Search

In the present context, synthesized zinc borate was demonstrated as a thermal resistant agent by applying it by in-situ method on the cotton fabric wherein zinc borate was synthesized from zinc nitrate and borax. Particle formation and its morphology were confirmed by particle size analyzer, and scanning electron microscopy analysis, respectively. It has been observed that zinc borate-cotton registered the high oxygen index value of 30% against 18% oxygen index of the control cotton fabric. Furthermore, zinc borate treated cotton fabric showed a black colour char and a char length of 25 mm. The extent of heat generated from the treated cotton fabric was also found to be 75% less compared to the untreated cotton fabric. A thermo-oxidative decomposition experiment was performed by thermo-gravimetry analyzer and reported in detail. It was found that the treated fabric recorded more than 40% weight retention at a higher temperature. The surface morphology of the charred mass was also examined to fortify the dehydration mechanism of the treated sample.

Online content streaming is the most popular form of entertainment in recent times due to COVID 19 lockdown. All popular streaming services use various product recommendation schemes to retain users to their services by intriguing them with content that they might like. Various recommendation systems have been used by famous streaming services like Netflix, Amazon Prime, Hulu, etc. but they lack consistency and accuracy as they suffer from some severe problems such as the first rater problem, sparsity problem, and various computations problems. In this research, we have come up with a hybrid machine learning recommender system which uses an ensemble of content-based and collaborative filtering techniques to not only solve all data sparsity problems but also provide more personalized recommendations to the users based on their watching history and user profile. This research provides a new algorithm that increases the quality of content that is being recommended to the users.

Sodium lignin sulfonate (SLS) has been explored as a fire retardant finishing agent on cotton fabric. 30% [w/v] SLS treated cotton fabric has registered LOI value of 28.5 with minimum char length of 4 cm (self-extinguishment) whereas control cotton fabric was found to burn out with flame and afterglow within 1 min. Thermo-gravimetry of the treated cotton fabric showed 35% mass retention at 500 °C while only 8% char mass was left for the control cotton fabric at the said temperature. Volatile species liberated during burning were analyzed by GC–MS technique which demonstrated the restriction of flammable gas formation from the SLS treated fabric. Char mass left after burning also has been characterized in terms of its morphology, elemental analysis, etc. Moreover, it has also been proven that SLS treatment imparts a natural attractive yellow color, UV protective property to the treated fabric without altering physical strength of the fabric which can be considered as an added advantage over flame retardant effect.

Multimodal emotion recognition is a challenging task because emotions can be expressed through various forms and modalities. It can be applied in various fields, for example, human-computer interaction, crime, healthcare, multimedia retrieval, etc. In recent times, neural networks have achieved overwhelming success in determining emotional states. Motivated by these advancements, we present a multimodal emotion recognition system that uses the following modalities: facial expression, speech, and body language. This paper specifies techniques used for the Emotion Recognition on Polish problem based Polish Emotion dataset. To recognise the current state of emotion in the various given videos, preprocessing of data and extraction of robust features is employed. For the given task, we have made use of facial landmark detection, and Mel-frequency cepstral coefficients (MFCCs) for speech audio. The presented data was in the format of variable length videos, subsequently, which led to underperformance by traditional algorithms for classification. Thus, they could not be used. Therefore, we implemented several long short-term memory (LSTM) networks. Each particular modality was trained for its specific LSTM model, in order to return the emotion having the highest probability at a given instance. Finally, each individual model is fused together using a weight average approach, where in context to all the modalities, the emotion having highest probability is the desirable emotion.

Textiles play an important role in our everyday life, from apparel to home furnishings to industrial usages. A major worry is that it is a potential fuel to ignite, create fire hazards, and thus jeopardize life. Thus a series of fire-retardant chemicals have been conceived, developed, and commercialized. Although satisfactory fire retardancy has been obtained by incorporating them into textiles using several approaches, challenges remain as either the composition is not free from toxicity or it loses the fabric’s inherent physical properties such as flexibility, strength, and feel. As a consequence, this has become an area of interest and stimulates researchers to search for new alternatives where less add-ons to textiles would create fire-retardant functionality without greatly affecting the fabric’s basic qualities. In this respect, nanoparticles could potentially be an important substitute. Hence, this chapter is intended to discuss the various options of fire retardants in nanoparticulate form to make textiles fire retardant. Promising research outcomes in this area and future challenges to commercialize this novel approach are also revealed.