ForEx++: A New Framework for Knowledge Discovery from Decision Forests

Adnan, Nasim; Islam, Zahidul

doi:10.3127/ajis.v21i0.1539

Cited by 19 publications

(17 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the arena of software development, it will also be tremendously useful to issue any certificate or approval letter. Detection of falsified documents can also be augmented using several data mining algorithms [16], [17], [18], [19].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

An Innovative Approach of Verification Mechanism for both Electronic and Printed Documents

Haque¹,

Adnan²,

Kabir³

et al. 2020

IJACSA

View full text Add to dashboard Cite

Documents are inevitably relevant in our day-today life. Forgery of document could have severe repercussions including financial losses, misjudgments, damage of respect, goodwill, etc. Hence, documents need to be secured from threats such as counterfeiting, falsification, tempering etc., and there should be an easy way of verification about the originality of documents. There are several existing methods for ensuring authenticity and integrity with modern technologies like the block chain, Digital Signature, etc. Most of the methods are not appropriate for public usage instantly due to their intricacy, excessive costing, and implementation problem for which the easy approach of verification is yet not available for mass people. In this situation, a method of document verification has been proposed in this paper which intends to provide (i) authenticity, (ii) integrity, (iii) availability, and (iv) non-repudiation. The proposed method will serve the purpose of mass people as it has no licensing fee, easily implementable and effortlessly useable for both electronic and printed documents. It is worth to mention that the proposed method will provide a mechanism to confirm the originality of the document using only a Smartphone in no time.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Four significant points have been covered here as (i) authenticity, (ii) integrity, (iii) non-repudiation, and (iv) availability. Authenticity is the assurance that a message, transaction, or other exchange of information is from the source it claims to be from [18]. Integrity refers to the document has not been distorted by anyone.…”

Section: Ensuring Securitymentioning

confidence: 99%

An Innovative Approach of Verification Mechanism for both Electronic and Printed Documents

Haque¹,

Adnan²,

Kabir³

et al. 2020

IJACSA

View full text Add to dashboard Cite

show abstract

“…the set of all decision nodes within each decision tree of an ensemble. Examples in the literature include: DefragTrees [30], Forex++ [31], RF+HC [32], inTrees [33], RuleFit [34], Brute [35]. All these methods generate a cascading rule list (CRL) as a simpler, surrogate of the original classification model.…”

Section: Xai and Interpretable Models -Current State Of The Artmentioning

confidence: 99%

“…Adnan and Islam [31] uses a novel algorithm to simplify an existing tree ensemble. The compact, surrogate model is a rule list that can be used for classifying unseen instances.…”

Section: Related Workmentioning

confidence: 99%

Ada-WHIPS: explaining AdaBoost classification with applications in the health sciences

Hatwell

Gaber

Azad

2020

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background Computer Aided Diagnostics (CAD) can support medical practitioners to make critical decisions about their patients’ disease conditions. Practitioners require access to the chain of reasoning behind CAD to build trust in the CAD advice and to supplement their own expertise. Yet, CAD systems might be based on black box machine learning models and high dimensional data sources such as electronic health records, magnetic resonance imaging scans, cardiotocograms, etc. These foundations make interpretation and explanation of the CAD advice very challenging. This challenge is recognised throughout the machine learning research community. eXplainable Artificial Intelligence (XAI) is emerging as one of the most important research areas of recent years because it addresses the interpretability and trust concerns of critical decision makers, including those in clinical and medical practice. Methods In this work, we focus on AdaBoost, a black box model that has been widely adopted in the CAD literature. We address the challenge – to explain AdaBoost classification – with a novel algorithm that extracts simple, logical rules from AdaBoost models. Our algorithm, Adaptive-Weighted High Importance Path Snippets (Ada-WHIPS), makes use of AdaBoost’s adaptive classifier weights. Using a novel formulation, Ada-WHIPS uniquely redistributes the weights among individual decision nodes of the internal decision trees of the AdaBoost model. Then, a simple heuristic search of the weighted nodes finds a single rule that dominated the model’s decision. We compare the explanations generated by our novel approach with the state of the art in an experimental study. We evaluate the derived explanations with simple statistical tests of well-known quality measures, precision and coverage, and a novel measure stability that is better suited to the XAI setting. Results Experiments on 9 CAD-related data sets showed that Ada-WHIPS explanations consistently generalise better (mean coverage 15%-68%) than the state of the art while remaining competitive for specificity (mean precision 80%-99%). A very small trade-off in specificity is shown to guard against over-fitting which is a known problem in the state of the art methods. Conclusions The experimental results demonstrate the benefits of using our novel algorithm for explaining CAD AdaBoost classifiers widely found in the literature. Our tightly coupled, AdaBoost-specific approach outperforms model-agnostic explanation methods and should be considered by practitioners looking for an XAI solution for this class of models.

show abstract

“…Scalable Information Systems 09 2017 -12 2017 | Volume 4 | Issue 15 | e2 algorithms available, for instance, SysFor [68], Forest PA [69] and ForEx++ [70] and these algorithms perfectly doing the job of classification, future prediction, and knowledge discovery. By modifying these algorithms, parallel processing can be employed to the Big Data as well as these can also be applied for knowledge discovery, classification and future prediction from Big Data.…”

Section: Eai Endorsed Transactions Onmentioning

confidence: 99%

Access methods for Big Data: current status and future directions

Rashid

2017

ICST Transactions on Scalable Information Systems

View full text Add to dashboard Cite

Heterogeneity, size, timeliness, difficulty & confidentiality problems with Big Data hinder advancement at all phases of the channel that can create value from data. Data analysis, organization, retrieval & modeling are initial challenges for Big Data. Data investigation is a clear traffic jam in many applications, both due to lack of scalability of the core algorithms and due to the difficulty of the data that needs to be analyzed. Despite this, the appearance of the results and its understanding by non-technical experts is vital to extracting actionable knowledge. To defeat these, there is a need for novel architectures, techniques, algorithms & analytics to deal with it as well as to retrieve the value and unseen knowledge. Further, we need to build up efficient and optimized access methods for countless reasons such as velocity of Big Data. In this article, we present a brief overview of the current status of access methods for Big data and discuss a few promising research directions.

show abstract

ForEx++: A New Framework for Knowledge Discovery from Decision Forests

Cited by 19 publications

References 36 publications

An Innovative Approach of Verification Mechanism for both Electronic and Printed Documents

An Innovative Approach of Verification Mechanism for both Electronic and Printed Documents

Ada-WHIPS: explaining AdaBoost classification with applications in the health sciences

Access methods for Big Data: current status and future directions

Contact Info

Product

Resources

About