Battery-Free Pork Freshness Estimation Based on Colorimetric Sensors and Machine Learning
Round 1
Reviewer 1 Report
Dear authors,
I am sorry to be so unkind and unpolite with you but the submitted manuscript is definitely unacceptable. The introduction makes no sense at all, some sentences have been copied and pasted without any logical flow, the references are missing, the treated topics are unrelated the one to the others and, at a certain point, you start speaking of you device without having provided the necessary background before.
EVEN pH IS WRITTEN IN THE WRONG WAY, WHICH IS UNACCEPTABLE FOR AN INTERNATIONAL JOURNAL!!!
Moving on, the classical sections that must be provided in a manuscript (2-Materials and methods, 3-Results and Discussion, 4-Conclusion) are not present but you decide to present your data as you prefer, which makes very difficult the reading. Last but not least, it was very hard to understand the meaning of your work, with no background provided and personal manuscript division.
Finally, the paper is definitely too long therefore consider to summarise or add some information in the SI.
In the present form the manuscript is far from being acceptable for publication on an international peer-review journal
Author Response
#1.1
The introduction makes no sense at all, some sentences have been copied and pasted without any logical flow, the references are missing, the treated topics are unrelated the one to the others and, at a certain point, you start speaking of you device without having provided the necessary background before.
- Reply) The introduction has been revised for easier comprehension. A missing reference has been added in the middle of the introduction. Here is the sentence with the added reference.
“Currently, researchers are exploring an approach to detecting the state of a target object, and the development of a color measurement system using NFC technology is fascinating [7,8,14].”
#1.2
EVEN pH IS WRITTEN IN THE WRONG WAY, WHICH IS UNACCEPTABLE FOR AN INTERNATIONAL JOURNAL!!!
- Reply) We have corrected the terminology as per your guidance, using the accurate notation. We apologize for any inconvenience caused by the notation error.
#1.3
Moving on, the classical sections that must be provided in a manuscript (2-Materials and methods, 3-Results and Discussion, 4-Conclusion) are not present but you decide to present your data as you prefer, which makes very difficult the reading. Last but not least, it was very hard to understand the meaning of your work, with no background provided and personal manuscript division.
- Reply) We have changed the title of Section 3 from "Device and Method" to "Materials and Methods." Additionally, we have revised the grammar throughout the paper, including the introduction, to make it easier to understand.
#1.4
Finally, the paper is definitely too long therefore consider to summarise or add some information in the SI.
- Reply) We have revised the sentences in the introduction and other sections to be concise and easy to understand. Furthermore, we have made the summary portion of the introduction clearer. The revised summary portion is as follows:
“The primary contributions of this study can be summarized as follows:
- Design of a compact sensor tag as a key component for monitoring the freshness of pork.
- Design of a system that can harvest RF energy, simplifying the process of designing and configuring the system.
- Design of a printed collinear antenna operating in the UHF band of 915 MHz, with the system's efficiency enhanced by using an antenna with high RF energy harvesting efficiency.
- Design of a machine learning algorithm for detecting meat quality, with the 1D-convolutional neural network (CNN) model outperforming other machine learning models.
- Development of an early warning system that prevents meat poisoning due to improper storage and exposure to warm temperatures during summer.
Section II presents an overview of smart sensor tags based on RF energy harvesting, and outlines the machine learning models used in the freshness monitoring system based on the presented sensor tag. In Section III, the content of RF harvesting experiments using the proposed system is described, along with the antenna design approach and sensor module for RF energy harvesting. Section IV explains the RF energy harvesting experiments.”
Thank you for providing precise guidance on the parts of the paper that need to be revised.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
The title of this work is unclear and misleading. The colorimetric sensor that is being used is the pork itself. Both the technical and non-technical language in this paper is also misleading. The use of ‘tag’ suggests that the sensor is embedded in the meat. What is described here is consistent with a smart camera or smart image sensor, which is a device that incorporates an image sensor, vision system (machine learning) and a communication interface. The technique itself is referred to as computer vision. These things need to be clear in the abstract and introduction.
While I was eventually able to follow the introduction, the grammar and word choice made things difficult to read i.e. “smells like it is sting”, “packaging gets plunged”, “the smell is the most visible factor”, “the meat is nosed”. Running this through an AI chatbot (ie ChatGPT) to clean up the language would be very beneficial.
The introduction doesn’t properly address bacterial growth, which is the primary concern for meat products. Batches are regularly tested before shipment to look for things like e-coli, which is also not mentioned in the text. How does bacterial or mold growth influence the color?
Computer vision has been extensively used to determine meat freshness, with many references on pork freshness. Furthermore, the use of energy harvesting is not a new one and should be more extensively cited. While it appears that the combination of these factors (machine learning, energy harvesting, communications protocol) has not been previously published, the way the paper is written is not properly rooted in prior work in these areas.
Author Response
#2.1
The title of this work is unclear and misleading. The colorimetric sensor that is being used is the pork itself. Both the technical and non-technical language in this paper is also misleading. The use of ‘tag’ suggests that the sensor is embedded in the meat. What is described here is consistent with a smart camera or smart image sensor, which is a device that incorporates an image sensor, vision system (machine learning) and a communication interface. The technique itself is referred to as computer vision. These things need to be clear in the abstract and introduction.
- Reply) We appreciate your insightful feedback and keen perspective. The RGB sensor used for the measurements consists of a 3 x 4 array of photodiodes. In comparison, the widely used Galaxy Note FE camera supports 12 million pixels, with each pixel comprising two photodiodes. We measure RGB values through an RGB sensor with a much lower resolution than cameras and use this data to classify the state. Instead of employing computer vision techniques such as OpenCV, we use general machine learning models like LSTM and MLP. We have clarified this in the abstract to avoid any confusion. Here is the revised portion of the abstract:
“The proposed smart sensor tag includes a red, green, and blue sensor that detects changes in the freshness of meat.”
#2.2
While I was eventually able to follow the introduction, the grammar and word choice made things difficult to read i.e. “smells like it is sting”, “packaging gets plunged”, “the smell is the most visible factor”, “the meat is nosed”. Running this through an AI chatbot (ie ChatGPT) to clean up the language would be very beneficial.
- Reply) We have improved the readability of the introduction. Grammatical revisions have been made throughout the paper, including the introduction, to enhance overall readability.
#2.3
The introduction doesn’t properly address bacterial growth, which is the primary concern for meat products. Batches are regularly tested before shipment to look for things like e-coli, which is also not mentioned in the text. How does bacterial or mold growth influence the color?
- Reply) There are a few studies conducted in controlled environments using refrigerated pork samples. However, these studies only confirm that the growth of bacteria or mold causes color changes, without providing specific details on how the color changes. Our research simultaneously measures and presents the changes in red color and gas values over time. Based on this paper, we anticipate numerous follow-up studies. In Section 5.3, we have added the content of the existing literature on the results of the gas sensor measurements from the pork samples. The added content is as follows:
“The results of these experiments are similar to those of previous studies [11,14,16]. Alt-hough the measured temperature and environment are different, we can confirm that the flow of sensor data changing over time is similar.”
#2.4
Computer vision has been extensively used to determine meat freshness, with many references on pork freshness. Furthermore, the use of energy harvesting is not a new one and should be more extensively cited. While it appears that the combination of these factors (machine learning, energy harvesting, communications protocol) has not been previously published, the way the paper is written is not properly rooted in prior work in these areas.
- Reply) We have added reference papers on energy harvesting in Section 4.1. The reference numbers are 38-41. We have reviewed the paper writing style and revised the sections explaining the introduction and overview. In accordance with traditional conventions, we have changed the title of Section 3 to "Materials and Methods."
Thank you for pointing out areas that could cause confusion. By addressing these points, we believe the paper has been improved and strengthened.
Author Response File: Author Response.pdf
Reviewer 3 Report
*The authors have done a very impressive academic study.
*The simulated and measured RF RF scavenging power is given in Figure 6. While these power converge at some points, they diverge at others. The reason for this situation should be explained.
*The appearance of Figure 11 and Figure 12 should be improved.
*The results should be compared with academic studies in the literature.
Author Response
#3.1
The simulated and measured RF, RF scavenging power is given in Figure 6. While these power converge at some points, they diverge at others. The reason for this situation should be explained.
- Reply) We have updated the figure with the filtered version. We have also provided a supplementary explanation for the differences between the simulation and actual measurements. The added content is as follows:
“Figure 6 shows a decrease in power as the distance from the transmitter increases, resulting in a negative slope. To minimize the effects of noise and variations in received power due to environmental factors, a moving average filter can be applied to the power measurement data. This filter calculates the average power over a moving window of a certain size, helping to smooth out fluctuations in the measured power. The resulting graph will depict the power received by the receiver after filtering with the moving average filter. Although the graph will still exhibit a negative slope as the distance from the transmitter increases, the variations in the measured power will be reduced, yielding a smoother curve.”
#3.2
The appearance of Figure 11 and Figure 12 should be improved.
- Reply) We have improved the appearance of Figures 11 and 12. Thank you for paying attention to even the smallest details.
#3.3
The results should be compared with academic studies in the literature.
- Reply) To enhance the credibility of the result analysis for Figure 11, we have compared it with the findings of previous studies by citing them. The additional explanatory sentence is as follows:
“The results of these experiments are similar to those of previous studies [11,14,16]. Although the measured temperature and environment are different, we can confirm that the flow of sensor data changing over time is similar.”
Thank you for pointing out an important aspect to be addressed.
Author Response File: 
Author Response.docx
Round 2
Reviewer 1 Report
Up to my the paper is still unsuitable, the authors just did some minimal changes, especially in the sections without really revising
-Materials and Methods means describe the experimental procedures you followe
-Results and Discussion means describe and comment the results you acquired
You just changed the titles with no sense and without modifying the content
Author Response
#1.1
Materials and Methods means to describe the experimental procedures you follow.
- Reply) In Section "3. Material and Method", we have detailed and summarized the experimental procedure. The added sentences are as follows.
“The freshness of pork is measured by the data generated by the decay over time inside a closed box. The smart sensor tag system consists of two types of sensors: color sensor (TCS34725, ams-OSRAM) and air quality sensor (CCS811, ams-OSRAM). The sensor data is continuously measured every 5 minutes for 5 days in an indoor environment with an average temperature of 26°C. The color sensor can discriminate the state up to 15 cm from the measurement target with 5 cm measurement increments. The freshness was measured at 13 cm from the sample. Additionally, the color sensor value was used to establish a criterion for the change in the state of pork according to the HSV data. The proposed sensor tag system's RGB measurements of pork were converted into data through the HSV color model, generating a training dataset for machine learning. Figure 10 shows the monitoring of pork using the smart sensor.”
#1.2
Results and Discussion means describe and comment on the results you acquired
- Reply) In "conclusion", we have added explanations for the results obtained from the experiment. This is the newly added sentence.
" The proposed smart sensor tag system aims to observe the gas and discoloration data produced by the decomposition of pork, and based on the measured data, its purpose is to classify the freshness level. We have developed an RF energy harvesting-based monitoring system to monitor the storage condition of pork at room temperature during the humid and hot month of August, which is prone to frequent cases of food poisoning accidents, and other humid summer months. Pork stored in a mart retains oxygen in the oxy-myoglobin state, resulting in a bright red color. Even during refrigerated storage, myoglobin gradually changes to met-myoglobin, progressively turning brown. In particular, when the pork is exposed to room temperature due to reasons such as transportation after purchase, it decays rapidly, and the browning process accelerates accordingly. Pork stored at room temperature reaches a state of decay within the first 6 hours of measurement initiation. The data measured by the proposed system includes the discoloration and changes in gas levels that occur with decay. When stored in a sealed container, eCO2 is initially produced, followed by an average production of TVOC after a short time. The color change and eCO2 change show a similar temporal trend, while TVOC data tends to occur slightly slower than eco data. Through this, it is suggested that the gas data produced by the decaying pork is related to eCO2, and depending on the degree of decay, the red hue and value in HSV are suitable indicators for decay."
Thank you for pointing out an important aspect to be addressed. We believe the paper has been improved and strengthened by addressing these points.
Author Response File: Author Response.docx
