Pub Date : 2024-01-01DOI: 10.2478/ijssis-2024-0006
T. Makarenya, Alexey I. Kalinichenko, A. S. Mannaa, Svetlana V. Petrenko
The purpose of this study is to build a cognitive model of the system–industrial complex of the Southern Federal District of Russia. The Southern Federal District is a region in the south of Russia, which includes the regions of Rostov, Volgograd, Astrakhan, and Krasnodar; the Republics of Adygea, Kalmykia, and Crimea; and the federal city of Sevastopol. The object of the study was the industrial complex of Southern Federal District, which ranks 6th in terms of the share of manufacturing among the federal districts. The study was conducted at the Southern Federal University, which is located in the Southern Federal District of Russia. This article discusses the use of the cognitive modeling method, which allows us to determine the degree of system stability and the direction of system development under varying degrees of influence of external factors. This method is used to build forecasts of the development of poorly structured socioeconomic systems. The cognitive modeling method made it possible to predict one of the scenarios for the development of the industrial complex of the Southern region of the Russian Federation. For the subject under study, indicative, controlling, and regulating peaks have been identified, but the difficulty of forecasting is noted due to the lack of a general program for the industrial complex of the federal district. The article presents scenarios of industrial development of the Rostov and Krasnodar regions as the most industrially developed regions in the Southern Federal District. Cognitive modeling allows building scenarios of development of the studied systems of regions by means of impulse influence, that is, when one vertex affects another vertex. The modeling results made it possible to build a cognitive map of the industrial complex of the Southern Federal District. This map showed that in the case of impulse impact on the industrial complex, it is necessary to strengthen regulatory measures on the part of the state.
{"title":"Forecasting the development of the industrial complex: Southern Federal District","authors":"T. Makarenya, Alexey I. Kalinichenko, A. S. Mannaa, Svetlana V. Petrenko","doi":"10.2478/ijssis-2024-0006","DOIUrl":"https://doi.org/10.2478/ijssis-2024-0006","url":null,"abstract":"\u0000 The purpose of this study is to build a cognitive model of the system–industrial complex of the Southern Federal District of Russia. The Southern Federal District is a region in the south of Russia, which includes the regions of Rostov, Volgograd, Astrakhan, and Krasnodar; the Republics of Adygea, Kalmykia, and Crimea; and the federal city of Sevastopol. The object of the study was the industrial complex of Southern Federal District, which ranks 6th in terms of the share of manufacturing among the federal districts. The study was conducted at the Southern Federal University, which is located in the Southern Federal District of Russia. This article discusses the use of the cognitive modeling method, which allows us to determine the degree of system stability and the direction of system development under varying degrees of influence of external factors. This method is used to build forecasts of the development of poorly structured socioeconomic systems. The cognitive modeling method made it possible to predict one of the scenarios for the development of the industrial complex of the Southern region of the Russian Federation. For the subject under study, indicative, controlling, and regulating peaks have been identified, but the difficulty of forecasting is noted due to the lack of a general program for the industrial complex of the federal district. The article presents scenarios of industrial development of the Rostov and Krasnodar regions as the most industrially developed regions in the Southern Federal District. Cognitive modeling allows building scenarios of development of the studied systems of regions by means of impulse influence, that is, when one vertex affects another vertex. The modeling results made it possible to build a cognitive map of the industrial complex of the Southern Federal District. This map showed that in the case of impulse impact on the industrial complex, it is necessary to strengthen regulatory measures on the part of the state.","PeriodicalId":45623,"journal":{"name":"International Journal on Smart Sensing and Intelligent Systems","volume":null,"pages":null},"PeriodicalIF":1.2,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140516084","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-01DOI: 10.2478/ijssis-2023-0006
A. Yudhana, Fathiyyah Warsino, S. A. Akbar, Fatma Nuraisyah, Ilham Mufandi
Abstract Glucose monitoring carried out through the urine testing to make it easier for patients to check their blood sugar without having to physically injure themselves and to prevent external bacteria from entering the body, which happens while using needles. This study aims to classify glucose-containing urine specimens based on diabetes levels by using the K-nearest neighbor method. Classification of urine specimens is achieved by using the Benedict method to produce the color of the urine specimen and the AS7262 sensor to detect the color produced by the specimen. The results showed that the classification of data on urine specimens has an accuracy of 96.33%. Previous studies conducted this experiment using a photodiode sensor and a TCS sensor, which produced red, green, and blue (RGB) colors. For identifying the color of a specimen, the AS7262 sensor can produce six colors (red, green, blue, yellow, violet, and orange) to identify the glucose level.
{"title":"Identification of glucose levels in urine based on classification using k-nearest neighbor algorithm method","authors":"A. Yudhana, Fathiyyah Warsino, S. A. Akbar, Fatma Nuraisyah, Ilham Mufandi","doi":"10.2478/ijssis-2023-0006","DOIUrl":"https://doi.org/10.2478/ijssis-2023-0006","url":null,"abstract":"Abstract Glucose monitoring carried out through the urine testing to make it easier for patients to check their blood sugar without having to physically injure themselves and to prevent external bacteria from entering the body, which happens while using needles. This study aims to classify glucose-containing urine specimens based on diabetes levels by using the K-nearest neighbor method. Classification of urine specimens is achieved by using the Benedict method to produce the color of the urine specimen and the AS7262 sensor to detect the color produced by the specimen. The results showed that the classification of data on urine specimens has an accuracy of 96.33%. Previous studies conducted this experiment using a photodiode sensor and a TCS sensor, which produced red, green, and blue (RGB) colors. For identifying the color of a specimen, the AS7262 sensor can produce six colors (red, green, blue, yellow, violet, and orange) to identify the glucose level.","PeriodicalId":45623,"journal":{"name":"International Journal on Smart Sensing and Intelligent Systems","volume":null,"pages":null},"PeriodicalIF":1.2,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48853794","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-01DOI: 10.2478/ijssis-2023-0011
Husham I. Hussein, Ahmed Alazawi, A. Rodríguez, F. Muñoz
Abstract The complexity of power quality disturbances (PQDs) is a significant risk factor in the electricity sector. An accurate and fast analysis of these disturbances provides crucial information to cover all the issues related to power quality. The main objective of this study is to explore a new analytic technique, including all kinds of disturbances that can appear in electrical networks, that differs from previous technologies such as the Fourier transform. Three methods based on the Stockwell transform, namely, the discrete orthonormal Stockwell transform (DOST), discrete cosine Stockwell transform (DCST), and discrete cosine transform (DCT), were used to analyze PQDs in time–frequency representation. These methods diagnose the disturbance's signal properties, which are dependent on resolution and absolute phase information. Nine PQDs, including normal sine waves, were mathematically modeled and used to evaluate the proposed methods. All the methods can effectively simulate and analyze PQDs. Among them, DOST is the most effective in providing clear and high-resolution time–frequency representations of signals. The classification of disturbances was fulfilled based on statistical features extracted from matrices derived from Stockwell transform-based methods, such as analytic approaches (mean, variation, standard deviation, entropy, skewness, and kurtosis). Neural networks, a method utilizing intelligence classifiers, were used for pattern recognition, and the patterns of the different methods were compared. Simulation results proved that DOST needs fewer samples than other methods; its capability to deal with signals in time–frequency resolution is also more viable. The neural network classifier has a higher accuracy rate than the K-nearest neighbor and decision tree methods and approximates the support vector machine method.
{"title":"Performance Evaluation of ST-Based Methods for Simulating and Analyzing Power Quality Disturbances","authors":"Husham I. Hussein, Ahmed Alazawi, A. Rodríguez, F. Muñoz","doi":"10.2478/ijssis-2023-0011","DOIUrl":"https://doi.org/10.2478/ijssis-2023-0011","url":null,"abstract":"Abstract The complexity of power quality disturbances (PQDs) is a significant risk factor in the electricity sector. An accurate and fast analysis of these disturbances provides crucial information to cover all the issues related to power quality. The main objective of this study is to explore a new analytic technique, including all kinds of disturbances that can appear in electrical networks, that differs from previous technologies such as the Fourier transform. Three methods based on the Stockwell transform, namely, the discrete orthonormal Stockwell transform (DOST), discrete cosine Stockwell transform (DCST), and discrete cosine transform (DCT), were used to analyze PQDs in time–frequency representation. These methods diagnose the disturbance's signal properties, which are dependent on resolution and absolute phase information. Nine PQDs, including normal sine waves, were mathematically modeled and used to evaluate the proposed methods. All the methods can effectively simulate and analyze PQDs. Among them, DOST is the most effective in providing clear and high-resolution time–frequency representations of signals. The classification of disturbances was fulfilled based on statistical features extracted from matrices derived from Stockwell transform-based methods, such as analytic approaches (mean, variation, standard deviation, entropy, skewness, and kurtosis). Neural networks, a method utilizing intelligence classifiers, were used for pattern recognition, and the patterns of the different methods were compared. Simulation results proved that DOST needs fewer samples than other methods; its capability to deal with signals in time–frequency resolution is also more viable. The neural network classifier has a higher accuracy rate than the K-nearest neighbor and decision tree methods and approximates the support vector machine method.","PeriodicalId":45623,"journal":{"name":"International Journal on Smart Sensing and Intelligent Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135010443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-01DOI: 10.2478/ijssis-2023-0012
Wasswa Shafik, S. Mojtaba Matinkhah, Fawad Shokoor
Abstract Context With the rapid advancement of unmanned aerial vehicle (UAV) technology, ensuring these autonomous systems’ security and integrity is paramount. UAVs are susceptible to cyberattacks, including unauthorized access, control, or manipulation of their systems, leading to potential safety risks or unauthorized data retrieval. Moreover, UAVs encounter limited computing resources, wireless communication and physical vulnerabilities, evolving threats and techniques, necessity for compliance with regulations, and human factors. Methods This review explores the potential cyberthreats faced by UAVs, including hacking, spoofing, and data breaches, and highlights the critical need for robust security measures. It examines various strategies and techniques used to protect UAVs from cyberattacks, e.g., encryption, authentication, and intrusion detection systems using cyberthreat analysis and assessment algorithms. The approach to assess the UAVs’ cybersecurity hazards included STRIDE (a model for identifying computer security-related threats) connected with the threats considered. Findings Emphasis was laid on the evaluation highly depending on the accuracy of UAV mission definition, potential intruders, and social and other human-related situations. The review discovered that most studies focused on possible intruders’ portraits, which can be crucial when conducting a cybersecurity assessment. Based on a review, future research directions to mitigate cybersecurity risks are presented. Significance Protecting UAVs from cyberthreats ensures safe operations and data integrity and preserves public trust in autonomous systems.
{"title":"Cybersecurity in Unmanned Aerial Vehicles: a Review","authors":"Wasswa Shafik, S. Mojtaba Matinkhah, Fawad Shokoor","doi":"10.2478/ijssis-2023-0012","DOIUrl":"https://doi.org/10.2478/ijssis-2023-0012","url":null,"abstract":"Abstract Context With the rapid advancement of unmanned aerial vehicle (UAV) technology, ensuring these autonomous systems’ security and integrity is paramount. UAVs are susceptible to cyberattacks, including unauthorized access, control, or manipulation of their systems, leading to potential safety risks or unauthorized data retrieval. Moreover, UAVs encounter limited computing resources, wireless communication and physical vulnerabilities, evolving threats and techniques, necessity for compliance with regulations, and human factors. Methods This review explores the potential cyberthreats faced by UAVs, including hacking, spoofing, and data breaches, and highlights the critical need for robust security measures. It examines various strategies and techniques used to protect UAVs from cyberattacks, e.g., encryption, authentication, and intrusion detection systems using cyberthreat analysis and assessment algorithms. The approach to assess the UAVs’ cybersecurity hazards included STRIDE (a model for identifying computer security-related threats) connected with the threats considered. Findings Emphasis was laid on the evaluation highly depending on the accuracy of UAV mission definition, potential intruders, and social and other human-related situations. The review discovered that most studies focused on possible intruders’ portraits, which can be crucial when conducting a cybersecurity assessment. Based on a review, future research directions to mitigate cybersecurity risks are presented. Significance Protecting UAVs from cyberthreats ensures safe operations and data integrity and preserves public trust in autonomous systems.","PeriodicalId":45623,"journal":{"name":"International Journal on Smart Sensing and Intelligent Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135009972","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-01DOI: 10.2478/ijssis-2023-0007
Goutam Datta, Nisheeth Joshi, Kusum Gupta
Abstract One of the important applications for which natural language processing (NLP) is used is the machine translation (MT) system, which automatically converts one natural language to another. It has witnessed various paradigm shifts since its inception. Statistical machine translation (SMT) has dominated MT research for decades. In the recent past, researchers have focused on developing MT systems based on artificial neural networks (ANN). In this paper, first, some important deep learning models that are mostly exploited in Neural Machine Translation (NMT) design are discussed. A systematic comparison was done between the performances of SMT and NMT concerning the English-to-Bangla and English-to-Hindi translation tasks. Most of the Indian scripts are morphologically rich, and the availability of a sufficient corpus is rare. We have presented and analyzed our work and a survey was conducted on other low-resource languages, and finally some useful conclusions have been drawn.
{"title":"Performance Comparison of Statistical vs. Neural-Based Translation System on Low-Resource Languages","authors":"Goutam Datta, Nisheeth Joshi, Kusum Gupta","doi":"10.2478/ijssis-2023-0007","DOIUrl":"https://doi.org/10.2478/ijssis-2023-0007","url":null,"abstract":"Abstract One of the important applications for which natural language processing (NLP) is used is the machine translation (MT) system, which automatically converts one natural language to another. It has witnessed various paradigm shifts since its inception. Statistical machine translation (SMT) has dominated MT research for decades. In the recent past, researchers have focused on developing MT systems based on artificial neural networks (ANN). In this paper, first, some important deep learning models that are mostly exploited in Neural Machine Translation (NMT) design are discussed. A systematic comparison was done between the performances of SMT and NMT concerning the English-to-Bangla and English-to-Hindi translation tasks. Most of the Indian scripts are morphologically rich, and the availability of a sufficient corpus is rare. We have presented and analyzed our work and a survey was conducted on other low-resource languages, and finally some useful conclusions have been drawn.","PeriodicalId":45623,"journal":{"name":"International Journal on Smart Sensing and Intelligent Systems","volume":null,"pages":null},"PeriodicalIF":1.2,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44672343","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-01DOI: 10.2478/ijssis-2023-0009
A. Vellingiri, K. Mohanasundaram, K. Tamilselvan, R. Maheswar, N. Ganesh
Abstract Many natural disasters occur in today's world, resulting in the loss of human life. The application of sensor technology would not stop natural disasters from happening, but it will help those who are affected. It will take time and effort to find the humans who are still alive beneath the rubbles. Ordinary bots that are assigned to rescue missions involving the discovery of living humans trapped beneath massive piles of debris are ordinarily subject to repeated harm arising from continuous contact with the damaged structures. As a result, a significant demand for sensors exists. Sensors are becoming more important as a means of gathering sensory data from the affected area. It is possible to locate humans who are still alive, as well as ascertain the condition of victims who require immediate medical attention in order to survive, using this information. The primary goal of this study is to provide an overview of current sensor-based rescue robot research. Several papers were reviewed in the areas of design, interfacing, controlling, simulation, and applications. Furthermore, this review discusses the use of sensors in the detection of humans as well as the potential for future developments.
{"title":"Multiple Sensor based Human Detection Robots: A Review","authors":"A. Vellingiri, K. Mohanasundaram, K. Tamilselvan, R. Maheswar, N. Ganesh","doi":"10.2478/ijssis-2023-0009","DOIUrl":"https://doi.org/10.2478/ijssis-2023-0009","url":null,"abstract":"Abstract Many natural disasters occur in today's world, resulting in the loss of human life. The application of sensor technology would not stop natural disasters from happening, but it will help those who are affected. It will take time and effort to find the humans who are still alive beneath the rubbles. Ordinary bots that are assigned to rescue missions involving the discovery of living humans trapped beneath massive piles of debris are ordinarily subject to repeated harm arising from continuous contact with the damaged structures. As a result, a significant demand for sensors exists. Sensors are becoming more important as a means of gathering sensory data from the affected area. It is possible to locate humans who are still alive, as well as ascertain the condition of victims who require immediate medical attention in order to survive, using this information. The primary goal of this study is to provide an overview of current sensor-based rescue robot research. Several papers were reviewed in the areas of design, interfacing, controlling, simulation, and applications. Furthermore, this review discusses the use of sensors in the detection of humans as well as the potential for future developments.","PeriodicalId":45623,"journal":{"name":"International Journal on Smart Sensing and Intelligent Systems","volume":null,"pages":null},"PeriodicalIF":1.2,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47250448","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-01DOI: 10.2478/ijssis-2023-0005
Toral Vyas, H. R. Varia
Abstract Objectives Traffic management is challenging during construction because of the effects of traffic congestion, travel time, delay, and queue length. Long-term work zones on urban roads lead to many problems such as speed, inconvenience, and economic losses to drivers, which are focused on in previous studies. Methods Moreover, due to the construction work zone (CWZ), the impact on environmental factors such as air quality and noise levels was not focused on. Because of the building work zones, this research focused on comprehending how traffic congestion measurements and environmental factors affect urban traffic management. Findings The present research uses TransCAD to estimate air pollution due to increased traffic in the urban areas. Furthermore, three nonlinear AI-based models (ANFIS, FFNN, and SVR) and one linear black box model were developed to predict the noise level in the city, in which each contained the total traffic and speed as well as the ratio of heavy vehicles in the traffic. Novelty For traffic control, a variety of techniques are available, including video data analysis, infrared sensors, inductive loop detection, wireless sensor networks, etc. These are all practical techniques for efficient traffic management. It is necessary to conduct studies on the amount of traffic, the topography, accidents, time delays, and the level of safety offered in the work area. Construction operations are facilitated by the implementation of traffic flow, and during this process, long-term CWZs are inevitable. Therefore, the proposed model accomplishes the goal, namely that only analytical research and a few traffic diverter signs point drivers to alternate routes to their destinations.
{"title":"Impact of Construction Work Zone on Urban Traffic Environment","authors":"Toral Vyas, H. R. Varia","doi":"10.2478/ijssis-2023-0005","DOIUrl":"https://doi.org/10.2478/ijssis-2023-0005","url":null,"abstract":"Abstract Objectives Traffic management is challenging during construction because of the effects of traffic congestion, travel time, delay, and queue length. Long-term work zones on urban roads lead to many problems such as speed, inconvenience, and economic losses to drivers, which are focused on in previous studies. Methods Moreover, due to the construction work zone (CWZ), the impact on environmental factors such as air quality and noise levels was not focused on. Because of the building work zones, this research focused on comprehending how traffic congestion measurements and environmental factors affect urban traffic management. Findings The present research uses TransCAD to estimate air pollution due to increased traffic in the urban areas. Furthermore, three nonlinear AI-based models (ANFIS, FFNN, and SVR) and one linear black box model were developed to predict the noise level in the city, in which each contained the total traffic and speed as well as the ratio of heavy vehicles in the traffic. Novelty For traffic control, a variety of techniques are available, including video data analysis, infrared sensors, inductive loop detection, wireless sensor networks, etc. These are all practical techniques for efficient traffic management. It is necessary to conduct studies on the amount of traffic, the topography, accidents, time delays, and the level of safety offered in the work area. Construction operations are facilitated by the implementation of traffic flow, and during this process, long-term CWZs are inevitable. Therefore, the proposed model accomplishes the goal, namely that only analytical research and a few traffic diverter signs point drivers to alternate routes to their destinations.","PeriodicalId":45623,"journal":{"name":"International Journal on Smart Sensing and Intelligent Systems","volume":null,"pages":null},"PeriodicalIF":1.2,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49279513","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-01DOI: 10.2478/ijssis-2023-0008
Rahmad Hidayat, A. Harjoko, Aina Musdholifah
Abstract A backpack is a type of carried object (CO) widely used for various purposes because of its practicality. Various valuable items such as wallets, laptops, cameras, and cellphones may be kept in backpacks. Detecting backpacks in video surveillance is challenging due to their varying shapes, sizes, and colors. The process of localizing the area of the backpack in the image is a critical stage and dramatically influences the success of detection. This paper focuses on the process of localizing the backpack area through a multi-scale segmentation approach, where different scales are intended to detect the various size of the backpacks. Based on the assumption that the backpack is generally located above the bend line, the body-part method is then used to select superpixels. The selected superpixel feature is then extracted and used to train the model. Model testing is carried out in two scenarios. In the first scenario, the model is tested using the HOG (histogram of oriented gradients) feature, while in the second scenario, the model is tested using a combination of the HOG and histogram features. The experiment results show that on the DIKE20 dataset, the proposed model obtained an average F1 score of 69%. On PETS2006 and i-LIDS datasets, the proposed model shows an average F1 score of 68%, better than the average F1 score obtained by the state-of-the-art method.
{"title":"Backpack detection model using multi-scale superpixel and body-part segmentation","authors":"Rahmad Hidayat, A. Harjoko, Aina Musdholifah","doi":"10.2478/ijssis-2023-0008","DOIUrl":"https://doi.org/10.2478/ijssis-2023-0008","url":null,"abstract":"Abstract A backpack is a type of carried object (CO) widely used for various purposes because of its practicality. Various valuable items such as wallets, laptops, cameras, and cellphones may be kept in backpacks. Detecting backpacks in video surveillance is challenging due to their varying shapes, sizes, and colors. The process of localizing the area of the backpack in the image is a critical stage and dramatically influences the success of detection. This paper focuses on the process of localizing the backpack area through a multi-scale segmentation approach, where different scales are intended to detect the various size of the backpacks. Based on the assumption that the backpack is generally located above the bend line, the body-part method is then used to select superpixels. The selected superpixel feature is then extracted and used to train the model. Model testing is carried out in two scenarios. In the first scenario, the model is tested using the HOG (histogram of oriented gradients) feature, while in the second scenario, the model is tested using a combination of the HOG and histogram features. The experiment results show that on the DIKE20 dataset, the proposed model obtained an average F1 score of 69%. On PETS2006 and i-LIDS datasets, the proposed model shows an average F1 score of 68%, better than the average F1 score obtained by the state-of-the-art method.","PeriodicalId":45623,"journal":{"name":"International Journal on Smart Sensing and Intelligent Systems","volume":null,"pages":null},"PeriodicalIF":1.2,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46013043","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-01DOI: 10.2478/ijssis-2023-0004
Soojun Lee, Hyeopgoo Yeo, Mingoo Kang
Abstract In this paper, a digital personal safe system was proposed with Fast ID Online (FIDO) transaction authentication and multiple decentralized ID (DID) personal authentications based on a home gateway. This individual custody model of personal multiple authentications will be linked to the transaction authentication of digital assets stored in the storage space of the home gateway by the DID of smart devices and the FIDO server for a public platform that excludes digital asset (cryptocurrency [e.g., Bitcoin] or NFT asset) management based on individual private keys and user interaction (user interface and user experience [UI/UX]) at home. To strengthen the security of the proposed digital custody model, it was proposed to apply a local device to which a biometric sensor equipped with an encryption module that can fundamentally block the hacking of biometric information is applied. It is implemented with Verilog for an embedded fingerprint sensor block and decryption program implemented with C.
{"title":"Biometric authentication sensor with an encryption module for prevention of h/w hacking in digital custody services","authors":"Soojun Lee, Hyeopgoo Yeo, Mingoo Kang","doi":"10.2478/ijssis-2023-0004","DOIUrl":"https://doi.org/10.2478/ijssis-2023-0004","url":null,"abstract":"Abstract In this paper, a digital personal safe system was proposed with Fast ID Online (FIDO) transaction authentication and multiple decentralized ID (DID) personal authentications based on a home gateway. This individual custody model of personal multiple authentications will be linked to the transaction authentication of digital assets stored in the storage space of the home gateway by the DID of smart devices and the FIDO server for a public platform that excludes digital asset (cryptocurrency [e.g., Bitcoin] or NFT asset) management based on individual private keys and user interaction (user interface and user experience [UI/UX]) at home. To strengthen the security of the proposed digital custody model, it was proposed to apply a local device to which a biometric sensor equipped with an encryption module that can fundamentally block the hacking of biometric information is applied. It is implemented with Verilog for an embedded fingerprint sensor block and decryption program implemented with C.","PeriodicalId":45623,"journal":{"name":"International Journal on Smart Sensing and Intelligent Systems","volume":null,"pages":null},"PeriodicalIF":1.2,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46906355","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-01DOI: 10.2478/ijssis-2023-0010
Goutam Datta, Nisheeth Joshi, Kusum Gupta
Abstract Machine translation (MT) is an important use case in natural language processing (NLP) that converts a source language to a target language automatically. Modern intelligent system or artificial intelligence (AI) uses a machine learning approach and the machine has acquired learning ability using datasets. Nowadays, in the MT domain, the neural machine translation (NMT) system has almost replaced the statistical machine translation (SMT) system. The NMT systems use a deep learning framework in their implementation. To achieve higher accuracy during the training of the NMT model, extensive hyper-parameter tuning is required. The paper highlights the significance of hyper-parameter tuning in various machine learning algorithms. And as a case study, in-house experimentation was conducted on a low-resource English–Bangla language pair by designing an NMT system and the significance of various hyper-parameter optimizations was analyzed while evaluating its performance with an automatic metric BLEU. The BLEU scores obtained for the first, second, and third randomly picked test sentences are 4.1, 3.2, and 3.01, respectively.
{"title":"Hyper-parameter optimization in neural-based translation systems: A case study","authors":"Goutam Datta, Nisheeth Joshi, Kusum Gupta","doi":"10.2478/ijssis-2023-0010","DOIUrl":"https://doi.org/10.2478/ijssis-2023-0010","url":null,"abstract":"Abstract Machine translation (MT) is an important use case in natural language processing (NLP) that converts a source language to a target language automatically. Modern intelligent system or artificial intelligence (AI) uses a machine learning approach and the machine has acquired learning ability using datasets. Nowadays, in the MT domain, the neural machine translation (NMT) system has almost replaced the statistical machine translation (SMT) system. The NMT systems use a deep learning framework in their implementation. To achieve higher accuracy during the training of the NMT model, extensive hyper-parameter tuning is required. The paper highlights the significance of hyper-parameter tuning in various machine learning algorithms. And as a case study, in-house experimentation was conducted on a low-resource English–Bangla language pair by designing an NMT system and the significance of various hyper-parameter optimizations was analyzed while evaluating its performance with an automatic metric BLEU. The BLEU scores obtained for the first, second, and third randomly picked test sentences are 4.1, 3.2, and 3.01, respectively.","PeriodicalId":45623,"journal":{"name":"International Journal on Smart Sensing and Intelligent Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135700023","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：