False Positive RFID Detection Using Classification Models

Alfian, Ganjar; Syafrudin, Muhammad; Yoon, Bohan; Rhee, Jongtae

doi:10.3390/app9061154

Cited by 33 publications

(8 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recently, machine learning techniques were investigated in RFID systems both for localization purposes [ 31 , 32 ] and RFID Smart Gate implementation [ 33 , 34 , 35 ]. In [ 33 ], a single antenna architecture was proposed to determine the direction of people crossing an indoor RFID gate based on an Artificial Neural Network (ANN).…”

Section: Rfid Gatesmentioning

confidence: 99%

“…The obtained accuracy is higher than

. Machine Learning solutions were also employed to solve the issue of stray reads [ 34 ], where a 97.5% classification accuracy among actual RFID tags crossing the gate and static or other tags moving close to the gate without crossing it was achieved with a single antenna architecture. However, such a system does not allow the crossing direction estimation.…”

Section: Rfid Gatesmentioning

confidence: 99%

See 1 more Smart Citation

An Action Classification Method for Forklift Monitoring in Industry 4.0 Scenarios

Motroni

Buffi

Nepa

et al. 2021

Sensors

View full text Add to dashboard Cite

The I-READ 4.0 project is aimed at developing an integrated and autonomous Cyber-Physical System for automatic management of very large warehouses with a high-stock rotation index. Thanks to a network of Radio Frequency Identification (RFID) readers operating in the Ultra-High-Frequency (UHF) band, both fixed and mobile, it is possible to implement an efficient management of assets and forklifts operating in an indoor scenario. A key component to accomplish this goal is the UHF-RFID Smart Gate, which consists of a checkpoint infrastructure based on RFID technology to identify forklifts and their direction of transit. This paper presents the implementation of a UHF-RFID Smart Gate with a single reader antenna with asymmetrical deployment, thus allowing the correct action classification with reduced infrastructure complexity and cost. The action classification method exploits the signal phase backscattered by RFID tags placed on the forklifts. The performance and the method capabilities are demonstrated through an on-site demonstrator in a real warehouse.

show abstract

Section: Rfid Gatesmentioning

confidence: 99%

“…The obtained accuracy is higher than

Section: Rfid Gatesmentioning

confidence: 99%

An Action Classification Method for Forklift Monitoring in Industry 4.0 Scenarios

Motroni

Buffi

Nepa

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…It is insignificant to achieve a recall of 100% by detecting all tags in response to the model. As a result of this, the number of missed tags also important to perfect the model and the recall is calculated below [14]:…”

Section: Evaluation Metricsmentioning

confidence: 99%

“…Despite such improvements, the drawbacks of RFID still exist, namely the processing time to estimate the object from 3 readers [12] and the effect of other environmental frequencies at the floor [13] amongst others. To date, there are many investigations that have been carried out utilizing SVM for classification that SVM have the highest classification accuracy among the others [14][15][16].…”

Section: Introductionmentioning

confidence: 99%

Automatic Identification and Categorize Zone of RFID Reading in Warehouse Management System

Choong

Nasir

Majeed

et al. 2020

Lecture Notes in Mechanical Engineering

View full text Add to dashboard Cite

Radio Frequency Identification (RFID) technology has improved the operational efficiency and process flow in the distribution of warehouse management system (WMS) around the globe. Nonetheless, a moving or missing tag as well as known and unknown tag's location that may occur in the detection could reduce the efficiency of process flow. This study aims at identifying the location of goods in between two RFID reading zones by means of machine learning, particularly Support Vector Machine (SVM). A total of seven statistical features are extracted from the received signal strength (RSS) value from the raw RFID readings. SVM classifier are evaluated by considering the combination of different statistical features namely COMBINE to produce a more effective classification in comparison to individual statistical feature. The performance of the classifier demonstrated a classification accuracy of approximately 94% by considering all features whereas the performance of the classifier by considering individual features alone is below than 90%. This preliminary study establishes the applicability of the proposed automatic identification is able to provide the management of goods as well as supply chain reasonably well without human intervention.

show abstract

“…Importantly, this will constrain the power consumption only to the active processor type. This, however, was only possible if we were first able to classify the assembly language codes according to their suitable processor variant, using some classification method [16].…”

Section: Introductionmentioning

confidence: 99%

An Optimization Framework for Codes Classification and Performance Evaluation of RISC Microprocessors

et al. 2019

View full text Add to dashboard Cite

Pipelines, in Reduced Instruction Set Computer (RISC) microprocessors, are expected to provide increased throughputs in most cases. However, there are a few instructions, and therefore entire assembly language codes, that execute faster and hazard-free without pipelines. It is usual for the compilers to generate codes from high level description that are more suitable for the underlying hardware to maintain symmetry with respect to performance; this, however, is not always guaranteed. Therefore, instead of trying to optimize the description to suit the processor design, we try to determine the more suitable processor variant for the given code during compile time, and dynamically reconfigure the system accordingly. In doing so, however, we first need to classify each code according to its suitability to a different processor variant. The latter, in turn, gives us confidence in performance symmetry against various types of codes—this is the primary contribution of the proposed work. We first develop mathematical performance models of three conventional microprocessor designs, and propose a symmetry-improving nonlinear optimization method to achieve code-to-design mapping. Our analysis is based on four different architectures and 324,000 different assembly language codes, each with between 10 and 1000 instructions with different percentages of commonly seen instruction types. Our results suggest that in the sub-micron era, where execution time of each instruction is merely in a few nanoseconds, codes accumulating as low as 5% (or above) hazard causing instructions execute more swiftly on processors without pipelines.

show abstract

False Positive RFID Detection Using Classification Models

Cited by 33 publications

References 52 publications

An Action Classification Method for Forklift Monitoring in Industry 4.0 Scenarios

An Action Classification Method for Forklift Monitoring in Industry 4.0 Scenarios

Automatic Identification and Categorize Zone of RFID Reading in Warehouse Management System

An Optimization Framework for Codes Classification and Performance Evaluation of RISC Microprocessors

Contact Info

Product

Resources

About