A zero-watermarking algorithm for privacy protection in biomedical signals
- Ali, Zulfiqar, Imran, Muhammad, Alsulaiman, Mansour, Zia, Tanveer, Shoaib, Muhammad
- Authors: Ali, Zulfiqar , Imran, Muhammad , Alsulaiman, Mansour , Zia, Tanveer , Shoaib, Muhammad
- Date: 2018
- Type: Text , Journal article
- Relation: Future Generation Computer Systems Vol. 82, no. (2018), p. 290-303
- Full Text:
- Reviewed:
- Description: Confidentiality of health information is indispensable to protect privacy of an individual. However, recent advances in electronic healthcare systems allow transmission of sensitive information through the Internet, which is prone to various vulnerabilities, attacks and may leads to unauthorized disclosure. Such situations may not only create adverse effects for individuals but may also cause severe consequences such as hefty regulatory fines, bad publicity, legal fees, and forensics. To avoid such predicaments, a privacy protected healthcare system is proposed in this study that protects the identity of an individual as well as detects vocal fold disorders. The privacy of the developed healthcare system is based on the proposed zero-watermarking algorithm, which embeds a watermark in a secret key instead of the signals to avoid the distortion in an audio sample. The identity is protected by the generation of its secret shares through visual cryptography. The generated shares are embedded by finding the patterns into the audio with the application of one-dimensional local binary pattern. The proposed zero-watermarking algorithm is evaluated by using audio samples taken from the Massachusetts Eye and Ear Infirmary voice disorder database. Experimental results demonstrate that the proposed algorithm achieves imperceptibility and is reliable in its extraction of identity. In addition, the proposed algorithm does not affect the results of disorder detection and it is robust against noise attacks of various signal-to-noise ratios. © 2017 Elsevier B.V.
- Authors: Ali, Zulfiqar , Imran, Muhammad , Alsulaiman, Mansour , Zia, Tanveer , Shoaib, Muhammad
- Date: 2018
- Type: Text , Journal article
- Relation: Future Generation Computer Systems Vol. 82, no. (2018), p. 290-303
- Full Text:
- Reviewed:
- Description: Confidentiality of health information is indispensable to protect privacy of an individual. However, recent advances in electronic healthcare systems allow transmission of sensitive information through the Internet, which is prone to various vulnerabilities, attacks and may leads to unauthorized disclosure. Such situations may not only create adverse effects for individuals but may also cause severe consequences such as hefty regulatory fines, bad publicity, legal fees, and forensics. To avoid such predicaments, a privacy protected healthcare system is proposed in this study that protects the identity of an individual as well as detects vocal fold disorders. The privacy of the developed healthcare system is based on the proposed zero-watermarking algorithm, which embeds a watermark in a secret key instead of the signals to avoid the distortion in an audio sample. The identity is protected by the generation of its secret shares through visual cryptography. The generated shares are embedded by finding the patterns into the audio with the application of one-dimensional local binary pattern. The proposed zero-watermarking algorithm is evaluated by using audio samples taken from the Massachusetts Eye and Ear Infirmary voice disorder database. Experimental results demonstrate that the proposed algorithm achieves imperceptibility and is reliable in its extraction of identity. In addition, the proposed algorithm does not affect the results of disorder detection and it is robust against noise attacks of various signal-to-noise ratios. © 2017 Elsevier B.V.
Chaos-based robust method of zero-watermarking for medical signals
- Ali, Zulfiqar, Imran, Muhammad, Alsulaiman, Mansour, Shoaib, Muhammad, Ullah, Sana
- Authors: Ali, Zulfiqar , Imran, Muhammad , Alsulaiman, Mansour , Shoaib, Muhammad , Ullah, Sana
- Date: 2018
- Type: Text , Journal article
- Relation: Future Generation Computer Systems Vol. 88, no. (2018), p. 400-412
- Full Text:
- Reviewed:
- Description: The growing use of wireless health data transmission via Internet of Things is significantly beneficial to the healthcare industry for optimal usage of health-related facilities. However, at the same time, the use raises concern of privacy protection. Health-related data are private and should be suitably protected. Several pathologies, such as vocal fold disorders, indicate high risks of prevalence in individuals with voice-related occupations, such as teachers, singers, and lawyers. Approximately, one-third of the world population suffers from the voice-related problems during the life span and unauthorized access to their data can create unavoidable circumstances in their personal and professional lives. In this study, a zero-watermarking method is proposed and implemented to protect the identity of patients who suffer from vocal fold disorders. In the proposed method, an image for a patient's identity is generated and inserted into secret keys instead of a host medical signal. Consequently, imperceptibility is naturally achieved. The locations for the insertion of the watermark are determined by a computation of local binary patterns from the time–frequency spectrum. The spectrum is calculated for low frequencies such that it may not be affected by noise attacks. The experimental results suggest that the proposed method has good performance and robustness against noise, and it is reliable in the recovery of an individual's identity. © 2018 Elsevier B.V.
- Authors: Ali, Zulfiqar , Imran, Muhammad , Alsulaiman, Mansour , Shoaib, Muhammad , Ullah, Sana
- Date: 2018
- Type: Text , Journal article
- Relation: Future Generation Computer Systems Vol. 88, no. (2018), p. 400-412
- Full Text:
- Reviewed:
- Description: The growing use of wireless health data transmission via Internet of Things is significantly beneficial to the healthcare industry for optimal usage of health-related facilities. However, at the same time, the use raises concern of privacy protection. Health-related data are private and should be suitably protected. Several pathologies, such as vocal fold disorders, indicate high risks of prevalence in individuals with voice-related occupations, such as teachers, singers, and lawyers. Approximately, one-third of the world population suffers from the voice-related problems during the life span and unauthorized access to their data can create unavoidable circumstances in their personal and professional lives. In this study, a zero-watermarking method is proposed and implemented to protect the identity of patients who suffer from vocal fold disorders. In the proposed method, an image for a patient's identity is generated and inserted into secret keys instead of a host medical signal. Consequently, imperceptibility is naturally achieved. The locations for the insertion of the watermark are determined by a computation of local binary patterns from the time–frequency spectrum. The spectrum is calculated for low frequencies such that it may not be affected by noise attacks. The experimental results suggest that the proposed method has good performance and robustness against noise, and it is reliable in the recovery of an individual's identity. © 2018 Elsevier B.V.
An innovative algorithm for privacy protection in a voice disorder detection system
- Ali, Zulfiqar, Imran, Muhammad, Abdul, Wadood, Shoaib, Muhammad
- Authors: Ali, Zulfiqar , Imran, Muhammad , Abdul, Wadood , Shoaib, Muhammad
- Date: 2018
- Type: Text , Conference paper
- Relation: 1st International Early Research Career Enhancement School on Biologically Inspired Cognitive Architectures, FIERCES on BICA 2017, Moscow, 1-6 August 2018 Vol. 636, p. 228-233
- Full Text: false
- Reviewed:
- Description: Health information is critical for the patient and its unauthorized access may have server impact. With the advancement in the healthcare systems especially through the Internet of Things give rises to patient privacy. We developed a healthcare system that protects identity of patients using innovative zero-watermarking algorithm along with vocal fold disorders detection. To avoid audio signal distortion, proposed system embeds watermark in a secret key of identity by visual cryptography rather than audio signal. The secret shares generated through visual cryptography are inserted in the secret watermark key by computing the features of audio signals. The proposed technique is evaluated using audio samples taken from voice disorder database of the Massachusetts Eye and Ear Infirmary (MEEI). Experimental results prove that the proposed technique achieves imperceptibility with reliability to extract identity, unaffected disorder detection result with high robustness. The results are provided in form of Normalized Cross-Correlation (NCR), Bit Error Rate (BER), and Energy Ratio (ENR). © Springer International Publishing AG 2018.
Blind detection of copy-move forgery in digital audio forensics
- Imran, Muhammad, Ali, Zulfiqar, Bakhsh, Sheikh, Akram, Sheeraz
- Authors: Imran, Muhammad , Ali, Zulfiqar , Bakhsh, Sheikh , Akram, Sheeraz
- Date: 2017
- Type: Text , Journal article
- Relation: IEEE Access Vol. 5, no. (2017), p. 12843-12855
- Full Text:
- Reviewed:
- Description: Although copy-move forgery is one of the most common fabrication techniques, blind detection of such tampering in digital audio is mostly unexplored. Unlike active techniques, blind forgery detection is challenging, because it does not embed a watermark or signature in an audio that is unknown in most of the real-life scenarios. Therefore, forgery localization becomes more challenging, especially when using blind methods. In this paper, we propose a novel method for blind detection and localization of copy-move forgery. One of the most crucial steps in the proposed method is a voice activity detection (VAD) module for investigating audio recordings to detect and localize the forgery. The VAD module is equally vital for the development of the copy-move forgery database, wherein audio samples are generated by using the recordings of various types of microphones. We employ a chaotic theory to copy and move the text in generated forged recordings to ensure forgery localization at any place in a recording. The VAD module is responsible for the extraction of words in a forged audio, these words are analyzed by applying a 1-D local binary pattern operator. This operator provides the patterns of extracted words in the form of histograms. The forged parts (copy and move text) have similar histograms. An accuracy of 96.59% is achieved, the proposed method is deemed robust against noise. © 2013 IEEE.
- Authors: Imran, Muhammad , Ali, Zulfiqar , Bakhsh, Sheikh , Akram, Sheeraz
- Date: 2017
- Type: Text , Journal article
- Relation: IEEE Access Vol. 5, no. (2017), p. 12843-12855
- Full Text:
- Reviewed:
- Description: Although copy-move forgery is one of the most common fabrication techniques, blind detection of such tampering in digital audio is mostly unexplored. Unlike active techniques, blind forgery detection is challenging, because it does not embed a watermark or signature in an audio that is unknown in most of the real-life scenarios. Therefore, forgery localization becomes more challenging, especially when using blind methods. In this paper, we propose a novel method for blind detection and localization of copy-move forgery. One of the most crucial steps in the proposed method is a voice activity detection (VAD) module for investigating audio recordings to detect and localize the forgery. The VAD module is equally vital for the development of the copy-move forgery database, wherein audio samples are generated by using the recordings of various types of microphones. We employ a chaotic theory to copy and move the text in generated forged recordings to ensure forgery localization at any place in a recording. The VAD module is responsible for the extraction of words in a forged audio, these words are analyzed by applying a 1-D local binary pattern operator. This operator provides the patterns of extracted words in the form of histograms. The forged parts (copy and move text) have similar histograms. An accuracy of 96.59% is achieved, the proposed method is deemed robust against noise. © 2013 IEEE.
Protection of records and data authentication based on secret shares and watermarking
- Ali, Zulfiqar, Imran, Muhammad, McClean, Sally, Khan, Naveed, Shoaib, Muhammad
- Authors: Ali, Zulfiqar , Imran, Muhammad , McClean, Sally , Khan, Naveed , Shoaib, Muhammad
- Date: 2019
- Type: Text , Journal article
- Relation: Future Generation Computer Systems Vol. 98, no. (2019), p. 331-341
- Full Text:
- Reviewed:
- Description: The rapid growth in communication technology facilitates the health industry in many aspects from transmission of sensor's data to real-time diagnosis using cloud-based frameworks. However, the secure transmission of data and its authenticity become a challenging task, especially, for health-related applications. The medical information must be accessible to only the relevant healthcare staff to avoid any unfortunate circumstances for the patient as well as for the healthcare providers. Therefore, a method to protect the identity of a patient and authentication of transmitted data is proposed in this study. The proposed method provides dual protection. First, it encrypts the identity using Shamir's secret sharing scheme without the increase in dimension of the original identity. Second, the identity is watermarked using zero-watermarking to avoid any distortion into the host signal. The experimental results show that the proposed method encrypts, embeds and extracts identities reliably. Moreover, in case of malicious attack, the method distorts the embedded identity which provides a clear indication of fabrication. An automatic disorder detection system using Mel-frequency cepstral coefficients and Gaussian mixture model is also implemented which concludes that malicious attacks greatly impact on the accurate diagnosis of disorders. © 2019 Elsevier B.V.
- Authors: Ali, Zulfiqar , Imran, Muhammad , McClean, Sally , Khan, Naveed , Shoaib, Muhammad
- Date: 2019
- Type: Text , Journal article
- Relation: Future Generation Computer Systems Vol. 98, no. (2019), p. 331-341
- Full Text:
- Reviewed:
- Description: The rapid growth in communication technology facilitates the health industry in many aspects from transmission of sensor's data to real-time diagnosis using cloud-based frameworks. However, the secure transmission of data and its authenticity become a challenging task, especially, for health-related applications. The medical information must be accessible to only the relevant healthcare staff to avoid any unfortunate circumstances for the patient as well as for the healthcare providers. Therefore, a method to protect the identity of a patient and authentication of transmitted data is proposed in this study. The proposed method provides dual protection. First, it encrypts the identity using Shamir's secret sharing scheme without the increase in dimension of the original identity. Second, the identity is watermarked using zero-watermarking to avoid any distortion into the host signal. The experimental results show that the proposed method encrypts, embeds and extracts identities reliably. Moreover, in case of malicious attack, the method distorts the embedded identity which provides a clear indication of fabrication. An automatic disorder detection system using Mel-frequency cepstral coefficients and Gaussian mixture model is also implemented which concludes that malicious attacks greatly impact on the accurate diagnosis of disorders. © 2019 Elsevier B.V.
An IoT-based smart healthcare system to detect dysphonia
- Ali, Zulfiqar, Imran, Muhammad, Shoaib, Muhammad
- Authors: Ali, Zulfiqar , Imran, Muhammad , Shoaib, Muhammad
- Date: 2022
- Type: Text , Journal article
- Relation: Neural Computing and Applications Vol. 34, no. 14 (2022), p. 11255-11265
- Full Text:
- Reviewed:
- Description: Smart healthcare systems for the internet of things (IoT) platform are cost-efficient and facilitate continuous remote monitoring of patients to avoid unnecessary hospital visits and long waiting times to see practitioners. Presenting a smart healthcare system for the detection of dysphonia can reduce the suffering and pain of patients by providing an initial evaluation of voice. This preliminary feedback of voice could minimize the burden on ENT specialists by referring only genuine cases to them as well as giving an early alarm of potential voice complications to patients. Any possible delay in the treatment and/or inaccurate diagnosis using the subjective nature of tools may lead to severe circumstances for an individual because some types of dysphonia are life-threatening. Therefore, an accurate and reliable smart healthcare system for IoT platform to detect dysphonia is proposed and implemented in this study. Higher-order directional derivatives are used to analyze the time–frequency spectrum of signals in the proposed system. The computed derivatives provide essential and vital information by analyzing the spectrum along different directions to capture the changes that appeared due to malfunctioning the vocal folds. The proposed system provides 99.1% accuracy, while the sensitivity and specificity are 99.4 and 98.1%, respectively. The experimental results showed that the proposed system could provide better classification accuracy than the traditional non-directional first-order derivatives. Hence, the system can be used as a reliable tool for detecting dysphonia and implemented in edge devices to avoid latency issues and protect privacy, unlike cloud processing. © 2021, Springer-Verlag London Ltd., part of Springer Nature.
- Authors: Ali, Zulfiqar , Imran, Muhammad , Shoaib, Muhammad
- Date: 2022
- Type: Text , Journal article
- Relation: Neural Computing and Applications Vol. 34, no. 14 (2022), p. 11255-11265
- Full Text:
- Reviewed:
- Description: Smart healthcare systems for the internet of things (IoT) platform are cost-efficient and facilitate continuous remote monitoring of patients to avoid unnecessary hospital visits and long waiting times to see practitioners. Presenting a smart healthcare system for the detection of dysphonia can reduce the suffering and pain of patients by providing an initial evaluation of voice. This preliminary feedback of voice could minimize the burden on ENT specialists by referring only genuine cases to them as well as giving an early alarm of potential voice complications to patients. Any possible delay in the treatment and/or inaccurate diagnosis using the subjective nature of tools may lead to severe circumstances for an individual because some types of dysphonia are life-threatening. Therefore, an accurate and reliable smart healthcare system for IoT platform to detect dysphonia is proposed and implemented in this study. Higher-order directional derivatives are used to analyze the time–frequency spectrum of signals in the proposed system. The computed derivatives provide essential and vital information by analyzing the spectrum along different directions to capture the changes that appeared due to malfunctioning the vocal folds. The proposed system provides 99.1% accuracy, while the sensitivity and specificity are 99.4 and 98.1%, respectively. The experimental results showed that the proposed system could provide better classification accuracy than the traditional non-directional first-order derivatives. Hence, the system can be used as a reliable tool for detecting dysphonia and implemented in edge devices to avoid latency issues and protect privacy, unlike cloud processing. © 2021, Springer-Verlag London Ltd., part of Springer Nature.
An automatic digital audio authentication/forensics system
- Ali, Zulfiqar, Imran, Muhammad, Alsulaiman, Mansour
- Authors: Ali, Zulfiqar , Imran, Muhammad , Alsulaiman, Mansour
- Date: 2017
- Type: Text , Journal article
- Relation: IEEE Access Vol. 5, no. (2017), p. 2994-3007
- Full Text:
- Reviewed:
- Description: With the continuous rise in ingenious forgery, a wide range of digital audio authentication applications are emerging as a preventive and detective control in real-world circumstances, such as forged evidence, breach of copyright protection, and unauthorized data access. To investigate and verify, this paper presents a novel automatic authentication system that differentiates between the forged and original audio. The design philosophy of the proposed system is primarily based on three psychoacoustic principles of hearing, which are implemented to simulate the human sound perception system. Moreover, the proposed system is able to classify between the audio of different environments recorded with the same microphone. To authenticate the audio and environment classification, the computed features based on the psychoacoustic principles of hearing are dangled to the Gaussian mixture model to make automatic decisions. It is worth mentioning that the proposed system authenticates an unknown speaker irrespective of the audio content i.e., independent of narrator and text. To evaluate the performance of the proposed system, audios in multi-environments are forged in such a way that a human cannot recognize them. Subjective evaluation by three human evaluators is performed to verify the quality of the generated forged audio. The proposed system provides a classification accuracy of 99.2% ± 2.6. Furthermore, the obtained accuracy for the other scenarios, such as text-dependent and text-independent audio authentication, is 100% by using the proposed system. © 2017 IEEE.
- Authors: Ali, Zulfiqar , Imran, Muhammad , Alsulaiman, Mansour
- Date: 2017
- Type: Text , Journal article
- Relation: IEEE Access Vol. 5, no. (2017), p. 2994-3007
- Full Text:
- Reviewed:
- Description: With the continuous rise in ingenious forgery, a wide range of digital audio authentication applications are emerging as a preventive and detective control in real-world circumstances, such as forged evidence, breach of copyright protection, and unauthorized data access. To investigate and verify, this paper presents a novel automatic authentication system that differentiates between the forged and original audio. The design philosophy of the proposed system is primarily based on three psychoacoustic principles of hearing, which are implemented to simulate the human sound perception system. Moreover, the proposed system is able to classify between the audio of different environments recorded with the same microphone. To authenticate the audio and environment classification, the computed features based on the psychoacoustic principles of hearing are dangled to the Gaussian mixture model to make automatic decisions. It is worth mentioning that the proposed system authenticates an unknown speaker irrespective of the audio content i.e., independent of narrator and text. To evaluate the performance of the proposed system, audios in multi-environments are forged in such a way that a human cannot recognize them. Subjective evaluation by three human evaluators is performed to verify the quality of the generated forged audio. The proposed system provides a classification accuracy of 99.2% ± 2.6. Furthermore, the obtained accuracy for the other scenarios, such as text-dependent and text-independent audio authentication, is 100% by using the proposed system. © 2017 IEEE.
Automatic gender detection based on characteristics of vocal folds for mobile healthcare system
- Alhussein, Musaed, Ali, Zulfiqar, Imran, Muhammad, Abdul, Wadood
- Authors: Alhussein, Musaed , Ali, Zulfiqar , Imran, Muhammad , Abdul, Wadood
- Date: 2016
- Type: Text , Journal article
- Relation: Mobile Information Systems Vol. 2016, no. (2016), p.
- Full Text:
- Reviewed:
- Description: An automatic gender detection may be useful in some cases of a mobile healthcare system. For example, there are some pathologies, such as vocal fold cyst, which mainly occur in female patients. If there is an automatic method for gender detection embedded into the system, it is easy for a healthcare professional to assess and prescribe appropriate medication to the patient. In human voice production system, contribution of the vocal folds is very vital. The length of the vocal folds is gender dependent; a male speaker has longer vocal folds than a female speaker. Due to longer vocal folds, the voice of a male becomes heavy and, therefore, contains more voice intensity. Based on this idea, a new type of time domain acoustic feature for automatic gender detection system is proposed in this paper. The proposed feature measures the voice intensity by calculating the area under the modified voice contour to make the differentiation between males and females. Two different databases are used to show that the proposed feature is independent of text, spoken language, dialect region, recording system, and environment. The obtained results for clean and noisy speech are 98.27% and 96.55%, respectively. © 2016 Musaed Alhussein et al.
- Authors: Alhussein, Musaed , Ali, Zulfiqar , Imran, Muhammad , Abdul, Wadood
- Date: 2016
- Type: Text , Journal article
- Relation: Mobile Information Systems Vol. 2016, no. (2016), p.
- Full Text:
- Reviewed:
- Description: An automatic gender detection may be useful in some cases of a mobile healthcare system. For example, there are some pathologies, such as vocal fold cyst, which mainly occur in female patients. If there is an automatic method for gender detection embedded into the system, it is easy for a healthcare professional to assess and prescribe appropriate medication to the patient. In human voice production system, contribution of the vocal folds is very vital. The length of the vocal folds is gender dependent; a male speaker has longer vocal folds than a female speaker. Due to longer vocal folds, the voice of a male becomes heavy and, therefore, contains more voice intensity. Based on this idea, a new type of time domain acoustic feature for automatic gender detection system is proposed in this paper. The proposed feature measures the voice intensity by calculating the area under the modified voice contour to make the differentiation between males and females. Two different databases are used to show that the proposed feature is independent of text, spoken language, dialect region, recording system, and environment. The obtained results for clean and noisy speech are 98.27% and 96.55%, respectively. © 2016 Musaed Alhussein et al.
- «
- ‹
- 1
- ›
- »