Browsing by Author "Huda, Mohammad Nurul"

Now showing 1 - 9 of 9

Analyzing Performance of Different Machine Learning Approaches with Doc2vec for Classifying Sentiment of Bengali Natural Language
(2nd International Conference on Electrical, Computer and Communication Engineering, IEEE, 2019-04-04) Hoque, Md. Tazimul; Islam, Ashraful; Ahmed, Eshtiak; Mamun, Khondaker A.; Huda, Mohammad Nurul
Vector or numeric representation of text documents has been a revolution in natural language processing as it represents similar parts of text in such a way that they are very close to each other, making it very easy to classify or find similarities among them. These vectors also represent the way we use the words or parts of documents as well which helps finding similarity even between pair of words. While word2vec is such a technique that represents each word as a vector, doc2vec takes it to another level by representing a whole sentence or document as a vector. Being able to represent an entire document as a vector allows comparing a substantial number of words or sentences at a time which can save computational power as well as bandwidth. This relatively newer doc2vec technology has not yet been implemented for Bengali sentiment analysis and its feasibility is also unknown. In this study, we have trained a doc2vec model using a corpus constructed with 7,000 Bengali sentences. The model consists of two types of data differentiated by their polarity i.e. positive and negative. Later, we have employed several machine learning algorithms for comparing the accuracy of classification among which Bi-Directional Long Short-Term Memory (BLSTM) has obtained the highest accuracy of 77.85% along with precision, recall and F-1 score of 78.06%,77.39% and 77.72% respectively.
Automatic Machine Translation for Bangla and English Resolving Ambiguities
(Scopus, 2021) Ohidujjaman; Faysal, Fahim; Sumon, Shams; Huda, Mohammad Nurul
The strategic borderless knowledge sharing and development of communication interacts with dialects. Significant factors such as education, medical, business, research and others are vastly diffused over the world based on various lingoes. Bilingual or multilingual expression is the standard of having unknown/new linguistic along with its resources. The initial endeavor of the study is to implement the MT (machine translation) approaches for English to Bangla language processing and vice-versa. The emphasis of the study is the distinct ambiguities are identified along with their best solutions. Certain machine translation approaches such as word-to-word, direct, transfer, interlingua, corpus-based and statistical translation are surviving and, few of them are deployed in this Smart Natural Language Processing (SNLP) for dispatching the source to the target language and vice-versa. Two different dictionaries (bilingual and monolingual) are developed for the execution process. An eminent resource Stanford POS Tagger (as a toolkit) is used for identifying the grammatical structure of the source (English) dialect. This research also focuses on output acquiring through performance analyzing of different translation models.
Automatic Machine Translation for Bangla and English Resolving Ambiguities
(2021 2nd International Conference on Robotics, Electrical and Signal Processing Techniques (ICREST), IEEE, 2021-01) Ohidujjaman; Faysal, Fahim; Sumon, Shams; Huda, Mohammad Nurul
The strategic borderless knowledge sharing and development of communication interacts with dialects. Significant factors such as education, medical, business, research and others are vastly diffused over the world based on various lingoes. Bilingual or multilingual expression is the standard of having unknown/new linguistic along with its resources. The initial endeavor of the study is to implement the MT (machine translation) approaches for English to Bangla language processing and vice-versa. The emphasis of the study is the distinct ambiguities are identified along with their best solutions. Certain machine translation approaches such as word-to-word, direct, transfer, interlingua, corpus-based and statistical translation are surviving and, few of them are deployed in this Smart Natural Language Processing (SNLP) for dispatching the source to the target language and vice-versa. Two different dictionaries (bilingual and monolingual) are developed for the execution process. An eminent resource Stanford POS Tagger (as a toolkit) is used for identifying the grammatical structure of the source (English) dialect. This research also focuses on output acquiring through performance analyzing of different translation models.
Computer vision based deep learning approach for toxic and harmful substances detection in fruits
(Scopus, 2024-02-15) Sattar, Abdus; Ridoy, Md. Asif Mahmud; Saha, Aloke Kumar; Babu, Hafiz Md. Hasan; Huda, Mohammad Nurul
Formaldehyde (CH₂O) is one of the significant chemicals mixed with different perishable fruits in Bangladesh. The fruits are artificially preserved for extended periods by dishonest vendors using this dangerous chemical. Such substances are complicated to detect in appearance. Hence, a reliable and robust detection technique is required. To overcome this challenge and address the issue, we introduce comprehensive deep learning-based techniques for detecting toxic substances. Four different types of fruits, both in fresh and chemically mixed conditions, are used in this experiment. We have applied diverse data augmentation techniques to enlarge the dataset. The performance of four different pre-trained deep learning models was then assessed, and a brand-new model named “DurbeenNet,” created especially for this task, was presented. The primary objective was to gauge the efficacy of our proposed model compared to well-established deep learning architectures. Our assessment centered on the models' accuracy in detecting toxic substances. According to our research, GoogleNet detected toxic substances with an accuracy rate of 85.53 %, VGG-16 with an accuracy rate of 87.44 %, DenseNet with an impressive accuracy rate of 90.37 %, and ResNet50 with an accuracy rate of 91.66 %. Notably, the proposed model, DurbeenNet, outshone all other models, boasting an impressive accuracy rate of 96.71 % in detecting toxic substances among the sample fruits.
Doly
(1st International Conference on Advances in Science, Engineering and Robotics Technology 2019, ICASERT, IEEE, 2019-12-19) Kowsher, Md.; Tithi, Farhana Sharmin; Alam, F, M Ashraful; Huda, Mohammad Nurul; Moheuddin, Mir Md
This Scientific Research paper is a procedure of an automated system "Doly: Bengali Chabot" which gives a reply to a user query on behalf of a human for the education system in the Bengali language. This is an AI-based Chabot, mainly based on machine learning algorithms and Bengali Natural Language Processing (BNLP). The machine gets embedded with this knowledge to identify the desired sentences and making a decision within itself, as a response to answer questions. There are many English Chabot’s which used in education, web query, banking sector & various sectors. In this research, we have propounded a complete data-driven retrieval based closed domain Chabot which is easily colloquy in the Bengali language with the users. We've created the train function adapter to train the Doly by encoding (encoding="utf8") our corpus from bot data. An input adapter has been created to take input and for output, an output adapter has been created to generate automated responses to a user's input. We have also used a machine learning algorithm like search algorithm for finding an appropriate list of matching results from the corpus and use Naïve Bayesian algorithm to generate the right answer from data. The main aim of this Chabot based system is to bridge the gap between the knowledge sources by providing instant replies to the questions and queries that have to ask in the Bengali language.
PAPR Reduction of OFDM Signal by Scrutiny of BER Assessment and SPS-SLM Method via AWGN Channel
(2021 6th International Conference on Inventive Computation Technologies (ICICT), IEEE, 2021-01-26) Ohidujjaman; Zannat, Raihana; Khatun, Tania; Rahman, Mahfujur; Raza, Salim; Huda, Mohammad Nurul
Orthogonal Frequency Division Multiplexing (OFDM) has been presently underneath powerful exploration for broadband radio transmission owing to its strength in opposition to multi-path diminishing. Nevertheless, implementation of the OFDM method necessitates numerous complications. The foremost downside is high Peak-to-Average Power Ratio (PAPR) that hints to rise Bit Error Rate (BER) on account of nonlinearity of the peak ability amplifier. The Selected Mapping (SLM) technique is prominent method to lessen PAPR of OFDM signal. With SLM technique, lateral evidence bits are required to recuperate actual data which lead to increase the proportion of data damage. In our article, an exact set of sequential phase sequences (SPS) has been developed to perform SLM technique along OFDM transceiver without requiring of side information. SPS based SLM (SPS-SLM) technique has been able to reduce almost same PAPR compared to the conventional SLM technique. Moreover, the BER performance has been studied considering different number of sub-carriers as well as modulation order.
Spectral analysis of bone-conducted speech using modified linear prediction
(Scopus, 2024) Hasan, Ohidujjaman, Mahmudul; Zhang, Shiming; Huda, Mohammad Nurul; Uddin, Mohammad Shorif
This paper improves the performance of linear prediction (LP) in precise spectral estimation of bone-conducted (BC) speech. Inherently, BC speech contains a wide spectral dynamic range that causes ill conditioning in the autocorrelation (ACR) method and its variants, where the Levinson–Durbin (L–D) algorithm is commonly implemented. Instead of the conventional LP-based spectral estimation methods, we utilize the covariance-based method, specifically the modified covariance (MC) method, where the orthogonal decomposition algorithm is deployed. In this paper, we derive the MC method from the least squares (LS) technique for BC speech analysis. The MC method reduces the eigenvalue expansion that compresses the spectral dynamic range of the BC speech signal. The effect of spectral dynamic range compression declines the ill-conditioned properties of LP. Through the proposed method using synthetic BC speech, the resulting power spectrum provides more accurate peaks than the conventional methods. The validity of the proposed method is also analyzed by inspecting real BC speech. This study reveals the utmost use of BC speech in speech processing systems. The experimental results demonstrate that the proposed method provides more accurate spectral estimation for synthetic and real BC speeches compared with conventional spectral estimation methods.
Spectral Analysis of Bone-conducted Speech Using Modified Linear Prediction
(Springer Nature, 2024-10-16) Ohidujjaman; Hasan, Mahmudul; Zhang, Shiming; Huda, Mohammad Nurul; Uddin, Mohammad Shorif
This paper improves the performance of linear prediction (LP) in precise spectral estimation of bone-conducted (BC) speech. Inherently, BC speech contains a wide spectral dynamic range that causes ill conditioning in the autocorrelation (ACR) method and its variants, where the Levinson–Durbin (L–D) algorithm is commonly implemented. Instead of the conventional LP-based spectral estimation methods, we utilize the covariance-based method, specifically the modified covariance (MC) method, where the orthogonal decomposition algorithm is deployed. In this paper, we derive the MC method from the least squares (LS) technique for BC speech analysis. The MC method reduces the eigenvalue expansion that compresses the spectral dynamic range of the BC speech signal. The effect of spectral dynamic range compression declines the ill-conditioned properties of LP. Through the proposed method using synthetic BC speech, the resulting power spectrum provides more accurate peaks than the conventional methods. The validity of the proposed method is also analyzed by inspecting real BC speech. This study reveals the utmost use of BC speech in speech processing systems. The experimental results demonstrate that the proposed method provides more accurate spectral estimation for synthetic and real BC speeches compared with conventional spectral estimation methods.
The Mystic in the Rebel
(Kazi Nazrul Islam and Abbasuddin Ahmed Research & Study Centre, Independent University, Bangladesh, 2014-05-01) Huda, Mohammad Nurul
Though popularly labelled as the Rebel poet of Bengal, Nazrul had been digging ceaselessly into the esoteric depth of his Seif and Soul, both taken as complementary to each other in the form of individual and universal concepts respectively. This inward investigation of a seemingly loud and overt social dissenter like him make his readers puzzle, although temporarily, to strike an assessment of him as a poet and philosopher grown out of tariqat and its mystic practice, known as Sufism. That Nazrul wanted to change the existing social order grown in the wake of colonial subjugation, looking for the earthly gain and equitable shares of wealth for people belonging to all classes including the grassroots level, is apparently incompatible with the concept of Islamic mysticism, verily known as Sufism, that does not approve of any worldly gain except enlightened and selfless reunion with God, the source of all creations, peace and eternal light. In fact, in Nazrul there is a duality of this worldly possession and divine selflessness, right from the beginning of his poetic career when he wrote his towering poem ‘Bidrohi’ (The Rebel, December 1921), suggesting diverse interpretations of the conflicting shades of the Self in the word-picture ‘AMI’ or T. In this poem of 141 uneven lines, Nazrul refers to this ‘I’ almost in each line, in a bid to diversify his identity which tends to defy the height of the Himalayan peak or the seat of the Creator, but finally expresses his interest of calming down, suggestive of surrendering to the Universal Self (implied in the last few lines of the text), when he will discover a world of peace at the end of all struggles in an oppression-free world. In this poem he also proclaims himself as a hermit, rather a warrior equipped with the weapon of tunes, and a prince with a royal attire of pale gairik (red ochre, the colour of selfless hermits). (Ami sanyasi, sursainik / Ami jubaraj, momo rajbesh mlan gairik). It reminds us of the Gautam Buddha, the prince who retired from royal affluence, attired in gairik dress. In fact this is a cherished situation of all mystic rebels who are in constant struggle to free them from their sinful self trying to get united with the divine self a symbol of purity, sublimity, stability and peace. This is exactly the practice of all Sufis, since the connotation of Sufism or Islamic mysticism is the seifless experiencing and actualization of the truth analogous with none but God. the Omnipotent. Every Sufi passes through an arduous path of struggle to free him from self-interest and it is certainly his insurgence against the corrupt self. Nazrul did the same thing at individual and collective level while waging his war against all possible forts of subjugation, oppression, tyranny and dominance. A Sufi is selfless, devoid of all mundane possessions and it is the extreme form of poverty, so to say. It is the crown of all mystic saints as well. A Sufi is a metaphor of a wool cloak on purity that resembles his soul. Nazrul echoes almost the same sentiment in his celebrated poem ‘Daridrya’ (Poverty) which starts with a famus line, ‘O poverty, you have made me great, you have given me the honour of Christ’ (Hey daridrya, tumi more korecho mohan / tumi more daniyacho Christer somman). It is also an echo of the saying of Prophet Mohammad (SM), ‘Poverty is my pride’. As we proceed to look further into his poetic and aesthetic quest, a mystic journey underlying his different texts in the form of prose and poetry is identified. The mystic Nazrul appears in many of his texts - either prose or poetry or speeches - that he created till 1942, the year he fell ill losing his speaking power and surrendered to a mysterious silence for more than three decades, breathing his last in 1976. The key concept we propose to look into his texts for Sufi interpretaion is ‘Self or ‘I’ (Individual and Universal) and its relation with Beauty (Amar Sundor, a confessional prose), Struggle and Oved-sundar (Oneness of beauty despite differences of its perspectives). It may be also interesting to identify a careful distinction between religious rituals and divine essence present in almost all religions. The rituals may differ from one religion to another, but the essence of union with God is almost identical in every divine cult. Even this concept has its implicit presence in Buddhism that does not clearly speak of God or divinity, but prescribes the concept of ‘Nirvana’ as the ultimate target of all human beings. This ‘Nirvana’ is somewhat a similar Sufi state of dissolving oneself peacefully into the universal self of God. In short, this paper would briefly investigate some key aspects of Sufism as reflected in the works of Nazrul, who lived a life of 34 years in almost a state of complete silence resembling the moraqaba of a Sufi saint. 2 Family, Tradition and Nazrul’s Individual ‘I’ diversified Are all poets basically and habitually mystic in their physical and mental make-up? The answer is not quite easy to sort out. But one thing seems common to all creators of imaginative texts that they look deep into the metaphysical essence underlying the physical world they usually encounter. This way of looking into inscape of a matter is somewhat identical with mystic investigation. Nazrul, for that matter, any imaginative creator is not an exception to it. But the shaping of mystic journey in Nazrul seemed to have stemmed from the mental structure of his predecessors, since we clearly identify a great sufi saint called Hajrat Nakshband who was son of Syed Mohammad Islam, now recognized as 7th grandfather of Kazi Nazrul Islam (in ‘Nazrul Borshopanji’, prepared by Khilkhil Kazi, 1405-1406 Bengali Year,