprehensive analytic framework for scenarios that, in addition to including ordinal classification problems, also have constraints on the number of classified samples of classes due to resource limitations. The framework uses a probability matrix generated by a trained ordinal classifier as the input for an optimization model with a minimum misclassification cost objective and resource allocation constraints. We illustrated the equivalence between the formulation of the resource allocation problem into samples and the transportation problem, enabling the utilization of established transportation heuristics for our solution. To demonstrate the effectiveness and applicability of the framework, we applied it with various ordinal machine-learning models to both tabular data and image datasets. The proposed framework performs significantly better than the alternative common approach of using non-ordinal classifiers, achieving an average cost reduction of 1% with ordinal decision tree-based models and 4. 4% with ordinal neural networks. Our results show that the proposed framework can provide an effective limited-resource allocation for ordinal classification problems. Our code is available at https: //github. com/liorRabkin/hybrid-cost-sensitive-ml-optimization.

Details DOI

EAAI Journal 2023 Journal Article

An adaptive machine learning algorithm for the resource-constrained classification problem

Danit Abukasis Shifman
Izack Cohen
Kejun Huang
Xiaochen Xian
Gonen Singer

Resource-constrained classification tasks are common in real-world applications such as allocating tests for disease diagnosis, hiring decisions when filling a limited number of positions, and defect detection in manufacturing settings under a limited inspection budget. Typical classification algorithms treat the learning process and the resource constraints as two separate and sequential tasks. We develop an adaptive learning approach that considers resource constraints and learning jointly by iteratively fine-tuning misclassification costs. Via a structured experimental study using a publicly available data set, we evaluate a decision tree classifier that utilizes the proposed approach. The adaptive learning approach performs significantly better than alternative approaches, especially for difficult classification problems in which the performance of common approaches may be unsatisfactory. The suggested approach reaches similar classification decisions for different costs, thus it may be useful when misclassification costs are not known precisely or are costly to achieve. We envision the suggested learning approach as an important addition to the repertoire of techniques for handling resource-constrained classification problems.

Details DOI

EAAI Journal 2021 Journal Article

A framework for smart control using machine-learning modeling for processes with closed-loop control in Industry 4.0

Gonen Singer
Yuval Cohen

Anomaly detection for processes with closed-loop control has become a widespread need in Industry 4. 0 shop floors. A major challenge in monitoring such processes arises from the unknown dependencies among monitored observations, as these dependencies may change dynamically and with high frequency. Motivated by these considerations, a novel framework is proposed for self-adaptive smart control using adaptive machine-learning models. On the one hand, data driven machine-learning algorithms can deal with patterns and dependencies within the data that were not necessarily known in advance. On the other hand, the recurrent self-adaptive mechanism triggers the need to switch to a new type of machine-learning model to capture and reflect new dependencies among monitored observations resulting from changes in the process. The proposed framework and the associated case study described in this paper could serve as a firm basis for implementing self-adaptive smart process control in Industry 4. 0 shop-floor processes with closed-loop control.

Details DOI