False Detection (Positives and Negatives) in Object Detection

Object detection is a very important function of visual perception systems. Since the early days of classical object detection based on HOG to modern deep learning based detectors, object detection has improved in accuracy. Two stage detectors usually have higher accuracy than single stage ones. Both types of detectors use some form of quantization of the search space of rectangular regions of image. There are far more of the quantized elements than true objects. The way these bounding boxes are filtered out possibly results in the false positive and false negatives. This empirical experimental study explores ways of reducing false positives and negatives with labelled data.. In the process also discovered insufficient labelling in Openimage 2019 Object Detection dataset.

Impact of Data Quality on Deep Neural Network Training

It is well known that data is critical for training neural networks. Lot have been written about quantities of data required to train networks well. However, there is not much publications on how data quality effects convergence of such networks. There is dearth of information on what is considered good data ( for the task ). This empirical experimental study explores some impacts of data quality. Specific results are shown in the paper how simple changes can have impact on Mean Average Precision (mAP).

Addressing Design Issues in Medical Expert System for Low Back Pain Management: Knowledge Representation, Inference Mechanism, and Conflict Resolution Using Bayesian Network

Aiming at developing a medical expert system for low back pain management, the paper proposes an efficient knowledge representation scheme using frame data structures, and also derives a reliable resolution logic through Bayesian Network. When a patient comes to the intended expert system for diagnosis, the proposed inference engine outputs a number of probable diseases in sorted order, with each disease being associated with a numeric measure to indicate its possibility of occurrence. When two or more diseases in the list have the same or closer possibility of occurrence, Bayesian Network is used for conflict resolution. The proposed scheme has been validated with cases of empirically selected thirty patients. Considering the expected value 0.75 as level of acceptance, the proposed system offers the diagnostic inference with the standard deviation of 0.029. The computational value of Chi-Squared test has been obtained as 11.08 with 12 degree of freedom, implying that the derived results from the designed system conform the homogeneity with the expected outcomes. Prior to any clinical investigations on the selected low back pain patients, the accuracy level (average) of 73.89% has been achieved by the proposed system, which is quite close to the expected clinical accuracy level of 75%.

Lattice-Based Fuzzy Medical Expert System for Low Back Pain Management

Low Back Pain (LBP) is a common medical condition that deprives many individuals worldwide of their normal routine activities. In the absence of external biomarkers, diagnosis of LBP is quite challenging. It requires dealing with several clinical variables, which have no precisely quantified values. Aiming at the development of a fuzzy medical expert system for LBP management, this research proposes an attractive lattice-based knowledge representation scheme for handling imprecision in knowledge, offering a suitable design methodology for a fuzzy knowledge base and a fuzzy inference system. The fuzzy knowledge base is constructed in modular fashion, with each module capturing interrelated medical knowledge about the relevant clinical history, clinical examinations and laboratory investigation results. This approach in design ensures optimality, consistency and preciseness in the knowledge base and scalability. The fuzzy inference system, which uses the Mamdani method, adopts the triangular membership function for fuzzification and the Centroid of Area technique for defuzzification. A prototype of this system has been built using the knowledge extracted from the domain expert physicians. The inference of the system against a few available patient records at the ESI Hospital, Sealdah has been checked. It was found to be acceptable by the verifying medical experts.

Rough set based lattice structure for knowledge representation in medical expert systems: low back pain management case study

The aim of medical knowledge representation is to capture the detailed domain knowledge in a clinically efficient manner and to offer a reliable resolution with the acquired knowledge. The knowledge base to be used by a medical expert system should allow incremental growth with inclusion of updated knowledge over the time. As knowledge are gathered from a variety of knowledge sources by different knowledge engineers, the problem of redundancy is an important concern here due to increased processing time of knowledge and occupancy of large computational storage to accommodate all the gathered knowledge. Also there may exist many inconsistent knowledge in the knowledge base. In this paper, we have proposed a rough set based lattice structure for knowledge representation in medical expert systems which overcomes the problem of redundancy and inconsistency in knowledge and offers computational efficiency with respect to both time and space. We have also generated an optimal set of decision rules that would be used directly by the inference engine. The reliability of each rule has been measured using a new metric called credibility factor, and the certainty and coverage factors of a decision rule have been re-defined. With a set of decisions rules arranged in descending order according to their reliability measures, the medical expert system will consider the highly reliable and certain rules at first, then it would search for the possible and uncertain rules at later stage, if recommended by physicians. The proposed knowledge representation technique has been illustrated using an example from the domain of low back pain. The proposed scheme ensures completeness, consistency, integrity, non-redundancy, and ease of access.